fix(auth): reduce file size

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

.env.example

@@ -67,14 +67,6 @@ DISABLE_SQLITE_AUTO_BACKUP=false
 # Used by: src/shared/utils/rateLimiter.ts
 # Example: redis://localhost:6379 (or redis://redis:6379 in Docker)
 # REDIS_URL=redis://localhost:6379
-# Host interface docker-compose publishes the Redis sidecar on.
-# Default: 127.0.0.1 (loopback only). The compose Redis runs WITHOUT
-# `requirepass`, and app containers reach it over the compose network
-# (redis:6379) — the published port is only for host-side tooling. Setting this
-# to 0.0.0.0 exposes an unauthenticated Redis to your whole LAN.
-# REDIS_BIND_HOST=127.0.0.1
-# Host port for the compose Redis sidecar. Default: 6379.
-# REDIS_PORT=6379
 
 # ═══════════════════════════════════════════════════════════════════════════════
 # 3. NETWORK & PORTS
@@ -345,18 +337,14 @@ ALLOW_API_KEY_REVEAL=false
 # OMNIROUTE_CHAT_HEAVY_TOOL_COUNT=64
 # Conservative string-size token estimate that classifies a request as heavyweight. Default 32000.
 # OMNIROUTE_CHAT_HEAVY_ESTIMATED_TOKENS=32000
-# Optional opt-in hard message-count cap; excess receives compact-required 413 before
-# compression can run. Unset/0 (the default) means no history cap: heap growth is bounded
-# by OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT and the heap-pressure shed instead. Set a positive
-# value only on memory-constrained deployments that need a hard ceiling.
-# OMNIROUTE_CHAT_HARD_MAX_MESSAGES=0
+# Hard message-count cap; excess receives compact-required 413. Default 800.
+# OMNIROUTE_CHAT_HARD_MAX_MESSAGES=800
 
 # Hard cap (bytes) for a non-streaming upstream response buffered fully into memory
 # (#5152). Past this the upstream reader is cancelled and the request fails fast
 # instead of growing an unbounded string until the V8 heap is exhausted.
 # Used by: open-sse/handlers/chatCore/nonStreamingResponseBody.ts
 # Default: 67108864 (64 MB)
-# OMNIROUTE_FORWARDING_HEADER_BUDGET_BYTES=768
 # OMNIROUTE_MAX_NONSTREAMING_RESPONSE_BYTES=67108864
 
 # CORS configuration — controls which cross-origin browser clients can call the API.
@@ -457,13 +445,6 @@ ALLOW_API_KEY_REVEAL=false
 # Default: false
 # OMNIROUTE_PREFER_CLAUDE_CODE_FOR_UNPREFIXED_CLAUDE_MODELS=false
 
-# Per-model concurrency cap for round-robin combos (#9100).
-# Used by: open-sse/services/comboConfig.ts — the round-robin combo semaphore
-# was hard-capped at 3 concurrent requests per model with no override, which
-# serialized higher-concurrency traffic behind that cap.
-# Validated to >= 1, clamped to <= 32.  |  Default: 3
-# COMBO_CONCURRENCY_PER_MODEL=3
-
 # ═══════════════════════════════════════════════════════════════════════════════
 # 7. URLS & CLOUD SYNC
 # ═══════════════════════════════════════════════════════════════════════════════
@@ -539,6 +520,16 @@ NEXT_PUBLIC_BASE_URL=http://localhost:20128
 # cost of more upstream polling; raise to reduce request volume.
 # OMNIROUTE_CGPT_WEB_PRO_POLL_INTERVAL_MS=4000
 
+# Timeout for the /api/jobs/:id/run-now endpoint, in milliseconds.
+# This bounds the CALL, not the job. runNow() dispatches the handler with
+# `void` and returns as soon as it has decided to start, so on the normal
+# path it resolves in milliseconds. It only matters when the job is already
+# running: runNow() then waits for the in-flight run before starting the
+# queued one, and this timeout prevents that wait from hanging forever.
+# Used by: src/app/api/jobs/[id]/run-now/route.ts
+# Default: 30000 (30 seconds)
+# OMNIROUTE_RUNNOW_TIMEOUT_MS=30000
+
 # Public cloud URL — client-side mirror of CLOUD_URL.
 NEXT_PUBLIC_CLOUD_URL=
 
@@ -797,16 +788,6 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
 # Disable the proactive recovery scheduler entirely (default: false).
 # OMNIROUTE_DISABLE_CONNECTION_RECOVERY=false
 
-# Proactive Claude warmup scheduler (#8848): fires a trivial request to opted-in
-# OAuth connections on a cron schedule (America/Los_Angeles) so accounts do not
-# hit the 5-hour sliding window cold. Off by default — set ENABLED=1 and flip
-# per-connection flags in settings.claudeWarmup.connections to activate.
-# Used by: src/lib/warmupScheduler.ts.
-# OMNIROUTE_WARMUP_ENABLED=false
-# OMNIROUTE_WARMUP_CRON="0 7 * * *"
-# OMNIROUTE_WARMUP_CONCURRENCY=3
-# OMNIROUTE_WARMUP_MODEL=
-
 # Background job interval for budget reset checks (ms).  Default: 600000 (10m).
 # Used by: src/lib/jobs/budgetResetJob.ts.  Floor: 10000.
 #OMNIROUTE_BUDGET_RESET_JOB_INTERVAL_MS=600000
@@ -871,12 +852,6 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
 # (>= 3 retrievals = never compressed). 1 disables the ramp (binary skip at the threshold only).
 # Used by: open-sse/services/compression/engines/ccr/index.ts.  Default: 2.
 #COMPRESSION_CCR_RETRIEVAL_RAMP_FACTOR=2
-# CCR durable block store (#9061). The in-memory store loses blocks to LRU eviction, the TTL, a
-# restart, or a retrieve landing on another instance, while the model is told it can retrieve them
-# verbatim. Set to false to keep blocks in memory only, at the cost of that promise. Blocks over
-# 512KB and cloud runtimes are memory-only regardless.
-# Used by: open-sse/services/compression/engines/ccr/index.ts.  Default: true.
-#COMPRESSION_CCR_DURABLE_STORE=true
 # T08/H5 — usage-observed prefix freeze (OPT-IN, default off). When enabled, a system prompt seen
 # >= THRESHOLD times is treated as a stable cacheable prefix and preserved from compression even
 # for providers the static cache-aware heuristic does not recognize (freeze = preserve, never
@@ -1061,17 +1036,6 @@ GITHUB_OAUTH_CLIENT_ID=Iv1.b507a08c87ecfe98
 # VISION_BRIDGE_BASE_URL=
 # VISION_BRIDGE_API_KEY=
 
-# ── Raycast Pro (local auto-import) ──
-# Raycast Pro AI is a reverse-engineered, unofficial API — local/personal use
-# only (no OAuth client_id/secret; token is captured via macOS Auto-Import
-# from the Keychain + local Raycast SQLite DB, or pasted manually). These
-# vars are optional manual overrides used by open-sse/services/raycast.ts
-# and the direct-probe benchmark script scripts/raycast/usage-benchmark.mjs.
-# RAYCAST_BEARER_TOKEN=
-# RAYCAST_DEVICE_ID=
-# RAYCAST_AID=
-# RAYCAST_SIG_SECRET=
-
 # ─────────────────────────────────────────────────────────────────────────────
 # ⚠️  GOOGLE OAUTH (Antigravity) & OTHER PROVIDERS — REMOTE SERVERS
 # ─────────────────────────────────────────────────────────────────────────────
@@ -1212,17 +1176,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # fallback when FETCH_TIMEOUT_MS is unset. Default: 120000 (2 min).
 # OMNIROUTE_DEFAULT_FETCH_TIMEOUT_MS=120000
 
-# ── Proxy/relay fetch (connection pooling, #9158) ──
-# Used by: open-sse/utils/proxyFetch.ts.
-# A hung relay must fail BEFORE the client/agent timeout (typically 30s) so the
-# caller sees a relay-specific failure instead of a generic upstream timeout.
-# Capped at 29000ms so this timeout always fires first. Default: 25000 (25s).
-# OMNIROUTE_RELAY_FETCH_TIMEOUT_MS=25000
-
-# Shared retry backoff (ms) for the direct/relay/proxy retry-once paths.
-# 0 = retry immediately. Default: 10.
-# OMNIROUTE_RETRY_BACKOFF_MS=10
-
 # ── Firecrawl web-fetch executor ──
 # Point at a self-hosted Firecrawl instance (defaults to the public cloud API).
 # When set to a non-cloud base URL, the API key becomes optional.
@@ -1284,14 +1237,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # OMNIROUTE_BROWSER_POOL=on
 # WEB_COOKIE_USE_BROWSER=0
 
-# ── Adobe Firefly browser sign-in (system Chrome/Edge CDP) ──
-# Used by: open-sse/services/adobeFireflyBrowserLogin.ts. The Firefly login
-# flow drives a real, system-installed Chrome or Microsoft Edge via CDP so the
-# user can sign in interactively; the executable is auto-detected from common
-# install paths per OS. Set this to override that detection (e.g. a portable
-# install or a non-standard path) when auto-detection fails.
-# OMNIROUTE_LOGIN_BROWSER_PATH=
-
 # ── Circuit breaker thresholds and reset windows ──
 # Used by: open-sse/config/constants.ts → src/lib/resilience/settings.ts.
 # Defaults match historical PROVIDER_PROFILES values (post-scaling for
@@ -1403,10 +1348,6 @@ APP_LOG_TO_FILE=true
 # Default: 100000
 # CALL_LOGS_TABLE_MAX_ROWS=100000
 
-# Force detailed request logging on or off, overriding the dashboard setting.
-# Values: true | false  |  Default: unset (follow dashboard setting)
-# ENABLE_REQUEST_LOGS=false
-
 # Maximum age for orphaned active request log entries before the in-memory
 # pending-request reaper removes them. Accepts milliseconds.
 # Default: 3600000 (1 hour)
@@ -1426,9 +1367,10 @@ APP_LOG_TO_FILE=true
 # bodies is retained in the database.
 # Used by: open-sse/handlers/chatCore.ts — cloneBoundedChatLogPayload()
 # CHAT_LOG_TEXT_LIMIT=65536                  # Max string length before truncation (default: 64 KB)
-# CHAT_LOG_ARRAY_TAIL_ITEMS=24               # Number of array items retained from tail (default: 24)
+# CHAT_LOG_ARRAY_TAIL_ITEMS=128               # Number of array items retained from tail (default: 128)
 # CHAT_LOG_MAX_DEPTH=6                       # Max nesting depth before truncation (default: 6)
 # CHAT_LOG_MAX_OBJECT_KEYS=80                # Max object keys retained (default: 80, 0 = no limit)
+# CHAT_LOG_MAX_BODY_KB=1024                  # Max request/response body size before summarizing, in KB (default: 1024)
 
 # Maximum rows in the proxy_logs SQLite table.
 # Default: 100000
@@ -1483,6 +1425,10 @@ APP_LOG_TO_FILE=true
 # Default: ~/.omniroute/plugins/  Override in dev/CI to point at a local plugin tree.
 # OMNIROUTE_PLUGIN_PATH=
 
+# Allow plugins to request the 'exec' permission (spawn child processes from the
+# plugin worker sandbox). Disabled by default; set to 1 to enable (local operator only).
+# OMNIROUTE_PLUGINS_ALLOW_EXEC=0
+
 # ── Prompt cache (system prompt deduplication) ──
 # Used by: open-sse/services — caches identical system prompts across requests.
 # PROMPT_CACHE_MAX_SIZE=50              # Max cached entries (default: 50)
@@ -1540,15 +1486,6 @@ APP_LOG_TO_FILE=true
 # ═══════════════════════════════════════════════════════════════════════════════
 # 19. MODEL SYNC (Dev)
 # ═══════════════════════════════════════════════════════════════════════════════
-# Enable the models.dev capability sync.  Default: false (opt-in only).
-# Also settable from Dashboard > Settings > AI. This variable wins over that
-# setting whenever it is set to anything non-empty, in either direction, so a
-# deployment can pin the sync on or off without depending on database state
-# surviving a rebuild. Leave it unset to let the dashboard toggle decide.
-# On: 1, true, yes or on (any casing). Any other value is off.
-# Used by: src/lib/modelsDevSync.ts
-# MODELS_DEV_SYNC_ENABLED=false
-
 # Development-time model catalog sync interval in seconds.
 # Used by: src/lib/modelsDevSync.ts
 # Default: 86400 (24 hours)
@@ -1571,14 +1508,6 @@ APP_LOG_TO_FILE=true
 # Default: 86400000 (24 hours)
 # OPENROUTER_CATALOG_TTL_MS=86400000
 
-# Enrich the dashboard providers list with OpenRouter weekly ranking stats.
-# ON by default; set false to skip the background fetch entirely (#9324).
-# Used by: src/lib/catalog/openrouterProviderStats.ts
-# OPENROUTER_PROVIDER_STATS_ENABLED=true
-# Cache TTL for the OpenRouter provider stats snapshot, in ms.
-# Default: 86400000 (24 hours)
-# OPENROUTER_PROVIDER_STATS_TTL_MS=86400000
-
 # ── Model catalog response shape ──
 # Include display-friendly name fields in /v1/models responses.
 # Disable for clients that expect model IDs only.
@@ -1599,13 +1528,6 @@ APP_LOG_TO_FILE=true
 # DESIGNER_WEB_POLL_TIMEOUT_MS=60000   # Max wait for job completion (default: 60s)
 # DESIGNER_WEB_POLL_INTERVAL_MS=2000   # Poll frequency (default: 2s)
 
-# ── Adobe Firefly (Image Upscale) ──
-# Base delay (ms) for the submit-retry exponential backoff when Adobe Firefly's
-# upscale job submission is rate-limited. Used by:
-# open-sse/services/adobeFireflyUpscale.ts::submitRetryDelayMs.
-# Default: 8000 (20 under NODE_ENV=test/VITEST/NODE_TEST_CONTEXT).
-# ADOBE_FIREFLY_SUBMIT_BASE_DELAY_MS=8000
-
 # ── AWS Bedrock (Kiro / Audio) ──
 # Region used to construct AWS Bedrock endpoints. Used by:
 # src/lib/providers/validation.ts and open-sse/handlers/audioSpeech.ts.
@@ -1700,26 +1622,6 @@ APP_LOG_TO_FILE=true
 # Used by: src/lib/services/bootstrap.ts, src/app/api/services/mux/_lib.ts
 # MUX_SERVICE_PORT=8322
 
-# ── Dario embedded service ──
-# Override the host/port the embedded Dario (Claude Code subscription proxy)
-# daemon binds to and is reached at. Always bound to 127.0.0.1 — never
-# configurable to 0.0.0.0. Rarely needed — defaults to 127.0.0.1:3456.
-# Used by: src/lib/services/installers/dario.ts, src/lib/services/bootstrap.ts,
-# src/app/api/services/dario/_lib.ts, src/app/api/services/dario/admin/_lib.ts,
-# open-sse/executors/dario.ts
-# DARIO_HOST=127.0.0.1
-# DARIO_PORT=3456
-
-# ── Dario embedded service ──
-# Override the host/port the embedded Dario (Claude Code subscription proxy)
-# daemon binds to and is reached at. Always bound to 127.0.0.1 — never
-# configurable to 0.0.0.0. Rarely needed — defaults to 127.0.0.1:3456.
-# Used by: src/lib/services/installers/dario.ts, src/lib/services/bootstrap.ts,
-# src/app/api/services/dario/_lib.ts, src/app/api/services/dario/admin/_lib.ts,
-# open-sse/executors/dario.ts
-# DARIO_HOST=127.0.0.1
-# DARIO_PORT=3456
-
 # ── Local hostnames (Docker networking) ──
 # Comma-separated additional hostnames treated as "local" for provider routing.
 # Used by: open-sse/config/providerRegistry.ts — allows Docker service names.
@@ -1952,18 +1854,6 @@ APP_LOG_TO_FILE=true
 # ── Devin CLI binary path ──
 # Used by: open-sse/executors/devin-cli.ts. Default: looked up via PATH.
 # CLI_DEVIN_BIN=devin
-# Agentic bridge-only binary override. The bridge still executes ACP stdio only.
-# CLI_DEVIN_AGENTIC_BIN=devin
-# Required isolated HOME for the agentic Devin child process.
-# DEVIN_AGENTIC_HOME=/home/bridge
-# Bounded ACP turn timeout in milliseconds. Default: 120000.
-# DEVIN_AGENTIC_ACP_TIMEOUT_MS=120000
-# Agentic bridge model aliases. Values must keep the devin-cli-agentic/ prefix.
-# DEVIN_BRIDGE_MODEL=devin-cli-agentic/swe-1-7
-# DEVIN_BRIDGE_SONNET_MODEL=devin-cli-agentic/swe-1-7
-# DEVIN_BRIDGE_OPUS_MODEL=devin-cli-agentic/swe-1-7
-# DEVIN_BRIDGE_HAIKU_MODEL=devin-cli-agentic/swe-1-7
-# DEVIN_BRIDGE_SUBAGENT_MODEL=devin-cli-agentic/swe-1-7
 
 # ── Command Code (custom CLI) callback ──
 # Local port used for OAuth-style callbacks from the Command Code CLI helper.
@@ -2018,15 +1908,6 @@ APP_LOG_TO_FILE=true
 # CHANGELOG_BASE_REF=origin/release/v0.0.0
 # ALLOW_CHANGELOG_REMOVALS=1
 
-# ── Remote audio provider nodes ──
-# Used by: src/app/api/v1/_shared/audioProviderNodes.ts — lets the /v1/audio/*
-# routes use an OpenAI-compatible provider node hosted outside localhost.
-# OFF by default: routing audio to a remote host changes egress identity, so it
-# must be an explicit operator decision. Loopback/private nodes (localhost,
-# 127.0.0.1, 172.16-31.x) are always allowed and unaffected by this flag.
-# When enabled, the node authenticates with the API key stored on its connection.
-# AUDIO_REMOTE_PROVIDER_NODES=false
-
 # ── 1Proxy egress pool ──
 # Used by: src/lib/oneproxySync.ts — fetches proxy nodes from the OmniRoute
 # CrofAI 1Proxy service. Disable, override URL, or tune the import quality.
@@ -2234,11 +2115,6 @@ PLAYGROUND_COMPARE_MAX_COLUMNS=4
 # MEMORY_TYPED_DECAY_EPISODIC_DAYS=30           # episodic TTL in days; 0 = episodic immune too
 # MEMORY_TYPED_DECAY_ACCESS_IMMUNITY=3          # access_count >= N → immune; 0 disables access immunity
 # MEMORY_TYPED_DECAY_SWEEP_INTERVAL=0           # periodic sweep interval (seconds); 0 = no periodic sweep
-# ─── Memory Backend Connectors (Generic HTTP) ──────────────────────────────
-# NOTION_API_KEY=
-# NOTION_API_URL=
-# OBSIDIAN_API_KEY=
-# OBSIDIAN_API_URL=
 # AgentBridge + Traffic Inspector (Group A)
 
 # AgentBridge
@@ -2254,15 +2130,6 @@ INSPECTOR_MAX_BODY_KB=1024
 INSPECTOR_MASK_SECRETS=true
 INSPECTOR_LLM_HOSTS_EXTRA=
 INSPECTOR_INTERNAL_INGEST_TOKEN=
-# Shared secret for identity-preserving internal REST hops (#9260): when an
-# OmniRoute component calls another local OmniRoute route, this token (sent as
-# x-omniroute-internal-service-token) marks the request as internal so the
-# original caller identity is preserved. OPT-IN: unset disables the mechanism.
-# Used by: src/lib/api/internalServiceAuth.ts
-# OMNIROUTE_INTERNAL_SERVICE_TOKEN=
-# File-based variant (secret-file pattern; wins only when the inline var is
-# unset): path to a file whose trimmed content is the token.
-# OMNIROUTE_INTERNAL_SERVICE_TOKEN_FILE=
 # Quota Sharing (Group B — planos 16+22)
 QUOTA_STORE_DRIVER=sqlite              # sqlite | redis
 # QUOTA_STORE_REDIS_URL=               # ex.: redis://localhost:6379 (apenas quando driver=redis)
@@ -2373,11 +2240,6 @@ QUOTA_STORE_DRIVER=sqlite              # sqlite | redis
 # Host port for the 1-click Redis launcher. Default: 6379. Bump if the host
 # already binds 6379. The container's internal port stays 6379.
 # OMNIROUTE_REDIS_HOST_PORT=
-# Host interface the 1-click Redis launcher publishes on. Default: 127.0.0.1
-# (loopback only). The launcher starts Redis WITHOUT a password, so binding
-# 0.0.0.0 hands every host on your LAN an unauthenticated Redis — only widen
-# this if you also set a password on the instance yourself.
-# OMNIROUTE_REDIS_BIND_HOST=
 # Redis image used by the 1-click Redis launcher. Default: redis:7-alpine.
 # Override to redis:8-alpine or a private registry mirror as needed.
 # OMNIROUTE_REDIS_IMAGE=
@@ -2480,37 +2342,20 @@ QUOTA_STORE_DRIVER=sqlite              # sqlite | redis
 # ─────────────────────────────────────────────────────────────────────────────
 # VIBEPROXY_DATA_DIR=
 
-# ── Internal service auth (management-plane service-to-service calls) ─────────
-# Inline token for internal service authentication; prefer the _FILE variant in
-# containerized deployments so the secret never lands in the environment table.
-# OMNIROUTE_INTERNAL_SERVICE_TOKEN=
-# Path to a file containing the internal service token (overrides the inline var).
-# OMNIROUTE_INTERNAL_SERVICE_TOKEN_FILE=
+# ─────────────────────────────────────────────────────────────────────────────
+# Telegram Mini App (inbound bot webhook + Mini App chat)
+# Used by: src/lib/telegram/*, src/app/api/telegram/update/route.ts
+# ─────────────────────────────────────────────────────────────────────────────
+# Bot token from @BotFather (<numeric_id>:<secret>). Enables the inbound
+# update webhook and doubles as the HMAC secret for Mini App initData
+# verification. When unset, /api/telegram/update returns 503.
+# TELEGRAM_BOT_TOKEN=
 
-# ═══════════════════════════════════════════════════════════════════════════════
-# 26. RADAR FEED (SELF-HOSTING)
-# ═══════════════════════════════════════════════════════════════════════════════
-# Optional add-on (feature flag RADAR_ENABLED, default off — see feature flag
-# settings, not an env var) that overlays a signed, freshly-curated free-model
-# catalog on top of the release baseline. All four variables below are optional
-# and only needed to point the client at a self-hosted/forked feed or
-# supporter-key flow instead of the default OmniRoute Radar service. Used by:
-# src/lib/radar/sync.ts, src/lib/radar/pinnedKeys.ts, src/lib/radar/links.ts.
+# Model used for Telegram chat replies (default: auto/chat).
+# TELEGRAM_DEFAULT_MODEL=auto/chat
 
-# Base URL of the Radar feed service. Overrides the built-in default so forks
-# and self-hosters can point at their own signed feed.
-# RADAR_FEED_URL=https://radar.omniroute.online
+# Bot API base URL override (for proxies/self-hosted Bot API servers).
+# TELEGRAM_BOT_API_BASE=https://api.telegram.org
 
-# Ed25519 public key (base64-DER SPKI or PEM) used to verify the feed
-# signature, replacing the pinned default key. Required when self-hosting a
-# feed signed with a different key pair.
-# RADAR_FEED_PUBKEY=
-
-# URL the dashboard's "I'm a contributor" button opens (GitHub OAuth
-# supporter-key claim flow). No pricing/value lives in this repo — only the
-# link.
-# RADAR_CONTRIBUTOR_CLAIM_URL=https://radar.omniroute.online/auth/github
-
-# URL the dashboard's "Support the project" button opens (payment/plans
-# page). No pricing/value lives in this repo — only the link.
-# RADAR_SUPPORTER_PLANS_URL=https://radar.omniroute.online/planos
+# Timeout (ms) for outbound Bot API calls (sendMessage/setWebhook).
+# TELEGRAM_WEBHOOK_TIMEOUT_MS=60000

.github/workflows/quality.yml

@@ -151,63 +151,6 @@ jobs:
           key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
           restore-keys: |
             eslint-${{ runner.os }}-
-      - run: npm run check:provider-consistency
-      - run: npm run check:fetch-targets
-      # docs-all / openapi-routes / docs-symbols live in docs-gates (path-filtered).
-      - run: npm run check:deps
-      # #8522: --base-ref mode for PR events — compare against max(frozen, base) so
-      # inherited drift (base already over frozen cap) doesn't red an innocent PR.
-      # workflow_dispatch (no PR base) falls back to absolute comparison.
-      - name: File-size ratchet (base-relative on PR)
-        env:
-          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
-        run: |
-          if [ -n "$PR_BASE_SHA" ]; then
-            npm run check:file-size -- --base-ref "$PR_BASE_SHA"
-          else
-            npm run check:file-size
-          fi
-      - run: npm run check:error-helper
-      - run: npm run check:migration-numbering
-      - run: npm run check:public-creds
-      - run: npm run check:db-rules
-      - run: npm run check:known-symbols
-      - run: npm run check:route-guard-membership
-      - run: npm run check:test-discovery
-      - run: npm run check:test-runner-api
-      # Guards tap.testFiles drift: a covering unit test absent from stryker.conf.json
-      # tap.testFiles makes its module's mutants survive on a cold nightly-mutation run,
-      # false-failing the blocking mutationScore ratchet. See check-mutation-test-coverage.mjs.
-      - run: npm run check:mutation-test-coverage
-      - run: npm run check:any-budget:t11
-      # Build-scope guard: fails if worktrees/cruft leak into the tsconfig include
-      # scope (would OOM `next build`). Instant. See incident 2026-06-25 / #5031.
-      - run: npm run check:build-scope
-      # Pack-policy (unexpected-files allowlist) WITHOUT a build — catches a stray file
-      # leaking into the npm tarball (v3.8.36: 6 ops bin/*.sh) per-PR instead of only on
-      # the release PR's heavy Package Artifact job.
-      - run: npm run check:pack-policy
-      # Complexity + cognitive-complexity: ONE ESLint walk (both baselines still
-      # enforced separately by ruleId). Avoids two cold tree walks on fast-path.
-      - run: npm run check:complexity-ratchets
-      # ── G0 (trilho .50): gates do trilho A que faltavam no trilho B ──────────────
-      # The god-file refactor happens in PRs→release/**; without these, the release
-      # rail never sees a new import cycle, dead code, duplication or a security
-      # regression until the release PR to main. Deliberately NOT brought here:
-      # bundle-size (self-skips without a build — this rail's build job is advisory
-      # and uploads nothing, so it would be dead configuration) and the coverage
-      # run (fast-unit already runs the full suite; the coverage ratchet stays on
-      # the main rail via --allow-missing in lint-guard).
-      - run: npm run check:cycles
-      - run: npm run check:lockfile
-      - name: Duplication ratchet
-        run: npm run check:duplication
-      - name: Dead-code ratchet (knip)
-        run: npm run check:dead-code
-      - name: Type coverage ratchet
-        run: npm run check:type-coverage
-      - name: Compression budget ratchet
-        run: npm run check:compression-budget
       # Security scanners — same hardened install as ci.yml quality-extended
       # (gh release download = authenticated, 5000 req/hr; curl to api.github.com
       # is rate-limited to 60/hr and silently no-ops when throttled). The blocking
@@ -251,30 +194,63 @@ jobs:
           "$HOME/.local/bin/osv-scanner" --version || true
           "$HOME/.local/bin/oasdiff" --version || true
           zizmor --version || true
-      - name: Secret scan (gitleaks, ratchet, blocking)
-        run: npm run check:secrets -- --ratchet
-      - name: Vulnerability ratchet (osv-scanner, ratchet, blocking)
-        run: npm run check:vuln-ratchet -- --ratchet
-      - name: Workflow lint (actionlint+zizmor, ratchet, blocking)
-        run: npm run check:workflows -- --ratchet
-      # BASE_REF is read by the script from the env (never interpolated into a
-      # shell body) — workflow-injection-safe. actions/checkout fetches remote
-      # refs, not a local branch named github.base_ref, so prefix origin/ or this
-      # gate self-skips every PR with reason=base-unresolved.
-      - name: OpenAPI breaking-change (oasdiff, ratchet, blocking)
+      # Quality gates (all, non-fail-fast) — #8542: replaces 17 bare check:* steps,
+      # 6 G0 gates, 4 ratchet gates, and 3 typecheck steps with a single aggregation
+      # step. Each gate runs in a loop with ::group::; failures are collected and
+      # reported at the end. set -uo pipefail (NOT set -e) so one failing gate does
+      # not abort the job and mask every later gate. Release-added gates are folded
+      # in: open-sse typecheck (#8781) and file-size base-relative mode (#8522).
+      - name: Quality gates (all, non-fail-fast)
         env:
+          # #8522: base-relative file-size mode on PR events — inherited drift (base
+          # already over frozen cap) must not red an innocent PR. Unset on
+          # workflow_dispatch (no PR base) → absolute comparison.
+          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
           BASE_REF: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
-        run: npm run check:openapi-breaking -- --ratchet
-      - name: Typecheck (core)
-        run: npm run typecheck:core
-      # #7033: dashboard-scoped typecheck gate — src/app/(dashboard) TSX is not
-      # covered by typecheck:core's curated allowlist. See check-dashboard-typecheck.mjs.
-      - name: Typecheck (dashboard)
-        run: npm run check:dashboard-typecheck
-      # #8781: open-sse workspace typecheck gate — the workspace imports @/ which
-      # escapes to src/ via undeclared path aliases. See check-open-sse-typecheck.mjs.
-      - name: Typecheck (open-sse)
-        run: npm run check:open-sse-typecheck
+        run: |
+          set -uo pipefail
+          gates=(
+            provider-consistency fetch-targets deps file-size error-helper
+            migration-numbering public-creds db-rules known-symbols
+            route-guard-membership test-discovery test-runner-api
+            mutation-test-coverage any-budget:t11 build-scope pack-policy
+            complexity-ratchets
+            cycles lockfile duplication dead-code type-coverage compression-budget
+            # #8781: open-sse workspace typecheck gate — the workspace imports @/ which
+            # escapes to src/ via undeclared path aliases. See check-open-sse-typecheck.mjs.
+            open-sse-typecheck
+          )
+          ratchet_gates=(
+            secrets vuln-ratchet workflows openapi-breaking
+          )
+          failed=()
+          for g in "${gates[@]}"; do
+            echo "::group::check:$g"
+            # #8522: file-size is base-relative on PR events (compare against
+            # max(frozen, base)) so inherited drift doesn't red an innocent PR;
+            # workflow_dispatch (no PR base) falls back to absolute comparison.
+            if [ "$g" = "file-size" ] && [ -n "${PR_BASE_SHA:-}" ]; then
+              npm run "check:$g" -- --base-ref "$PR_BASE_SHA" || failed+=("$g")
+            else
+              npm run "check:$g" || failed+=("$g")
+            fi
+            echo "::endgroup::"
+          done
+          for g in "${ratchet_gates[@]}"; do
+            echo "::group::check:$g (ratchet)"
+            npm run "check:$g" -- --ratchet || failed+=("$g")
+            echo "::endgroup::"
+          done
+          echo "::group::typecheck:core"
+          npm run typecheck:core || failed+=("typecheck:core")
+          echo "::endgroup::"
+          echo "::group::check:dashboard-typecheck"
+          npm run check:dashboard-typecheck || failed+=("check:dashboard-typecheck")
+          echo "::endgroup::"
+          if (( ${#failed[@]} )); then
+            printf '::error::%d gate(s) failed: %s\n' "${#failed[@]}" "${failed[*]}"
+            exit 1
+          fi
       # WS4.2 (v3.8.49 plan): TypeScript 7 native-compiler SHADOW — advisory only.
       # TS7 went GA 2026-07-08 with 8-12x type-check speedups; its Compiler API only
       # arrives in 7.1, so typescript-eslint / type-coverage / Stryker stay on 6.x

.gitignore

@@ -72,7 +72,6 @@ yarn-error.log*
 # env files (can opt-in for committing if needed)
 .env*
 !.env.example
-!.env.devin-bridge.example
 !.env.homolog.example
 # Provider API keys (never commit)
 *.api-key
@@ -172,6 +171,7 @@ config/quality/test-impact-map.json
 # GitNexus local index
 .gitnexus
 .worktrees
+bin/omniroute.mjs
 
 # Consistent with .dockerignore / .npmignore
 .omc/
@@ -201,17 +201,12 @@ scripts/i18n/_pending-keys.json
 .codegraph/
 
 # Fumadocs generated source
-/.source/
-
-# Temporary local worktrees used to build unpublished npm tarballs
-/.deploy-build-*/
+.source/
 
 # AI agent local settings and configs
 .agents/
 .antigravitycli/
 .claude/
-!tests/fixtures/devin-bridge/e2e-workspace/.claude/
-!tests/fixtures/devin-bridge/e2e-workspace/.claude/**
 
 # PR Reviews and local feedback files
 pr_reviews*.json
@@ -226,6 +221,26 @@ CODEX-SETUP-PROMPT.md
 # Quality ratchet — métricas efêmeras (baseline commitado em config/quality/; métricas não)
 config/quality/quality-metrics.json
 
+# Electron desktop build output unpacked into the repo root.
+# `electron-builder` (squirrel-windows target) unpacks the packaged app — the
+# entire Chromium runtime, ~24k files — directly into the repository root.
+# Every rule below is ROOT-ANCHORED (leading `/`) on purpose: a bare `locales/`
+# or `resources/` would also swallow tracked sources such as the CLI
+# translations in `bin/cli/locales/*.json`.
+/OmniRoute.exe
+/Uninstall OmniRoute.exe
+/uninstallerIcon.ico
+/locales/
+/resources/
+/*.pak
+/*.dll
+/icudtl.dat
+/snapshot_blob.bin
+/v8_context_snapshot.bin
+/vk_swiftshader_icd.json
+/LICENSE.electron.txt
+/LICENSES.chromium.html
+
 # Runtime logs (diretório local, nunca versionado)
 /logs/
 -home-diegosouzapw-dev-automações-bots-yt-downloader-20260504 .txt
@@ -238,10 +253,7 @@ omniroute.md
 
 # mise configuration
 mise.toml
-# release-green artifacts (.gitignore has no inline comments — a trailing
-# `# ...` becomes part of the pattern, so it must sit on its own line).
-# Already covered by /_*/ above; kept explicit for discoverability.
-_artifacts/
+_artifacts/          # release-green artifacts
 .claude-flow/
 
 # ESLint file cache (npm run lint --cache / complexity ratchets)
@@ -251,8 +263,6 @@ _artifacts/
 
 # CI/local quality artifacts (eslint-results.json, quality-ratchet.md, etc.)
 .artifacts/
-# Isolated Devin bridge workspaces, evidence, and test databases
-.sandbox/
 
 # Homologation E2E suite (npm run homolog) — real-environment credentials + report output
 .env.homolog
@@ -260,12 +270,8 @@ tests/homolog/.auth/
 tests/homolog/ui/.auth/
 homolog-report/
 docker-compose.yml.bak
-.playwright-cli/
-# Playwright screenshot/log output. Today every artifact happens to land inside
-# output/**/.playwright-cli/ (covered above), but anything written directly to
-# output/ would otherwise show up as untracked.
-/output/
 
-# _tasks e um repo git SEPARADO (ver AGENTS.md). _tasks/ (com barra) NAO ignora um
-# SYMLINK _tasks; /_tasks (ancorado) cobre symlink/dir na raiz (incidente 2026-08-08).
+# _tasks e um repo git SEPARADO (ver AGENTS.md). A linha _tasks/ (com barra) NAO
+# ignora um SYMLINK chamado _tasks; /_tasks (ancorado) cobre arquivo/symlink/dir na raiz
+# e impede que um git add -A recapture o symlink (incidente 2026-08-08).
 /_tasks

@omniroute/opencode-plugin/src/index.ts

@@ -4403,11 +4403,11 @@ export function buildStaticProviderEntry(
       entry.release_date = raw.release_date;
     }
 
-    // OC's static-catalog reader parses each key on `/` and rejects the
-    // entire provider block if ANY key resolves to a parsed providerID that
-    // has no corresponding provider block. So bare keys (no `/`) MUST be
-    // prefixed with the resolved providerId. Already-prefixed keys
-    // (e.g. `cc/claude-opus-4-7`) are left as-is to avoid double-prefixing.
+    // #9175: OC's `getModel` looks the model up by BARE id — the part after
+    // the first `/` in the user's request — so a dict key with an embedded
+    // provider prefix (`<providerId>/<raw-id>`) is unreachable. Keys are the
+    // raw id verbatim; ids that already contain `/` (e.g. `cc/claude-opus-4-7`)
+    // keep it because the slash is part of the upstream model id itself.
     models[raw.id] = entry;
   }
 

@omniroute/opencode-plugin/tests/config-shim.test.ts

@@ -227,7 +227,7 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
   // Stripped per-model shape: name + cap flags + modalities + (optional)
   // cost. OC's SDK static schema accepts only `limit.{context,output}` —
   // `limit.input` is NOT in the SDK shape and gets dropped silently.
-  const claude = entry.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = entry.models["claude-sonnet-4-6"];
   assert.ok(claude, "claude model surfaced");
   assert.equal(claude.name, "claude-sonnet-4-6");
   assert.equal(claude.attachment, true);
@@ -248,7 +248,7 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
 
   // Combo surfaces under bare key + LCD'd
   // (gemini's reasoning=false → combo reasoning=false).
-  const combo = entry.models["omniroute/claude-tier"];
+  const combo = entry.models["claude-tier"];
   assert.ok(combo, "combo surfaced under bare key");
   assert.equal(combo.name, "Claude Tier");
   assert.equal(combo.reasoning, false, "LCD: any member reasoning=false → combo reasoning=false");
@@ -471,10 +471,10 @@ test("config: combos fetcher throws → emit models-only catalog (no combos in m
   assert.ok(entry);
   const ids = Object.keys(entry.models).sort();
   assert.deepEqual(ids, [
-    "opencode-omniroute/claude-sonnet-4-6",
-    "opencode-omniroute/gemini-3-flash",
+    "claude-sonnet-4-6",
+    "gemini-3-flash",
   ]);
-  assert.equal(entry.models["omniroute/claude-tier"], undefined, "no combo entry");
+  assert.equal(entry.models["claude-tier"], undefined, "no combo entry");
   assert.ok(
     logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
     "combos-fetch breadcrumb emitted"
@@ -723,7 +723,7 @@ test("buildStaticProviderEntry: stripped per-model shape matches sibling @omniro
   }
 
   // Sanity: claude entry has all expected stripped fields.
-  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = block.models["claude-sonnet-4-6"];
   assert.equal(typeof claude.name, "string");
   assert.equal(typeof claude.attachment, "boolean");
   assert.equal(typeof claude.reasoning, "boolean");
@@ -748,8 +748,8 @@ test("buildStaticProviderEntry: hidden combos are excluded", () => {
     "https://or.example/v1",
     "sk-test"
   );
-  assert.equal(block.models["omniroute/claude-tier"], undefined);
-  assert.ok(block.models["opencode-omniroute/claude-sonnet-4-6"]);
+  assert.equal(block.models["claude-tier"], undefined);
+  assert.ok(block.models["claude-sonnet-4-6"]);
 });
 
 // ────────────────────────────────────────────────────────────────────────────
@@ -765,7 +765,7 @@ test("buildStaticProviderEntry: emits modalities.input from raw.input_modalities
     "https://or.example/v1",
     "sk-test"
   );
-  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = block.models["claude-sonnet-4-6"];
   assert.deepEqual(claude.modalities?.input, ["text", "image"]);
   assert.deepEqual(claude.modalities?.output, ["text"]);
 });
@@ -779,7 +779,7 @@ test("buildStaticProviderEntry: never emits limit.input (OC SDK rejects it)", ()
     "https://or.example/v1",
     "sk-test"
   );
-  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = block.models["claude-sonnet-4-6"];
   assert.equal((claude.limit as Record<string, unknown>).input, undefined);
   assert.equal(typeof claude.limit?.context, "number");
   assert.equal(typeof claude.limit?.output, "number");
@@ -807,7 +807,7 @@ test("buildStaticProviderEntry: emits cost when enrichment carries pricing", ()
     "sk-test",
     enrichment
   );
-  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = block.models["claude-sonnet-4-6"];
   assert.equal(claude.cost?.input, 3);
   assert.equal(claude.cost?.output, 15);
   assert.equal(claude.cost?.cache_read, 0.3);
@@ -828,8 +828,8 @@ test("buildStaticProviderEntry: emits release_date when raw carries it; omits wh
     "https://or.example/v1",
     "sk-test"
   );
-  assert.equal(block.models["opencode-omniroute/claude-with-date"].release_date, "2026-02-19");
-  assert.equal(block.models["opencode-omniroute/gemini-3-flash"].release_date, undefined);
+  assert.equal(block.models["claude-with-date"].release_date, "2026-02-19");
+  assert.equal(block.models["gemini-3-flash"].release_date, undefined);
 });
 
 test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)", () => {
@@ -858,7 +858,7 @@ test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)
     "https://or.example/v1",
     "sk-test"
   );
-  const combo = block.models["omniroute/mixed-tier"];
+  const combo = block.models["mixed-tier"];
   assert.ok(combo, "combo emitted under slug key");
   // claude has text+image, text-only has text → intersection drops image.
   assert.deepEqual(combo.modalities?.input, ["text"]);
@@ -967,10 +967,10 @@ test("config: enrichment fetched + name overlaid on raw-model entries", async ()
     "opencode-omniroute"
   ];
   assert.ok(entry);
-  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
-  assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini 3 Flash");
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
+  assert.equal(entry.models["gemini-3-flash"].name, "Gemini 3 Flash");
   // Combo names still come from /api/combos — enrichment overlay does NOT touch combos.
-  assert.equal(entry.models["omniroute/claude-tier"].name, "Claude Tier");
+  assert.equal(entry.models["claude-tier"].name, "Claude Tier");
   assert.equal(enrichmentFetcher.callCount(), 1);
 });
 
@@ -1000,7 +1000,7 @@ test("config: features.enrichment=false skips enrichment fetch + keeps raw-id na
   assert.ok(entry);
   assert.equal(enrichmentFetcher.callCount(), 0, "enrichment fetch suppressed by feature flag");
   assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entry.models["claude-sonnet-4-6"].name,
     "claude-sonnet-4-6",
     "raw id retained"
   );
@@ -1027,7 +1027,7 @@ test("config: enrichment fetcher throws → soft-fail (warn + raw-id static cata
   ];
   assert.ok(entry, "static block still published on enrichment failure");
   assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entry.models["claude-sonnet-4-6"].name,
     "claude-sonnet-4-6",
     "raw id retained"
   );
@@ -1229,11 +1229,11 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
     "opencode-omniroute"
   ];
   assert.ok(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"],
+    entry.models["claude-sonnet-4-6"],
     "stale snapshot hydrated into static block"
   );
   assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entry.models["claude-sonnet-4-6"].name,
     "Claude Sonnet 4.6 (cached)",
     "stale enrichment also reused"
   );
@@ -1281,7 +1281,7 @@ test("config: cached rawEnrichment from earlier provider hook is reused (no refe
   const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
     "opencode-omniroute"
   ];
-  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
 });
 
 // ─────────────────────────────────────────────────────────────────────
@@ -1332,12 +1332,12 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
   ];
   assert.ok(entry);
   assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entry.models["claude-sonnet-4-6"].name,
     "Claude - Claude Sonnet 4.6"
   );
-  assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
+  assert.equal(entry.models["gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
   // Combos stay untouched — `Combo: ` prefix already conveys multi-upstream.
-  assert.equal(entry.models["omniroute/claude-tier"].name, "Claude Tier");
+  assert.equal(entry.models["claude-tier"].name, "Claude Tier");
 });
 
 test("config: providerTag=false suppresses the suffix", async () => {
@@ -1364,7 +1364,7 @@ test("config: providerTag=false suppresses the suffix", async () => {
     "opencode-omniroute"
   ];
   assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entry.models["claude-sonnet-4-6"].name,
     "Claude Sonnet 4.6",
     "enriched name kept, provider tag suppressed"
   );
@@ -1396,7 +1396,7 @@ test("config: providerTag falls back to UPPER(alias) when providerDisplayName mi
   const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
     "opencode-omniroute"
   ];
-  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "CC - Claude Sonnet 4.6");
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "CC - Claude Sonnet 4.6");
 });
 
 test("config: providerTag skipped entirely when neither providerDisplayName nor providerAlias set", async () => {
@@ -1423,7 +1423,7 @@ test("config: providerTag skipped entirely when neither providerDisplayName nor
   const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
     "opencode-omniroute"
   ];
-  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
 });
 
 test("config: providerTag is idempotent — second hook call doesn't double-suffix", async () => {
@@ -1451,7 +1451,7 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
     "opencode-omniroute"
   ];
   assert.equal(
-    entryA.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entryA.models["claude-sonnet-4-6"].name,
     "Claude - Claude Sonnet 4.6"
   );
 
@@ -1462,7 +1462,7 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
     "opencode-omniroute"
   ];
   assert.equal(
-    entryB.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entryB.models["claude-sonnet-4-6"].name,
     "Claude - Claude Sonnet 4.6"
   );
 });
@@ -1516,7 +1516,7 @@ test("buildStaticProviderEntry: nested combo-ref context is the bottleneck acros
   );
   // Pre-fix: Parent would advertise 200_000 (only raw-big counted).
   // Post-fix: Parent should advertise 8_000 (TinyCombo bottleneck).
-  const parent = block.models["omniroute/parent"];
+  const parent = block.models["parent"];
   assert.ok(parent, "Parent combo must be in the static catalog");
   assert.equal(parent.limit?.context, 8_000);
 });

@omniroute/opencode-plugin/tests/provider-id-routing.test.ts

@@ -111,7 +111,9 @@ test("#6859: createOmniRouteProviderHook end-to-end — catalog keys/providerID
 // `opencode-omniroute`. Confirmed against the issue's own curl repro
 // (`model: "opencode-omniroute/hermes-smart-stack"` → "No active
 // credentials for provider: opencode-omniroute").
-test("#7976: buildStaticProviderEntry keys bare-slug combo ids with the unprefixed omnirouteProviderId (no double OC-gate prefix)", () => {
+// #9175 tightened this further: OC's `getModel` looks models up by BARE id,
+// so combo dict keys now carry NO prefix at all (not even `omniroute/`).
+test("#7976/#9175: buildStaticProviderEntry keys combos by bare slug (no prefix at all — never the OC-gate providerId)", () => {
   const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
   assert.equal(resolved.providerId, "opencode-omniroute");
   assert.equal(resolved.omnirouteProviderId, "omniroute");
@@ -131,7 +133,7 @@ test("#7976: buildStaticProviderEntry keys bare-slug combo ids with the unprefix
     "sk-test"
   );
 
-  assert.deepEqual(Object.keys(block.models), ["omniroute/hermes-smart-stack"]);
+  assert.deepEqual(Object.keys(block.models), ["hermes-smart-stack"]);
   assert.equal(
     block.models["opencode-omniroute/hermes-smart-stack"],
     undefined,

AGENTS.md

@@ -627,7 +627,7 @@ procedures are in [`docs/architecture/QUALITY_GATES.md`](docs/architecture/QUALI
   complexity) must not regress vs `quality-baseline.json`. Update via
   `npm run quality:ratchet -- --update` when a metric genuinely improves.
 - Job `test-vitest` runs `npm run test:vitest` (MCP tools, autoCombo, cache) — blocking.
-  `test:vitest:ui` is advisory until UI component tests are triaged.
+  `test:vitest:ui` has been blocking since PR #7127.
 
 **Allowlist policy (short form):** Fix the cause; use the allowlist only for pre-existing
 violations you cannot fix in the same PR. Add a comment with justification + issue number.

Dockerfile

@@ -93,7 +93,15 @@ RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
 # build from 17min to 9min on the same 32-core box. Webpack stays available as the
 # escape hatch: `--build-arg`/-e OMNIROUTE_USE_TURBOPACK=0.
 # See docs/ops/QUALITY_GATE_PLAYBOOK.md Parte 6.
-ENV OMNIROUTE_USE_TURBOPACK=1
+#
+# Declared as ARG+ENV, not a bare ENV: a bare ENV shadows any same-named ARG for
+# the rest of the stage, so `--build-arg OMNIROUTE_USE_TURBOPACK=0` was silently
+# ignored and the escape hatch above only ever worked via `-e` at runtime, never
+# at build time. Turbopack compiles in native Rust memory that lives outside the
+# V8 heap, so OMNIROUTE_BUILD_MEMORY_MB cannot bound it and a memory-constrained
+# build host gets SIGKILLed by the cgroup OOM killer with no error message.
+ARG OMNIROUTE_USE_TURBOPACK=1
+ENV OMNIROUTE_USE_TURBOPACK="${OMNIROUTE_USE_TURBOPACK}"
 
 # Next.js basePath is fixed at build time; pass OMNIROUTE_BASE_PATH here when the
 # image should serve under a reverse-proxy subpath without a runtime patch.

Makefile

@@ -0,0 +1,69 @@
+.PHONY: help install dev start build build-release lint typecheck typecheck-strict \
+        test test-unit test-vitest test-coverage test-all test-integration test-e2e \
+        check check-cycles check-docs env-sync clean
+
+# OmniRoute — convenience wrapper around the npm scripts.
+# All targets delegate to the canonical package.json scripts (single source of truth).
+
+help: ## Show this help
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-18s\033[0m %s\n", $$1, $$2}'
+
+install: ## Install dependencies (auto-generates .env from .env.example)
+	npm install
+
+dev: ## Dev server at http://localhost:20128
+	npm run dev
+
+start: ## Production server (requires a prior build)
+	npm run start
+
+build: ## Production build (Next.js 16 standalone)
+	npm run build
+
+build-release: ## Release build
+	npm run build:release
+
+lint: ## ESLint (0 errors expected)
+	npm run lint
+
+typecheck: ## TypeScript check (core)
+	npm run typecheck:core
+
+typecheck-strict: ## Strict check (no implicit any)
+	npm run typecheck:noimplicit:core
+
+test: ## Unit tests (Node native runner)
+	npm run test:unit
+
+test-unit: ## Alias for `test`
+	npm run test:unit
+
+test-vitest: ## Vitest (MCP server, autoCombo, cache)
+	npm run test:vitest
+
+test-coverage: ## Unit tests + coverage gate (60/60/60/60)
+	npm run test:coverage
+
+test-all: ## All suites (unit + vitest + ecosystem + e2e)
+	npm run test:all
+
+test-integration: ## Integration tests
+	npm run test:integration
+
+test-e2e: ## E2E (Playwright)
+	npm run test:e2e
+
+check: ## lint + test combined
+	npm run check
+
+check-cycles: ## Detect circular dependencies
+	npm run check:cycles
+
+check-docs: ## Validate documentation (incl. fabricated-docs)
+	npm run check:docs-all
+
+env-sync: ## Sync .env from .env.example
+	npm run env:sync
+
+clean: ## Remove build artifacts
+	rm -rf .build dist coverage .eslintcache

bin/cli/runtime/processSupervisor.mjs

@@ -52,8 +52,11 @@ export class ServerSupervisor {
     // silently, so a boot that never becomes ready looked like a dead hang with zero
     // output even at APP_LOG_LEVEL=debug. Pipe stdout too and buffer it alongside
     // stderr so a readiness timeout can surface what the child actually printed.
+    // #9156: macOS launchd cannot resolve bare "node" because its PATH is
+    // minimal. Always use process.execPath (the absolute path to the running
+    // Node.js binary) so the supervisor never depends on PATH resolution.
     this.child = spawn(
-      process.versions.bun ? process.execPath : "node",
+      process.execPath,
       process.versions.bun
         ? [this.serverPath]
         : buildNodeRuntimeArgs(process.env, this.memoryLimit, this.serverPath),

changelog.d/features/9000-encrypted-reasoning-replay.md

@@ -0,0 +1,2 @@
+- Add a default-off connection setting for Codex, OpenAI, and OpenAI-compatible Responses API providers that preserves client-supplied `reasoning.encrypted_content` items for replay, including per-target combo routing.
+- Omit opaque encrypted reasoning values from persisted call logs while retaining compact diagnostic markers.

changelog.d/fixes/7754-best-free-fallback.md

@@ -0,0 +1 @@
+- test(combo): guard auto/best-free never leaks the combo name as a model (#7754)

changelog.d/fixes/8542-fix.plan.md

@@ -0,0 +1 @@
+- fix(ci): aggregate all fast-gates into non-fail-fast loop so one red gate no longer masks later gates (#8542)

changelog.d/fixes/8847-bun-prebuilds.md

@@ -0,0 +1 @@
+- fix(build): include better-sqlite3 prebuilds in standalone bun bundle

changelog.d/fixes/8906-quota-pool-combo-cleanup.md

@@ -0,0 +1 @@
+- **fix(quota):** Deleting a quota pool now removes its scoped managed combos without racing in-flight pool mutations ([#8906](https://github.com/diegosouzapw/OmniRoute/pull/8906)) — thanks @xiaoyaner0201

changelog.d/fixes/8951-fix.plan.md

@@ -0,0 +1 @@
+- fix(github): add targetFormat to GPT-5.6 Sol/Terra/Luna models (#8951)

changelog.d/fixes/8997-gpt56-max-reasoning.plan.md

@@ -0,0 +1 @@
+- **fix(translator):** the Responses-to-Chat promotion path called `normalizeResponsesReasoningEffort` without the model argument, so GPT-5.6 Sol/Terra/Luna requests with `reasoning.effort: "max""` were downgraded to `"xhigh"`. The model is now threaded through, preserving `max` for GPT-5.6 while keeping the legacy downgrade for older models ([#8997](https://github.com/diegosouzapw/OmniRoute/pull/8997))

changelog.d/fixes/9034-fix.plan.md

@@ -0,0 +1 @@
+- fix(api): use configured prefix instead of raw node UUID for alias-backed model id in /v1/models (#9034)

changelog.d/fixes/9057-fix.plan.md

@@ -0,0 +1 @@
+- fix(api): auto/* routing aliases bypass API-key allowedConnections/disableNonPublicModels (#9057)

changelog.d/fixes/9096-fix-audio-speech-transcriptions-translations-provider-nodes.plan.md

@@ -0,0 +1 @@
+- fix(providers): admit audio-speech/audio-transcriptions apiType in audio route provider-node filters (#9096)

changelog.d/fixes/9134-fix.plan.md

@@ -0,0 +1 @@
+- fix(providers): resolve combo names in audio transcriptions route so /v1/models stays honest (#9134)

changelog.d/fixes/9140-fix.plan.md

@@ -0,0 +1 @@
+- fix(vscode): allow built-in auto-routing models in VS Code model filter (#9140)

changelog.d/fixes/9142-fix.plan.md

@@ -0,0 +1 @@
+- fix(background): detect Anthropic top-level system prompts for background task detection (#9142)

changelog.d/fixes/9156-macos-autostart-execpath.md

@@ -0,0 +1 @@
+- fix(cli): use process.execPath for macOS launchd autostart

changelog.d/fixes/9160-fix.plan.md

@@ -0,0 +1 @@
+- fix(model-discovery): ingest capabilities.effort_tiers for synced models (#9160)

changelog.d/fixes/9168-streamed-responses-tool-null.plan.md

@@ -0,0 +1 @@
+- fix(translator): buffer and normalize upstream tool-call argument deltas so optional null values are stripped before reaching the client (#9168)

changelog.d/fixes/9177-fix.plan.md

@@ -0,0 +1 @@
+- fix(translator): avoid double-normalizing tool names in Gemini-to-Claude response path (#9177)

changelog.d/fixes/9269-fix.plan.md

@@ -0,0 +1 @@
+- **fix(classify429):** add missing `have exhausted their quota` pattern so the synthetic 429 from auth.ts is recognized as quota exhaustion, preventing the combo loop from burning retries against the same provider instead of falling back to a healthy one ([#9269](https://github.com/diegosouzapw/OmniRoute/issues/9269))

changelog.d/fixes/9305-fix.plan.md

@@ -0,0 +1 @@
+- fix(sse): broaden OMNIROUTE_SSE_COMMENTS to accept 'false','0','no' and gate metadata comment emission (#9305)

changelog.d/fixes/9306-fix.plan.md

@@ -0,0 +1 @@
+- fix(lmarena): encode SSE stream chunks as Uint8Array to prevent TextDecoder TypeError (#9306)

changelog.d/fixes/9486-claude-400-quota.md

@@ -0,0 +1 @@
+- fix(providers): classify 400 out of extra usage as quota_exhausted for Anthropic OAuth

changelog.d/fixes/9615-docker-colocate-partial-trace.md

@@ -0,0 +1 @@
+- **fix(docker):** standalone co-location now completes packages Next's file tracing materialized partially (package.json without its `main` payload) — unblocks the Docker Hub publish that failed on every v3.8.50 push with `Cannot find module '@atjsh/llmlingua-2/dist/index.js'` ([#9615](https://github.com/diegosouzapw/OmniRoute/pull/9615))

changelog.d/fixes/9623-connection-test-recovery.md

@@ -0,0 +1 @@
+- fix(resilience): failed connection test now sets a short cooldown so connections recover after transient outages (#9623)

changelog.d/fixes/9624-telemetry-cleanup-wiring.md

@@ -0,0 +1 @@
+- fix(db): wire telemetry cleanup scheduler in Next.js startup path (#9624)

changelog.d/fixes/9625-domain-cost-ms.md

@@ -0,0 +1 @@
+- fix(db): align domain_cost_history cleanup cutoff with millisecond column (#9625)

changelog.d/fixes/9626-playground-errors.md

@@ -0,0 +1 @@
+- fix(playground): surface provider model loading errors and offer retry (#9626)

changelog.d/fixes/9633-npm-build-files.md

@@ -0,0 +1 @@
+- fix(build): add build-next-isolated.mjs sibling imports to package.json files array

changelog.d/fixes/9675-anonymous-fallback-disable-toggle.md

@@ -0,0 +1 @@
+- **fix(providers):** new per-provider `noAuthFallbackDisabledProviders` setting lets operators disable the synthetic anonymous (no-auth) credential fallback for API-key providers whose static definition declares `anonymousFallback: true` (e.g. `opencode-go`, `opencode-zen`) — upstream endpoints now reject anonymous requests with `401 Missing API key`, so the fallback added latency and caused UI health/reconnect churn. Real keyed connections keep working and recover automatically once quota state clears; true no-auth providers (`opencode`, `mimocode`, …) are unaffected, with `blockedProviders` remaining their disable mechanism. Default behavior is unchanged ([#9675](https://github.com/diegosouzapw/OmniRoute/pull/9675))

changelog.d/fixes/9695-docker-bundler-build-arg.md

@@ -0,0 +1 @@
+- **fix(docker):** `--build-arg OMNIROUTE_USE_TURBOPACK=0` now reaches the builder stage — a bare `ENV` was shadowing the `ARG`, so the documented webpack escape hatch was silently ignored and memory-constrained hosts were OOM-killed with no error output ([#9695](https://github.com/diegosouzapw/OmniRoute/pull/9695))

changelog.d/fixes/9719-combo-connection-pins.md

@@ -0,0 +1 @@
+- fix(db): clear stale combo connection pins when provider connections are deleted (#9719)

changelog.d/fixes/9730-persist-rtk-renderers.md

@@ -0,0 +1 @@
+- fix(compression): persist `enableRenderers` through `normalizeRtkConfig` so RTK renderer settings survive a DB round-trip ([#9730](https://github.com/diegosouzapw/OmniRoute/pull/9730))

changelog.d/fixes/9737-memory-id-route-backend.md

@@ -0,0 +1 @@
+- Fixed `GET`/`PUT`/`DELETE /api/memory/[id]` always failing with a 500 (`Primary backend "sqlite" not registered`) when the route was reached before any other memory endpoint in the same process.

changelog.d/fixes/9737-route-body-validation.md

@@ -0,0 +1 @@
+- Replaced hand-rolled body type checks with Zod validation in the plugins marketplace install route and the three Dario admin routes, restoring the `t06:route-validation` gate (Hard Rule #7).

changelog.d/fixes/9737-vietnamese-locale-parity.md

@@ -0,0 +1 @@
+- Restore Vietnamese locale parity after the entity-normalization sync dropped Radar, provider, and mini-playground messages.

changelog.d/fixes/9788-model-catalog-gateway-permissions.md

@@ -0,0 +1 @@
+- **fix(api):** Model catalogs no longer expose functional gateway mirrors unless the API key permits the mirror's final public model ID ([#9788](https://github.com/diegosouzapw/OmniRoute/pull/9788)) — thanks @xz-dev

changelog.d/fixes/9826-command-code-responses-usage.md

@@ -0,0 +1 @@
+- **fix(executors):** preserve Command Code usage in `/v1/responses` streams so Codex clients receive real input, output, cache, and reasoning token counts ([#9826](https://github.com/diegosouzapw/OmniRoute/pull/9826)) — thanks @MrShitFox

changelog.d/fixes/9828-codex-redundant-oneof-enum.md

@@ -0,0 +1 @@
+- **fix(executors):** prevent intermittent Codex `upstream_empty_response` errors for tool schemas that combine `oneOf` const branches with a matching sibling `enum` by removing only the semantically redundant `oneOf`; bare, narrowing, non-matching, and type-discriminated `oneOf` schemas remain unchanged. ([#9828](https://github.com/diegosouzapw/OmniRoute/pull/9828))

changelog.d/fixes/9834-cursor-selected-image-blobid.md

@@ -0,0 +1 @@
+- **fix(cursor):** SelectedImage uses `blobIdWithData` + session blobStore, with JPEG soft-cap prep via sharp ([#9834](https://github.com/diegosouzapw/OmniRoute/pull/9834)) — thanks @yansigit

changelog.d/maintenance/9614-opencode-plugin-bare-key-suite.md

@@ -0,0 +1 @@
+- **test(cli):** OpenCode plugin suite realigned to the bare-key static-catalog contract from #9178/#9175 (21 tests were red on every opencode-plugin CI run; 287/287 after) ([#9614](https://github.com/diegosouzapw/OmniRoute/pull/9614))

changelog.d/maintenance/9839-v3850-quality-ratchets.md

@@ -0,0 +1 @@
+- Reconcile the final v3.8.50 bundle-size and file-size ratchets against the measured release tip, preserving exact direction-down ceilings and their source attribution.

config/quality/dependency-allowlist.json

@@ -44,6 +44,7 @@
     "commander",
     "concurrently",
     "cross-env",
+    "cron-parser",
     "csv-stringify",
     "ctrf",
     "dompurify",

config/quality/eslint-suppressions.json

@@ -1673,7 +1673,7 @@
   },
   "tests/unit/base-executor-sanitize-effort.test.ts": {
     "@typescript-eslint/no-explicit-any": {
-      "count": 48
+      "count": 6
     }
   },
   "tests/unit/batch-deletion.test.ts": {
@@ -3339,4 +3339,4 @@
       "count": 5
     }
   }
-}
+}

config/quality/file-size-baseline.json

@@ -1,6 +1,8 @@
 {
+  "_rebaseline_2026_08_09_9296_adobe_media_capabilities": "PR #9296 (artickc, fix/adobe-firefly-model-capabilities) own growth: src/app/api/v1/models/catalog.ts 1590->1597 (+7). The image and video catalog serializers now expose the already-normalized Adobe Firefly discovery capability data (media_capabilities, plus the existing video modality/size fields) at their only response-emission chokepoints. The discovery parser and capability normalization remain in open-sse/services/adobeFireflyModels.ts; extracting these seven serialization fields would obscure the catalog contract. Covered by tests/unit/adobe-firefly.test.ts and tests/unit/image-upscale.test.ts.",
   "_rebaseline_2026_08_08_v3850_base_drift_batch_9757": "Base drift on release/v3.8.50, not own growth: the 08-06..08-08 merge batches grew 12 already-frozen (or newly-landed) files without carrying their rebaselines — the dedicated rebaseline PR #9616 was closed as 'superseded' but its file-size entries never actually reached the base, and later merges (#8894 combos page, #9539 EditConnectionModal, #8895 models route, #9294/#9293 catalog, #9541 db/core, #8970 tokenHealthCheck, #8925 mcp schemas+server, #8890 accountFallback, #9467 chat.ts, #8931 openai-to-kiro, ProxyRegistryManager) kept growing them. All 12 values re-measured on THIS branch's tree (= pure tip + this PR's 1-line chat.ts fix, which adds zero lines). This PR's own source changes (chat.ts identifier restore, stream.ts format carve-out) do not grow any frozen file past these values.",
   "_rebaseline_2026_08_08_migration_135_collision": "fix(db): resolve migration version 135 numbering collision — #9449's 135_connection_runtime_state.sql and #8908's 135_migrate_model_capability_max_token.sql both claimed version 135 (#9449 branched before #8908 merged and never got renumbered before landing on release/v3.8.50), which threw 'Migration version collision detected' the moment ANY code touched the database — a fresh install/deploy from this tip cannot even boot. Renumbered the later-landing file to 140 (next free slot) and added the matching isSchemaAlreadyApplied('140') retroactive guard, matching the established pattern already used for the prior 135/136 -> 137/138 renumber in the same file. Own growth: src/lib/db/migrationRunner.ts 1084->1094 (+10, the new case block) — irreducible, matches the existing per-case guard pattern exactly. Covered by tests/unit/migration-135-numbering-collision.test.ts (2/2), confirmed failing (reproducing the exact live crash) against the pre-fix colliding filenames, passing after.",
+  "_rebaseline_2026_08_08_9183_reasoning_cache_index_sync": "Extracted fix(responses-api): sync reasoning-cache write index with the fixed read side (from the originally-authored #9183) — chatCore.ts's write side cached every response under a hardcoded messageIndex:0, and translator/index.ts's plain-turn (non-tool-call) cache-key lookup ALSO still hardcoded messageIndex 0 at its call site (a second, previously-undiscovered instance of the same hardcoding bug, found while re-verifying this fix against the current upstream tip — the two never agreed once a conversation went past its first assistant turn, so DeepSeek/Xiaomi-mimo plain-turn reasoning replay silently missed the cache). Own growth: open-sse/handlers/chatCore.ts 5034->5042 (+8, computing messageIndex from the incoming request's message count at both the streaming and non-streaming cache-write call sites) — irreducible call-site wiring. Covered by tests/unit/reasoning-cache.test.ts (new end-to-end write/read regression test, rebaselined below) and tests/unit/translator-helper-branches.test.ts fixture updates. Other #9183 sub-fixes (output_index collision prevention, reasoning-content-alias generalization) were originally assumed already superseded by upstream's own independent fix — a live incident 2026-08-08 disproved that for the message-vs-tool-call collision case specifically (fixed separately in #9822); not re-extracted here since this PR's own scope is the narrower messageIndex sync only.",
   "_rebaseline_2026_08_02_9259_rolling_rpm": "PR #9259 (issue #8733) own growth: open-sse/services/rateLimitManager.ts baseline 1060->1167 (+107; final source 1153). The existing withRateLimit chokepoint now composes process-local rolling RPM leases with Bottleneck admission, releases pre-dispatch leases on queue timeout/abort/connection disable, preserves caller abort reasons, and wires 429/header state into the extracted rollingRpmGate.ts. The remaining growth is irreducible lifecycle wiring at the dispatch boundary plus the real watchdog test hooks needed to verify queued-wedge recovery; moving it further would obscure lease ownership and Bottleneck cleanup. Covered by the focused rate-limit manager/sliding-window suite (33/33); distributed multi-instance coordination remains explicitly out of scope.",
   "_rebaseline_2026_07_24_8470_hyperagent_sticky_thread": "PR #8470 (artickc, fix/hyperagent-tool-loop-thread-sticky) own growth: open-sse/executors/hyperagent.ts 936->1025 (wc -l; check-file-size.mjs counts via split(\"\\n\").length so the gate sees 937->1026, +89, crosses the 1000 cap). Fixes a real bug where a reverse-conversion proxy (text-Intent/JSON to Claude Code native tool_calls) rewrites assistant messages between agentic tool-loop turns, breaking HyperAgent’s conversation-prefix fingerprint and cold-starting the thread mid tool-loop. Adds Anthropic tool_use/tool_result flattening to extractMessageText() plus a new rootUserFingerprint()/root-key lookup tier in resolveHyperAgentThreadBinding()/storeHyperAgentThreadAfterTurn() so the thread stays sticky across the tool loop. Cohesive additions inside the existing single-file executor; not extractable without splitting the executor mid-request-flow. Covered by tests/unit/executor-hyperagent.test.ts (19/19, +5 new cases for tool_result/tool_use flattening + root-key stickiness). Pre-merge review flagged a cross-conversation root-key collision risk (tracked in the PR’s own mandatory pre-merge checklist, not yet addressed) — unrelated to this file-size ratchet, tracked separately by /fix-prs.",
   "_rebaseline_2026_07_25_8494_capability_filter_fail_closed": "PR #8494 (fix/capability-filters-fail-closed, #8488) own growth: open-sse/services/combo.ts 3640->3693 (+53) adds a fail-closed guard after filterTargetsByRequestCompatibility() — when every eligible target is excluded by request-capability filtering (vision/tools/etc) instead of quota/health, the combo now returns an explicit `capability_mismatch` 400 (describeCapabilityFilterExhaustion, imported from combo/comboStructure.ts) rather than silently falling through to a generic no-targets error, plus a `compatFilterFailOpen` escape hatch (combo config OR settings) mirrored at both the main/auto and round-robin call sites for symmetry. combo/comboStructure.ts (previously under cap, un-frozen) grows 794->918 (+124) — new home for describeCapabilityFilterExhaustion + providerSupportsEmulatedToolCalling (#5240 emulated tool-calling exemption so fail-closed does not regress prompt-emulation-only combos like all-chatgpt-web). Irreducible orchestration wiring at the existing filter chokepoint (same precedent as #7301's universal-cooldown-retry generalization). Companion test tests/unit/combo-routing-engine.test.ts 3409->3449 (+40, fail-closed/fail-open coverage across both call sites) also rebaselined. Covered by tests/unit/8488-capability-filter-fail-closed.test.ts (new) + 95/95 passing across both files. Structural shrink of combo.ts tracked in #3501.",
@@ -16,7 +18,6 @@
   "_rebaseline_2026_07_19_7546_ghe_copilot_route": "PR #7546 (GHE Copilot OAuth provider) own growth: oauth/[provider]/[action]/route.ts 960->963 (gate units, +3 = ghe-copilot device-code wiring at the existing multi-provider device-code branch — reading + HTTPS-validating the gheUrl search param (isValidGheUrl guards at both raw entry points, security-review hardening, 963->970), adding ghe-copilot to the no-PKCE provider set, and building the provider config override / threading gheUrl through poll->postExchange extraData). Mirrors the existing kiro/amazon-q startUrl override pattern right above it in the same branch; cohesive with the existing device-code dispatch chokepoint, not separately extractable without splitting a single provider-switch mid-branch. Frozen so can only shrink; structural shrink tracked in #3501.",
   "_rebaseline_2026_07_19_6846_nvidia_concurrency_gate": "Issue #6846 Phase 1 (nvidia NIM local RPM budget + per-model lockout + per-connection concurrency cap) own growth: open-sse/executors/default.ts 877->890 (+13 = the irreducible call-site wiring at DefaultExecutor.execute(), the only place nvidia requests dispatch through — the existing session-pool body was extracted verbatim into a new private executeWithSessionPool() so the outer execute() can wrap it in the nvidia concurrency-gate acquire/finally-release). All actual gating logic (semaphore key + cap resolution) lives in the new leaf open-sse/executors/default/nvidiaConcurrencyGate.ts (not frozen, well under cap). Covered by tests/unit/nvidia-quota-phase1.test.ts.",
   "_rebaseline_2026_07_18_v3849_provider_detail_wiring": "Merge campaign R2/R3 (2026-07-18): three authorized PRs each add irreducible call-site wiring to ProviderDetailPageClient.tsx — #7360 +5 (ProviderQuotaVisibilityToggle render, component extracted), #7419 +4 (NoAuthProviderControls wiring), #7062 +3 (Dahl provider hook) = 786->798. All three follow the extracted-component pattern (AgentrouterConsoleFields precedent); the frozen file only takes the wiring. Structural shrink tracked in #3501.",
-  "_rebaseline_2026_07_25_dario_upstream_proxy_selector": "PR #8523 (Dario embedded service): upstream-proxy mode selector replaces the binary CLIProxyAPI toggle with Native/CLIProxyAPI/Dario/Fallback + a fallback-backend picker. ProviderDetailPageClient.tsx 798->804 (+6, new hook fields threaded through to ConnectionsListPanel), ConnectionRow.tsx 942->958 (+16, the mode <select> + conditional fallback-backend <select> replacing a single pill button), useProviderConnections.ts 954->986 (+32, upstreamProxyMode/upstreamProxyFallbackBackend state + handleSetUpstreamProxyMode, handleToggleCliproxyapiMode kept as a thin backward-compat wrapper for the existing hook-shape test). All additive UI/state for the new modes — no unrelated refactor.",
   "_rebaseline_2026_07_18_pr7653_chat_tracker_import": "PR #7653 merge-interaction growth: release moved chat.ts to its 1796 cap while this PR adds the single side-effect import 'quotaTrackersBatch.ts' (line 130) — chat.ts IS the canonical quota-fetcher registration point (codex/bailian/deepseek/openrouter/opencode/generic all import+register there), so the +1 is irreducible call-site wiring. 1796->1797. Covered by tests/unit/{agentrouter,v0,freemodel}-quota-fetcher.test.ts.",
   "_rebaseline_2026_07_17_pr7653_agentrouter_console_fields": "PR #7653 own growth (missing acceptance criterion: the AgentRouter quota tracker (#6850) read providerSpecificData.consoleApiKey/newApiUserId but neither field had dashboard UI for provider agentrouter — consoleApiKey was gated to bailian-coding-plan only and newApiUserId had zero UI). AddApiKeyModal.tsx 961->967 (+6) and EditConnectionModal.tsx 1278->1286 (+8) = import + a single <AgentrouterConsoleFields .../> render call plus the newApiUserId formData init field. The actual Input rendering (both consoleApiKey reuse + the new newApiUserId field) was EXTRACTED into a new leaf src/app/(dashboard)/dashboard/providers/[id]/components/modals/AgentrouterConsoleFields.tsx (48 LOC, <cap), mirroring the QuotaScrapingFields.tsx / GlmTeamQuotaFields.tsx precedent (#6351) so the frozen modals only carry the irreducible call-site wiring. Persist logic lives in connectionProviderSpecificData.ts (not frozen). Covered by tests/unit/agentrouter-connection-modal-fields.test.ts.",
   "_rebaseline_2026_07_17_v3849_6842_free_window_wiring": "PR #7651 (openrouter :free-window quota tracking) follow-up: the counter shipped built but never wired into the request pipeline, so combos kept spending guaranteed-429 requests on exhausted free-tier targets. Own growth: src/sse/services/auth.ts 2461->2462 (+1, irreducible at the existing model-aware preflight chokepoint — the `provider === \"codex\"` check that forwards requestedModel into the connection arg is extended to also cover `openrouter`, one added boolean + a doc comment, offset to a single net line by dropping the now-redundant inline condition). Enforcement itself lives in open-sse/services/openrouterQuotaFetcher.ts (not frozen) and the dispatch-time record/correct hooks live in open-sse/executors/base.ts (not frozen). Covered by tests/unit/openrouter-free-window-wiring-6842.test.ts.",
@@ -161,136 +162,11 @@
   "_rebaseline_2026_06_20_1409_1294_models": "Re-baseline src/lib/db/models.ts 1184->1221: combined growth of sibling fixes #1409 (cascade-delete orphaned model aliases when a provider is removed) + #1294 (persist max_input_tokens/max_output_tokens on custom models), both adding CRUD at the existing models domain module. Cohesive db module; not extractable.",
   "_rebaseline_2026_06_20_4389_thinking_toolchoice": "Re-baseline base.ts 1387->1399 (#4389): tool_choice-forced thinking guard at the existing Claude wire-image injection chokepoint (effThinking gate avoids the Anthropic 400 when tool_choice forces a tool). Cohesive guard; structural shrink tracked in #3501.",
   "_rebaseline_2026_07_18_6979_codex_test": "PR #6979 own growth: executor-codex.test.ts 1340->1347 (+7 = generalized ensureThinkingBudget assertion added to the existing codex thinking-budget cases). antigravity-test bump 942->977 REVERTED here: #7408's test split dropped that file to 888, so this PR's +35 fits under the original 942 frozen cap.",
+  "_rebaseline_2026_07_24_8354_logs_timeline_sidebar": "PR #8354 (hartmark, feature/scrolling-log) own growth: src/shared/constants/sidebarVisibility/sections.ts 812->820 (+8, the single new logs-timeline SidebarItemDefinition entry added to LOGS_GROUP.items for the new /dashboard/logs/timeline scrolling request-timeline page). Irreducible data-literal wiring at the existing sidebar-sections chokepoint, same shape as every other item in the file; not extractable without an ad-hoc single-item exception to the file's otherwise-uniform multi-line item style.",
   "cap": 1000,
-  "frozen": {
-    "_rebaseline_2026_06_22_4644_deepseek_web_tools": "PR #4644 (BugsBag/robust deepseek-web tool-call parsing): open-sse/executors/deepseek-web.ts 1117->1125 (+8). The new agentic tool-call path emits surrounding text + reasoning before tool_calls and swaps to the dedicated deepseekWebTools.ts parser; the +8 lines are cohesive wiring at the existing transformSSE chokepoint (the parser itself lives in the new deepseekWebTools.ts file, already under cap). The PR's own fast-gate (PR->release) does not run check:file-size, so this surfaced only at release reconcile. Covered by tests/unit/deepseek-web-tools-variants.test.ts + deepseek-web-tools-execute.test.ts.",
-    "_rebaseline_2026_06_23_4712_deepseek_web_tool_results": "PR for #4712 (deepseek-web drops role:tool): open-sse/executors/deepseek-web.ts 1125->1148 (+23). messagesToPrompt() now folds role:\"tool\" results into the single-prompt transcript (recovering the tool name from the preceding assistant tool_calls by tool_call_id) instead of silently dropping them; the lines are cohesive wiring inside the existing function. Covered by tests/unit/deepseek-web-tool-result-prompt-4712.test.ts.",
-    "_rebaseline_2026_06_24_headroom_strategy": "Headroom-aware connection selection (dario technique): combo.ts 3168->3180 (+12 = a new `else if (strategy === \"headroom\")` dispatch branch in handleComboChat that delegates to orderTargetsByHeadroom + its log line, plus the import). The actual logic lives OUT of the god-file: the pure ranker rankByHeadroom/computeHeadroom is the new leaf open-sse/services/combo/headroomRanking.ts (91 LOC, <cap) and the async orderer orderTargetsByHeadroom is appended to the existing open-sse/services/combo/quotaStrategies.ts (<cap) next to its sibling reset-aware/reset-window orderers (reuses their connection-expansion machinery). headroom = 1 - max(util_5h, util_7d) from getSaturation (src/lib/quota/saturationSignals.ts), prefers the connection with the most free capacity. Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. fill-first stays default; all existing strategies untouched. Covered by tests/unit/combo-headroom-ranking.test.ts (pure helper) + tests/unit/combo-headroom-strategy.test.ts (orderer, saturation injected). Structural shrink of combo.ts tracked in #3501.",
-    "_rebaseline_2026_06_24_quota_share_strategy": "Dedicated quota-share strategy (Phase 3 #9): combo.ts 3180->3190 (+10 = one new `else if (strategy === \"quota-share\")` dispatch branch in handleComboChat that delegates 100% to selectQuotaShareTarget + its log line, plus the import). All the new logic lives OUT of the god-file in two new leaves under open-sse/services/combo/: quotaShareInflight.ts (in-flight counter with TTL/lease, ~150 LOC <cap) and quotaShareStrategy.ts (per-model bucket gating via isBucketSaturated + DRR proportional to weight + P2C over in-flight, ~240 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the headroom/reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. ZERO existing strategy cases were modified — only this branch was added, and the qtSd/ combos switched from fill-first to quota-share in src/lib/quota/quotaCombos.ts. Covered by tests/unit/quota-share-strategy.test.ts (gating, DRR fairness, P2C in-flight, fail-open, activation). Structural shrink of combo.ts tracked in #3501.",
-    "_rebaseline_2026_06_24_task_aware_routing": "Task-aware routing strategy (port PR #2045, OmniRoute #4945): combo.ts 3190->3225 (+35) = one new `else if (strategy === \"task-aware\")` dispatch branch delegating 100% to selectTaskAwareTarget + its imports/log lines. All scoring/classification logic lives OUT of the god-file in the new leaf open-sse/services/taskAwareRouting.ts (553 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors quota-share/headroom/reset-aware branches). ZERO existing strategy cases modified. Covered by tests/unit/combo-task-aware.test.ts (35 tests). Structural shrink of combo.ts tracked in #3501.",
-    "_rebaseline_2026_06_26_fidelity_gate_extraction": "Milestone-B fidelity-gate wiring residual: bodyToText+gateAdvance extracted to fidelityGateStep.ts (889->854, -35), but the StackOptions.fidelityGate field, the `const fidelityGate` reads at the two stacked-loop dispatch chokepoints, and the import of FidelityGateConfig are irreducible wiring that cannot leave strategySelector without an architectural refactor of the pre-existing stacked pipeline. Net: 889->854 (+6 vs the pre-Milestone-B frozen 848). Covered by tests/unit/compression/*.test.ts (940 pass).",
-    "_rebaseline_2026_06_27_5193_5203_antigravity_oauthmodal": "Antigravity remote-login own growth: OAuthModal.tsx 960->969 (gate units). #5193 (+~4: remote paste instruction shown for all remote incl. Google + its rationale comment) and #5203 (+~5: handleManualSubmit credential-blob branch + button guard; submit logic extracted to oauthBlobSubmit.ts to minimize). Frozen set to the SUM so either merge order passes. Cohesive at the existing manual-submit chokepoint.",
-    "_rebaseline_2026_06_27_5193_antigravity_basered": "Base-red (pre-existing release drift, fast-gate PR->release skips check:file-size): accountFallback.ts 1773->1777 and src/app/api/providers/[id]/test/route.ts 924->940 were already over their frozen caps on release/v3.8.39 independent of any antigravity change. Owner chose to rebaseline (keep the documented issue-reference comments #1846/#1449/#347 etc.) rather than accept the contributor comment-stripping in #5200/#5198. Reverted #5200 to restore the comments; bumped these two frozen caps to the actual base sizes. No logic change.",
-    "_rebaseline_2026_06_28_5237_impersonation_ua_refresh": "PR #5237 (refresh impersonation UAs): grok-web.ts 1871->1873 (+2), muse-spark-web.ts 1284->1302 (+18), perplexity-web.ts 1013->1032 (+19). Net semantic change in each file is a single User-Agent constant (Chrome 147->149 for grok/muse; perplexity kept at Firefox 148 to stay matched with the firefox_148 TLS profile — the contributor's 152 bump was reverted to avoid a UA-vs-JA3 mismatch, #2459). The growth is Prettier reflow that lint-staged unavoidably applies to these grandfathered long-line files the moment they are touched; not extractable. src/sse/services/auth.ts 2336->2401 in the same reconcile is #5222's antigravity-LRU-retry growth that merged via --admin without a baseline bump.",
-    "_rebaseline_2026_06_28_5243_risk_gate_prepass": "PR #5243 (compression risk-gate pre-pass) own growth: open-sse/services/compression/strategySelector.ts 854->899 (+45). The three exported entry points (applyCompression/applyStackedCompression/applyStackedCompressionAsync) become thin wrappers over pure-extracted private bodies (runCompression/runStackedCompression/runStackedCompressionAsync) so the risk-gate mask->run->restore wrapper sits strictly OUTSIDE the per-step loop — a single universal integration point. The wrapper logic itself (resolveRiskGate/withRiskGate) lives in the new riskGate/strategyWrap.ts (<cap); the residual growth is the duplicated thin-wrapper signatures + the extracted bodies' dispatch boundary, guarded by a byte-identical parity test (riskGateIntegration). Default off (DEFAULT_COMPRESSION_CONFIG unchanged). Not extractable without hiding the dispatch boundary, mirroring prior compression rebaselines. Structural shrink tracked in #3501.",
-    "_rebaseline_2026_06_28_5275_correlation_id_extract": "Extraction of the safe CorrelationId subset of #5275 (hartmark) — request correlation id stored in call_logs (migration 109) and returned via the X-Correlation-Id response header, WITHOUT the combo/resilience or build/lazy-loading changes (those stay in #5275). Own growth: callLogs.ts 975->985 (correlation_id column on CallLogSummaryRow + read/map), usageHistory.ts 983->988 (correlationId metadata normalize), chat.ts 1575->1632 (withCorrelationId response wiring + combo-failure log carrying correlationId), chatHelpers.ts new 811 (withCorrelationId helper + reqId threading; was 791<cap pre-feature). Cohesive request/logging chokepoint wiring; structural shrink of chat.ts tracked in #3501.",
-    "_rebaseline_2026_06_29_4038_cas_guard": "PR (#4038) own growth: tokenRefresh.ts 2103->2181 (+78 = the compare-and-swap guard on the refresh persist — runWithCasGuard/getActiveCasGuard AsyncLocalStorage pair mirroring runWithOnPersist, casGuardShouldSkipPersist that rereads the row right before persisting and skips the write when a concurrent writer already rotated the refresh_token past the one presented, plus getCasGuardStats counters). Fixes the sibling-rotation-revert → token-family-revocation storm. Gated behind an active guard (opt-in; no guard => byte-identical). Wiring lives at the two persist chokepoints inside getAccessToken; the comparison reuses wasRefreshTokenRotated from refreshSerializer. Not extractable without splitting the refresh hot path.",
-    "_rebaseline_2026_06_29_5286_memoization": "PR #5286 own growth: strategySelector.ts 899->960 (+61 = the opt-in result-memoization branches in applyCompression/applyCompressionAsync — principal+determinism gate, makeMemoKey lookup/store with model+supportsVision folded into the key, recompute-with-memo-off). Default off (memoizeCompressionResults), so zero behavior change. The memo helpers live in the leaf resultMemo.ts (<cap); the chokepoint wiring here is not extractable. Structural shrink of this hot-path file tracked in #3501.",
-    "_rebaseline_2026_07_01_v3843_release_5609": "Rebaseline v3.8.43 (PR #5609 release reconciliation). DRIFT dos 109 commits do ciclo: 8 god-files existentes cresceram (ApiManagerPageClient 2983->3017, combos/page 4594->4608, AddApiKeyModal 868->869, providerPageHelpers 974->996, chat.ts 1635->1647, auth.ts 2401->2403, batchProcessor 828->915, combo.ts 3368->3387) + 2 novos acima do cap (huggingchat.ts 813, tests web-cookie-providers-new 827) + 4 test files cresceram. Modularizacao deferida (blast-radius mid-release); congelado no estado atual p/ o proximo ciclo ratchetar daqui.",
-    "_rebaseline_2026_07_02_5816_qoder": "PR #5816 (@AgentKiller45, qoder PAT via qodercli): qoderCli.ts 666->989, new-above-cap frozen (owner-approved baseline freeze). The growth is the legitimate PAT job-token exchange + quota parsing CLI transport (the pure-JS Cosy path 500'd on every PAT request); extracting the spawn/parse helpers now would just add indirection to a contributor PR mid-merge. Test frozen also raised for this PR's coverage growth: providers-page-utils.test.ts 1052->1092. Additionally clears an inherited base-red from the already-merged #5933 (codex json_schema->text.format): translator-openai-responses-req.test.ts 1097->1172 (+75 regression tests, no offending branch left). All remain frozen (cannot grow further); release captain's rebaseline-at-release supersedes.",
-    "_rebaseline_2026_07_09_6126_clinepass_dual_auth": "PR #6126 (@hajilok, dual-auth ClinePass) own growth: tokenRefresh.ts 2181->2182 (+1 = a single `case \"clinepass\":` fallthrough label added to the existing `case \"cline\":` in _getAccessTokenInternal's provider switch, so clinepass token refresh dispatches to the already-shared refreshClineToken() instead of silently falling through to the generic OAuth refresh). Irreducible 1-line switch-case wiring at the existing chokepoint; the header-building logic for the same feature was extracted to a new leaf src/shared/utils/clineAuth.ts::buildClinepassHeaders() (well under cap) to avoid growing open-sse/executors/default.ts. Covered by tests/unit/clinepass-provider.test.ts.",
-    "_rebaseline_2026_07_09_6363_kiro_external_idp": "PR #6363 (@artickc, Kiro external IdP) own growth: tokenRefresh.ts 2182->2249 (+67 = the external_idp refresh branch inside refreshKiroToken — standard public-client OAuth2 refresh_token grant against the org IdP tokenEndpoint via buildExternalIdpRefreshParams/isExternalIdpAuthMethod from the new leaf open-sse/services/kiroExternalIdp.ts, with invalid_grant/invalid_client -> unrecoverable_refresh_error mapping). Cohesive addition at the existing refreshKiroToken chokepoint. Covered by tests/unit/kiro-external-idp.test.ts.",
-    "_rebaseline_2026_07_09_6587_kiro_api_key_auth": "PR #6587 (@strangersp) own growth for Kiro long-lived API-key auth, merged onto v3.8.47 tip: openai-to-kiro.ts 890->912 (+22, auth-header selection for API-key-vs-OAuth-token connections), providerLimits.ts 998->1000 (+2, API-key auth-type branch), translator-openai-to-kiro.test.ts 1234->1257 (+23), providers-page-utils.test.ts 1109->1107 (net -2 after merging with parallel release drift; connectionMatchesProviderCard api_key coverage added), provider-validation-specialty.test.ts 2856->2980 (+124 net after merge with parallel release drift; this PR also removed the file's `@typescript-eslint/no-explicit-any` eslint-suppression entry by fixing all `any` usages, adding typed replacements). Cohesive additive feature growth, well tested; not extractable without splitting the existing chokepoints mid-merge.",
-    "_rebaseline_2026_07_09_6678_routing_strategy_9router": "#6678 (SeaXen) — 9router-parity Routing Strategy settings card + per-provider/combo sticky-round-robin override. Own growth: ProviderDetailPageClient.tsx 784->786 (single ProviderAccountRoutingCard mount + import), auth.ts 2448->2458 (providerStrategies override resolution: fallbackStrategy/stickyRoundRobinLimit per-provider cascade in getProviderCredentials). Both additive, zero unrelated refactor; new UI/logic lives in new files (ProviderAccountRoutingCard.tsx, RoutingStrategyCard.tsx, rrState.ts::resolveComboStickyRoundRobinLimit). chat.ts value below reflects the current release tip (grown by other concurrent PRs, e.g. #6640), not this PR own change.",
-    "_rebaseline_2026_07_10_6318_omp_letta": "PR #6318 (@hamsa0x7, omp+letta CLI integrations) own growth: cliTools.ts (+53 = 2 registry entries incl. omp docsUrl) and cliRuntime.ts (+18 = runtime-detection wiring for the 2 new tools). Cohesive registry/wiring growth at the existing chokepoints; scope reduced from the original 5 tools (pi/codewhale/jcode shipped separately).",
-    "_rebaseline_2026_07_10_gcf_v3_2_decode": "PR #6838 own growth: new vendored file open-sse/services/compression/engines/headroom/gcf/decode_generic.ts frozen at 880 (> 800 cap). It is the vendored GCF generic-profile decoder (spec v3.2 nested flattening plus the prototype-pollution / hasOwnProperty hardening added in this PR's Gemini review). Kept as one file faithful to upstream gcf-typescript so re-vendoring stays a clean copy rather than a re-split each cycle (sibling generic.ts/scalar.ts stay < cap; extraction would also fragment the file's frozen eslint no-explicit-any suppressions). Round-trip + prototype-pollution regression coverage in tests/unit/compression/headroom-smartcrusher.test.ts. Frozen: only shrinks from here.",
-    "_rebaseline_2026_07_12_v3847_mergeprs_tail": "v3.8.47 /merge-prs tail (owner-approved): src/lib/localDb.ts NEW>800 (799->805, +6 re-exports countFreeProxies + recordFreeProxySyncErrors/clearFreeProxySyncErrors/getFreeProxySyncErrors + FreeProxySyncErrors type for #6909 free-pool relay-repair; re-export-only per Hard Rule #2, not extractable).",
-    "_rebaseline_2026_07_15_7070_combos_memo": "PR #7070 (perf/p1-memo) own growth: src/app/(dashboard)/dashboard/combos/page.tsx 4655->4656 (+1 = React.memo wrapping of ComboCard). Covered by tests/unit/ui/combos-page-smoke.test.tsx.",
-    "_rebaseline_2026_07_18_7399_xai_oauth_modal": "PR #7399 (xAI OAuth PKCE) own growth: OAuthModal.tsx 993->998 (+5 = provider entry + PKCE flow branch wiring at the existing provider-switch chokepoint; the provider logic itself lives in src/lib/oauth/providers/xai-oauth.ts, new leaf). Third irreducible wiring bump on this modal (969->989->993->998); structural shrink tracked in #3501.",
-    "_rebaseline_2026_07_19_6636_codex_session_json": "#6636 own growth: OAuthModal.tsx 998->1030 (gate units, split(\"\\n\").length incl. trailing newline; +32 = session-JSON paste branch for handleManualSubmit plus a shared submitCodexAccessToken() helper extracted from the pre-existing bare-JWT branch, mirroring the #5203 oauthBlobSubmit.ts extraction precedent; the normalizer logic itself lives in the new src/lib/oauth/utils/codexSessionImport.ts leaf module, not here). Fourth irreducible wiring bump on this modal (969->989->993->998->1030); structural shrink tracked in #3501.",
-    "_rebaseline_2026_07_19_7546_ghe_copilot_modal": "PR #7546 (GHE Copilot OAuth provider) own growth: OAuthModal.tsx 1030->1056 (gate units). Adds a gheUrl input state, routes ghe-copilot through the existing device-code branch, and threads gheUrl into the device-code request/poll extraData at the existing provider-switch chokepoints (+~24 lines, cohesive with the same pattern as #7399/#6636). The standalone GHE enterprise-URL config step JSX (originally +31 lines inline) was extracted to the new src/shared/components/oauthModal/GheConfigStep.tsx leaf component to minimize the bump; what remains is the irreducible provider-branch wiring. Fifth bump on this modal (969->989->993->998->1030->1056); structural shrink tracked in #3501.",
-    "_rebaseline_2026_07_19_7787_ic2_localdb_reexports": "PR #7787 (IC2 raw connections cache + lazy-decrypt) own growth: localDb.ts 805->807 (gate units, +2). localDb.ts is the re-export-only layer (hard rule #2 — no logic); the PR adds 4 new db/readCache re-exports (touchConnectionLastUsed, getCachedRawProviderConnections, getCachedProviderConnectionById, getCachedProviderNodes) required by existing barrel importers. Irreducible for a re-export list; frozen so it can only shrink.",
-    "_rebaseline_2026_07_20_7779_routingcombo_thread": "PR #7779 own growth: chatHelpers.ts 876->877 (+1, thread routingComboId into executeChatWithBreaker for compression-combo assignment). Frozen so it can only shrink.",
-    "_rebaseline_2026_07_20_7819_autocandidateoverrides_reexport": "PR for #7819 (Level 1+2: read-only auto/* candidate transparency + per-API-key exclusions) own growth: localDb.ts 807->808 (+1). Adds a single `export * from \"./db/autoCandidateOverrides\"` barrel re-export (hard rule #2 — no logic) for the new DB module backing per-apiKey candidate exclusions. Irreducible for a re-export list; frozen so it can only shrink.",
-    "_rebaseline_2026_07_21_8027_grok_cli_auth_json_paste": "PR #8027 (RaviTharuma, fix(grok-cli) #7610) own growth: OAuthModal.tsx 1080->1100 (gate units). Requires the full ~/.grok/auth.json (with refresh_token) on the paste-import path instead of a bare JWT, at the existing paste-token chokepoint (renamed tab label, updated instructions/placeholder, textarea for the auth.json blob, inline error surface). The validation logic itself (parseGrokCliPasteToken, previously an inline ~75-line function) was extracted to the new src/lib/oauth/utils/grokCliAuthJson.ts leaf module — mirroring the #6636/#7546 extraction precedent — so only the irreducible UI wiring remains here. Sixth bump on this modal (969->989->993->998->1030->1056->1100); structural shrink tracked in #3501.",
-    "_rebaseline_2026_07_21_8034_compression_exclusions_sidebar": "#8034 (compression exclusions dashboard tab) own growth: sections.ts 796->806 (+10, one new COMPRESSION_CONTEXT_GROUP sidebar item linking /dashboard/compression/exclusions). The file was already 796/800 before this PR (organic growth from prior sidebar entries), so a single new nav item pushed it 6 lines over cap. Freezing at 806 (cannot grow further); the sidebar item array is data, not extractable logic.",
-    "_rebaseline_2026_07_22_7936_namespace_roundtrip": "#7936 (@RCrushMe, Responses-Chat namespace round-trip identity seam) own growth: open-sse/translator/response/openai-responses.ts 1092->1125 (+33) and open-sse/utils/stream.ts 2814->2869 (+55) — threading the namespace-identity seam through the Responses↔Chat translation + stream paths so tool-call namespaces survive the round-trip. Cohesive translation/stream wiring at existing chokepoints, frozen at new size.",
-    "_rebaseline_2026_07_22_8010_codex_responses_engine": "PR #8010 (@JxnLexn) own growth: open-sse/mcp-server/schemas/tools.ts 1497->1505 (+8 = threading the new \"codex-responses\" literal into the compressionConfigureInput strategy/autoTriggerMode Zod enums and setCompressionEngineInput engine enum, mirroring the existing rtk/omniglyph enum entries; no new tool). open-sse/services/compression/strategySelector.ts 1043->1054 (+11 = one new `if (mode === \"codex-responses\")` dispatch branch in runCompression that delegates 100% to the new codexResponsesEngine.apply, mirroring the existing rtk single-mode dispatch, plus threading config.codexResponsesConfig.preserveToolNames into the shared adaptBodyForCompression call at the 3 existing call sites). src/lib/db/compression.ts (untracked, new-file cap 800) 794->845 (+51 = normalizeCodexResponsesConfig, mirroring the existing normalizeRtkConfig normalizer, plus registering \"codex-responses\" in the COMPRESSION_MODES/STACKED_PIPELINE_ENGINE_IDS/SINGLE_MODE_ENGINE sets and the getCompressionSettings load/save switch) — added to the baseline at its current size. All three are cohesive dispatch/normalizer wiring at existing chokepoints (mirroring the prior compression-mode rebaselines #6534/#6556), not extractable without hiding the mode-dispatch boundary. Covered by tests/unit/compression/codex-responses.test.ts (6) + omniglyph-registries.test.ts/types.test.ts (22, updated for the new mode).",
-    "_rebaseline_2026_07_22_8034_compression_exclusions_persistence": "#8034 (compression exclusions) own growth: src/lib/db/compression.ts 845->850 (+5 = threading the new compressionExclusions field through the existing getCompressionSettings/saveCompressionSettings load/save switch over the shared key_value compression namespace — no new table, no raw SQL). Mirrors the prior compression-field rebaselines (#8010 codex-responses normalizer at the same chokepoint); the load/save switch is a single dispatch boundary, not extractable without hiding it. Covered by the PR's 8 node:test + 3 vitest cases.",
-    "_rebaseline_2026_07_22_8050_model_lockout_exact_family": "#8050 (@AndrianBalanescu) own growth: accountFallback.ts 1864->1892 (+28) — exact-vs-family model-lockout scoping (getModelLockKey/isModelLocked/clearModelLock/getModelLockoutInfo) so an Antigravity 404 for one bare model no longer hijacks the whole family cooldown. Cohesive lockout logic; frozen at new size.",
-    "_rebaseline_2026_07_22_8056_headroom_minrows": "#8056 (@RaviTharuma, persist Headroom minRows) own growth: src/lib/db/compression.ts 850->866 (+16 HeadroomConfig+DEFAULT_HEADROOM_CONFIG+normalize/store in get/updateCompressionSettings) and open-sse/services/compression/strategySelector.ts 1054->1060 (+6 merge settings.headroom into stacked stepConfig). Cohesive settings-persistence + stacked-merge wiring at existing chokepoints, frozen at new size.",
-    "_rebaseline_2026_07_22_8081_reasoning_placeholder_guard": "#8081 (@Dingding-leo) own growth: openai-responses.ts 1125->1137 (+12) restructuring the reasoning-placeholder guard so it skips only the empty content block and still emits finish_reason/tool_calls in the same chunk. Cohesive translator wiring; frozen at new size.",
-    "_rebaseline_2026_07_22_8210_openrouter_midstream_error": "PR #8210 (hartmark, fix/openrouter-midstream-error-surfacing) own growth: open-sse/translator/response/openai-responses.ts 1137->1163 (+26) measured on the merged tip (release 1137 + this PR own growth). Adds a single new branch inside openaiToOpenAIResponsesResponse() that detects an OpenRouter-style mid-stream aggregator error (HTTP 200 SSE chunk with empty choices + a top-level error object) and surfaces it as state.upstreamError instead of silently falling through to the no-op/awaitingTrailingUsage path, which previously masked the failure as a false empty-success completion and skipped combo fallback. Irreducible call-site addition at the existing chunk-dispatch chokepoint (mirrors the Gemini-to-OpenAI translator's #4177 precedent for the same class of upstream error surfacing). Note: this baseline entry does NOT cover the separate pre-existing +11 drift already on the release tip from #8081/#8162 (1125->1136, unrelated reasoning-placeholder-stripping fix merged after this PR branched) — that drift belongs to the maintainer's rebaseline, not this PR.",
-    "_rebaseline_2026_07_22_8211_gemini_malformed_tool_choice": "PR #8211 (hartmark, fix/gemini-malformed-function-call-tool-choice) own growth: open-sse/translator/response/gemini-to-openai.ts 771->821 (+50, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds MALFORMED_FUNCTION_CALL/UNEXPECTED_TOOL_CALL handling inside geminiToOpenAIResponse(): synthesizes a `malformed_tool_call` tool_calls entry so finish_reason normalizes to the standard \"tool_calls\" instead of an unrecognized raw enum value that OpenAI-compatible clients (e.g. OpenClaw) silently ignore, and always synthesizes (rather than skipping when a real tool call already exists) so a malformed attempt alongside a real one in the same turn is not silently discarded. Irreducible cohesive addition at the existing candidate/finishReason translation chokepoint (mirrors the 9router#2462 raw-finish-reason precedent immediately below it in the same function). Covered by the PR's own tests/unit test additions for both the malformed-only and malformed-plus-real-call cases.",
-    "_rebaseline_2026_07_22_8213_chat_abandoned_target_abort": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/sse/handlers/chat.ts 1794->1860 (+66, measured against the PR's own merge-base — the release tip separately carries an unrelated -5 net shrink from #8013's antigravity callable-catalog alignment, which this PR's branch does not include and this entry does not cover). Adds resolveDispatchClientRawRequest(): merges a per-target modelAbortSignal into clientRawRequest.signal (via mergeAbortSignals) so a combo target abandoned by comboTargetTimeoutMs actually observes its own abort and reaches its cleanup path, instead of hanging forever inside withRateLimit/acquireAccountSemaphore and leaking a permanent 'pending' dashboard entry (live incident, log id 1784418258231-14961a). Also wires combo-exhausted rejection logging to capture request body + attempted models via the new rejectedRequestUsage helper. Irreducible additions at the existing chat dispatch chokepoint. Covered by the PR's own combo-config + integration test additions.",
-    "_rebaseline_2026_07_22_8213_combo_cooldown_wait_recording": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/combo.ts 3548->3604 (+56, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Fixes combo cooldown-wait state recording so a bogus 503 is no longer crystallized when the cooldown-wait vars reset every setTry, adds an OpenAI-format SSE error frame path for combo-exhausted rejections (capturing request body + attempted models), and gives an abandoned per-target dispatch its own timeout instead of leaking a permanent 'pending' dashboard entry. Irreducible additions at the existing handleComboChat dispatch/retry chokepoint (mirrors the prior quota-share/headroom/task-aware strategy-branch precedents already frozen in this file). Covered by the PR's own combo-config + Gemini TPM-ceiling benchmark test additions.",
-    "_rebaseline_2026_07_22_8213_gemini_tpm_quota_cooldown_wait": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/accountFallback.ts 1857->1932 on the merged tip (release 1892 incl #8050 +35, plus this PR own growth +40); measured against the PR own merge-base was 1857->1898 (+41 — the release tip separately carries an unrelated +34 from #8050's antigravity 404 model-not-found lockout scoping, which this PR's branch does not include and this entry does not cover). Own growth is the Gemini TPM-ceiling classification + cooldown-wait wiring feeding into the combo cooldown-wait state machine (rate-limit wedge recovery) introduced by this PR's commit series. Irreducible additions at the existing account-fallback/model-lockout chokepoint. Covered by the PR's own gemini-rate-limit-tracker and TPM-ceiling benchmark test additions.",
-    "_rebaseline_2026_07_22_8213_health_unblock_model_cooldowns": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/app/(dashboard)/dashboard/health/page.tsx 1094->1165 (+71, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds handleUnblockAll/handleUnblockOne dashboard actions (DELETE /api/resilience/model-cooldowns) so an operator can manually clear a Gemini TPM-wedge model lockout surfaced by this PR's cooldown-wait fixes, instead of waiting out the ceiling. Irreducible UI wiring at the existing health-page action chokepoint. Covered by the PR's own dashboard/resilience test additions.",
-    "_rebaseline_2026_07_22_8213_requestloggerdetail_unblock_ui": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/shared/components/RequestLoggerDetail.tsx 799->941 (+142, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip; crosses the general 800-line new-file cap so is frozen here for the first time). Adds a collapsible section header (open/expand-less toggle) plus per-log-entry unblock (`unblocking`/`cleared` state, isCombo503 detection) so the request-logger detail panel surfaces the same Gemini TPM cooldown-wait / model-lockout unblock action introduced by this PR at the individual-request level (mirrors the health-page bulk unblock action added in the same PR). Covered by the PR's own dashboard/resilience test additions.",
-    "_rebaseline_2026_07_22_fusion_8013_8098_antigravity": "Fusion of #8013 (backryun, catalog/IDE-CLI-split rewrite) + #8098 (nguyenha935, protocol-fidelity/fail-closed/credits/tool-cloaking): open-sse/services/usage/antigravity.ts NEW 802 (>cap 800, +2 — #8098 credits/tier usage service on #8013's profile-aware headers). Test growth (models-catalog-route 1605->1608, provider-models-route 1752->1757 from #8013 Gemini 3.6 catalog) tracked in testFrozen.",
-    "_rebaseline_2026_07_23_8127_grok_weekly_quota": "#8127 (@apoapostolov) own growth: src/sse/handlers/chat.ts 1861->1865 (+4) — weekly quota tracking for grok-web wires a quota-fetch hook at the existing dispatch chokepoint. Thin wiring mirroring adjacent provider-quota branches; not extractable. Covered by tests/unit/grok-quota-fetcher.test.ts.",
-    "_rebaseline_2026_07_23_8143_empty_catch_logging": "#8143 (@chirag127) own growth: open-sse/utils/stream.ts 2869->2887 (+18) — replacing empty catch blocks in the SSE stream subsystem with console.debug logging (Rule #6 silent-swallow fix, issues #8138-#8142). Cohesive logging additions at the existing catch chokepoints, not extractable; frozen at new size. Covered by tests/unit/stream-handler-catch-logging-8143.test.ts.",
-    "_rebaseline_2026_07_23_8219_cache_ttl_settings_sidebar": "#8219 (@oyi77) own growth: sections.ts 806->813 (+7) — configurable model-catalog cache-TTL settings adds a new sidebar nav entry + its visibility wiring. Sidebar item array is data, not extractable logic; frozen at new size.",
-    "_rebaseline_2026_07_23_8247_8248_model_unhealthy": "#8247+#8248 own growth: accountFallback.ts 1940->1941 (+1, irreducible import statement only — the substantive #8248 DEGRADED-pattern classifier was extracted into open-sse/config/errorConfig.ts, which has ample headroom, instead of growing this frozen file; #8247's fix is a single existing-line condition change, net zero lines). Scoping the credits-exhausted 403/429 branch to isCompatibleProvider() (per-model-quota openai/anthropic-compatible-* nicknames) so it stays model-scoped instead of terminalling the whole connection, and classifying NVIDIA NIM 'Function ... DEGRADED' 400 bodies as model-access-denied instead of a raw passthrough 400. Covered by tests/unit/8247-accountfallback-model-unhealthy.test.ts and tests/unit/8248-accountfallback-nvidia-degraded.test.ts.",
-    "_rebaseline_2026_07_23_8252_combo_400_advance": "#8252 (@RaviTharuma) own growth: accountFallback.ts 1932->1940 (+8) + combo.ts 3604->3630 (+26) — advance combo on model-scoped 400s wrapped as invalid/Bad-Request. Irreducible wiring at existing account-fallback + combo dispatch chokepoints. Covered by combo-model-scoped-400-advance.test.ts.",
-    "_rebaseline_2026_07_23_8266_alibaba_media": "#8266 (@backryun) own growth: imageRegistry.ts 821->979 (+158) — Alibaba-family media models (Qwen image/video, Bailian, Wan) added to the image/video registry. Registry model data, not extractable logic; frozen at new size.",
-    "_rebaseline_2026_07_24_8388_compression_detail_persist": "#8388 (compression engine DETAIL settings — Headroom/session-dedup/CCR — dropped on save) own growth: src/lib/db/compression.ts 866->872 (+6 = irreducible call-site wiring at the existing getCompressionSettings/updateCompressionSettings chokepoint: one import line, one `...buildDetailConfigDefaults()` spread in the seed config, and one `case \"sessionDedup\": case \"ccr\": applyDetailConfigUpdate(config, key, parsed); break;` load-switch case, mirroring the existing headroom/#8056 case immediately above it). The actual normalizer logic (normalizeSessionDedupConfig/normalizeCcrConfig, matching SESSION_DEDUP_SCHEMA/CCR_SCHEMA bounds) was EXTRACTED into a new leaf src/lib/db/compressionDetailNormalizers.ts (well under cap) so this frozen file only carries the minimal dispatch wiring. Covered by tests/unit/8388-compression-detail-persist.test.ts (schema-accept + full DB save->reload round-trip for both new sub-objects, plus a no-regression assertion on the existing headroom round-trip).",
-    "_rebaseline_2026_07_24_responses_toolcalls_log_summary": "hartmark, fix/responses-tool-calls-log-summary own growth: open-sse/translator/response/openai-responses.ts 1163->1174 (+11). closeToolCall() now also writes the completed tool call into the shared state.toolCalls Map (already populated by the openai-to-claude / claude-to-openai / gemini-to-openai response translators) so stream.ts's completion-log summary builder (which reads state.toolCalls, not this translator's own funcCallIds/funcNames/funcArgsBuf bookkeeping) reports finish_reason \"tool_calls\" and message.tool_calls for openai->openai-responses translated streams instead of always logging \"stop\" with no tool_calls — the actual client-facing SSE events were already correct; only the persisted call-log summary was wrong. Irreducible call-site addition at the existing tool-call-close chokepoint. Covered by the new regression test in tests/unit/translator-resp-openai-responses.test.ts.",
-    "_rebaseline_2026_07_25_8476_combo_input_bound_homogeneous_scope": "PR #8476 (herjarsa, fix/8375-8459-combo-image-fixes, #8375) own growth: open-sse/services/combo.ts 3642->3679 (+37 net: +29 the PR's own isInputBoundFailure short-circuit for deterministic context_length_exceeded/context_window_exceeded failures, +8 a /green-prs pre-merge fix scoping that short-circuit to homogeneous remainders only — the shipped code fired unconditionally on ANY target, regressing the intentional heterogeneous-combo fallback #6637/isContextOverflow400 protects, exactly as flagged by this PR's own review evidence but never actually implemented in the branch). The fix compares orderedTargets[i+1..] modelStr against the failing target's modelStr at the existing executeTarget dispatch chokepoint (mirrors the sameProviderNext precedent a few lines below) — irreducible call-site wiring, not extractable without hiding the dispatch boundary. Covered by tests/unit/combo-input-bound-failure-8375.test.ts (homogeneous pool still short-circuits) and the new tests/unit/combo-input-bound-heterogeneous-8375.test.ts (heterogeneous combo now correctly falls through to the larger-context target).",
-    "_rebaseline_2026_07_25_adobe_firefly_reference_images": "Follow-up to #8006: storage upload + referenceBlobs for image/video and /v1/images/edits dispatch. adobeFireflyClient.ts 1958->2317 (+upload helpers, extract sources, resolve blob ids). Note: 2317 not 2316 — check-file-size.mjs counts LOC via split(\"\\n\").length (counts the trailing-newline empty element), which is 1 higher than `wc -l` on a file ending in \\n; the PR's original entry (2316) was measured with wc -l and undercounted by 1 against the actual gate.",
-    "_rebaseline_pr1043_minimax_tts": "Upstream port decolua/9router#1043 (toanalien) own growth: audioSpeech.ts 965->1061 (+96). Adds MiniMax T2A v2 TTS dispatch (handleMinimaxSpeech + hexToBytes helper) — provider entry was already in audioRegistry (format: minimax-tts) but no handler existed, falling through to the OpenAI-compatible default that fails (T2A has custom shape + hex-encoded audio + base_resp envelope). New branch sits next to the other inline provider branches (xiaomi-mimo, coqui, tortoise, aws-polly) — extracting would just create indirection. Covered by tests/unit/minimax-tts-1043.test.ts (3 tests, GREEN: success, base_resp error, invalid-hex).",
-    "_rebaseline_pr4592_exclude_exhausted_auto": "Reconcile #4592 already-merged growth: combo.ts 2991->3036 (+45, terminal-status quota-cutoff exclusion in buildAutoCandidates + opt-in gate). Fast-gate PR->release does not run check:file-size.",
-    "open-sse/executors/antigravity.ts": 1528,
-    "open-sse/executors/base.ts": 1640,
-    "open-sse/executors/chatgpt-web.ts": 3241,
-    "open-sse/executors/codex.ts": 1562,
-    "open-sse/executors/cursor.ts": 1563,
-    "open-sse/executors/deepseek-web.ts": 1148,
-    "open-sse/executors/grok-web.ts": 1044,
-    "open-sse/executors/muse-spark-web.ts": 1405,
-    "open-sse/handlers/chatCore.ts": 5034,
-    "open-sse/handlers/imageGeneration.ts": 3101,
-    "open-sse/handlers/responseSanitizer.ts": 1128,
-    "open-sse/handlers/search.ts": 1536,
-    "open-sse/handlers/videoGeneration.ts": 1063,
-    "open-sse/mcp-server/schemas/tools.ts": 1553,
-    "open-sse/mcp-server/server.ts": 1448,
-    "open-sse/mcp-server/tools/advancedTools.ts": 1120,
-    "open-sse/services/accountFallback.ts": 1978,
-    "open-sse/services/adobeFireflyClient.ts": 2385,
-    "open-sse/services/claudeCodeCompatible.ts": 1202,
-    "open-sse/services/combo.ts": 3648,
-    "open-sse/services/compression/strategySelector.ts": 1060,
-    "open-sse/services/rateLimitManager.ts": 1167,
-    "open-sse/translator/response/openai-responses.ts": 1204,
-    "open-sse/utils/cursorAgentProtobuf.ts": 1505,
-    "open-sse/utils/stream.ts": 2889,
-    "src/app/(dashboard)/dashboard/HomePageClient.tsx": 1388,
-    "src/app/(dashboard)/dashboard/analytics/ComboHealthTab.tsx": 1031,
-    "src/app/(dashboard)/dashboard/api-manager/ApiManagerPageClient.tsx": 3117,
-    "src/app/(dashboard)/dashboard/cache/media/MediaPageClient.tsx": 1067,
-    "src/app/(dashboard)/dashboard/combos/page.tsx": 4703,
-    "src/app/(dashboard)/dashboard/costs/CostOverviewTab.tsx": 1283,
-    "src/app/(dashboard)/dashboard/costs/quota-share/components/PoolWizard.tsx": 1022,
-    "src/app/(dashboard)/dashboard/endpoint/EndpointPageClient.tsx": 2615,
-    "src/app/(dashboard)/dashboard/health/page.tsx": 1165,
-    "src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx": 1324,
-    "src/app/(dashboard)/dashboard/providers/page.tsx": 1944,
-    "src/app/(dashboard)/dashboard/runtime/RuntimePageClient.tsx": 1201,
-    "src/app/(dashboard)/dashboard/settings/components/PricingTab.tsx": 1019,
-    "src/app/(dashboard)/dashboard/settings/components/ProxyRegistryManager.tsx": 1470,
-    "src/app/(dashboard)/dashboard/settings/components/ResilienceTab.tsx": 1123,
-    "src/app/(dashboard)/dashboard/settings/components/RoutingTab.tsx": 1629,
-    "src/app/(dashboard)/dashboard/settings/components/SystemStorageTab.tsx": 1573,
-    "src/app/(dashboard)/dashboard/usage/components/BudgetTab.tsx": 1028,
-    "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": 2148,
-    "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx": 1119,
-    "src/app/api/providers/[id]/models/route.ts": 2361,
-    "src/app/api/v1/models/catalog.ts": 1590,
-    "src/lib/tokenHealthCheck.ts": 1053,
-    "src/lib/db/apiKeys.ts": 1529,
-    "src/lib/db/core.ts": 1639,
-    "src/lib/db/migrationRunner.ts": 1094,
-    "src/lib/db/models.ts": 1097,
-    "src/lib/db/providers.ts": 1034,
-    "src/lib/memory/retrieval.ts": 1073,
-    "src/lib/tailscaleTunnel.ts": 1202,
-    "src/lib/usage/providerLimits.ts": 1013,
-    "src/shared/components/OAuthModal.tsx": 1134,
-    "src/shared/components/RequestLoggerV2.tsx": 1629,
-    "src/shared/components/analytics/charts.tsx": 1035,
-    "src/shared/services/cliRuntime.ts": 1122,
-    "src/sse/handlers/chat.ts": 1904,
-    "src/sse/services/auth.ts": 2508,
-    "tests/unit/account-fallback-service.test.ts": 1572,
-    "tests/unit/provider-validation-specialty.test.ts": 2985,
-    "open-sse/executors/hyperagent.ts": 1026,
-    "open-sse/executors/default.ts": 1042,
-    "open-sse/executors/kiro.ts": 1069,
-    "open-sse/translator/request/openai-to-kiro.ts": 1057
-  },
   "testCap": 1000,
   "testFrozen": {
+    "tests/unit/reasoning-cache.test.ts": 1035,
     "_rebaseline_2026_06_27_5193_antigravity_test": "#5193 own test growth: oauth-providers-config.test.ts 870->873 (+3: antigravity projectId assertion + 50ms tick for the now fire-and-forget onboarding, matching the no-PKCE/no-openid flow).",
     "_rebaseline_2026_07_02_5928_base_red": "web-cookie-providers-new.test.ts 845->850: #5928 (test(security) Kimi Web URL host parse, CodeQL #689) grew the file +5 lines and merged into release/v3.8.44 WITHOUT rebaselining, leaving a fast-gates base-red that blocked every subsequent PR->release. Test growth is legitimate (a security regression test); maintainer absorbs the drift here. Frozen at 850.",
     "_rebaseline_2026_07_09_6126_clinepass_dualauth": "#6126 (ClinePass dual-auth) own test growth: oauth-providers-config.test.ts 842->845 (+3: clinepass key/config/required-fields entries reusing the Cline WorkOS flow config, needed after registering clinepass in the oauth.ts PROVIDERS enum).",
@@ -413,7 +289,134 @@
   "_rebaseline_2026_07_27_3850_relax_filesize_cap_v2_20pct": "OWNER-APPROVED TEMPORARY relax for v3.8.50-3.8.54 PREPARE phase (docs/ROADMAP.md). v1 was cap 800->900 / testCap 800->900 on 2026-07-27; v2 = v1 +20% buffer = cap 900->1000 (+100), testCap 900->1000 (+100). Justification: same as complexity v2 — the v3.8.50 release cut coincides with high-merge activity; owner accepted enlarging the headroom to cover the entire PREPARE phase (5 minor cycles .50-.54) without per-PR rebaseline noise. Targets: decompose-existing-frozen unchanged (frozen still only-shrink — see frozen[] entries and the 105 files >900 that still need structural decomposition regardless of cap); this only relaxes the cap for NEW files in the decompose/extract-while-PREPARE phase (.51='executor registry in-place' and .52='combo.ts decomposition' create new leaf modules above 800). RE-TIGHTENING MANDATORY in v3.8.51: cap target 850 = 850 once decomposition wave stabilizes (gives 150 units of post-tighten headroom vs the new 1000 ceiling). Tracked via same roadmap issue as complexity v2. Window: v3.8.50 (release cut) → v3.8.54 close (RE-TIGHTEN at v3.8.51 prep merge per ROADMAP.md). Last entry unless measured regression. v1 entry retained below for audit trail.",
   "_rebaseline_2026_07_27_3850_relax_filesize_cap": "OWNER-APPROVED TEMPORARY relax for v3.8.50-3.8.54 PREPARE phase (docs/ROADMAP.md). cap 800->900 (+100), testCap 800->900 (+100). Targets: decompose-existing-frozen unchanged (frozen still only-shrink); this only relaxes the cap for NEW files in the decompose/extract-while-PREPARE phase (.51='executor registry in-place' and .52='combo.ts decomposition' create new leaf modules above 800). RE-TIGHTENING MANDATORY in v3.8.51: cap target 850 = 850 once decomposition wave stabilizes. SUPERSEDED by _rebaseline_2026_07_27_3850_relax_filesize_cap_v2_20pct (v1 +20% buffer) — retained for audit. Tracked via same roadmap issue.",
   "_rebaseline_2026_07_27_v3849_train1h": "Merge-train 1H (31 PRs) — owner-approved 2026-07-27. Two distinct causes, kept separate on purpose: (1) GENUINE irreducible growth at existing chokepoints — providerLimits/auth (#8632 Kimi quota-reset recovery), rateLimitManager (#8616 idle wedged limiters), models-catalog-route.test (#8610 OpenCode Go effort aliases); (2) COLLISION with #8585, which banked shrinks measured on the pre-train release tip while 30 sibling PRs in the SAME train grew those files again — chat/accountFallback (#8628), chatCore (#8613), videoGeneration (#8581), imageGeneration. The zero-headroom frozen entries cannot absorb either. Ceilings re-pinned to the post-merge tip; #8612 (also in this train) automates shrink-banking so this self-inflicted drift stops recurring. Detail: src/lib/usage/providerLimits.ts 1006->1013 (#8632); src/sse/services/auth.ts 2492->2508 (#8632); open-sse/services/rateLimitManager.ts 1014->1060 (#8616); src/sse/handlers/chat.ts 1842->1845 (#8628); open-sse/handlers/chatCore.ts 4939->4955 (#8613); open-sse/handlers/imageGeneration.ts 3100->3101 ((sem PR — teto do #8585)); open-sse/handlers/videoGeneration.ts 1038->1063 (#8581); open-sse/services/accountFallback.ts 1965->1966 (#8628); tests/unit/models-catalog-route.test.ts 1608->1636 (#8610)",
-  "_rebaseline_2026_08_02_9242_token_health_transient": "PR #9242 (fix/refresh-circuit-transient): src/lib/tokenHealthCheck.ts 1021 (new file, above cap 1000). The file consolidates token-refresh health checking logic that was previously scattered across auth.ts and tokenRefresh.ts. Cohesive single-responsibility module for refresh circuit state management; not extractable without splitting the refresh state machine. Covered by tests/unit/tokenHealthCheck-transient.test.ts.",
+  "frozen": {
+    "_rebaseline_2026_06_22_4644_deepseek_web_tools": "PR #4644 (BugsBag/robust deepseek-web tool-call parsing): open-sse/executors/deepseek-web.ts 1117->1125 (+8). The new agentic tool-call path emits surrounding text + reasoning before tool_calls and swaps to the dedicated deepseekWebTools.ts parser; the +8 lines are cohesive wiring at the existing transformSSE chokepoint (the parser itself lives in the new deepseekWebTools.ts file, already under cap). The PR's own fast-gate (PR->release) does not run check:file-size, so this surfaced only at release reconcile. Covered by tests/unit/deepseek-web-tools-variants.test.ts + deepseek-web-tools-execute.test.ts.",
+    "_rebaseline_2026_06_23_4712_deepseek_web_tool_results": "PR for #4712 (deepseek-web drops role:tool): open-sse/executors/deepseek-web.ts 1125->1148 (+23). messagesToPrompt() now folds role:\"tool\" results into the single-prompt transcript (recovering the tool name from the preceding assistant tool_calls by tool_call_id) instead of silently dropping them; the lines are cohesive wiring inside the existing function. Covered by tests/unit/deepseek-web-tool-result-prompt-4712.test.ts.",
+    "_rebaseline_2026_06_24_headroom_strategy": "Headroom-aware connection selection (dario technique): combo.ts 3168->3180 (+12 = a new `else if (strategy === \"headroom\")` dispatch branch in handleComboChat that delegates to orderTargetsByHeadroom + its log line, plus the import). The actual logic lives OUT of the god-file: the pure ranker rankByHeadroom/computeHeadroom is the new leaf open-sse/services/combo/headroomRanking.ts (91 LOC, <cap) and the async orderer orderTargetsByHeadroom is appended to the existing open-sse/services/combo/quotaStrategies.ts (<cap) next to its sibling reset-aware/reset-window orderers (reuses their connection-expansion machinery). headroom = 1 - max(util_5h, util_7d) from getSaturation (src/lib/quota/saturationSignals.ts), prefers the connection with the most free capacity. Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. fill-first stays default; all existing strategies untouched. Covered by tests/unit/combo-headroom-ranking.test.ts (pure helper) + tests/unit/combo-headroom-strategy.test.ts (orderer, saturation injected). Structural shrink of combo.ts tracked in #3501.",
+    "_rebaseline_2026_06_24_quota_share_strategy": "Dedicated quota-share strategy (Phase 3 #9): combo.ts 3180->3190 (+10 = one new `else if (strategy === \"quota-share\")` dispatch branch in handleComboChat that delegates 100% to selectQuotaShareTarget + its log line, plus the import). All the new logic lives OUT of the god-file in two new leaves under open-sse/services/combo/: quotaShareInflight.ts (in-flight counter with TTL/lease, ~150 LOC <cap) and quotaShareStrategy.ts (per-model bucket gating via isBucketSaturated + DRR proportional to weight + P2C over in-flight, ~240 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the headroom/reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. ZERO existing strategy cases were modified — only this branch was added, and the qtSd/ combos switched from fill-first to quota-share in src/lib/quota/quotaCombos.ts. Covered by tests/unit/quota-share-strategy.test.ts (gating, DRR fairness, P2C in-flight, fail-open, activation). Structural shrink of combo.ts tracked in #3501.",
+    "_rebaseline_2026_06_24_task_aware_routing": "Task-aware routing strategy (port PR #2045, OmniRoute #4945): combo.ts 3190->3225 (+35) = one new `else if (strategy === \"task-aware\")` dispatch branch delegating 100% to selectTaskAwareTarget + its imports/log lines. All scoring/classification logic lives OUT of the god-file in the new leaf open-sse/services/taskAwareRouting.ts (553 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors quota-share/headroom/reset-aware branches). ZERO existing strategy cases modified. Covered by tests/unit/combo-task-aware.test.ts (35 tests). Structural shrink of combo.ts tracked in #3501.",
+    "_rebaseline_2026_06_26_fidelity_gate_extraction": "Milestone-B fidelity-gate wiring residual: bodyToText+gateAdvance extracted to fidelityGateStep.ts (889->854, -35), but the StackOptions.fidelityGate field, the `const fidelityGate` reads at the two stacked-loop dispatch chokepoints, and the import of FidelityGateConfig are irreducible wiring that cannot leave strategySelector without an architectural refactor of the pre-existing stacked pipeline. Net: 889->854 (+6 vs the pre-Milestone-B frozen 848). Covered by tests/unit/compression/*.test.ts (940 pass).",
+    "_rebaseline_2026_06_27_5193_5203_antigravity_oauthmodal": "Antigravity remote-login own growth: OAuthModal.tsx 960->969 (gate units). #5193 (+~4: remote paste instruction shown for all remote incl. Google + its rationale comment) and #5203 (+~5: handleManualSubmit credential-blob branch + button guard; submit logic extracted to oauthBlobSubmit.ts to minimize). Frozen set to the SUM so either merge order passes. Cohesive at the existing manual-submit chokepoint.",
+    "_rebaseline_2026_06_27_5193_antigravity_basered": "Base-red (pre-existing release drift, fast-gate PR->release skips check:file-size): accountFallback.ts 1773->1777 and src/app/api/providers/[id]/test/route.ts 924->940 were already over their frozen caps on release/v3.8.39 independent of any antigravity change. Owner chose to rebaseline (keep the documented issue-reference comments #1846/#1449/#347 etc.) rather than accept the contributor comment-stripping in #5200/#5198. Reverted #5200 to restore the comments; bumped these two frozen caps to the actual base sizes. No logic change.",
+    "_rebaseline_2026_06_28_5237_impersonation_ua_refresh": "PR #5237 (refresh impersonation UAs): grok-web.ts 1871->1873 (+2), muse-spark-web.ts 1284->1302 (+18), perplexity-web.ts 1013->1032 (+19). Net semantic change in each file is a single User-Agent constant (Chrome 147->149 for grok/muse; perplexity kept at Firefox 148 to stay matched with the firefox_148 TLS profile — the contributor's 152 bump was reverted to avoid a UA-vs-JA3 mismatch, #2459). The growth is Prettier reflow that lint-staged unavoidably applies to these grandfathered long-line files the moment they are touched; not extractable. src/sse/services/auth.ts 2336->2401 in the same reconcile is #5222's antigravity-LRU-retry growth that merged via --admin without a baseline bump.",
+    "_rebaseline_2026_06_28_5243_risk_gate_prepass": "PR #5243 (compression risk-gate pre-pass) own growth: open-sse/services/compression/strategySelector.ts 854->899 (+45). The three exported entry points (applyCompression/applyStackedCompression/applyStackedCompressionAsync) become thin wrappers over pure-extracted private bodies (runCompression/runStackedCompression/runStackedCompressionAsync) so the risk-gate mask->run->restore wrapper sits strictly OUTSIDE the per-step loop — a single universal integration point. The wrapper logic itself (resolveRiskGate/withRiskGate) lives in the new riskGate/strategyWrap.ts (<cap); the residual growth is the duplicated thin-wrapper signatures + the extracted bodies' dispatch boundary, guarded by a byte-identical parity test (riskGateIntegration). Default off (DEFAULT_COMPRESSION_CONFIG unchanged). Not extractable without hiding the dispatch boundary, mirroring prior compression rebaselines. Structural shrink tracked in #3501.",
+    "_rebaseline_2026_06_28_5275_correlation_id_extract": "Extraction of the safe CorrelationId subset of #5275 (hartmark) — request correlation id stored in call_logs (migration 109) and returned via the X-Correlation-Id response header, WITHOUT the combo/resilience or build/lazy-loading changes (those stay in #5275). Own growth: callLogs.ts 975->985 (correlation_id column on CallLogSummaryRow + read/map), usageHistory.ts 983->988 (correlationId metadata normalize), chat.ts 1575->1632 (withCorrelationId response wiring + combo-failure log carrying correlationId), chatHelpers.ts new 811 (withCorrelationId helper + reqId threading; was 791<cap pre-feature). Cohesive request/logging chokepoint wiring; structural shrink of chat.ts tracked in #3501.",
+    "_rebaseline_2026_06_29_4038_cas_guard": "PR (#4038) own growth: tokenRefresh.ts 2103->2181 (+78 = the compare-and-swap guard on the refresh persist — runWithCasGuard/getActiveCasGuard AsyncLocalStorage pair mirroring runWithOnPersist, casGuardShouldSkipPersist that rereads the row right before persisting and skips the write when a concurrent writer already rotated the refresh_token past the one presented, plus getCasGuardStats counters). Fixes the sibling-rotation-revert → token-family-revocation storm. Gated behind an active guard (opt-in; no guard => byte-identical). Wiring lives at the two persist chokepoints inside getAccessToken; the comparison reuses wasRefreshTokenRotated from refreshSerializer. Not extractable without splitting the refresh hot path.",
+    "_rebaseline_2026_06_29_5286_memoization": "PR #5286 own growth: strategySelector.ts 899->960 (+61 = the opt-in result-memoization branches in applyCompression/applyCompressionAsync — principal+determinism gate, makeMemoKey lookup/store with model+supportsVision folded into the key, recompute-with-memo-off). Default off (memoizeCompressionResults), so zero behavior change. The memo helpers live in the leaf resultMemo.ts (<cap); the chokepoint wiring here is not extractable. Structural shrink of this hot-path file tracked in #3501.",
+    "_rebaseline_2026_07_01_v3843_release_5609": "Rebaseline v3.8.43 (PR #5609 release reconciliation). DRIFT dos 109 commits do ciclo: 8 god-files existentes cresceram (ApiManagerPageClient 2983->3017, combos/page 4594->4608, AddApiKeyModal 868->869, providerPageHelpers 974->996, chat.ts 1635->1647, auth.ts 2401->2403, batchProcessor 828->915, combo.ts 3368->3387) + 2 novos acima do cap (huggingchat.ts 813, tests web-cookie-providers-new 827) + 4 test files cresceram. Modularizacao deferida (blast-radius mid-release); congelado no estado atual p/ o proximo ciclo ratchetar daqui.",
+    "_rebaseline_2026_07_02_5816_qoder": "PR #5816 (@AgentKiller45, qoder PAT via qodercli): qoderCli.ts 666->989, new-above-cap frozen (owner-approved baseline freeze). The growth is the legitimate PAT job-token exchange + quota parsing CLI transport (the pure-JS Cosy path 500'd on every PAT request); extracting the spawn/parse helpers now would just add indirection to a contributor PR mid-merge. Test frozen also raised for this PR's coverage growth: providers-page-utils.test.ts 1052->1092. Additionally clears an inherited base-red from the already-merged #5933 (codex json_schema->text.format): translator-openai-responses-req.test.ts 1097->1172 (+75 regression tests, no offending branch left). All remain frozen (cannot grow further); release captain's rebaseline-at-release supersedes.",
+    "_rebaseline_2026_07_09_6126_clinepass_dual_auth": "PR #6126 (@hajilok, dual-auth ClinePass) own growth: tokenRefresh.ts 2181->2182 (+1 = a single `case \"clinepass\":` fallthrough label added to the existing `case \"cline\":` in _getAccessTokenInternal's provider switch, so clinepass token refresh dispatches to the already-shared refreshClineToken() instead of silently falling through to the generic OAuth refresh). Irreducible 1-line switch-case wiring at the existing chokepoint; the header-building logic for the same feature was extracted to a new leaf src/shared/utils/clineAuth.ts::buildClinepassHeaders() (well under cap) to avoid growing open-sse/executors/default.ts. Covered by tests/unit/clinepass-provider.test.ts.",
+    "_rebaseline_2026_07_09_6363_kiro_external_idp": "PR #6363 (@artickc, Kiro external IdP) own growth: tokenRefresh.ts 2182->2249 (+67 = the external_idp refresh branch inside refreshKiroToken — standard public-client OAuth2 refresh_token grant against the org IdP tokenEndpoint via buildExternalIdpRefreshParams/isExternalIdpAuthMethod from the new leaf open-sse/services/kiroExternalIdp.ts, with invalid_grant/invalid_client -> unrecoverable_refresh_error mapping). Cohesive addition at the existing refreshKiroToken chokepoint. Covered by tests/unit/kiro-external-idp.test.ts.",
+    "_rebaseline_2026_07_09_6587_kiro_api_key_auth": "PR #6587 (@strangersp) own growth for Kiro long-lived API-key auth, merged onto v3.8.47 tip: openai-to-kiro.ts 890->912 (+22, auth-header selection for API-key-vs-OAuth-token connections), providerLimits.ts 998->1000 (+2, API-key auth-type branch), translator-openai-to-kiro.test.ts 1234->1257 (+23), providers-page-utils.test.ts 1109->1107 (net -2 after merging with parallel release drift; connectionMatchesProviderCard api_key coverage added), provider-validation-specialty.test.ts 2856->2980 (+124 net after merge with parallel release drift; this PR also removed the file's `@typescript-eslint/no-explicit-any` eslint-suppression entry by fixing all `any` usages, adding typed replacements). Cohesive additive feature growth, well tested; not extractable without splitting the existing chokepoints mid-merge.",
+    "_rebaseline_2026_07_09_6678_routing_strategy_9router": "#6678 (SeaXen) — 9router-parity Routing Strategy settings card + per-provider/combo sticky-round-robin override. Own growth: ProviderDetailPageClient.tsx 784->786 (single ProviderAccountRoutingCard mount + import), auth.ts 2448->2458 (providerStrategies override resolution: fallbackStrategy/stickyRoundRobinLimit per-provider cascade in getProviderCredentials). Both additive, zero unrelated refactor; new UI/logic lives in new files (ProviderAccountRoutingCard.tsx, RoutingStrategyCard.tsx, rrState.ts::resolveComboStickyRoundRobinLimit). chat.ts value below reflects the current release tip (grown by other concurrent PRs, e.g. #6640), not this PR own change.",
+    "_rebaseline_2026_07_10_6318_omp_letta": "PR #6318 (@hamsa0x7, omp+letta CLI integrations) own growth: cliTools.ts (+53 = 2 registry entries incl. omp docsUrl) and cliRuntime.ts (+18 = runtime-detection wiring for the 2 new tools). Cohesive registry/wiring growth at the existing chokepoints; scope reduced from the original 5 tools (pi/codewhale/jcode shipped separately).",
+    "_rebaseline_2026_07_10_gcf_v3_2_decode": "PR #6838 own growth: new vendored file open-sse/services/compression/engines/headroom/gcf/decode_generic.ts frozen at 880 (> 800 cap). It is the vendored GCF generic-profile decoder (spec v3.2 nested flattening plus the prototype-pollution / hasOwnProperty hardening added in this PR's Gemini review). Kept as one file faithful to upstream gcf-typescript so re-vendoring stays a clean copy rather than a re-split each cycle (sibling generic.ts/scalar.ts stay < cap; extraction would also fragment the file's frozen eslint no-explicit-any suppressions). Round-trip + prototype-pollution regression coverage in tests/unit/compression/headroom-smartcrusher.test.ts. Frozen: only shrinks from here.",
+    "_rebaseline_2026_07_12_v3847_mergeprs_tail": "v3.8.47 /merge-prs tail (owner-approved): src/lib/localDb.ts NEW>800 (799->805, +6 re-exports countFreeProxies + recordFreeProxySyncErrors/clearFreeProxySyncErrors/getFreeProxySyncErrors + FreeProxySyncErrors type for #6909 free-pool relay-repair; re-export-only per Hard Rule #2, not extractable).",
+    "_rebaseline_2026_07_15_7070_combos_memo": "PR #7070 (perf/p1-memo) own growth: src/app/(dashboard)/dashboard/combos/page.tsx 4655->4656 (+1 = React.memo wrapping of ComboCard). Covered by tests/unit/ui/combos-page-smoke.test.tsx.",
+    "_rebaseline_2026_07_18_7399_xai_oauth_modal": "PR #7399 (xAI OAuth PKCE) own growth: OAuthModal.tsx 993->998 (+5 = provider entry + PKCE flow branch wiring at the existing provider-switch chokepoint; the provider logic itself lives in src/lib/oauth/providers/xai-oauth.ts, new leaf). Third irreducible wiring bump on this modal (969->989->993->998); structural shrink tracked in #3501.",
+    "_rebaseline_2026_07_19_6636_codex_session_json": "#6636 own growth: OAuthModal.tsx 998->1030 (gate units, split(\"\\n\").length incl. trailing newline; +32 = session-JSON paste branch for handleManualSubmit plus a shared submitCodexAccessToken() helper extracted from the pre-existing bare-JWT branch, mirroring the #5203 oauthBlobSubmit.ts extraction precedent; the normalizer logic itself lives in the new src/lib/oauth/utils/codexSessionImport.ts leaf module, not here). Fourth irreducible wiring bump on this modal (969->989->993->998->1030); structural shrink tracked in #3501.",
+    "_rebaseline_2026_07_19_7546_ghe_copilot_modal": "PR #7546 (GHE Copilot OAuth provider) own growth: OAuthModal.tsx 1030->1056 (gate units). Adds a gheUrl input state, routes ghe-copilot through the existing device-code branch, and threads gheUrl into the device-code request/poll extraData at the existing provider-switch chokepoints (+~24 lines, cohesive with the same pattern as #7399/#6636). The standalone GHE enterprise-URL config step JSX (originally +31 lines inline) was extracted to the new src/shared/components/oauthModal/GheConfigStep.tsx leaf component to minimize the bump; what remains is the irreducible provider-branch wiring. Fifth bump on this modal (969->989->993->998->1030->1056); structural shrink tracked in #3501.",
+    "_rebaseline_2026_07_19_7787_ic2_localdb_reexports": "PR #7787 (IC2 raw connections cache + lazy-decrypt) own growth: localDb.ts 805->807 (gate units, +2). localDb.ts is the re-export-only layer (hard rule #2 — no logic); the PR adds 4 new db/readCache re-exports (touchConnectionLastUsed, getCachedRawProviderConnections, getCachedProviderConnectionById, getCachedProviderNodes) required by existing barrel importers. Irreducible for a re-export list; frozen so it can only shrink.",
+    "_rebaseline_2026_07_20_7779_routingcombo_thread": "PR #7779 own growth: chatHelpers.ts 876->877 (+1, thread routingComboId into executeChatWithBreaker for compression-combo assignment). Frozen so it can only shrink.",
+    "_rebaseline_2026_07_20_7819_autocandidateoverrides_reexport": "PR for #7819 (Level 1+2: read-only auto/* candidate transparency + per-API-key exclusions) own growth: localDb.ts 807->808 (+1). Adds a single `export * from \"./db/autoCandidateOverrides\"` barrel re-export (hard rule #2 — no logic) for the new DB module backing per-apiKey candidate exclusions. Irreducible for a re-export list; frozen so it can only shrink.",
+    "_rebaseline_2026_07_21_8027_grok_cli_auth_json_paste": "PR #8027 (RaviTharuma, fix(grok-cli) #7610) own growth: OAuthModal.tsx 1080->1100 (gate units). Requires the full ~/.grok/auth.json (with refresh_token) on the paste-import path instead of a bare JWT, at the existing paste-token chokepoint (renamed tab label, updated instructions/placeholder, textarea for the auth.json blob, inline error surface). The validation logic itself (parseGrokCliPasteToken, previously an inline ~75-line function) was extracted to the new src/lib/oauth/utils/grokCliAuthJson.ts leaf module — mirroring the #6636/#7546 extraction precedent — so only the irreducible UI wiring remains here. Sixth bump on this modal (969->989->993->998->1030->1056->1100); structural shrink tracked in #3501.",
+    "_rebaseline_2026_07_21_8034_compression_exclusions_sidebar": "#8034 (compression exclusions dashboard tab) own growth: sections.ts 796->806 (+10, one new COMPRESSION_CONTEXT_GROUP sidebar item linking /dashboard/compression/exclusions). The file was already 796/800 before this PR (organic growth from prior sidebar entries), so a single new nav item pushed it 6 lines over cap. Freezing at 806 (cannot grow further); the sidebar item array is data, not extractable logic.",
+    "_rebaseline_2026_07_22_7936_namespace_roundtrip": "#7936 (@RCrushMe, Responses-Chat namespace round-trip identity seam) own growth: open-sse/translator/response/openai-responses.ts 1092->1125 (+33) and open-sse/utils/stream.ts 2814->2869 (+55) — threading the namespace-identity seam through the Responses↔Chat translation + stream paths so tool-call namespaces survive the round-trip. Cohesive translation/stream wiring at existing chokepoints, frozen at new size.",
+    "_rebaseline_2026_07_22_8010_codex_responses_engine": "PR #8010 (@JxnLexn) own growth: open-sse/mcp-server/schemas/tools.ts 1497->1505 (+8 = threading the new \"codex-responses\" literal into the compressionConfigureInput strategy/autoTriggerMode Zod enums and setCompressionEngineInput engine enum, mirroring the existing rtk/omniglyph enum entries; no new tool). open-sse/services/compression/strategySelector.ts 1043->1054 (+11 = one new `if (mode === \"codex-responses\")` dispatch branch in runCompression that delegates 100% to the new codexResponsesEngine.apply, mirroring the existing rtk single-mode dispatch, plus threading config.codexResponsesConfig.preserveToolNames into the shared adaptBodyForCompression call at the 3 existing call sites). src/lib/db/compression.ts (untracked, new-file cap 800) 794->845 (+51 = normalizeCodexResponsesConfig, mirroring the existing normalizeRtkConfig normalizer, plus registering \"codex-responses\" in the COMPRESSION_MODES/STACKED_PIPELINE_ENGINE_IDS/SINGLE_MODE_ENGINE sets and the getCompressionSettings load/save switch) — added to the baseline at its current size. All three are cohesive dispatch/normalizer wiring at existing chokepoints (mirroring the prior compression-mode rebaselines #6534/#6556), not extractable without hiding the mode-dispatch boundary. Covered by tests/unit/compression/codex-responses.test.ts (6) + omniglyph-registries.test.ts/types.test.ts (22, updated for the new mode).",
+    "_rebaseline_2026_07_22_8034_compression_exclusions_persistence": "#8034 (compression exclusions) own growth: src/lib/db/compression.ts 845->850 (+5 = threading the new compressionExclusions field through the existing getCompressionSettings/saveCompressionSettings load/save switch over the shared key_value compression namespace — no new table, no raw SQL). Mirrors the prior compression-field rebaselines (#8010 codex-responses normalizer at the same chokepoint); the load/save switch is a single dispatch boundary, not extractable without hiding it. Covered by the PR's 8 node:test + 3 vitest cases.",
+    "_rebaseline_2026_07_22_8050_model_lockout_exact_family": "#8050 (@AndrianBalanescu) own growth: accountFallback.ts 1864->1892 (+28) — exact-vs-family model-lockout scoping (getModelLockKey/isModelLocked/clearModelLock/getModelLockoutInfo) so an Antigravity 404 for one bare model no longer hijacks the whole family cooldown. Cohesive lockout logic; frozen at new size.",
+    "_rebaseline_2026_07_22_8056_headroom_minrows": "#8056 (@RaviTharuma, persist Headroom minRows) own growth: src/lib/db/compression.ts 850->866 (+16 HeadroomConfig+DEFAULT_HEADROOM_CONFIG+normalize/store in get/updateCompressionSettings) and open-sse/services/compression/strategySelector.ts 1054->1060 (+6 merge settings.headroom into stacked stepConfig). Cohesive settings-persistence + stacked-merge wiring at existing chokepoints, frozen at new size.",
+    "_rebaseline_2026_07_22_8081_reasoning_placeholder_guard": "#8081 (@Dingding-leo) own growth: openai-responses.ts 1125->1137 (+12) restructuring the reasoning-placeholder guard so it skips only the empty content block and still emits finish_reason/tool_calls in the same chunk. Cohesive translator wiring; frozen at new size.",
+    "_rebaseline_2026_07_22_8210_openrouter_midstream_error": "PR #8210 (hartmark, fix/openrouter-midstream-error-surfacing) own growth: open-sse/translator/response/openai-responses.ts 1137->1163 (+26) measured on the merged tip (release 1137 + this PR own growth). Adds a single new branch inside openaiToOpenAIResponsesResponse() that detects an OpenRouter-style mid-stream aggregator error (HTTP 200 SSE chunk with empty choices + a top-level error object) and surfaces it as state.upstreamError instead of silently falling through to the no-op/awaitingTrailingUsage path, which previously masked the failure as a false empty-success completion and skipped combo fallback. Irreducible call-site addition at the existing chunk-dispatch chokepoint (mirrors the Gemini-to-OpenAI translator's #4177 precedent for the same class of upstream error surfacing). Note: this baseline entry does NOT cover the separate pre-existing +11 drift already on the release tip from #8081/#8162 (1125->1136, unrelated reasoning-placeholder-stripping fix merged after this PR branched) — that drift belongs to the maintainer's rebaseline, not this PR.",
+    "_rebaseline_2026_07_22_8211_gemini_malformed_tool_choice": "PR #8211 (hartmark, fix/gemini-malformed-function-call-tool-choice) own growth: open-sse/translator/response/gemini-to-openai.ts 771->821 (+50, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds MALFORMED_FUNCTION_CALL/UNEXPECTED_TOOL_CALL handling inside geminiToOpenAIResponse(): synthesizes a `malformed_tool_call` tool_calls entry so finish_reason normalizes to the standard \"tool_calls\" instead of an unrecognized raw enum value that OpenAI-compatible clients (e.g. OpenClaw) silently ignore, and always synthesizes (rather than skipping when a real tool call already exists) so a malformed attempt alongside a real one in the same turn is not silently discarded. Irreducible cohesive addition at the existing candidate/finishReason translation chokepoint (mirrors the 9router#2462 raw-finish-reason precedent immediately below it in the same function). Covered by the PR's own tests/unit test additions for both the malformed-only and malformed-plus-real-call cases.",
+    "_rebaseline_2026_07_22_8213_chat_abandoned_target_abort": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/sse/handlers/chat.ts 1794->1860 (+66, measured against the PR's own merge-base — the release tip separately carries an unrelated -5 net shrink from #8013's antigravity callable-catalog alignment, which this PR's branch does not include and this entry does not cover). Adds resolveDispatchClientRawRequest(): merges a per-target modelAbortSignal into clientRawRequest.signal (via mergeAbortSignals) so a combo target abandoned by comboTargetTimeoutMs actually observes its own abort and reaches its cleanup path, instead of hanging forever inside withRateLimit/acquireAccountSemaphore and leaking a permanent 'pending' dashboard entry (live incident, log id 1784418258231-14961a). Also wires combo-exhausted rejection logging to capture request body + attempted models via the new rejectedRequestUsage helper. Irreducible additions at the existing chat dispatch chokepoint. Covered by the PR's own combo-config + integration test additions.",
+    "_rebaseline_2026_07_22_8213_combo_cooldown_wait_recording": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/combo.ts 3548->3604 (+56, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Fixes combo cooldown-wait state recording so a bogus 503 is no longer crystallized when the cooldown-wait vars reset every setTry, adds an OpenAI-format SSE error frame path for combo-exhausted rejections (capturing request body + attempted models), and gives an abandoned per-target dispatch its own timeout instead of leaking a permanent 'pending' dashboard entry. Irreducible additions at the existing handleComboChat dispatch/retry chokepoint (mirrors the prior quota-share/headroom/task-aware strategy-branch precedents already frozen in this file). Covered by the PR's own combo-config + Gemini TPM-ceiling benchmark test additions.",
+    "_rebaseline_2026_07_22_8213_gemini_tpm_quota_cooldown_wait": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/accountFallback.ts 1857->1932 on the merged tip (release 1892 incl #8050 +35, plus this PR own growth +40); measured against the PR own merge-base was 1857->1898 (+41 — the release tip separately carries an unrelated +34 from #8050's antigravity 404 model-not-found lockout scoping, which this PR's branch does not include and this entry does not cover). Own growth is the Gemini TPM-ceiling classification + cooldown-wait wiring feeding into the combo cooldown-wait state machine (rate-limit wedge recovery) introduced by this PR's commit series. Irreducible additions at the existing account-fallback/model-lockout chokepoint. Covered by the PR's own gemini-rate-limit-tracker and TPM-ceiling benchmark test additions.",
+    "_rebaseline_2026_07_22_8213_health_unblock_model_cooldowns": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/app/(dashboard)/dashboard/health/page.tsx 1094->1165 (+71, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds handleUnblockAll/handleUnblockOne dashboard actions (DELETE /api/resilience/model-cooldowns) so an operator can manually clear a Gemini TPM-wedge model lockout surfaced by this PR's cooldown-wait fixes, instead of waiting out the ceiling. Irreducible UI wiring at the existing health-page action chokepoint. Covered by the PR's own dashboard/resilience test additions.",
+    "_rebaseline_2026_07_22_8213_requestloggerdetail_unblock_ui": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/shared/components/RequestLoggerDetail.tsx 799->941 (+142, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip; crosses the general 800-line new-file cap so is frozen here for the first time). Adds a collapsible section header (open/expand-less toggle) plus per-log-entry unblock (`unblocking`/`cleared` state, isCombo503 detection) so the request-logger detail panel surfaces the same Gemini TPM cooldown-wait / model-lockout unblock action introduced by this PR at the individual-request level (mirrors the health-page bulk unblock action added in the same PR). Covered by the PR's own dashboard/resilience test additions.",
+    "_rebaseline_2026_07_22_fusion_8013_8098_antigravity": "Fusion of #8013 (backryun, catalog/IDE-CLI-split rewrite) + #8098 (nguyenha935, protocol-fidelity/fail-closed/credits/tool-cloaking): open-sse/services/usage/antigravity.ts NEW 802 (>cap 800, +2 — #8098 credits/tier usage service on #8013's profile-aware headers). Test growth (models-catalog-route 1605->1608, provider-models-route 1752->1757 from #8013 Gemini 3.6 catalog) tracked in testFrozen.",
+    "_rebaseline_2026_07_23_8127_grok_weekly_quota": "#8127 (@apoapostolov) own growth: src/sse/handlers/chat.ts 1861->1865 (+4) — weekly quota tracking for grok-web wires a quota-fetch hook at the existing dispatch chokepoint. Thin wiring mirroring adjacent provider-quota branches; not extractable. Covered by tests/unit/grok-quota-fetcher.test.ts.",
+    "_rebaseline_2026_07_23_8143_empty_catch_logging": "#8143 (@chirag127) own growth: open-sse/utils/stream.ts 2869->2887 (+18) — replacing empty catch blocks in the SSE stream subsystem with console.debug logging (Rule #6 silent-swallow fix, issues #8138-#8142). Cohesive logging additions at the existing catch chokepoints, not extractable; frozen at new size. Covered by tests/unit/stream-handler-catch-logging-8143.test.ts.",
+    "_rebaseline_2026_07_23_8219_cache_ttl_settings_sidebar": "#8219 (@oyi77) own growth: sections.ts 806->813 (+7) — configurable model-catalog cache-TTL settings adds a new sidebar nav entry + its visibility wiring. Sidebar item array is data, not extractable logic; frozen at new size.",
+    "_rebaseline_2026_07_23_8247_8248_model_unhealthy": "#8247+#8248 own growth: accountFallback.ts 1940->1941 (+1, irreducible import statement only — the substantive #8248 DEGRADED-pattern classifier was extracted into open-sse/config/errorConfig.ts, which has ample headroom, instead of growing this frozen file; #8247's fix is a single existing-line condition change, net zero lines). Scoping the credits-exhausted 403/429 branch to isCompatibleProvider() (per-model-quota openai/anthropic-compatible-* nicknames) so it stays model-scoped instead of terminalling the whole connection, and classifying NVIDIA NIM 'Function ... DEGRADED' 400 bodies as model-access-denied instead of a raw passthrough 400. Covered by tests/unit/8247-accountfallback-model-unhealthy.test.ts and tests/unit/8248-accountfallback-nvidia-degraded.test.ts.",
+    "_rebaseline_2026_07_23_8252_combo_400_advance": "#8252 (@RaviTharuma) own growth: accountFallback.ts 1932->1940 (+8) + combo.ts 3604->3630 (+26) — advance combo on model-scoped 400s wrapped as invalid/Bad-Request. Irreducible wiring at existing account-fallback + combo dispatch chokepoints. Covered by combo-model-scoped-400-advance.test.ts.",
+    "_rebaseline_2026_07_23_8266_alibaba_media": "#8266 (@backryun) own growth: imageRegistry.ts 821->979 (+158) — Alibaba-family media models (Qwen image/video, Bailian, Wan) added to the image/video registry. Registry model data, not extractable logic; frozen at new size.",
+    "_rebaseline_2026_07_24_8388_compression_detail_persist": "#8388 (compression engine DETAIL settings — Headroom/session-dedup/CCR — dropped on save) own growth: src/lib/db/compression.ts 866->872 (+6 = irreducible call-site wiring at the existing getCompressionSettings/updateCompressionSettings chokepoint: one import line, one `...buildDetailConfigDefaults()` spread in the seed config, and one `case \"sessionDedup\": case \"ccr\": applyDetailConfigUpdate(config, key, parsed); break;` load-switch case, mirroring the existing headroom/#8056 case immediately above it). The actual normalizer logic (normalizeSessionDedupConfig/normalizeCcrConfig, matching SESSION_DEDUP_SCHEMA/CCR_SCHEMA bounds) was EXTRACTED into a new leaf src/lib/db/compressionDetailNormalizers.ts (well under cap) so this frozen file only carries the minimal dispatch wiring. Covered by tests/unit/8388-compression-detail-persist.test.ts (schema-accept + full DB save->reload round-trip for both new sub-objects, plus a no-regression assertion on the existing headroom round-trip).",
+    "_rebaseline_2026_07_24_responses_toolcalls_log_summary": "hartmark, fix/responses-tool-calls-log-summary own growth: open-sse/translator/response/openai-responses.ts 1163->1174 (+11). closeToolCall() now also writes the completed tool call into the shared state.toolCalls Map (already populated by the openai-to-claude / claude-to-openai / gemini-to-openai response translators) so stream.ts's completion-log summary builder (which reads state.toolCalls, not this translator's own funcCallIds/funcNames/funcArgsBuf bookkeeping) reports finish_reason \"tool_calls\" and message.tool_calls for openai->openai-responses translated streams instead of always logging \"stop\" with no tool_calls — the actual client-facing SSE events were already correct; only the persisted call-log summary was wrong. Irreducible call-site addition at the existing tool-call-close chokepoint. Covered by the new regression test in tests/unit/translator-resp-openai-responses.test.ts.",
+    "_rebaseline_2026_07_25_8476_combo_input_bound_homogeneous_scope": "PR #8476 (herjarsa, fix/8375-8459-combo-image-fixes, #8375) own growth: open-sse/services/combo.ts 3642->3679 (+37 net: +29 the PR's own isInputBoundFailure short-circuit for deterministic context_length_exceeded/context_window_exceeded failures, +8 a /green-prs pre-merge fix scoping that short-circuit to homogeneous remainders only — the shipped code fired unconditionally on ANY target, regressing the intentional heterogeneous-combo fallback #6637/isContextOverflow400 protects, exactly as flagged by this PR's own review evidence but never actually implemented in the branch). The fix compares orderedTargets[i+1..] modelStr against the failing target's modelStr at the existing executeTarget dispatch chokepoint (mirrors the sameProviderNext precedent a few lines below) — irreducible call-site wiring, not extractable without hiding the dispatch boundary. Covered by tests/unit/combo-input-bound-failure-8375.test.ts (homogeneous pool still short-circuits) and the new tests/unit/combo-input-bound-heterogeneous-8375.test.ts (heterogeneous combo now correctly falls through to the larger-context target).",
+    "_rebaseline_2026_07_25_adobe_firefly_reference_images": "Follow-up to #8006: storage upload + referenceBlobs for image/video and /v1/images/edits dispatch. adobeFireflyClient.ts 1958->2317 (+upload helpers, extract sources, resolve blob ids). Note: 2317 not 2316 — check-file-size.mjs counts LOC via split(\"\\n\").length (counts the trailing-newline empty element), which is 1 higher than `wc -l` on a file ending in \\n; the PR's original entry (2316) was measured with wc -l and undercounted by 1 against the actual gate.",
+    "_rebaseline_pr1043_minimax_tts": "Upstream port decolua/9router#1043 (toanalien) own growth: audioSpeech.ts 965->1061 (+96). Adds MiniMax T2A v2 TTS dispatch (handleMinimaxSpeech + hexToBytes helper) — provider entry was already in audioRegistry (format: minimax-tts) but no handler existed, falling through to the OpenAI-compatible default that fails (T2A has custom shape + hex-encoded audio + base_resp envelope). New branch sits next to the other inline provider branches (xiaomi-mimo, coqui, tortoise, aws-polly) — extracting would just create indirection. Covered by tests/unit/minimax-tts-1043.test.ts (3 tests, GREEN: success, base_resp error, invalid-hex).",
+    "_rebaseline_pr4592_exclude_exhausted_auto": "Reconcile #4592 already-merged growth: combo.ts 2991->3036 (+45, terminal-status quota-cutoff exclusion in buildAutoCandidates + opt-in gate). Fast-gate PR->release does not run check:file-size.",
+    "open-sse/executors/antigravity.ts": 1528,
+    "open-sse/executors/base.ts": 1640,
+    "open-sse/executors/chatgpt-web.ts": 3241,
+    "open-sse/executors/codex.ts": 1562,
+    "open-sse/executors/cursor.ts": 1563,
+    "open-sse/executors/deepseek-web.ts": 1148,
+    "open-sse/executors/grok-web.ts": 1044,
+    "open-sse/executors/muse-spark-web.ts": 1405,
+    "open-sse/handlers/chatCore.ts": 5042,
+    "open-sse/handlers/imageGeneration.ts": 3101,
+    "open-sse/handlers/responseSanitizer.ts": 1128,
+    "open-sse/handlers/search.ts": 1536,
+    "open-sse/handlers/videoGeneration.ts": 1063,
+    "open-sse/mcp-server/schemas/tools.ts": 1553,
+    "open-sse/mcp-server/server.ts": 1448,
+    "open-sse/mcp-server/tools/advancedTools.ts": 1120,
+    "open-sse/services/accountFallback.ts": 1978,
+    "open-sse/services/adobeFireflyClient.ts": 2385,
+    "open-sse/services/claudeCodeCompatible.ts": 1202,
+    "open-sse/services/combo.ts": 3648,
+    "open-sse/services/compression/strategySelector.ts": 1060,
+    "open-sse/services/rateLimitManager.ts": 1167,
+    "open-sse/translator/response/openai-responses.ts": 1224,
+    "open-sse/utils/cursorAgentProtobuf.ts": 1505,
+    "open-sse/utils/stream.ts": 2889,
+    "src/app/(dashboard)/dashboard/HomePageClient.tsx": 1388,
+    "src/app/(dashboard)/dashboard/analytics/ComboHealthTab.tsx": 1031,
+    "src/app/(dashboard)/dashboard/api-manager/ApiManagerPageClient.tsx": 3117,
+    "src/app/(dashboard)/dashboard/cache/media/MediaPageClient.tsx": 1067,
+    "src/app/(dashboard)/dashboard/combos/page.tsx": 4703,
+    "src/app/(dashboard)/dashboard/costs/CostOverviewTab.tsx": 1283,
+    "src/app/(dashboard)/dashboard/costs/quota-share/components/PoolWizard.tsx": 1022,
+    "src/app/(dashboard)/dashboard/endpoint/EndpointPageClient.tsx": 2615,
+    "src/app/(dashboard)/dashboard/health/page.tsx": 1165,
+    "src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx": 1324,
+    "src/app/(dashboard)/dashboard/providers/page.tsx": 1944,
+    "src/app/(dashboard)/dashboard/runtime/RuntimePageClient.tsx": 1201,
+    "src/app/(dashboard)/dashboard/settings/components/PricingTab.tsx": 1019,
+    "src/app/(dashboard)/dashboard/settings/components/ProxyRegistryManager.tsx": 1470,
+    "src/app/(dashboard)/dashboard/settings/components/ResilienceTab.tsx": 1123,
+    "src/app/(dashboard)/dashboard/settings/components/RoutingTab.tsx": 1629,
+    "src/app/(dashboard)/dashboard/settings/components/SystemStorageTab.tsx": 1573,
+    "src/app/(dashboard)/dashboard/usage/components/BudgetTab.tsx": 1028,
+    "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": 2148,
+    "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx": 1119,
+    "src/app/api/providers/[id]/models/route.ts": 2361,
+    "src/app/api/v1/models/catalog.ts": 1597,
+    "src/lib/db/apiKeys.ts": 1529,
+    "src/lib/db/core.ts": 1639,
+    "src/lib/db/migrationRunner.ts": 1094,
+    "src/lib/db/models.ts": 1097,
+    "src/lib/db/providers.ts": 1034,
+    "src/lib/memory/retrieval.ts": 1073,
+    "src/lib/tailscaleTunnel.ts": 1202,
+    "src/lib/usage/providerLimits.ts": 1013,
+    "src/shared/components/OAuthModal.tsx": 1134,
+    "src/shared/components/RequestLoggerV2.tsx": 1629,
+    "src/shared/components/analytics/charts.tsx": 1035,
+    "src/shared/services/cliRuntime.ts": 1122,
+    "src/sse/handlers/chat.ts": 1904,
+    "src/sse/services/auth.ts": 2520,
+    "tests/unit/account-fallback-service.test.ts": 1572,
+    "tests/unit/provider-validation-specialty.test.ts": 2985,
+    "open-sse/executors/hyperagent.ts": 1026,
+    "src/lib/tokenHealthCheck.ts": 1053,
+    "open-sse/executors/default.ts": 1042,
+    "open-sse/executors/kiro.ts": 1069,
+    "open-sse/translator/request/openai-to-kiro.ts": 1057,
+    "open-sse/utils/sseHeartbeat.ts": 149
+  },
   "_rebaseline_2026_07_27_v3849_train2": "Merge-train 2 (7 PRs) — owner-approved 2026-07-27. Single entry: chatCore.ts 4955->5006 (#8595, Responses multi-turn image compaction before the context hard-reject). Genuine irreducible growth at the existing compaction chokepoint in handleChatCore — the PR adds a last-resort retry against the concrete budget plus the estimateFinalInputTokens helper, both wired at the pre-existing call site rather than a new branch. Covered by tests/unit/8560-responses-image-compaction.test.ts (4 tests).",
   "_rebaseline_2026_07_27_v3849_train3": "Merge-train 3 (13 PRs) — owner-approved 2026-07-27. Both entries are genuine irreducible growth at existing chokepoints, not new branches: src/lib/db/apiKeys.ts 1518->1529 (#8805 cx/* ≡ codex/* API-key model permissions); open-sse/handlers/chatCore.ts 5006->5020 (#8806 real response payload into plugin onResponse hooks). Covered by tests/unit/db-apiKeys-crud.test.ts (4 new cases) and the two plugin-hook test files updated in #8806 respectively.",
   "_rebaseline_2026_07_28_8842_antigravity_projectid_refresh": "PR #8842 (fix/antigravity-projectid-refresh) own growth: open-sse/executors/antigravity.ts 1493->1528 (+35 = projectId discovery in refreshCredentials: import ensureAntigravityProjectAssigned + trim projectId + call ensureAntigravityProjectAssigned with 8s timeout + persistDiscoveredAntigravityProjectId + log success/failure). Irreducible wiring at the existing credential-refresh chokepoint. Covered by tests/unit/executor-antigravity.test.ts (4 new test cases).",
@@ -421,15 +424,148 @@
   "_rebaseline_2026_07_28_8860_tokenrefresh_projectid": "PR #8860 (fix/antigravity-projectid-centralized) own test growth: tests/unit/token-refresh-service.test.ts 1311->1378 (+67 = 4 cases covering projectId discovery on the tokenRefresh.ts path — the Dashboard/health-check refresh route, which #8842 did not reach since that fixed the executor path). Covered by the same file.",
   "_rebaseline_2026_07_28_8861_xiaomi_token_plan": "PR #8861 (feat/xiaomi-token-plan-protocol-selector) own growth: EditConnectionModal.tsx 1283->1316 (+33 = the per-connection API-protocol selector field) and open-sse/executors/base.ts 1540->1562 (+22 = alternate-format resolution at the existing buildUrl/headers chokepoint). Both are irreducible wiring at existing call sites.",
   "_rebaseline_2026_07_28_8863_firefly_detail_level": "PR #8863 (fix/adobe-firefly-gpt-detail-level-max) own growth: adobeFireflyClient.ts 2317->2322 (+5 = gpt-image detailLevel defaulting to maximal at the existing payload-build site). Covered by tests/unit/adobe-firefly.test.ts.",
-  "_rebaseline_2026_07_28_8870_firefly_ref_cap_timeout": "PR #8870 (fix/adobe-firefly-gpt-ref-cap-timeout) own growth: adobeFireflyClient.ts 2322->2385 (+63 = gpt-image subject-ref hard cap at 2 + adaptive poll timeout budget (base 300s + 60s/ref, max 600s) + defensive .slice on referenceBlobs for gpt/nano/generic families). Fixes live 504s on multi-screenshot listing jobs (Featured Promo / Box Art) where 3–4+ subject refs stall colligo until the old 180s poll budget expires. Helpers adobeFireflyMaxImageRefs/adobeFireflyImageTimeoutMs live next to the existing payload/poll chokepoint (not extractable without splitting the wire recipe mid-PR). Covered by tests/unit/adobe-firefly.test.ts (ref-cap + timeout cases). Structural shrink tracked in #3501.",
   "_rebaseline_2026_07_29_8281_home_quickstart_prefetch": "Release v3.8.49 base-red fix (no PR — captain sweep): src/app/(dashboard)/dashboard/HomePageClient.tsx 1377->1381 (+4). #8292 added prefetch={false} to the sidebar but left /home's five quick-start Links prefetching, so first paint still fired 12 speculative RSC requests — caught by navigation.spec.ts only after the e2e helper bug (APP_ROUTE_PATTERN missing /home) was repaired in the same cycle. Growth is the five prefetch attributes; it was offset first by extracting the repeated className literals (INLINE_LINK x4, DOCS_LINK x1), which collapsed five wrapped <Link> blocks back to one line each — a naive fix measured 1391. Guard: tests/unit/sidebar-prefetch-policy-8281.test.ts.",
+  "_rebaseline_2026_08_02_v3850_agentrouter_responses": "Release v3.8.50 AgentRouter/Codex compatibility reconciliation. open-sse/executors/base.ts 1562->1578: #9190 wires AgentRouter's selected Claude/OpenAI/Responses protocol through the existing executor URL, auth, identity-header and fingerprint chokepoints; the reusable alternate resolver remains outside base.ts. open-sse/utils/stream.ts 2887->2889: #9213 evaluates Responses ID and usage normalization independently so response.completed always receives finite usage.total_tokens instead of short-circuiting after an ID rewrite. tests/unit/chatcore-translation-paths.test.ts 2769->2776: #9191 updates the existing Claude-Code bridge assertions for the dynamic AgentRouter wire image. PR #9224 offsets its own chatCore growth by extracting the AgentRouter protocol decisions into chatCore/agentRouterProtocol.ts, leaving chatCore below its frozen ceiling. Covered by agentrouter executor/chatCore protocol tests, chatcore translation-path tests, and responses-commentary-passthrough tests.",
+  "_rebaseline_2026_08_08_v3850_base_drift_batch_9757": "Base drift on release/v3.8.50, not own growth: the 08-06..08-08 merge batches grew 12 already-frozen (or newly-landed) files without carrying their rebaselines — the dedicated rebaseline PR #9616 was closed as 'superseded' but its file-size entries never actually reached the base, and later merges (#8894 combos page, #9539 EditConnectionModal, #8895 models route, #9294/#9293 catalog, #9541 db/core, #8970 tokenHealthCheck, #8925 mcp schemas+server, #8890 accountFallback, #9467 chat.ts, #8931 openai-to-kiro, ProxyRegistryManager) kept growing them. All 12 values re-measured on THIS branch's tree (= pure tip + this PR's 1-line chat.ts fix, which adds zero lines). This PR's own source changes (chat.ts identifier restore, stream.ts format carve-out) do not grow any frozen file past these values.",
+  "_rebaseline_2026_08_08_migration_135_collision": "fix(db): resolve migration version 135 numbering collision — #9449's 135_connection_runtime_state.sql and #8908's 135_migrate_model_capability_max_token.sql both claimed version 135 (#9449 branched before #8908 merged and never got renumbered before landing on release/v3.8.50), which threw 'Migration version collision detected' the moment ANY code touched the database — a fresh install/deploy from this tip cannot even boot. Renumbered the later-landing file to 140 (next free slot) and added the matching isSchemaAlreadyApplied('140') retroactive guard, matching the established pattern already used for the prior 135/136 -> 137/138 renumber in the same file. Own growth: src/lib/db/migrationRunner.ts 1084->1094 (+10, the new case block) — irreducible, matches the existing per-case guard pattern exactly. Covered by tests/unit/migration-135-numbering-collision.test.ts (2/2), confirmed failing (reproducing the exact live crash) against the pre-fix colliding filenames, passing after.",
+  "_rebaseline_2026_08_02_9259_rolling_rpm": "PR #9259 (issue #8733) own growth: open-sse/services/rateLimitManager.ts baseline 1060->1167 (+107; final source 1153). The existing withRateLimit chokepoint now composes process-local rolling RPM leases with Bottleneck admission, releases pre-dispatch leases on queue timeout/abort/connection disable, preserves caller abort reasons, and wires 429/header state into the extracted rollingRpmGate.ts. The remaining growth is irreducible lifecycle wiring at the dispatch boundary plus the real watchdog test hooks needed to verify queued-wedge recovery; moving it further would obscure lease ownership and Bottleneck cleanup. Covered by the focused rate-limit manager/sliding-window suite (33/33); distributed multi-instance coordination remains explicitly out of scope.",
+  "_rebaseline_2026_07_25_dario_upstream_proxy_selector": "PR #8523 (Dario embedded service): upstream-proxy mode selector replaces the binary CLIProxyAPI toggle with Native/CLIProxyAPI/Dario/Fallback + a fallback-backend picker. ProviderDetailPageClient.tsx 798->804 (+6, new hook fields threaded through to ConnectionsListPanel), ConnectionRow.tsx 942->958 (+16, the mode <select> + conditional fallback-backend <select> replacing a single pill button), useProviderConnections.ts 954->986 (+32, upstreamProxyMode/upstreamProxyFallbackBackend state + handleSetUpstreamProxyMode, handleToggleCliproxyapiMode kept as a thin backward-compat wrapper for the existing hook-shape test). All additive UI/state for the new modes — no unrelated refactor.",
+  "_rebaseline_2026_08_02_9242_token_health_transient": "PR #9242 (fix/refresh-circuit-transient): src/lib/tokenHealthCheck.ts 1021 (new file, above cap 1000). The file consolidates token-refresh health checking logic that was previously scattered across auth.ts and tokenRefresh.ts. Cohesive single-responsibility module for refresh circuit state management; not extractable without splitting the refresh state machine. Covered by tests/unit/tokenHealthCheck-transient.test.ts.",
+  "_rebaseline_2026_07_28_8870_firefly_ref_cap_timeout": "PR #8870 (fix/adobe-firefly-gpt-ref-cap-timeout) own growth: adobeFireflyClient.ts 2322->2385 (+63 = gpt-image subject-ref hard cap at 2 + adaptive poll timeout budget (base 300s + 60s/ref, max 600s) + defensive .slice on referenceBlobs for gpt/nano/generic families). Fixes live 504s on multi-screenshot listing jobs (Featured Promo / Box Art) where 3–4+ subject refs stall colligo until the old 180s poll budget expires. Helpers adobeFireflyMaxImageRefs/adobeFireflyImageTimeoutMs live next to the existing payload/poll chokepoint (not extractable without splitting the wire recipe mid-PR). Covered by tests/unit/adobe-firefly.test.ts (ref-cap + timeout cases). Structural shrink tracked in #3501.",
   "_rebaseline_2026_08_01_8964_xai_agent_tools": "PR #8964 own growth: chatCore.ts 5020->5034 at the existing native-passthrough chokepoint. Adds xAI Agent Tools passthrough for /v1/responses (xai/xai-oauth/xao): resolve nativeXaiResponsesPassthrough, force openai-responses targetFormat, stamp body marker, and OR into the existing nativeCodexPassthrough sites (web-search bypass + requestEndpointPath). Leaf logic in passthroughHelpers, responsesEndpoint, targetFormat, xai executor, responseSanitizer, usageTracking. Cohesive wiring at the Codex passthrough boundary.",
   "_rebaseline_2026_08_01_8964_response_sanitizer": "PR #8964 own growth: responseSanitizer.ts 1115->1128. Keep cost_in_usd_ticks / server_side_tool_usage(_details) through sanitizeResponsesApiResponse allowlists so native xAI tool responses retain usage.",
-  "_rebaseline_2026_08_02_v3850_agentrouter_responses": "Release v3.8.50 AgentRouter/Codex compatibility reconciliation. open-sse/executors/base.ts 1562->1578: #9190 wires AgentRouter's selected Claude/OpenAI/Responses protocol through the existing executor URL, auth, identity-header and fingerprint chokepoints; the reusable alternate resolver remains outside base.ts. open-sse/utils/stream.ts 2887->2889: #9213 evaluates Responses ID and usage normalization independently so response.completed always receives finite usage.total_tokens instead of short-circuiting after an ID rewrite. tests/unit/chatcore-translation-paths.test.ts 2769->2776: #9191 updates the existing Claude-Code bridge assertions for the dynamic AgentRouter wire image. PR #9224 offsets its own chatCore growth by extracting the AgentRouter protocol decisions into chatCore/agentRouterProtocol.ts, leaving chatCore below its frozen ceiling. Covered by agentrouter executor/chatCore protocol tests, chatcore translation-path tests, and responses-commentary-passthrough tests.",
   "_rebaseline_2026_08_05_9323_agentrouter_waf_retry": "PR #9323 (fix(agentrouter): retry on 400 content-blocked + burst guard) own growth: open-sse/executors/base.ts 1578->1623 (check-file-size.mjs conta via split(\"\\n\").length; wc -l ve 1622). As +45 linhas sao o WAF_RETRY_CONFIG + o burst guard via gateOutboundRequest() para o WAF do agentrouter.org, com comentarios explicando o porque de cada mitigacao e cobertos por tests/unit/base-executor-waf-retry.test.ts e tests/unit/wafRateLimit.test.ts. Crescimento funcional legitimo, nao inchaco.",
   "_rebaseline_2026_08_05_9529_own_growth": "PR #9529 own growth (base release/v3.8.50 medida EXATAMENTE nos frozen antigos, entao o modo base-relative #8522 nao cobre): open-sse/services/rateLimitManager.ts 1060->1105 (+45: helper applyLimiterSettings() que re-arma o heartbeat do reservoir apos updateSettings — fix do bug Bottleneck 2.19.5 que congelava a fila weighted; TDD em tests/unit/ratelimit-reservoir-refresh.test.ts); tests/integration/chat-pipeline.test.ts 1592->1598 (+6: User-Agent do codex derivado de getCodexClientVersion() em vez de literal pinado — teste-irmao alinhado ao contrato); tests/unit/provider-validation-specialty.test.ts 2980->2985 (+5: cobertura NOVA claude-web 429 -> valid:false, alinhamento #9406); open-sse/translator/response/openai-responses.ts 1174->1204 (+30: buildResponsesReasoningSummaryDelta MOVIDA do leaf pureHelpers.ts para o host — a funcao do #9500 muta stream state e violava o contrato do leaf puro; o LOC total do par host+leaf nao cresceu, o pureHelpers encolheu o mesmo tanto). Crescimento por fix de producao + cobertura adicional + realocacao arquitetural, nao inchaco.",
   "_rebaseline_2026_08_06_v3850_inherited_drift_reconcile": "Reconciliacao 2026-08-06 do drift ACUMULADO da release/v3.8.50 apos o lote de merges de 08-05/06: 13 arquivos acima do frozen no tip puro 8180b49ce1 (medidos pelo proprio gate). O modo PR base-relative (#8522) deixa PRs inocentes passarem, e os rebaselines individuais dos PRs se perderam nas resolucoes sucessivas de conflito deste hot-file — o drift so aparece no modo absoluto (nightly/local). Crescimentos funcionais dos PRs mergeados: #9024 topology click-nav src/app/(dashboard)/dashboard/HomePageClient.tsx; #9324 OpenRouter enrich src/app/(dashboard)/dashboard/providers/page.tsx; #9329 quota card ordering src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx; #9193 context-window suffixes src/sse/handlers/chat.ts; #9332 nested Claude server tool ids open-sse/executors/base.ts; #9228 strip orphaned tool outputs open-sse/executors/codex.ts; #9236 nvidia tool-name normalize open-sse/executors/default.ts; #9314 nested tool_call validation open-sse/executors/kiro.ts; #9260 caller identity REST hops open-sse/mcp-server/server.ts; #8934 cache breakpoints tests tests/unit/chatcore-translation-paths.test.ts; #9193 suffix tests tests/unit/combo-routing-engine.test.ts; #9196 reasoning-on-tool-finish tests tests/unit/sse-auth.test.ts; #9163 GPT-5.6 Max reasoning tests tests/unit/translator-openai-to-kiro.test.ts. default.ts e kiro.ts entram no frozen (estavam sem entrada, acima do cap 1000). Atualizacao pos-medicao (a base avancou durante o ciclo do PR): src/sse/handlers/chat.ts 1857->1877 (#9184 affinity EOF evict) e open-sse/executors/default.ts 1027->1042 (#9005 Kimi K3 tool-name backfill).",
   "_rebaseline_2026_08_06b_v3850_sweepreds_drift": "Segunda reconciliacao de 2026-08-06 (/sweep-reds sobre o tip puro 2ddbbc61a6): 3 arquivos voltaram a passar do frozen apos os merges do mesmo dia, com atribuicao 1:1 por commit. (1) src/app/(dashboard)/dashboard/providers/page.tsx 1928->1944 e (2) open-sse/executors/base.ts 1635->1640, ambos do #9515 (feat(radar): flag-gated signed free-model catalog overlay, commit e7f6b1d130) — o overlay do Radar entra por wiring nos chokepoints ja existentes (a resolucao/verificacao do catalogo assinado mora fora destes dois arquivos); +16 e +5 linhas liquidas nao sao extraiveis sem inventar um leaf por callsite. (3) open-sse/services/accountFallback.ts 1966->1972 do #8704 (commit c4527f97bd), +6 linhas de dados em CREDITS_EXHAUSTED_SIGNALS ('has been exhausted', fixes #8631). src/sse/handlers/chat.ts 1880>1877 tambem estava violando e NAO entra aqui de proposito: e drenado por encolhimento na PR #9598, sem rebaseline. Crescimento proprio DESTA PR: src/lib/db/migrationRunner.ts 1077->1084 (+7) — o guard retroativo em isSchemaAlreadyApplied para os arquivos renumerados 137/138, exigido pela propria mensagem de erro de colisao do runner (ambas as migracoes sao ALTER TABLE ADD COLUMN puro, nao idempotente). Dois `case` + dois `return hasColumn(...)` + 3 linhas de comentario dentro do switch existente; nao extraivel.",
   "_rebaseline_2026_08_06c_v3850_sweepreds_pr2": "Segunda PR do /sweep-reds (fix/release-v3.8.50-basereds-0806b): tests/unit/provider-models-route.test.ts 1784->1787 (medido pelo gate, que conta split(\"\\n\").length) (+2 apos compressao de comentarios) — alinhamento de contrato forcado por dois merges do dia: #9106 tornou gemini-3.1-pro-high user-callable (a entry do alias entra na lista esperada do teste de discovery-retry, +1 linha de dado + 1 de comentario) e ff012ff420 adicionou onboardUser como bootstrap hop (exclusao no mock, ja comprimida a 1 linha). Nao ha o que encolher sem apagar o comentario que explica o porque.",
-  "_rebaseline_2026_08_07_v3850_sweepreds_pr2_toolnamemap": "tests/unit/translator-openai-to-gemini.test.ts 1616->1619 (+3). O frozen estava EXATAMENTE no tamanho da base, entao qualquer linha nova viola. #9568 (c9a3361e5a) fez buildChangedToolNameMap emitir entradas IDENTIDADE (o Gemini minusculiza nomes de tool nas respostas, entao o tradutor de resposta precisa da chave para mapear de volta), o que passou a incluir `_toolNameMap` no envelope Antigravity de qualquer request com tools. As 3 linhas sao: a chave nova na lista esperada de Object.keys, 1 comentario explicando POR QUE ela aparece (sem ele o proximo leitor tenta remove-la de novo) e 1 assert do CONTEUDO do map — presenca de chave sozinha nao provaria a entrada identidade, que e justamente o comportamento novo. Nao ha o que extrair: e alinhamento de contrato dentro de um teste existente."
+  "_rebaseline_2026_08_07_v3850_sweepreds_pr2_toolnamemap": "tests/unit/translator-openai-to-gemini.test.ts 1616->1619 (+3). O frozen estava EXATAMENTE no tamanho da base, entao qualquer linha nova viola. #9568 (c9a3361e5a) fez buildChangedToolNameMap emitir entradas IDENTIDADE (o Gemini minusculiza nomes de tool nas respostas, entao o tradutor de resposta precisa da chave para mapear de volta), o que passou a incluir `_toolNameMap` no envelope Antigravity de qualquer request com tools. As 3 linhas sao: a chave nova na lista esperada de Object.keys, 1 comentario explicando POR QUE ela aparece (sem ele o proximo leitor tenta remove-la de novo) e 1 assert do CONTEUDO do map — presenca de chave sozinha nao provaria a entrada identidade, que e justamente o comportamento novo. Nao ha o que extrair: e alinhamento de contrato dentro de um teste existente.",
+  "_rebaseline_2026_06_22_4644_deepseek_web_tools": "PR #4644 (BugsBag/robust deepseek-web tool-call parsing): open-sse/executors/deepseek-web.ts 1117->1125 (+8). The new agentic tool-call path emits surrounding text + reasoning before tool_calls and swaps to the dedicated deepseekWebTools.ts parser; the +8 lines are cohesive wiring at the existing transformSSE chokepoint (the parser itself lives in the new deepseekWebTools.ts file, already under cap). The PR's own fast-gate (PR->release) does not run check:file-size, so this surfaced only at release reconcile. Covered by tests/unit/deepseek-web-tools-variants.test.ts + deepseek-web-tools-execute.test.ts.",
+  "_rebaseline_2026_06_23_4712_deepseek_web_tool_results": "PR for #4712 (deepseek-web drops role:tool): open-sse/executors/deepseek-web.ts 1125->1148 (+23). messagesToPrompt() now folds role:\\\"tool\\\" results into the single-prompt transcript (recovering the tool name from the preceding assistant tool_calls by tool_call_id) instead of silently dropping them; the lines are cohesive wiring inside the existing function. Covered by tests/unit/deepseek-web-tool-result-prompt-4712.test.ts.",
+  "_rebaseline_2026_06_24_headroom_strategy": "Headroom-aware connection selection (dario technique): combo.ts 3168->3180 (+12 = a new `else if (strategy === \\\"headroom\\\")` dispatch branch in handleComboChat that delegates to orderTargetsByHeadroom + its log line, plus the import). The actual logic lives OUT of the god-file: the pure ranker rankByHeadroom/computeHeadroom is the new leaf open-sse/services/combo/headroomRanking.ts (91 LOC, <cap) and the async orderer orderTargetsByHeadroom is appended to the existing open-sse/services/combo/quotaStrategies.ts (<cap) next to its sibling reset-aware/reset-window orderers (reuses their connection-expansion machinery). headroom = 1 - max(util_5h, util_7d) from getSaturation (src/lib/quota/saturationSignals.ts), prefers the connection with the most free capacity. Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. fill-first stays default; all existing strategies untouched. Covered by tests/unit/combo-headroom-ranking.test.ts (pure helper) + tests/unit/combo-headroom-strategy.test.ts (orderer, saturation injected). Structural shrink of combo.ts tracked in #3501.",
+  "_rebaseline_2026_06_24_quota_share_strategy": "Dedicated quota-share strategy (Phase 3 #9): combo.ts 3180->3190 (+10 = one new `else if (strategy === \\\"quota-share\\\")` dispatch branch in handleComboChat that delegates 100% to selectQuotaShareTarget + its log line, plus the import). All the new logic lives OUT of the god-file in two new leaves under open-sse/services/combo/: quotaShareInflight.ts (in-flight counter with TTL/lease, ~150 LOC <cap) and quotaShareStrategy.ts (per-model bucket gating via isBucketSaturated + DRR proportional to weight + P2C over in-flight, ~240 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the headroom/reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. ZERO existing strategy cases were modified — only this branch was added, and the qtSd/ combos switched from fill-first to quota-share in src/lib/quota/quotaCombos.ts. Covered by tests/unit/quota-share-strategy.test.ts (gating, DRR fairness, P2C in-flight, fail-open, activation). Structural shrink of combo.ts tracked in #3501.",
+  "_rebaseline_2026_06_24_task_aware_routing": "Task-aware routing strategy (port PR #2045, OmniRoute #4945): combo.ts 3190->3225 (+35) = one new `else if (strategy === \\\"task-aware\\\")` dispatch branch delegating 100% to selectTaskAwareTarget + its imports/log lines. All scoring/classification logic lives OUT of the god-file in the new leaf open-sse/services/taskAwareRouting.ts (553 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors quota-share/headroom/reset-aware branches). ZERO existing strategy cases modified. Covered by tests/unit/combo-task-aware.test.ts (35 tests). Structural shrink of combo.ts tracked in #3501.",
+  "_rebaseline_2026_06_26_fidelity_gate_extraction": "Milestone-B fidelity-gate wiring residual: bodyToText+gateAdvance extracted to fidelityGateStep.ts (889->854, -35), but the StackOptions.fidelityGate field, the `const fidelityGate` reads at the two stacked-loop dispatch chokepoints, and the import of FidelityGateConfig are irreducible wiring that cannot leave strategySelector without an architectural refactor of the pre-existing stacked pipeline. Net: 889->854 (+6 vs the pre-Milestone-B frozen 848). Covered by tests/unit/compression/*.test.ts (940 pass).",
+  "_rebaseline_2026_06_27_5193_5203_antigravity_oauthmodal": "Antigravity remote-login own growth: OAuthModal.tsx 960->969 (gate units). #5193 (+~4: remote paste instruction shown for all remote incl. Google + its rationale comment) and #5203 (+~5: handleManualSubmit credential-blob branch + button guard; submit logic extracted to oauthBlobSubmit.ts to minimize). Frozen set to the SUM so either merge order passes. Cohesive at the existing manual-submit chokepoint.",
+  "_rebaseline_2026_06_27_5193_antigravity_basered": "Base-red (pre-existing release drift, fast-gate PR->release skips check:file-size): accountFallback.ts 1773->1777 and src/app/api/providers/[id]/test/route.ts 924->940 were already over their frozen caps on release/v3.8.39 independent of any antigravity change. Owner chose to rebaseline (keep the documented issue-reference comments #1846/#1449/#347 etc.) rather than accept the contributor comment-stripping in #5200/#5198. Reverted #5200 to restore the comments; bumped these two frozen caps to the actual base sizes. No logic change.",
+  "_rebaseline_2026_06_28_5237_impersonation_ua_refresh": "PR #5237 (refresh impersonation UAs): grok-web.ts 1871->1873 (+2), muse-spark-web.ts 1284->1302 (+18), perplexity-web.ts 1013->1032 (+19). Net semantic change in each file is a single User-Agent constant (Chrome 147->149 for grok/muse; perplexity kept at Firefox 148 to stay matched with the firefox_148 TLS profile — the contributor's 152 bump was reverted to avoid a UA-vs-JA3 mismatch, #2459). The growth is Prettier reflow that lint-staged unavoidably applies to these grandfathered long-line files the moment they are touched; not extractable. src/sse/services/auth.ts 2336->2401 in the same reconcile is #5222's antigravity-LRU-retry growth that merged via --admin without a baseline bump.",
+  "_rebaseline_2026_06_28_5243_risk_gate_prepass": "PR #5243 (compression risk-gate pre-pass) own growth: open-sse/services/compression/strategySelector.ts 854->899 (+45). The three exported entry points (applyCompression/applyStackedCompression/applyStackedCompressionAsync) become thin wrappers over pure-extracted private bodies (runCompression/runStackedCompression/runStackedCompressionAsync) so the risk-gate mask->run->restore wrapper sits strictly OUTSIDE the per-step loop — a single universal integration point. The wrapper logic itself (resolveRiskGate/withRiskGate) lives in the new riskGate/strategyWrap.ts (<cap); the residual growth is the duplicated thin-wrapper signatures + the extracted bodies' dispatch boundary, guarded by a byte-identical parity test (riskGateIntegration). Default off (DEFAULT_COMPRESSION_CONFIG unchanged). Not extractable without hiding the dispatch boundary, mirroring prior compression rebaselines. Structural shrink tracked in #3501.",
+  "_rebaseline_2026_06_28_5275_correlation_id_extract": "Extraction of the safe CorrelationId subset of #5275 (hartmark) — request correlation id stored in call_logs (migration 109) and returned via the X-Correlation-Id response header, WITHOUT the combo/resilience or build/lazy-loading changes (those stay in #5275). Own growth: callLogs.ts 975->985 (correlation_id column on CallLogSummaryRow + read/map), usageHistory.ts 983->988 (correlationId metadata normalize), chat.ts 1575->1632 (withCorrelationId response wiring + combo-failure log carrying correlationId), chatHelpers.ts new 811 (withCorrelationId helper + reqId threading; was 791<cap pre-feature). Cohesive request/logging chokepoint wiring; structural shrink of chat.ts tracked in #3501.",
+  "_rebaseline_2026_06_29_4038_cas_guard": "PR (#4038) own growth: tokenRefresh.ts 2103->2181 (+78 = the compare-and-swap guard on the refresh persist — runWithCasGuard/getActiveCasGuard AsyncLocalStorage pair mirroring runWithOnPersist, casGuardShouldSkipPersist that rereads the row right before persisting and skips the write when a concurrent writer already rotated the refresh_token past the one presented, plus getCasGuardStats counters). Fixes the sibling-rotation-revert → token-family-revocation storm. Gated behind an active guard (opt-in; no guard => byte-identical). Wiring lives at the two persist chokepoints inside getAccessToken; the comparison reuses wasRefreshTokenRotated from refreshSerializer. Not extractable without splitting the refresh hot path.",
+  "_rebaseline_2026_06_29_5286_memoization": "PR #5286 own growth: strategySelector.ts 899->960 (+61 = the opt-in result-memoization branches in applyCompression/applyCompressionAsync — principal+determinism gate, makeMemoKey lookup/store with model+supportsVision folded into the key, recompute-with-memo-off). Default off (memoizeCompressionResults), so zero behavior change. The memo helpers live in the leaf resultMemo.ts (<cap); the chokepoint wiring here is not extractable. Structural shrink of this hot-path file tracked in #3501.",
+  "_rebaseline_2026_07_01_v3843_release_5609": "Rebaseline v3.8.43 (PR #5609 release reconciliation). DRIFT dos 109 commits do ciclo: 8 god-files existentes cresceram (ApiManagerPageClient 2983->3017, combos/page 4594->4608, AddApiKeyModal 868->869, providerPageHelpers 974->996, chat.ts 1635->1647, auth.ts 2401->2403, batchProcessor 828->915, combo.ts 3368->3387) + 2 novos acima do cap (huggingchat.ts 813, tests web-cookie-providers-new 827) + 4 test files cresceram. Modularizacao deferida (blast-radius mid-release); congelado no estado atual p/ o proximo ciclo ratchetar daqui.",
+  "_rebaseline_2026_07_02_5816_qoder": "PR #5816 (@AgentKiller45, qoder PAT via qodercli): qoderCli.ts 666->989, new-above-cap frozen (owner-approved baseline freeze). The growth is the legitimate PAT job-token exchange + quota parsing CLI transport (the pure-JS Cosy path 500'd on every PAT request); extracting the spawn/parse helpers now would just add indirection to a contributor PR mid-merge. Test frozen also raised for this PR's coverage growth: providers-page-utils.test.ts 1052->1092. Additionally clears an inherited base-red from the already-merged #5933 (codex json_schema->text.format): translator-openai-responses-req.test.ts 1097->1172 (+75 regression tests, no offending branch left). All remain frozen (cannot grow further); release captain's rebaseline-at-release supersedes.",
+  "_rebaseline_2026_07_09_6126_clinepass_dual_auth": "PR #6126 (@hajilok, dual-auth ClinePass) own growth: tokenRefresh.ts 2181->2182 (+1 = a single `case \\\"clinepass\\\":` fallthrough label added to the existing `case \\\"cline\\\":` in _getAccessTokenInternal's provider switch, so clinepass token refresh dispatches to the already-shared refreshClineToken() instead of silently falling through to the generic OAuth refresh). Irreducible 1-line switch-case wiring at the existing chokepoint; the header-building logic for the same feature was extracted to a new leaf src/shared/utils/clineAuth.ts::buildClinepassHeaders() (well under cap) to avoid growing open-sse/executors/default.ts. Covered by tests/unit/clinepass-provider.test.ts.",
+  "_rebaseline_2026_07_09_6363_kiro_external_idp": "PR #6363 (@artickc, Kiro external IdP) own growth: tokenRefresh.ts 2182->2249 (+67 = the external_idp refresh branch inside refreshKiroToken — standard public-client OAuth2 refresh_token grant against the org IdP tokenEndpoint via buildExternalIdpRefreshParams/isExternalIdpAuthMethod from the new leaf open-sse/services/kiroExternalIdp.ts, with invalid_grant/invalid_client -> unrecoverable_refresh_error mapping). Cohesive addition at the existing refreshKiroToken chokepoint. Covered by tests/unit/kiro-external-idp.test.ts.",
+  "_rebaseline_2026_07_09_6587_kiro_api_key_auth": "PR #6587 (@strangersp) own growth for Kiro long-lived API-key auth, merged onto v3.8.47 tip: openai-to-kiro.ts 890->912 (+22, auth-header selection for API-key-vs-OAuth-token connections), providerLimits.ts 998->1000 (+2, API-key auth-type branch), translator-openai-to-kiro.test.ts 1234->1257 (+23), providers-page-utils.test.ts 1109->1107 (net -2 after merging with parallel release drift; connectionMatchesProviderCard api_key coverage added), provider-validation-specialty.test.ts 2856->2980 (+124 net after merge with parallel release drift; this PR also removed the file's `@typescript-eslint/no-explicit-any` eslint-suppression entry by fixing all `any` usages, adding typed replacements). Cohesive additive feature growth, well tested; not extractable without splitting the existing chokepoints mid-merge.",
+  "_rebaseline_2026_07_09_6678_routing_strategy_9router": "#6678 (SeaXen) — 9router-parity Routing Strategy settings card + per-provider/combo sticky-round-robin override. Own growth: ProviderDetailPageClient.tsx 784->786 (single ProviderAccountRoutingCard mount + import), auth.ts 2448->2458 (providerStrategies override resolution: fallbackStrategy/stickyRoundRobinLimit per-provider cascade in getProviderCredentials). Both additive, zero unrelated refactor; new UI/logic lives in new files (ProviderAccountRoutingCard.tsx, RoutingStrategyCard.tsx, rrState.ts::resolveComboStickyRoundRobinLimit). chat.ts value below reflects the current release tip (grown by other concurrent PRs, e.g. #6640), not this PR own change.",
+  "_rebaseline_2026_07_10_6318_omp_letta": "PR #6318 (@hamsa0x7, omp+letta CLI integrations) own growth: cliTools.ts (+53 = 2 registry entries incl. omp docsUrl) and cliRuntime.ts (+18 = runtime-detection wiring for the 2 new tools). Cohesive registry/wiring growth at the existing chokepoints; scope reduced from the original 5 tools (pi/codewhale/jcode shipped separately).",
+  "_rebaseline_2026_07_10_gcf_v3_2_decode": "PR #6838 own growth: new vendored file open-sse/services/compression/engines/headroom/gcf/decode_generic.ts frozen at 880 (> 800 cap). It is the vendored GCF generic-profile decoder (spec v3.2 nested flattening plus the prototype-pollution / hasOwnProperty hardening added in this PR's Gemini review). Kept as one file faithful to upstream gcf-typescript so re-vendoring stays a clean copy rather than a re-split each cycle (sibling generic.ts/scalar.ts stay < cap; extraction would also fragment the file's frozen eslint no-explicit-any suppressions). Round-trip + prototype-pollution regression coverage in tests/unit/compression/headroom-smartcrusher.test.ts. Frozen: only shrinks from here.",
+  "_rebaseline_2026_07_12_v3847_mergeprs_tail": "v3.8.47 /merge-prs tail (owner-approved): src/lib/localDb.ts NEW>800 (799->805, +6 re-exports countFreeProxies + recordFreeProxySyncErrors/clearFreeProxySyncErrors/getFreeProxySyncErrors + FreeProxySyncErrors type for #6909 free-pool relay-repair; re-export-only per Hard Rule #2, not extractable).",
+  "_rebaseline_2026_07_15_7070_combos_memo": "PR #7070 (perf/p1-memo) own growth: src/app/(dashboard)/dashboard/combos/page.tsx 4655->4656 (+1 = React.memo wrapping of ComboCard). Covered by tests/unit/ui/combos-page-smoke.test.tsx.",
+  "_rebaseline_2026_07_18_7399_xai_oauth_modal": "PR #7399 (xAI OAuth PKCE) own growth: OAuthModal.tsx 993->998 (+5 = provider entry + PKCE flow branch wiring at the existing provider-switch chokepoint; the provider logic itself lives in src/lib/oauth/providers/xai-oauth.ts, new leaf). Third irreducible wiring bump on this modal (969->989->993->998); structural shrink tracked in #3501.",
+  "_rebaseline_2026_07_19_6636_codex_session_json": "#6636 own growth: OAuthModal.tsx 998->1030 (gate units, split(\\\"\\\\n\\\").length incl. trailing newline; +32 = session-JSON paste branch for handleManualSubmit plus a shared submitCodexAccessToken() helper extracted from the pre-existing bare-JWT branch, mirroring the #5203 oauthBlobSubmit.ts extraction precedent; the normalizer logic itself lives in the new src/lib/oauth/utils/codexSessionImport.ts leaf module, not here). Fourth irreducible wiring bump on this modal (969->989->993->998->1030); structural shrink tracked in #3501.",
+  "_rebaseline_2026_07_19_7546_ghe_copilot_modal": "PR #7546 (GHE Copilot OAuth provider) own growth: OAuthModal.tsx 1030->1056 (gate units). Adds a gheUrl input state, routes ghe-copilot through the existing device-code branch, and threads gheUrl into the device-code request/poll extraData at the existing provider-switch chokepoints (+~24 lines, cohesive with the same pattern as #7399/#6636). The standalone GHE enterprise-URL config step JSX (originally +31 lines inline) was extracted to the new src/shared/components/oauthModal/GheConfigStep.tsx leaf component to minimize the bump; what remains is the irreducible provider-branch wiring. Fifth bump on this modal (969->989->993->998->1030->1056); structural shrink tracked in #3501.",
+  "_rebaseline_2026_07_19_7787_ic2_localdb_reexports": "PR #7787 (IC2 raw connections cache + lazy-decrypt) own growth: localDb.ts 805->807 (gate units, +2). localDb.ts is the re-export-only layer (hard rule #2 — no logic); the PR adds 4 new db/readCache re-exports (touchConnectionLastUsed, getCachedRawProviderConnections, getCachedProviderConnectionById, getCachedProviderNodes) required by existing barrel importers. Irreducible for a re-export list; frozen so it can only shrink.",
+  "_rebaseline_2026_07_20_7779_routingcombo_thread": "PR #7779 own growth: chatHelpers.ts 876->877 (+1, thread routingComboId into executeChatWithBreaker for compression-combo assignment). Frozen so it can only shrink.",
+  "_rebaseline_2026_07_20_7819_autocandidateoverrides_reexport": "PR for #7819 (Level 1+2: read-only auto/* candidate transparency + per-API-key exclusions) own growth: localDb.ts 807->808 (+1). Adds a single `export * from \\\"./db/autoCandidateOverrides\\\"` barrel re-export (hard rule #2 — no logic) for the new DB module backing per-apiKey candidate exclusions. Irreducible for a re-export list; frozen so it can only shrink.",
+  "_rebaseline_2026_07_21_8027_grok_cli_auth_json_paste": "PR #8027 (RaviTharuma, fix(grok-cli) #7610) own growth: OAuthModal.tsx 1080->1100 (gate units). Requires the full ~/.grok/auth.json (with refresh_token) on the paste-import path instead of a bare JWT, at the existing paste-token chokepoint (renamed tab label, updated instructions/placeholder, textarea for the auth.json blob, inline error surface). The validation logic itself (parseGrokCliPasteToken, previously an inline ~75-line function) was extracted to the new src/lib/oauth/utils/grokCliAuthJson.ts leaf module — mirroring the #6636/#7546 extraction precedent — so only the irreducible UI wiring remains here. Sixth bump on this modal (969->989->993->998->1030->1056->1100); structural shrink tracked in #3501.",
+  "_rebaseline_2026_07_21_8034_compression_exclusions_sidebar": "#8034 (compression exclusions dashboard tab) own growth: sections.ts 796->806 (+10, one new COMPRESSION_CONTEXT_GROUP sidebar item linking /dashboard/compression/exclusions). The file was already 796/800 before this PR (organic growth from prior sidebar entries), so a single new nav item pushed it 6 lines over cap. Freezing at 806 (cannot grow further); the sidebar item array is data, not extractable logic.",
+  "_rebaseline_2026_07_22_7936_namespace_roundtrip": "#7936 (@RCrushMe, Responses-Chat namespace round-trip identity seam) own growth: open-sse/translator/response/openai-responses.ts 1092->1125 (+33) and open-sse/utils/stream.ts 2814->2869 (+55) — threading the namespace-identity seam through the Responses↔Chat translation + stream paths so tool-call namespaces survive the round-trip. Cohesive translation/stream wiring at existing chokepoints, frozen at new size.",
+  "_rebaseline_2026_07_22_8010_codex_responses_engine": "PR #8010 (@JxnLexn) own growth: open-sse/mcp-server/schemas/tools.ts 1497->1505 (+8 = threading the new \\\"codex-responses\\\" literal into the compressionConfigureInput strategy/autoTriggerMode Zod enums and setCompressionEngineInput engine enum, mirroring the existing rtk/omniglyph enum entries; no new tool). open-sse/services/compression/strategySelector.ts 1043->1054 (+11 = one new `if (mode === \\\"codex-responses\\\")` dispatch branch in runCompression that delegates 100% to the new codexResponsesEngine.apply, mirroring the existing rtk single-mode dispatch, plus threading config.codexResponsesConfig.preserveToolNames into the shared adaptBodyForCompression call at the 3 existing call sites). src/lib/db/compression.ts (untracked, new-file cap 800) 794->845 (+51 = normalizeCodexResponsesConfig, mirroring the existing normalizeRtkConfig normalizer, plus registering \\\"codex-responses\\\" in the COMPRESSION_MODES/STACKED_PIPELINE_ENGINE_IDS/SINGLE_MODE_ENGINE sets and the getCompressionSettings load/save switch) — added to the baseline at its current size. All three are cohesive dispatch/normalizer wiring at existing chokepoints (mirroring the prior compression-mode rebaselines #6534/#6556), not extractable without hiding the mode-dispatch boundary. Covered by tests/unit/compression/codex-responses.test.ts (6) + omniglyph-registries.test.ts/types.test.ts (22, updated for the new mode).",
+  "_rebaseline_2026_07_22_8034_compression_exclusions_persistence": "#8034 (compression exclusions) own growth: src/lib/db/compression.ts 845->850 (+5 = threading the new compressionExclusions field through the existing getCompressionSettings/saveCompressionSettings load/save switch over the shared key_value compression namespace — no new table, no raw SQL). Mirrors the prior compression-field rebaselines (#8010 codex-responses normalizer at the same chokepoint); the load/save switch is a single dispatch boundary, not extractable without hiding it. Covered by the PR's 8 node:test + 3 vitest cases.",
+  "_rebaseline_2026_07_22_8050_model_lockout_exact_family": "#8050 (@AndrianBalanescu) own growth: accountFallback.ts 1864->1892 (+28) — exact-vs-family model-lockout scoping (getModelLockKey/isModelLocked/clearModelLock/getModelLockoutInfo) so an Antigravity 404 for one bare model no longer hijacks the whole family cooldown. Cohesive lockout logic; frozen at new size.",
+  "_rebaseline_2026_07_22_8081_reasoning_placeholder_guard": "#8081 (@Dingding-leo) own growth: openai-responses.ts 1125->1137 (+12) restructuring the reasoning-placeholder guard so it skips only the empty content block and still emits finish_reason/tool_calls in the same chunk. Cohesive translator wiring; frozen at new size.",
+  "_rebaseline_2026_07_22_8210_openrouter_midstream_error": "PR #8210 (hartmark, fix/openrouter-midstream-error-surfacing) own growth: open-sse/translator/response/openai-responses.ts 1137->1163 (+26) measured on the merged tip (release 1137 + this PR own growth). Adds a single new branch inside openaiToOpenAIResponsesResponse() that detects an OpenRouter-style mid-stream aggregator error (HTTP 200 SSE chunk with empty choices + a top-level error object) and surfaces it as state.upstreamError instead of silently falling through to the no-op/awaitingTrailingUsage path, which previously masked the failure as a false empty-success completion and skipped combo fallback. Irreducible call-site addition at the existing chunk-dispatch chokepoint (mirrors the Gemini-to-OpenAI translator's #4177 precedent for the same class of upstream error surfacing). Note: this baseline entry does NOT cover the separate pre-existing +11 drift already on the release tip from #8081/#8162 (1125->1136, unrelated reasoning-placeholder-stripping fix merged after this PR branched) — that drift belongs to the maintainer's rebaseline, not this PR.",
+  "_rebaseline_2026_07_22_8211_gemini_malformed_tool_choice": "PR #8211 (hartmark, fix/gemini-malformed-function-call-tool-choice) own growth: open-sse/translator/response/gemini-to-openai.ts 771->821 (+50, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds MALFORMED_FUNCTION_CALL/UNEXPECTED_TOOL_CALL handling inside geminiToOpenAIResponse(): synthesizes a `malformed_tool_call` tool_calls entry so finish_reason normalizes to the standard \\\"tool_calls\\\" instead of an unrecognized raw enum value that OpenAI-compatible clients (e.g. OpenClaw) silently ignore, and always synthesizes (rather than skipping when a real tool call already exists) so a malformed attempt alongside a real one in the same turn is not silently discarded. Irreducible cohesive addition at the existing candidate/finishReason translation chokepoint (mirrors the 9router#2462 raw-finish-reason precedent immediately below it in the same function). Covered by the PR's own tests/unit test additions for both the malformed-only and malformed-plus-real-call cases.",
+  "_rebaseline_2026_07_22_8213_chat_abandoned_target_abort": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/sse/handlers/chat.ts 1794->1860 (+66, measured against the PR's own merge-base — the release tip separately carries an unrelated -5 net shrink from #8013's antigravity callable-catalog alignment, which this PR's branch does not include and this entry does not cover). Adds resolveDispatchClientRawRequest(): merges a per-target modelAbortSignal into clientRawRequest.signal (via mergeAbortSignals) so a combo target abandoned by comboTargetTimeoutMs actually observes its own abort and reaches its cleanup path, instead of hanging forever inside withRateLimit/acquireAccountSemaphore and leaking a permanent 'pending' dashboard entry (live incident, log id 1784418258231-14961a). Also wires combo-exhausted rejection logging to capture request body + attempted models via the new rejectedRequestUsage helper. Irreducible additions at the existing chat dispatch chokepoint. Covered by the PR's own combo-config + integration test additions.",
+  "_rebaseline_2026_07_22_8213_combo_cooldown_wait_recording": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/combo.ts 3548->3604 (+56, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Fixes combo cooldown-wait state recording so a bogus 503 is no longer crystallized when the cooldown-wait vars reset every setTry, adds an OpenAI-format SSE error frame path for combo-exhausted rejections (capturing request body + attempted models), and gives an abandoned per-target dispatch its own timeout instead of leaking a permanent 'pending' dashboard entry. Irreducible additions at the existing handleComboChat dispatch/retry chokepoint (mirrors the prior quota-share/headroom/task-aware strategy-branch precedents already frozen in this file). Covered by the PR's own combo-config + Gemini TPM-ceiling benchmark test additions.",
+  "_rebaseline_2026_07_22_8213_gemini_tpm_quota_cooldown_wait": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/accountFallback.ts 1857->1932 on the merged tip (release 1892 incl #8050 +35, plus this PR own growth +40); measured against the PR own merge-base was 1857->1898 (+41 — the release tip separately carries an unrelated +34 from #8050's antigravity 404 model-not-found lockout scoping, which this PR's branch does not include and this entry does not cover). Own growth is the Gemini TPM-ceiling classification + cooldown-wait wiring feeding into the combo cooldown-wait state machine (rate-limit wedge recovery) introduced by this PR's commit series. Irreducible additions at the existing account-fallback/model-lockout chokepoint. Covered by the PR's own gemini-rate-limit-tracker and TPM-ceiling benchmark test additions.",
+  "_rebaseline_2026_07_22_8213_health_unblock_model_cooldowns": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/app/(dashboard)/dashboard/health/page.tsx 1094->1165 (+71, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds handleUnblockAll/handleUnblockOne dashboard actions (DELETE /api/resilience/model-cooldowns) so an operator can manually clear a Gemini TPM-wedge model lockout surfaced by this PR's cooldown-wait fixes, instead of waiting out the ceiling. Irreducible UI wiring at the existing health-page action chokepoint. Covered by the PR's own dashboard/resilience test additions.",
+  "_rebaseline_2026_07_22_8213_requestloggerdetail_unblock_ui": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/shared/components/RequestLoggerDetail.tsx 799->941 (+142, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip; crosses the general 800-line new-file cap so is frozen here for the first time). Adds a collapsible section header (open/expand-less toggle) plus per-log-entry unblock (`unblocking`/`cleared` state, isCombo503 detection) so the request-logger detail panel surfaces the same Gemini TPM cooldown-wait / model-lockout unblock action introduced by this PR at the individual-request level (mirrors the health-page bulk unblock action added in the same PR). Covered by the PR's own dashboard/resilience test additions.",
+  "_rebaseline_2026_07_22_fusion_8013_8098_antigravity": "Fusion of #8013 (backryun, catalog/IDE-CLI-split rewrite) + #8098 (nguyenha935, protocol-fidelity/fail-closed/credits/tool-cloaking): open-sse/services/usage/antigravity.ts NEW 802 (>cap 800, +2 — #8098 credits/tier usage service on #8013's profile-aware headers). Test growth (models-catalog-route 1605->1608, provider-models-route 1752->1757 from #8013 Gemini 3.6 catalog) tracked in testFrozen.",
+  "_rebaseline_2026_07_23_8127_grok_weekly_quota": "#8127 (@apoapostolov) own growth: src/sse/handlers/chat.ts 1861->1865 (+4) — weekly quota tracking for grok-web wires a quota-fetch hook at the existing dispatch chokepoint. Thin wiring mirroring adjacent provider-quota branches; not extractable. Covered by tests/unit/grok-quota-fetcher.test.ts.",
+  "_rebaseline_2026_07_23_8143_empty_catch_logging": "#8143 (@chirag127) own growth: open-sse/utils/stream.ts 2869->2887 (+18) — replacing empty catch blocks in the SSE stream subsystem with console.debug logging (Rule #6 silent-swallow fix, issues #8138-#8142). Cohesive logging additions at the existing catch chokepoints, not extractable; frozen at new size. Covered by tests/unit/stream-handler-catch-logging-8143.test.ts.",
+  "_rebaseline_2026_07_23_8219_cache_ttl_settings_sidebar": "#8219 (@oyi77) own growth: sections.ts 806->813 (+7) — configurable model-catalog cache-TTL settings adds a new sidebar nav entry + its visibility wiring. Sidebar item array is data, not extractable logic; frozen at new size.",
+  "_rebaseline_2026_07_23_8247_8248_model_unhealthy": "#8247+#8248 own growth: accountFallback.ts 1940->1941 (+1, irreducible import statement only — the substantive #8248 DEGRADED-pattern classifier was extracted into open-sse/config/errorConfig.ts, which has ample headroom, instead of growing this frozen file; #8247's fix is a single existing-line condition change, net zero lines). Scoping the credits-exhausted 403/429 branch to isCompatibleProvider() (per-model-quota openai/anthropic-compatible-* nicknames) so it stays model-scoped instead of terminalling the whole connection, and classifying NVIDIA NIM 'Function ... DEGRADED' 400 bodies as model-access-denied instead of a raw passthrough 400. Covered by tests/unit/8247-accountfallback-model-unhealthy.test.ts and tests/unit/8248-accountfallback-nvidia-degraded.test.ts.",
+  "_rebaseline_2026_07_23_8252_combo_400_advance": "#8252 (@RaviTharuma) own growth: accountFallback.ts 1932->1940 (+8) + combo.ts 3604->3630 (+26) — advance combo on model-scoped 400s wrapped as invalid/Bad-Request. Irreducible wiring at existing account-fallback + combo dispatch chokepoints. Covered by combo-model-scoped-400-advance.test.ts.",
+  "_rebaseline_2026_07_23_8266_alibaba_media": "#8266 (@backryun) own growth: imageRegistry.ts 821->979 (+158) — Alibaba-family media models (Qwen image/video, Bailian, Wan) added to the image/video registry. Registry model data, not extractable logic; frozen at new size.",
+  "_rebaseline_2026_07_24_8388_compression_detail_persist": "#8388 (compression engine DETAIL settings — Headroom/session-dedup/CCR — dropped on save) own growth: src/lib/db/compression.ts 866->872 (+6 = irreducible call-site wiring at the existing getCompressionSettings/updateCompressionSettings chokepoint: one import line, one `...buildDetailConfigDefaults()` spread in the seed config, and one `case \\\"sessionDedup\\\": case \\\"ccr\\\": applyDetailConfigUpdate(config, key, parsed); break;` load-switch case, mirroring the existing headroom/#8056 case immediately above it). The actual normalizer logic (normalizeSessionDedupConfig/normalizeCcrConfig, matching SESSION_DEDUP_SCHEMA/CCR_SCHEMA bounds) was EXTRACTED into a new leaf src/lib/db/compressionDetailNormalizers.ts (well under cap) so this frozen file only carries the minimal dispatch wiring. Covered by tests/unit/8388-compression-detail-persist.test.ts (schema-accept + full DB save->reload round-trip for both new sub-objects, plus a no-regression assertion on the existing headroom round-trip).",
+  "_rebaseline_2026_07_24_responses_toolcalls_log_summary": "hartmark, fix/responses-tool-calls-log-summary own growth: open-sse/translator/response/openai-responses.ts 1163->1174 (+11). closeToolCall() now also writes the completed tool call into the shared state.toolCalls Map (already populated by the openai-to-claude / claude-to-openai / gemini-to-openai response translators) so stream.ts's completion-log summary builder (which reads state.toolCalls, not this translator's own funcCallIds/funcNames/funcArgsBuf bookkeeping) reports finish_reason \\\"tool_calls\\\" and message.tool_calls for openai->openai-responses translated streams instead of always logging \\\"stop\\\" with no tool_calls — the actual client-facing SSE events were already correct; only the persisted call-log summary was wrong. Irreducible call-site addition at the existing tool-call-close chokepoint. Covered by the new regression test in tests/unit/translator-resp-openai-responses.test.ts.",
+  "_rebaseline_2026_07_25_8476_combo_input_bound_homogeneous_scope": "PR #8476 (herjarsa, fix/8375-8459-combo-image-fixes, #8375) own growth: open-sse/services/combo.ts 3642->3679 (+37 net: +29 the PR's own isInputBoundFailure short-circuit for deterministic context_length_exceeded/context_window_exceeded failures, +8 a /green-prs pre-merge fix scoping that short-circuit to homogeneous remainders only — the shipped code fired unconditionally on ANY target, regressing the intentional heterogeneous-combo fallback #6637/isContextOverflow400 protects, exactly as flagged by this PR's own review evidence but never actually implemented in the branch). The fix compares orderedTargets[i+1..] modelStr against the failing target's modelStr at the existing executeTarget dispatch chokepoint (mirrors the sameProviderNext precedent a few lines below) — irreducible call-site wiring, not extractable without hiding the dispatch boundary. Covered by tests/unit/combo-input-bound-failure-8375.test.ts (homogeneous pool still short-circuits) and the new tests/unit/combo-input-bound-heterogeneous-8375.test.ts (heterogeneous combo now correctly falls through to the larger-context target).",
+  "_rebaseline_2026_07_25_adobe_firefly_reference_images": "Follow-up to #8006: storage upload + referenceBlobs for image/video and /v1/images/edits dispatch. adobeFireflyClient.ts 1958->2317 (+upload helpers, extract sources, resolve blob ids). Note: 2317 not 2316 — check-file-size.mjs counts LOC via split(\\\"\\\\n\\\").length (counts the trailing-newline empty element), which is 1 higher than `wc -l` on a file ending in \\\\n; the PR's original entry (2316) was measured with wc -l and undercounted by 1 against the actual gate.",
+  "_rebaseline_pr1043_minimax_tts": "Upstream port decolua/9router#1043 (toanalien) own growth: audioSpeech.ts 965->1061 (+96). Adds MiniMax T2A v2 TTS dispatch (handleMinimaxSpeech + hexToBytes helper) — provider entry was already in audioRegistry (format: minimax-tts) but no handler existed, falling through to the OpenAI-compatible default that fails (T2A has custom shape + hex-encoded audio + base_resp envelope). New branch sits next to the other inline provider branches (xiaomi-mimo, coqui, tortoise, aws-polly) — extracting would just create indirection. Covered by tests/unit/minimax-tts-1043.test.ts (3 tests, GREEN: success, base_resp error, invalid-hex).",
+  "_rebaseline_pr4592_exclude_exhausted_auto": "Reconcile #4592 already-merged growth: combo.ts 2991->3036 (+45, terminal-status quota-cutoff exclusion in buildAutoCandidates + opt-in gate). Fast-gate PR->release does not run check:file-size.",
+  "open-sse/executors/antigravity.ts": "1528",
+  "open-sse/executors/base.ts": "1640",
+  "open-sse/executors/chatgpt-web.ts": "3241",
+  "open-sse/executors/codex.ts": "1562",
+  "open-sse/executors/cursor.ts": "1563",
+  "open-sse/executors/deepseek-web.ts": "1148",
+  "open-sse/executors/grok-web.ts": "1044",
+  "open-sse/executors/muse-spark-web.ts": "1405",
+  "open-sse/handlers/chatCore.ts": "5034",
+  "open-sse/handlers/imageGeneration.ts": "3101",
+  "open-sse/handlers/responseSanitizer.ts": "1128",
+  "open-sse/handlers/search.ts": "1536",
+  "open-sse/handlers/videoGeneration.ts": "1063",
+  "open-sse/mcp-server/schemas/tools.ts": "1553",
+  "open-sse/mcp-server/server.ts": "1448",
+  "open-sse/mcp-server/tools/advancedTools.ts": "1120",
+  "open-sse/services/accountFallback.ts": "1978",
+  "open-sse/services/adobeFireflyClient.ts": "2385",
+  "open-sse/services/claudeCodeCompatible.ts": "1202",
+  "open-sse/services/combo.ts": "3648",
+  "open-sse/services/compression/strategySelector.ts": "1060",
+  "open-sse/services/rateLimitManager.ts": "1167",
+  "open-sse/translator/response/openai-responses.ts": "1204",
+  "open-sse/utils/cursorAgentProtobuf.ts": "1505",
+  "open-sse/utils/stream.ts": "2889",
+  "src/app/(dashboard)/dashboard/HomePageClient.tsx": "1388",
+  "src/app/(dashboard)/dashboard/analytics/ComboHealthTab.tsx": "1031",
+  "src/app/(dashboard)/dashboard/api-manager/ApiManagerPageClient.tsx": "3117",
+  "src/app/(dashboard)/dashboard/cache/media/MediaPageClient.tsx": "1067",
+  "src/app/(dashboard)/dashboard/combos/page.tsx": "4703",
+  "src/app/(dashboard)/dashboard/costs/CostOverviewTab.tsx": "1283",
+  "src/app/(dashboard)/dashboard/costs/quota-share/components/PoolWizard.tsx": "1022",
+  "src/app/(dashboard)/dashboard/endpoint/EndpointPageClient.tsx": "2615",
+  "src/app/(dashboard)/dashboard/health/page.tsx": "1165",
+  "src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx": "1324",
+  "src/app/(dashboard)/dashboard/providers/page.tsx": "1944",
+  "src/app/(dashboard)/dashboard/runtime/RuntimePageClient.tsx": "1201",
+  "src/app/(dashboard)/dashboard/settings/components/PricingTab.tsx": "1019",
+  "src/app/(dashboard)/dashboard/settings/components/ProxyRegistryManager.tsx": "1470",
+  "src/app/(dashboard)/dashboard/settings/components/ResilienceTab.tsx": "1123",
+  "src/app/(dashboard)/dashboard/settings/components/RoutingTab.tsx": "1629",
+  "src/app/(dashboard)/dashboard/settings/components/SystemStorageTab.tsx": "1573",
+  "src/app/(dashboard)/dashboard/usage/components/BudgetTab.tsx": "1028",
+  "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": "2148",
+  "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx": "1119",
+  "src/app/api/providers/[id]/models/route.ts": "2361",
+  "src/app/api/v1/models/catalog.ts": "1597",
+  "src/lib/tokenHealthCheck.ts": "1053",
+  "src/lib/db/apiKeys.ts": "1529",
+  "src/lib/db/core.ts": "1639",
+  "src/lib/db/migrationRunner.ts": "1094",
+  "src/lib/db/models.ts": "1097",
+  "src/lib/db/providers.ts": "1034",
+  "src/lib/memory/retrieval.ts": "1073",
+  "src/lib/tailscaleTunnel.ts": "1202",
+  "src/lib/usage/providerLimits.ts": "1013",
+  "src/shared/components/OAuthModal.tsx": "1134",
+  "src/shared/components/RequestLoggerV2.tsx": "1629",
+  "src/shared/components/analytics/charts.tsx": "1035",
+  "src/shared/services/cliRuntime.ts": "1122",
+  "src/sse/handlers/chat.ts": "1904",
+  "src/sse/services/auth.ts": "2508",
+  "tests/unit/account-fallback-service.test.ts": "1572",
+  "tests/unit/provider-validation-specialty.test.ts": "2985",
+  "open-sse/executors/hyperagent.ts": "1026",
+  "open-sse/executors/default.ts": "1042",
+  "open-sse/executors/kiro.ts": "1069",
+  "open-sse/translator/request/openai-to-kiro.ts": "1057",
+  "open-sse/utils/sseHeartbeat.ts": "142",
+  "_rebaseline_2026_08_04_9305_sse_comments": "#9305 fix: broadened sseCommentsEnabled()",
+  "_rebaseline_2026_08_09_v3850_release_close": "Release v3.8.50 close reconciliation on e0ce95c592: src/sse/handlers/chat.ts 1904->1918 is the irreducible request-pipeline wiring from #9759 that invokes the Modality Bridge guardrail without moving its implementation into the handler; covered by the 17 Vision Bridge canaries plus the PR-1 focused suite. open-sse/translator/response/openai-responses.ts 1204->1215 is #9168's Responses tool-call argument delta buffering/normalization at the existing translator state-machine chokepoint; covered by its dedicated translator regression tests. Both values are measured by check:file-size (split-newline semantics), and the gate remains frozen at the new exact sizes.",
+  "_rebaseline_2026_08_08_toolcall_message_index_collision": "fix(responses-api): tool call after a text message collided on the same output_index. own growth: open-sse/translator/response/openai-responses.ts 1204->1224 (+20, extracted toolCallOutputIndexBase() shared helper so emitToolCall/closeToolCall can no longer compute a tool call's output_index independently and collide with a text message emitted in the same turn). Live incident (2026-08-08, OpenClaw agent): a client that tracks response items by output_index saw the tool call's added/delta/done events land on an index it had already marked complete (the just-closed text message), and silently dropped them — the agent spoke its preamble and never executed the tool call, even though OmniRoute's own recorded responseBody had a complete, valid tool_calls entry. Covered by the new regression test in tests/unit/translator-resp-openai-responses.test.ts reproducing the exact live scenario."
 }

config/quality/quality-baseline.json

@@ -177,12 +177,13 @@
       "dedicatedGate": true
     },
     "bundleSize": {
-      "value": 7666,
+      "value": 8045,
       "direction": "down",
       "dedicatedGate": true,
       "_rebaseline_2026_07_07_v3846_release_close": "5601->6534 (+933). v3.8.46 release close: gzip of the 4 bin/*.mjs entrypoints (size-limit + @size-limit/file) grew from this cycle's feature/fix merges pulled transitively into the CLI entrypoints (new providers, combo pipeline strategy #6396, effort/thinking standardization #6241, catalog cache-invalidation #6408). Measured 6534 locally via `check:bundle-size --ratchet` (deterministic gzip, matches CI). Legitimate cycle growth; shrink is separate debt.",
       "_rebaseline_2026_07_19_7808_codeql_alias_resolver_hook": "6534->6762 (+228). PR #7808 (CodeQL js/incomplete-url-substring-sanitization fix): the ESM loader hook source moved out of the inline `HOOK_SOURCE` template literal in bin/aliasResolver.mjs into a real file bin/aliasResolverHook.mjs, loaded via pathToFileURL() instead of a dynamically-built `data:text/javascript,...` URL. The new file is now counted by size-limit as a 5th bin/*.mjs entrypoint. Net +228 = the hook's gzip size (previously hidden inside aliasResolver.mjs because the template literal was compressed away). Security-driven; no shrink opportunity.",
-      "_rebaseline_2026_07_28_v3849_release_preflight": "6762 -> 7666 (+904). Fechamento do ciclo v3.8.49: gzip dos entrypoints bin/*.mjs (size-limit + @size-limit/file) cresceu com o que os merges do ciclo puxam transitivamente para o CLI (novos provedores — 271->290, seletor de protocolo por conexão #8861, catálogos de busca #8814, resiliência). Crescimento legítimo de ciclo, medido localmente com `npm run check:bundle-size` = 7666 (gzip determinístico, bate com o CI). Encolher é dívida separada."
+      "_rebaseline_2026_07_28_v3849_release_preflight": "6762 -> 7666 (+904). Fechamento do ciclo v3.8.49: gzip dos entrypoints bin/*.mjs (size-limit + @size-limit/file) cresceu com o que os merges do ciclo puxam transitivamente para o CLI (novos provedores — 271->290, seletor de protocolo por conexão #8861, catálogos de busca #8814, resiliência). Crescimento legítimo de ciclo, medido localmente com `npm run check:bundle-size` = 7666 (gzip determinístico, bate com o CI). Encolher é dívida separada.",
+      "_rebaseline_2026_08_09_v3850_release_close": "7666 -> 8045 (+379 gzip bytes, +4.9%). Release v3.8.50 close reconciliation measured twice with the real size-limit + @size-limit/file path on tip e0ce95c592. Per-entry measurements remain below their absolute budgets: omniroute.mjs 4380/15000, mcp-server.mjs 1195/5000, nodeRuntimeSupport.mjs 887/8000, reset-password.mjs 1583/6000. The growth accumulated through legitimate CLI/runtime work in this cycle, including global-install ESM alias resolution, Termux cache preparation, and MCP stdio startup hardening; no entrypoint is near its absolute ceiling. The direction:down ratchet stays blocking from this exact measured tip."
     },
     "openapiBreaking": {
       "value": 0,

config/quality/test-discovery-baseline.json

@@ -1,24 +1,10 @@
 {
   "_comment": "Catraca de test-discovery (check-test-discovery.mjs). Cada entrada e um arquivo de teste que NENHUM runner coleta (ele nunca roda) — divida congelada na auditoria 6A.1 (2026-06-09; 195 originais, 135 religados no node runner em 6A.1c). So pode DIMINUIR: religue o teste (ajustando o glob do runner ou movendo o arquivo) e remova a entrada via --update. NAO adicione novos orfaos — corrija o runner.",
-  "_remaining_60": "Categorias: 33 .test.tsx de tests/unit (religaveis via vitest.config root, MAS o experimento 2026-06-09 mostrou 24 arquivos vermelhos — triagem de drift de UI na janela 2026-06-16, junto com os 14 fails do proprio test:vitest:ui atual); 9 open-sse __tests__ + 8 src __tests__ (includes de vitest.config que NENHUM script executa sem filtro); 4 golden-set + 1 benchmarks + 1 live + 1 stress (deliberadamente manuais — decidir runner/gating); 3 integration/services (gated RUN_SERVICES_INT=1, sem runner CI).",
+  "_remaining_13": "13 orfaos restantes: 2 testes de API em settings + 1 snapshot de quota do DB; 4 golden-set + 1 benchmark + 1 teste live + 1 stress (deliberadamente manuais — decidir runner/gating); 3 integration/services (gated RUN_SERVICES_INT=1, sem runner CI).",
   "orphans": [
-    "open-sse/services/__tests__/chatgptTlsClient.test.ts",
-    "open-sse/services/__tests__/claudeTlsClient.test.ts",
-    "open-sse/services/__tests__/grokTlsClient.test.ts",
-    "open-sse/services/__tests__/manifestAdapter.test.ts",
-    "open-sse/services/__tests__/specificityDetector.test.ts",
-    "open-sse/services/__tests__/tierResolver.test.ts",
-    "open-sse/services/__tests__/volumeDetector.test.ts",
-    "open-sse/translator/helpers/__tests__/maxTokensHelper.test.ts",
-    "open-sse/translator/helpers/__tests__/schemaCoercion.test.ts",
     "src/app/api/settings/__tests__/memory.test.ts",
     "src/app/api/settings/__tests__/settings.test.ts",
     "src/lib/db/__tests__/quotaSnapshots.test.ts",
-    "src/lib/memory/__tests__/injection.test.ts",
-    "src/lib/memory/__tests__/qdrant-wiring.test.ts",
-    "src/lib/memory/__tests__/retrieval.test.ts",
-    "src/lib/memory/__tests__/schemas.test.ts",
-    "src/lib/skills/__tests__/integration.test.ts",
     "tests/benchmarks/pipeline-accuracy.test.ts",
     "tests/golden-set/compression-caveman-v2.test.ts",
     "tests/golden-set/compression-quality.test.ts",
@@ -28,36 +14,6 @@
     "tests/integration/services/full-lifecycle.int.test.ts",
     "tests/integration/services/route-guard-services.int.test.ts",
     "tests/live/deepseek-web-live.test.ts",
-    "tests/theoldllm-stress.test.ts",
-    "tests/unit/AutoComboCatalog.test.tsx",
-    "tests/unit/SkillsConceptCard.test.tsx",
-    "tests/unit/agent-skills-page.test.tsx",
-    "tests/unit/dashboard/batch/components/BatchDetailModal.test.tsx",
-    "tests/unit/dashboard/batch/components/ExpirationBadge.test.tsx",
-    "tests/unit/dashboard/batch/components/NewBatchWizard.test.tsx",
-    "tests/unit/dashboard/batch/components/ProgressBarBicolor.test.tsx",
-    "tests/unit/dashboard/batch/components/UploadFileModal.test.tsx",
-    "tests/unit/dashboard/batch/components/useBatchActions.test.tsx",
-    "tests/unit/dashboard/batch/concept-cards.test.tsx",
-    "tests/unit/dashboard/batch/list-regression.test.tsx",
-    "tests/unit/dashboard/batch/sanitization.test.tsx",
-    "tests/unit/omni-skills-page.test.tsx",
-    "tests/unit/shared-clipboard.test.tsx",
-    "tests/unit/shared/components/AutoRoutingBanner.test.tsx",
-    "tests/unit/shared/components/KiroAuthModal.test.tsx",
-    "tests/unit/shared/components/ProxyConfigModal.test.tsx",
-    "tests/unit/translator-friendly-advanced-section.test.tsx",
-    "tests/unit/translator-friendly-compression.test.tsx",
-    "tests/unit/translator-friendly-concept-card.test.tsx",
-    "tests/unit/translator-friendly-integration.test.tsx",
-    "tests/unit/translator-friendly-monitor-tab.test.tsx",
-    "tests/unit/translator-friendly-page-client.test.tsx",
-    "tests/unit/translator-friendly-pipeline-view.test.tsx",
-    "tests/unit/translator-friendly-raw-json-panel.test.tsx",
-    "tests/unit/translator-friendly-result-narrated.test.tsx",
-    "tests/unit/translator-friendly-simple-controls.test.tsx",
-    "tests/unit/translator-friendly-stream-transformer.test.tsx",
-    "tests/unit/translator-friendly-test-bench.test.tsx",
-    "tests/unit/translator-friendly-translate-tab.test.tsx"
+    "tests/theoldllm-stress.test.ts"
   ]
 }

docs/architecture/QUALITY_GATES.md

@@ -186,10 +186,10 @@ Runs on pull requests only.
 
 Runs after `build`. Blocks merge on failure.
 
-| Suite            | Validates                                               | Blocking                                                                   |
-| ---------------- | ------------------------------------------------------- | -------------------------------------------------------------------------- |
-| `test:vitest`    | MCP server (94 tools), autoCombo, cache — vitest runner | Yes                                                                        |
-| `test:vitest:ui` | UI component tests — vitest runner                      | **Advisory** (`continue-on-error: true`) — failing until Fase 6A UI triage |
+| Suite            | Validates                                               | Blocking                                                                                                      |
+| ---------------- | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
+| `test:vitest`    | MCP server (94 tools), autoCombo, cache — vitest runner | Yes                                                                                                           |
+| `test:vitest:ui` | UI component tests — vitest runner                      | **Blocking** — pre-existing failures are explicitly excluded in `vitest.config.ts`; new failures fail the job |
 
 ### Nightly workflows (scheduled, advisory)
 
@@ -401,7 +401,7 @@ several "obvious" merges turned out to hide debt and are **not** clean drop-ins.
 
 - `check:openapi-security-tiers` (advisory) — ❌ **NOT cleanly flippable.** It exits 0 but warns that several `traffic-inspector` routes under `LOCAL_ONLY_API_PREFIXES` lack the `x-loopback-only: true` annotation. Enforcing it requires adding those annotations to `openapi.yaml` first.
 - `typecheck:noimplicit:core` (advisory) — largely subsumed by the blocking `check:type-coverage` ratchet. Flip to a ratchet or drop the redundant second `tsc` pass.
-- `test:vitest:ui` (advisory, 14 parked fails) — fix-and-block or delete; don't leave rotting.
+- `test:vitest:ui` (now **blocking**) — pre-existing failures are explicitly excluded in `vitest.config.ts` with `// #8618` tracking comments; new failures fail the job.
 - `check:secrets` (gitleaks, blocking ratchet frozen at 3 documented false-positives) — allowlist the 3 to reach 0, or demote to advisory. Overlaps GitHub native secret-scanning + `check:public-creds`.
 - `check:pr-evidence` (blocking, greps PR-body prose) — high false-positive risk; weakens Hard Rule #18 enforcement if dropped, so this is a genuine policy call.
 - `semgrep` (advisory standalone) — overlaps CodeQL for the OWASP families; wire its baseline to a ratchet or drop.

docs/guides/DOCKER_GUIDE.md

@@ -147,11 +147,11 @@ The prod stack runs in parallel with the dev compose (different container names,
 
 The repository ships a multi-stage Dockerfile (`Dockerfile`). Three stages are exposed; pick the right `target` for your use case.
 
-| Stage         | Base image                 | Purpose                                                                                                                                                            |
-| ------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `builder`     | `node:24.15.0-trixie-slim` | Installs deps (`npm ci --legacy-peer-deps`) and runs `npm run build -- --webpack`                                                                                  |
-| `runner-base` | `node:24.15.0-trixie-slim` | Production runtime with the Next.js standalone output. **No provider CLIs bundled.**                                                                               |
-| `runner-cli`  | `runner-base`              | Adds `git`, `docker.io`, `docker-compose` and global CLIs: `@openai/codex`, `@anthropic-ai/claude-code`, `droid`, `openclaw`. **Pick this for agentic workflows.** |
+| Stage         | Base image            | Purpose                                                                                                                                                            |
+| ------------- | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `builder`     | `node:26-trixie-slim` | Installs deps (`npm ci --legacy-peer-deps`) and runs `npm run build` (Turbopack by default — see Build-time resources below)                                       |
+| `runner-base` | `node:26-trixie-slim` | Production runtime with the Next.js standalone output. **No provider CLIs bundled.**                                                                               |
+| `runner-cli`  | `runner-base`         | Adds `git`, `docker.io`, `docker-compose` and global CLIs: `@openai/codex`, `@anthropic-ai/claude-code`, `droid`, `openclaw`. **Pick this for agentic workflows.** |
 
 Build a specific target manually:
 
@@ -160,14 +160,50 @@ docker build --target runner-base -t omniroute:base .
 docker build --target runner-cli  -t omniroute:cli  .
 ```
 
-Defaults exported by `runner-base`: `PORT=20128`, `HOSTNAME=0.0.0.0`, `NODE_OPTIONS=--max-old-space-size=512`, `DATA_DIR=/app/data`, `OMNIROUTE_MIGRATIONS_DIR=/app/migrations`.
+### Build-time resources
+
+Two build args control what the `builder` stage costs. They are build-time only —
+`OMNIROUTE_MEMORY_MB` (below) is a separate, runtime knob.
+
+| Build arg                   | Default | Effect                                                                 |
+| --------------------------- | ------- | ---------------------------------------------------------------------- |
+| `OMNIROUTE_USE_TURBOPACK`   | `1`     | `0` builds with webpack instead. Lower peak memory, slower.            |
+| `OMNIROUTE_BUILD_MEMORY_MB` | `4096`  | V8 heap ceiling (`--max-old-space-size`) for the spawned `next build`. |
+
+Turbopack compiles in native Rust memory that lives **outside** the V8 heap, so
+`OMNIROUTE_BUILD_MEMORY_MB` does not bound it. On a host with a memory ceiling the
+build is then SIGKILLed by the OOM killer with no error text at all — it simply
+stops mid-`Creating an optimized production build`, which reads like a hang rather
+than an out-of-memory. If the build host is constrained, switch bundlers:
+
+```bash
+docker build --target runner-base \
+  --build-arg OMNIROUTE_USE_TURBOPACK=0 \
+  -t omniroute:base .
+```
+
+`webpackBuildWorker` is enabled, so `next build` runs a parent **and** a worker
+process and each honours `OMNIROUTE_BUILD_MEMORY_MB` separately. Size the container
+ceiling above roughly twice that value, not once.
+
+Measured on this tree (`--target runner-base`, `OMNIROUTE_BUILD_MEMORY_MB=6144`):
+
+| Bundler   | Container ceiling | Result                        |
+| --------- | ----------------- | ----------------------------- |
+| Turbopack | 8 GiB / 16 GiB    | OOM-killed at both, silently  |
+| webpack   | 8 GiB             | build worker SIGKILLed        |
+| webpack   | 12 GiB            | succeeded, peaked at 11.1 GiB |
+
+### Runtime defaults
+
+Defaults exported by `runner-base`: `PORT=20128`, `HOSTNAME=0.0.0.0`, `OMNIROUTE_MEMORY_MB=1024`, `NODE_OPTIONS=--max-old-space-size=1024`, `DATA_DIR=/app/data`, `OMNIROUTE_MIGRATIONS_DIR=/app/migrations`.
 
 Memory behavior in Docker:
 
-- `NODE_OPTIONS=--max-old-space-size=512` is baked into the image as a fallback.
+- The image sets `OMNIROUTE_MEMORY_MB=1024` and derives `NODE_OPTIONS=--max-old-space-size=1024` from it.
 - The actual server process is started by the standalone launcher, which reads `OMNIROUTE_MEMORY_MB` and appends `--max-old-space-size=<OMNIROUTE_MEMORY_MB>`.
 - Node uses the last repeated `--max-old-space-size` value, so setting `OMNIROUTE_MEMORY_MB` controls the effective Docker heap limit.
-- If `OMNIROUTE_MEMORY_MB` is unset, the launcher uses `512`.
+- Because the image always sets it, the launcher's own RAM-calibrated fallback never applies under Docker. Raise it explicitly (`-e OMNIROUTE_MEMORY_MB=2048`) on a host with headroom.
 
 ## Critical Environment Variables
 
@@ -180,7 +216,7 @@ Beyond the defaults documented in [ENVIRONMENT.md](../reference/ENVIRONMENT.md),
 | `REDIS_PORT`                  | Host-side port for the bundled Redis container                                                      | `6379`                   |
 | `REDIS_BIND_HOST`             | Host interface the bundled Redis port is published on (loopback unless you add AUTH)                | `127.0.0.1`              |
 | `AUTO_UPDATE_HOST_REPO_DIR`   | Host path mounted into `cli` profile at `/workspace/omniroute` for self-update workflows            | `.` (current directory)  |
-| `OMNIROUTE_MEMORY_MB`         | Runtime Node heap ceiling for the Docker standalone server; overrides the image fallback above      | `512`                    |
+| `OMNIROUTE_MEMORY_MB`         | Runtime Node heap ceiling for the Docker standalone server; overrides the image default above       | `1024`                   |
 | `DASHBOARD_PORT` / `API_PORT` | Override exposed ports for dashboard (20128) and API (20129)                                        | `20128` / `20129`        |
 | `OMNIROUTE_BASE_PATH`         | URL subpath when the app is published behind a reverse proxy (e.g. `/omniroute`)                    | _(empty = root)_         |
 | `NEXT_PUBLIC_BASE_URL`        | Public browser origin including the subpath (e.g. `https://host/omniroute`)                         | unset                    |

docs/guides/TROUBLESHOOTING.md

@@ -523,6 +523,12 @@ exhausts its bounds of `10,000` visited nodes or depth `12`.
 Each process uses a process-local guard to reserve limited heavyweight capacity before retaining
 and parsing a large request body. A heavyweight lease remains held for the lifetime of an SSE
 response.
+
+When capacity is busy, a heavyweight request first waits up to
+`OMNIROUTE_CHAT_ADMISSION_QUEUE_MS` (default `5000`, `0` disables the wait) for a slot to free up
+before answering the retryable `503`. The bounded wait exists so agent-style clients
+(OpenCode, Claude Code, Cursor) that fan out heavy sub-requests concurrently serialize the burst
+instead of burning their whole retry budget on immediate rejections and dying mid-task.
 Current heavyweight lease occupancy is not surfaced in the dashboard.
 Settings → Resilience → Request Queue → Concurrent Requests does not control this; that setting
 governs a separate provider request-queue mechanism.
@@ -530,13 +536,18 @@ governs a separate provider request-queue mechanism.
 **Fix:**
 
 1. Retry first. Clients should honor `Retry-After` and use backoff rather than immediately
-   repeating the request.
+   repeating the request. Note that with the default `OMNIROUTE_CHAT_ADMISSION_QUEUE_MS=5000`
+   a heavy request already waited up to 5 seconds before the `503`, so a client retry loop should
+   back off beyond that instead of hammering.
 2. If normal deployment traffic repeatedly exhausts the guard, you can cautiously raise
    `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT` from its default of `1`. Increase it one step at a time,
    restart OmniRoute after each change, and observe memory headroom under representative load.
    Every additional heavyweight request can increase concurrent V8 heap use and container or
    host OOM risk. No value is safe for every deployment; validate the setting against your own
    traffic and memory limits rather than assuming that `2` is universally safe.
+3. Prefer widening the wait (`OMNIROUTE_CHAT_ADMISSION_QUEUE_MS`) over raising the in-flight
+   limit when bursts are short: waiting costs latency, while an extra concurrent heavyweight
+   request costs heap residency for the whole request lifetime.
 
 See the [environment-variable reference](../reference/ENVIRONMENT.md#4-security--authentication)
 for the authoritative admission settings. Loosening the heavyweight classification thresholds

docs/proposals/TELEGRAM-MINIAPP.md

@@ -0,0 +1,143 @@
+---
+title: "Feasibility — Telegram Mini App Integration"
+version: 3.8.49
+lastUpdated: 2026-08-08
+---
+
+# Telegram Mini App Integration — Feasibility Analysis
+
+**Status: FEASIBLE with moderate effort (estimated 2–4 dev-days for a working slice)**
+
+## 1. What "Telegram Mini App" means here
+
+A Telegram Mini App is an iframe-hosted web app opened inside Telegram (via
+inline buttons / bot menu buttons) that talks to a bot backend through the
+[Telegram WebApp SDK](https://core.telegram.org/bots/webapps). For OmniRoute
+the natural shape is:
+
+- **Bot backend** (new): receives Telegram updates (webhook), validates the
+  Mini App's `initData` signature, and proxies chat requests to OmniRoute's
+  existing OpenAI-compatible `/v1/chat/completions` surface.
+- **Mini App frontend** (new): a small chat UI served by OmniRoute (Next.js
+  route or `public/` static bundle), using the Telegram WebApp JS SDK.
+
+## 2. Current state of the codebase (verified against `main` @ 918fba5e3)
+
+### Already present — outbound notifications only
+
+| Piece                        | Location                                    | What it does                                                                                    |
+| ---------------------------- | ------------------------------------------- | ----------------------------------------------------------------------------------------------- |
+| Telegram webhook integration | `src/lib/webhooks/integrations/telegram.ts` | Builds `sendMessage` payloads for **outbound** gateway events (model, provider, latency, error) |
+| Webhook dispatcher           | `src/lib/webhookDispatcher.ts`              | Routes by kind; decrypts `botToken` from DB metadata for telegram                               |
+| Webhook kinds                | `src/lib/db/webhooks.ts`                    | `slack \| telegram \| discord \| custom`                                                        |
+| Webhook CRUD + test          | `src/app/api/webhooks/*`                    | Create/update/test; telegram kind skips `url` (uses bot token + chat_id)                        |
+| Bot token validation         | `telegram.ts:18`                            | `BOT_TOKEN_RE = /^\d+:[A-Za-z0-9_-]{35,}$/`                                                     |
+| Encryption requirement       | `webhooks/route.ts:77`                      | Telegram webhooks require DB encryption enabled (bot tokens stored at rest)                     |
+
+### Missing — what a Mini App needs that does not exist yet
+
+| Gap                              | Detail                                                                                                                                                                                      |
+| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Inbound Bot API listener**     | No `setWebhook` registration, no `/bot<token>/getUpdates` polling, no update handling anywhere. Only the `sendMessage` direction exists.                                                    |
+| **WebApp `initData` validation** | No HMAC-SHA256 check of `initData` against the bot token (`WebAppData` hash validation from the Bot API docs).                                                                              |
+| **Telegram bot library**         | `package.json` has no `telegraf`/`grammy`/`telegram-bot-api` dependency. Would need to add one or hand-roll the (small) HMAC + fetch logic.                                                 |
+| **Mini App hosting surface**     | `public/` exists (static assets) and Next.js routes exist; no `/miniapp` route or static bundle yet.                                                                                        |
+| **Session → API key mapping**    | Mini App users need to authenticate to `/v1/chat/completions`. Two options: per-user generated OmniRoute API keys (via `src/lib/db/apiKeys`) or a bot-side proxy that injects a shared key. |
+
+## 3. Constraints
+
+### 3.1 Architectural
+
+- **No existing inbound-bot layer.** The webhook system is strictly
+  event→outbound. A Mini App needs a _new_ Bot API webhook endpoint
+  (`POST /api/telegram/webhook/<botToken-prefix>` or a dedicated route) plus
+  update dispatch. This is additive — no conflicts with the existing
+  `webhooks/` subsystem, but the two must not share the `botToken` storage
+  semantics blindly (webhooks store bot tokens for _outbound_; the Mini App
+  needs the same token for _inbound_ signature checks — same token, new use).
+- **Public HTTPS required.** Telegram only delivers updates to an HTTPS
+  endpoint with a valid cert. Self-hosted OmniRoute behind Tailscale/ngrok
+  needs a public tunnel or Cloudflare Tunnel for the webhook path
+  (`TELEGRAM_WEBHOOK_URL`-style env). The dashboard can render the current
+  public origin (`OMNIROUTE_PUBLIC_BASE_URL`) but no webhook registration
+  helper exists.
+- **Encryption gate.** `webhooks/route.ts:77` already refuses telegram
+  kinds without DB encryption. The Mini App bot token has the same
+  sensitivity (it _is_ the HMAC secret for initData validation) — same gate
+  applies, which is a _good_ constraint (no plaintext tokens).
+
+### 3.2 Telegram platform
+
+- **initData is the only trust anchor.** Mini App auth = verify
+  `hash` field of `initData` using HMAC-SHA256(key = SHA256(bot_token),
+  data = sorted `key=value` pairs minus `hash`). Must be implemented
+  server-side; never trust the client.
+- **No inbound push to arbitrary users.** Telegram bots cannot initiate
+  conversations. The Mini App works for users who _already_ have the bot —
+  or you add a `/start` command handler + deep-link (`t.me/bot?startapp=`).
+- **Rate limits.** Bot API ~30 msg/s per bot, 20 msg/min per chat group.
+  Chat responses via `sendMessage`/`answerWebAppQuery` are fine at gateway
+  scale, but streaming must be emulated (send progressive edits or chunked
+  messages) — no native SSE into Telegram.
+- **WebApp SDK quirks.** `Telegram.WebApp.ready()` must be called; theme
+  params come from the SDK; the mini app is sandboxed iframe (no
+  `window.open` to external, clipboard limited). For a chat UI this is fine.
+
+### 3.3 Security / policy
+
+- **Per-user key issuance is the clean model.** Rather than exposing the
+  admin's own API keys, mint a scoped OmniRoute API key per Telegram user
+  (`apiKeys` table + `isModelAllowedForKey` policy), or proxy with a single
+  gateway key and map `user_id` → account. Recommendation: per-user keys so
+  existing rate-limit / model-allowlist / policy code applies unchanged.
+- **initData expiry.** `auth_date` in initData must be checked (Telegram
+  recommends < 24h; short TTLs for chat flows).
+- **Secret handling.** Bot token must stay in the encrypted DB / env —
+  mirror the existing `isEncryptionEnabled()` gate.
+
+## 4. Required next steps (implementation plan)
+
+### Phase 0 — Spike (½–1 dev-day)
+
+1. Add `grammy` or `telegraf` (or ~60 lines of hand-rolled HMAC + fetch).
+2. Implement `src/lib/telegram/initData.ts` — `verifyInitData(initData, botToken)`.
+3. Stand up a throwaway `POST /api/telegram/miniapp/webhook` route behind
+   `TELEGRAM_WEBHOOK_SECRET`; register via `setWebhook` once, locally.
+
+### Phase 1 — Minimal chat slice (1–2 dev-days)
+
+1. **Webhook endpoint** `POST /api/telegram/bot/update` (or
+   `/api/telegram/miniapp/update`): parse Update, verify initData, dispatch.
+2. **Command handler**: `/start` → reply with deep link
+   `https://t.me/<bot>?startapp=<userKey>`; `startapp` param carries a
+   one-time token that maps to a generated OmniRoute API key.
+3. **Chat proxy**: map `initData.user.id` → API key → call
+   `handleChat` (same path as `/v1/chat/completions`) → reply via
+   `sendMessage` (non-stream) or chunked edits (fake streaming).
+4. **Mini App page**: `src/app/(dashboard)/miniapp/page.tsx` (or static
+   bundle in `public/miniapp/`) — Telegram WebApp SDK init + minimal chat
+   UI posting to the bot webhook.
+5. **Config**: `TELEGRAM_BOT_TOKEN` env (or reuse webhook metadata),
+   `OMNIROUTE_PUBLIC_BASE_URL` for webhook URL display; doc in
+   `.env.example` + `ENVIRONMENT.md` (env-doc-sync check).
+
+### Phase 2 — Production hardening (1 dev-day)
+
+- Streaming emulation (message edits), error/backpressure mapping to Bot API
+  limits, per-user key revocation (`/logout` command → revoke API key),
+  usage/rate-limit surfacing (reuse `enforceApiKeyPolicy`), webhook
+  registration helper in dashboard settings, i18n for the mini app UI.
+
+## 5. Verdict
+
+**Feasible.** The gateway already exposes the exact API a Mini App chat
+needs (`/v1/chat/completions` with per-key policy), and the outbound
+Telegram webhook shows the team already handles bot tokens safely
+(encryption gate + token format validation). The genuinely new surface is
+small: an inbound update webhook + initData HMAC verification + a thin
+chat proxy + a static Mini App page. No changes to the core SSE/relay
+pipeline are required.
+
+**Primary risks:** (1) public HTTPS requirement for the webhook (tunnel
+needed on self-hosted installs), (2) no native streaming to Telegram
+(UX tradeoff), (3) initData trust must be strictly server-side.

docs/reference/ENVIRONMENT.md

@@ -43,7 +43,6 @@ lastUpdated: 2026-06-28
 - [22. Debugging](#22-debugging)
 - [23. GitHub Integration](#23-github-integration)
 - [24. Skills Sandbox (v3.8.0+)](#24-skills-sandbox-v380)
-- [27. Radar Feed (Self-Hosting)](#27-radar-feed-self-hosting)
 - [Deployment Scenarios](#deployment-scenarios)
 - [Audit: Removed / Dead Variables](#audit-removed--dead-variables)
 
@@ -190,20 +189,19 @@ OmniRoute uses **SQLite** (via `better-sqlite3`) for all persistence. These vari
 | `MAX_BODY_SIZE_BYTES`                   | `10485760` (10 MB)      | `src/shared/middleware/bodySizeGuard.ts`         | Maximum allowed request body size. Rejects payloads exceeding this limit.                                                                                                                                                                                                                                                                                          |
 | `OMNIROUTE_CHAT_LARGE_BODY_BYTES`       | `262144` (256 KB)       | `src/shared/middleware/chatBodyAdmission.ts`     | Actual request bodies at or above this threshold require an atomic process-local heavyweight admission lease before JSON parsing.                                                                                                                                                                                                                                  |
 | `OMNIROUTE_CHAT_HARD_MAX_BODY_BYTES`    | `52428800` (50 MB)      | `src/shared/middleware/chatBodyAdmission.ts`     | Chat-route hard cap enforced against bytes read during bounded ingestion, including requests with missing, invalid, or dishonest `Content-Length`; excess receives `413`.                                                                                                                                                                                          |
-| `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT`    | `1`                     | `src/shared/middleware/chatBodyAdmission.ts`     | Maximum heavyweight chat requests admitted concurrently in one process. When capacity is unavailable, OmniRoute returns retryable `503` with `Retry-After`.                                                                                                                                                                                                        |
+| `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT`    | `1`                     | `src/shared/middleware/chatBodyAdmission.ts`     | Maximum heavyweight chat requests admitted concurrently in one process. When capacity is unavailable, OmniRoute waits up to `OMNIROUTE_CHAT_ADMISSION_QUEUE_MS` for a slot, then returns retryable `503` with `Retry-After`.                                                                                                                                    |
+| `OMNIROUTE_CHAT_ADMISSION_QUEUE_MS`     | `5000`                  | `src/shared/middleware/chatBodyAdmission.ts`     | How long a heavyweight chat request waits for an admission slot before the retryable `503`. A bounded wait serializes agent bursts (OpenCode, Claude Code, Cursor sub-requests) that would otherwise burn their client retry budget on immediate rejections; `0` restores the legacy immediate-reject behaviour.                                                |
 | `OMNIROUTE_CHAT_HEAVY_MESSAGE_COUNT`    | `200`                   | `src/shared/middleware/chatBodyAdmission.ts`     | Message count that classifies a chat request as heavyweight even when its body is below the byte threshold.                                                                                                                                                                                                                                                        |
 | `OMNIROUTE_CHAT_HEAVY_TOOL_COUNT`       | `64`                    | `src/shared/middleware/chatBodyAdmission.ts`     | Tool count that classifies a chat request as heavyweight even when its body is below the byte threshold.                                                                                                                                                                                                                                                           |
 | `OMNIROUTE_CHAT_HEAVY_ESTIMATED_TOKENS` | `32000`                 | `src/shared/middleware/chatBodyAdmission.ts`     | Conservative string-size token estimate that classifies a request as heavyweight; this is an admission-cost proxy, not provider billing tokenization.                                                                                                                                                                                                              |
-| `OMNIROUTE_CHAT_HARD_MAX_MESSAGES`      | `0` (disabled)          | `src/shared/middleware/chatBodyAdmission.ts`     | Optional opt-in chat history cap. Disabled by default: a message count is deployment policy, not a universal property of a request, and capping here rejects conversations with a terminal `413` before the compression pipeline can make them servable. Heap growth is bounded by `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT` and the heap-pressure shed. Set a positive value on memory-constrained deployments that need a hard ceiling; excess then receives structured compact-required `413`. |
+| `OMNIROUTE_CHAT_HARD_MAX_MESSAGES`      | `800`                   | `src/shared/middleware/chatBodyAdmission.ts`     | Hard chat history cap. Requests above it receive structured compact-required `413` before compression, translation, or provider dispatch.                                                                                                                                                                                                                           |
 | `OMNIROUTE_MAX_NONSTREAMING_RESPONSE_BYTES` | `67108864` (64 MB)  | `open-sse/handlers/chatCore/nonStreamingResponseBody.ts` | Hard cap for a non-streaming upstream response buffered fully into memory. Past this the upstream reader is cancelled and the request fails fast instead of growing an unbounded string until the heap is exhausted.                                                                                                                                                 |
-| `OMNIROUTE_FORWARDING_HEADER_BUDGET_BYTES` | `768`                   | `open-sse/handlers/chatCore/responseHeaders.ts` | Max wire bytes forwarded from upstream response headers. When the budget is exceeded, lower-priority headers (e.g., custom `x-codex-*`, `x-oai-request-id`) are dropped to stay within common reverse-proxy header limits. Set higher to forward more upstream metadata at the cost of larger response header size.                                             |
 | `CORS_ORIGIN`                           | _(unset)_               | `src/server/cors/origins.ts`                    | Legacy single-origin CORS allowlist. Prefer `CORS_ALLOWED_ORIGINS` for new deployments. CORS is only for cross-origin browser API clients; authenticated dashboard writes use same-origin requests plus session-bound CSRF protection instead.                                                                                                                     |
 | `CORS_ALLOWED_ORIGINS`                  | _(unset)_               | `src/server/cors/origins.ts`                    | Comma-separated CORS allowlist. No wildcard is sent unless `CORS_ALLOW_ALL=true` is explicitly configured.                                                                                                                                                                                                                                                         |
 | `CORS_ALLOW_ALL`                        | `false`                 | `src/server/cors/origins.ts`                    | Development-only escape hatch to echo any browser `Origin`. Do not enable on shared or production deployments.                                                                                                                                                                                                                                                     |
 | `OUTBOUND_SSRF_GUARD_ENABLED`           | `true`                  | `src/shared/network/outboundUrlGuard.ts`         | Block provider calls targeting private/loopback/link-local IP ranges. Disable only in isolated test envs.                                                                                                                                                                                                                                                          |
 | `OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS` | `false`                 | `src/shared/network/outboundUrlGuard.ts`         | Allow provider URLs pointing to private/local networks (localhost, 192.168.x.x, 10.x.x.x, etc.). **REQUIRED for self-hosted providers** (LM Studio, Ollama, vLLM, Llamafile, Triton, SearXNG). When `false`, the dashboard rejects validation of local URLs.                                                                                                       |
 | `OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS`   | `true`                  | `src/shared/network/outboundUrlGuard.ts`         | Allow adding/validating providers on local/private addresses (127.0.0.1, localhost, LAN, private ranges) — scoped to the provider validation path. **Default `true`** (local-first); set `false` to enforce strict public-only blocking. Cloud-metadata endpoints (169.254.169.254, metadata.google.internal) stay blocked regardless. (#5066)                     |
-| `AUDIO_REMOTE_PROVIDER_NODES`           | `false`                 | `src/app/api/v1/_shared/audioProviderNodes.ts`   | Let the `/v1/audio/*` routes (transcriptions, speech, translations) use an OpenAI-compatible provider node hosted outside localhost. Off by default — routing audio to a remote host changes egress identity and must be an explicit operator decision. Loopback/private nodes (localhost, 127.0.0.1, 172.16-31.x) are always allowed and unaffected. (#3963)      |
 
 ### Hardening Checklist
 
@@ -267,7 +265,6 @@ OmniRoute provides a two-layer defense: request-side injection scanning and resp
 | `OMNIROUTE_PAYLOAD_RULES_PATH`                              | `./config/payloadRules.json` | `open-sse/services/payloadRules.ts` | Path to payload manipulation rules JSON file (per-model/protocol upstream tweaks).                                                                                                                                                                         |
 | `OMNIROUTE_PAYLOAD_RULES_RELOAD_MS`                         | `5000`                       | `open-sse/services/payloadRules.ts` | Reload interval (ms) for hot-reloading the payload rules file. Minimum `1000`.                                                                                                                                                                             |
 | `OMNIROUTE_PREFER_CLAUDE_CODE_FOR_UNPREFIXED_CLAUDE_MODELS` | `false`                      | `open-sse/services/model.ts`        | Opt-in: route bare `claude-*` model IDs from Claude Code clients through the Claude Code OAuth account instead of requiring a provider prefix. Explicit provider prefixes still win. Also configurable via a dashboard toggle on the Claude provider page. |
-| `COMBO_CONCURRENCY_PER_MODEL`                               | `3`                          | `open-sse/services/comboConfig.ts`  | Per-model concurrency cap for round-robin combos (#9100). The round-robin combo semaphore was hard-capped at 3 concurrent requests per model with no override, serializing higher-concurrency traffic behind that cap. Validated to `>= 1`, clamped to `<= 32`.                                          |
 
 ---
 
@@ -381,14 +378,6 @@ Controls how OmniRoute discovers and launches CLI sidecars (Claude Code, Codex,
 | `CLI_QODER_BIN`           | `qoder`     | `src/shared/services/cliRuntime.ts`                 | Custom path to Qoder CLI binary.                                                                                                                                               |
 | `CLI_QWEN_BIN`            | `qwen`      | `src/shared/services/cliRuntime.ts`                 | Custom path to the Qwen Code CLI binary.                                                                                                                                       |
 | `CLI_DEVIN_BIN`           | `devin`     | `open-sse/executors/devin-cli.ts`                   | Custom path to the Devin CLI binary (v3.8.0). Used by the Windsurf/Devin executor.                                                                                             |
-| `CLI_DEVIN_AGENTIC_BIN`   | `devin`     | `open-sse/executors/devin-cli-agentic.ts`           | Agentic bridge-only Devin CLI override. The executor accepts only the local ACP stdio upstream.                                                                               |
-| `DEVIN_AGENTIC_HOME`      | _(required)_ | `open-sse/executors/devin-cli-agentic.ts`           | Absolute isolated home for the agentic Devin subprocess; accepted bridge paths are `/home/bridge` and task-local `.sandbox` paths.                                            |
-| `DEVIN_AGENTIC_ACP_TIMEOUT_MS` | `120000` | `open-sse/executors/devin-cli-agentic.ts`           | Maximum duration of one Devin ACP turn before the bridge terminates the child and returns an explicit timeout.                                                                |
-| `DEVIN_BRIDGE_MODEL` | `devin-cli-agentic/swe-1-7` | `docker/devin-bridge/compose.yml` | Main Claude Code model alias for the isolated bridge. The live harness replaces the example with a model returned by the current Devin account. |
-| `DEVIN_BRIDGE_SONNET_MODEL` | `DEVIN_BRIDGE_MODEL` | `docker/devin-bridge/compose.yml` | Isolated bridge alias used when Claude Code requests its Sonnet default. |
-| `DEVIN_BRIDGE_OPUS_MODEL` | `DEVIN_BRIDGE_MODEL` | `docker/devin-bridge/compose.yml` | Isolated bridge alias used when Claude Code requests its Opus default. |
-| `DEVIN_BRIDGE_HAIKU_MODEL` | `DEVIN_BRIDGE_MODEL` | `docker/devin-bridge/compose.yml` | Isolated bridge alias used when Claude Code requests its Haiku default. |
-| `DEVIN_BRIDGE_SUBAGENT_MODEL` | `DEVIN_BRIDGE_MODEL` | `docker/devin-bridge/compose.yml` | Isolated bridge alias used for Claude Code subagents. |
 | `AUGGIE_BIN`              | `auggie`    | `open-sse/executors/auggie.ts`                      | Absolute-path override for the Augment (Auggie) CLI binary used by the local `auggie` provider. Falls back to `CLI_AUGGIE_BIN`, then a PATH lookup.                            |
 | `CLI_AUGGIE_BIN`          | `auggie`    | `open-sse/executors/auggie.ts`                      | Alias override for the Augment (Auggie) CLI binary path (checked after `AUGGIE_BIN`).                                                                                          |
 | `HERMES_HOME`             | `~/.hermes` | `src/lib/cli-helper/config-generator/hermesHome.ts` | Hermes Agent home directory where OmniRoute reads/writes the Hermes CLI config. Matches the env var the Hermes PowerShell installer sets on Windows (`%LOCALAPPDATA%\hermes`). |
@@ -426,6 +415,7 @@ detection above).
 | `OMNIROUTE_HTTP_TIMEOUT_MS`    | `30000`    | `bin/cli/api.mjs`                       | Per-attempt HTTP timeout (ms) for CLI → server requests.                                                                           |
 | `OMNIROUTE_VERBOSE`            | `0`        | `bin/cli/api.mjs`                       | Set to `1` to print retry/backoff diagnostics to stderr during CLI commands.                                                       |
 | `OMNIROUTE_PLUGIN_PATH`        | _(unset)_  | `bin/cli/plugins.mjs`                   | Custom directory for CLI plugin discovery (`omniroute-cmd-*` packages). Defaults to `~/.omniroute/plugins/` when unset.            |
+| `OMNIROUTE_PLUGINS_ALLOW_EXEC` | `0`        | `src/lib/plugins/pluginWorker.ts`       | Set to `1` to allow plugins to request the `exec` permission (spawn child processes from the worker sandbox). Local operator only. |
 
 ---
 
@@ -462,7 +452,6 @@ detection above).
 | `COMPRESSION_PIPELINE_BREAKER_THRESHOLD`        | `3`                                                 | `open-sse/services/compression/pipelineEngineBreaker.ts`    | Consecutive cross-request failures before an engine's breaker opens.                                                                                                    |
 | `COMPRESSION_PIPELINE_BREAKER_COOLDOWN_MS`      | `30000`                                             | `open-sse/services/compression/pipelineEngineBreaker.ts`    | Milliseconds an opened engine stays skipped before a half-open probe.                                                                                                   |
 | `COMPRESSION_CCR_RETRIEVAL_RAMP_FACTOR`         | `2`                                                 | `open-sse/services/compression/engines/ccr/index.ts`        | T08/H8 CCR retrieval-feedback ramp: each prior retrieval of a stored block raises its effective `minChars` linearly (frequently-retrieved content compresses less; `>=3` retrievals = never compressed). `1` disables the ramp (binary skip at the threshold only). |
-| `COMPRESSION_CCR_DURABLE_STORE`                 | `true`                                              | `open-sse/services/compression/engines/ccr/index.ts`        | CCR durable block store (#9061). Backs the in-memory store with SQLite so a block survives LRU eviction, the TTL, a restart, or a retrieve landing on another instance. Set `false` to keep blocks in memory only. Blocks over 512KB and cloud runtimes stay memory-only regardless. |
 | `COMPRESSION_PREFIX_FREEZE_ENABLED`             | `false`                                             | `open-sse/services/compression/prefixFreeze.ts`             | T08/H5 usage-observed prefix freeze master switch. **Opt-in (default off)** — when on, a system prompt observed `>=` the threshold is treated as a stable cacheable prefix and preserved from compression even for providers the static cache heuristic misses (freeze only *preserves*, never mutates). |
 | `COMPRESSION_PREFIX_FREEZE_THRESHOLD`           | `3`                                                 | `open-sse/services/compression/prefixFreeze.ts`             | Observations of a system prompt before it is treated as a frozen stable prefix.                                                                                         |
 | `OMNIROUTE_BOOTSTRAPPED`                        | `false`                                             | `src/app/(dashboard)/dashboard/page.tsx`                    | Set `true` by bootstrap script after initial setup. Controls setup wizard visibility.                                                                                   |
@@ -518,12 +507,8 @@ Built-in credentials for **localhost development**. For remote deployments, regi
 | `OMNIROUTE_QODER_WORKSPACE`       | Qoder                   | Alias for `QODER_CLI_WORKSPACE`.                                                                                                                                                                                                                |
 | `QODER_CLI_CONFIG_DIR`            | Qoder                   | Override the Qoder CLI config dir (isolated PAT session, avoids clobbering a browser login).                                                                                                                                                     |
 | `BLACKBOX_WEB_VALIDATED_TOKEN`    | Blackbox Web            | Frontend `tk` token to send as `validated` on `/api/chat`. Required when Blackbox enforces token matching; otherwise OmniRoute falls back to a random UUID. See issue #2252.                                                                    |
-| `VISION_BRIDGE_BASE_URL`          | Vision Bridge guardrail | OpenAI-compatible base URL for non-Anthropic vision-bridge calls. Defaults to the legacy OpenAI URL env or api.openai.com. Point at OmniRoute's `/v1` self-loop or any OpenAI-compat endpoint (Gemini OpenAI-compat, OpenRouter). Issue #2232. When the URL is OmniRoute's own `/v1`, the describe sub-request sends `x-omniroute-admission-bypass: internal` and authenticates with the resolved self-loop credential (`sk_omniroute` sentinel in local mode, or `OMNIROUTE_API_KEY` / `ROUTER_API_KEY` — #1350) so `REQUIRE_API_KEY=true` deployments work. |
+| `VISION_BRIDGE_BASE_URL`          | Vision Bridge guardrail | OpenAI-compatible base URL for non-Anthropic vision-bridge calls. Defaults to the legacy OpenAI URL env or api.openai.com. Point at OmniRoute's `/v1` self-loop or any OpenAI-compat endpoint (Gemini OpenAI-compat, OpenRouter). Issue #2232.  |
 | `VISION_BRIDGE_API_KEY`           | Vision Bridge guardrail | API key for the URL above. Overrides per-provider OpenAI / Google env vars for non-Anthropic vision-bridge calls. Anthropic models keep their dedicated Anthropic key path. Issue #2232.                                                        |
-| `RAYCAST_BEARER_TOKEN`            | Raycast Pro              | Optional manual override for the Raycast access token (normally captured via macOS Auto-Import). No OAuth client_id/secret — reverse-engineered, local/personal use only.                        |
-| `RAYCAST_DEVICE_ID`               | Raycast Pro              | Optional manual override for the Raycast device ID used to sign requests.                                                                                                                        |
-| `RAYCAST_AID`                     | Raycast Pro              | Optional manual override for the Raycast account/app ID; falls back to the device ID when unset.                                                                                                 |
-| `RAYCAST_SIG_SECRET`              | Raycast Pro              | Optional override for the request-signing HMAC secret. Defaults to a community-extracted value in `open-sse/services/raycast.ts`.                                                                |
 
 > [!WARNING]
 >
@@ -671,13 +656,12 @@ REQUEST_TIMEOUT_MS (global override)
 | `API_BRIDGE_SERVER_SOCKET_TIMEOUT_MS`     | `0`                  | Raw socket timeout (0 = disabled).                                                                                                                              |
 | `SHUTDOWN_TIMEOUT_MS`                     | `30000`              | Grace period on SIGTERM/SIGINT before force-exit.                                                                                                               |
 | `OMNIROUTE_DEFAULT_FETCH_TIMEOUT_MS`      | `120000`             | Fallback used by `src/shared/utils/fetchTimeout.ts` when `FETCH_TIMEOUT_MS` is unset.                                                                           |
-| `OMNIROUTE_RELAY_FETCH_TIMEOUT_MS`        | `25000`               | Relay-specific fetch timeout in `open-sse/utils/proxyFetch.ts` (#9158). A hung relay must fail before the client/agent timeout (~30s) so callers see a relay-specific failure instead of a generic upstream timeout. Capped at `29000` so it always fires first. |
-| `OMNIROUTE_RETRY_BACKOFF_MS`              | `10`                  | Shared retry backoff for the direct/relay/proxy retry-once paths in `open-sse/utils/proxyFetch.ts` (#9158). `0` = retry immediately.                            |
 | `OMNIROUTE_CHATGPT_TLS_TIMEOUT_MS`        | `60000`              | Wire-level timeout for the bogdanfinn/tls-client koffi binding (`chatgptTlsClient.ts`).                                                                         |
 | `OMNIROUTE_CHATGPT_TLS_GRACE_MS`          | `10000`              | JS-side grace added on top of the wire timeout when the native binding is wedged.                                                                               |
-| `OMNIROUTE_CHATGPT_STREAM_FIRST_BYTE_TIMEOUT_MS` | `30000` (30s) | Max wait for the first streamed byte from the ChatGPT TLS sidecar (`chatgptTlsClient.ts`) before aborting a dead stream. Raise if upstream cold-starts exceed the window. |
-| `OMNIROUTE_CLAUDE_TLS_TIMEOUT_MS`         | `60000`              | Wire-level timeout for the bogdanfinn/tls-client koffi binding (`claudeTlsClient.ts`).                                                                          |
-| `OMNIROUTE_CLAUDE_TLS_GRACE_MS`           | `10000`              | JS-side grace added on top of the wire timeout when the native binding is wedged.                                                                               |
+| `OMNIROUTE_CHATGPT_STREAM_FIRST_BYTE_TIMEOUT_MS` | `30000` | Max wait for the first streamed byte from the ChatGPT TLS sidecar. |
+| `OMNIROUTE_CLAUDE_TLS_TIMEOUT_MS`            | `60000`  | Wire-level timeout for the bogdanfinn/tls-client koffi binding. |
+| `OMNIROUTE_CLAUDE_TLS_GRACE_MS`              | `10000`  | JS-side grace added on top of the wire timeout when the native binding is wedged. |
+| `OMNIROUTE_RUNNOW_TIMEOUT_MS`                | `30000`  | Timeout for the `/api/jobs/:id/run-now` endpoint. Bounds how long a run-now call waits for an in-flight job to finish before starting the queued run. See `src/app/api/jobs/[id]/run-now/route.ts`. |
 | `OMNIROUTE_PPLX_TLS_TIMEOUT_MS`           | `30000`              | Wire-level timeout for the bogdanfinn/tls-client koffi binding (`perplexityTlsClient.ts`).                                                                      |
 | `OMNIROUTE_PPLX_TLS_GRACE_MS`             | `10000`              | JS-side grace added on top of the wire timeout when the native binding is wedged.                                                                               |
 | `OMNIROUTE_GROK_TLS_TIMEOUT_MS`           | `60000`              | Wire-level timeout for the bogdanfinn/tls-client koffi binding (`grokTlsClient.ts`).                                                                            |
@@ -686,7 +670,6 @@ REQUEST_TIMEOUT_MS (global override)
 | `OMNIROUTE_NOTION_TLS_GRACE_MS`           | `10000`              | JS-side grace added on top of the wire timeout when the native binding is wedged.                                                                               |
 | `OMNIROUTE_BROWSER_POOL`                  | `on`                 | Shared Playwright browser pool for browser-backed web-cookie chat (`browserPool.ts`); set `off` to disable.                                                     |
 | `WEB_COOKIE_USE_BROWSER`                  | `0`                  | Opt a web-cookie chat request into the browser-backed path (`browserBackedChat.ts`); `1` to enable.                                                             |
-| `OMNIROUTE_LOGIN_BROWSER_PATH`            | _(auto-detected)_    | Path to a system Chrome/Edge executable for the Adobe Firefly interactive browser sign-in (`adobeFireflyBrowserLogin.ts`); overrides per-OS auto-detection.     |
 
 Combo target attempts inherit the resolved upstream request timeout (`FETCH_TIMEOUT_MS`, or
 `REQUEST_TIMEOUT_MS` when it supplies the fetch default). Set `targetTimeoutMs` in a combo,
@@ -734,16 +717,16 @@ The logging system writes to both stdout and rotated log files. All configuratio
 | `CALL_LOG_RETENTION_DAYS`                 | `7`                        | Days to keep request/call log entries in the database.                            |
 | `CALL_LOG_MAX_ENTRIES`                    | `10000`                    | Max call log entries in the in-memory buffer.                                     |
 | `CALL_LOGS_TABLE_MAX_ROWS`                | `100000`                   | Max rows in the `call_logs` SQLite table before pruning.                          |
-| `ENABLE_REQUEST_LOGS`                     | _(unset)_                  | Force detailed request logging on or off, overriding the dashboard setting.       |
 | `MAX_PENDING_REQUEST_AGE_MS`              | `3600000` (1 hour)         | Max age for orphaned active request log entries before in-memory cleanup.         |
 | `CALL_LOG_PIPELINE_CAPTURE_STREAM_CHUNKS` | `true`                     | Store stream chunks in pipeline artifacts when `call_log_pipeline_enabled=true`.  |
 | `CALL_LOG_PIPELINE_MAX_SIZE_KB`           | `512`                      | Max pipeline call log artifact size in KB when `call_log_pipeline_enabled=true`.  |
 | `PROXY_LOGS_TABLE_MAX_ROWS`               | `100000`                   | Max rows in the `proxy_logs` SQLite table before pruning.                         |
 | `APP_LOG_ROTATION_CHECK_INTERVAL_MS`      | `60000` (1 min)            | How often `src/lib/logRotation.ts` re-checks the active log file size.            |
 | `CHAT_LOG_TEXT_LIMIT`                     | `65536`                    | Max string length retained in chat log artifacts (default 64 KB).                 |
-| `CHAT_LOG_ARRAY_TAIL_ITEMS`               | `24`                       | Number of array items retained from the tail when truncating chat log payloads.   |
+| `CHAT_LOG_ARRAY_TAIL_ITEMS`               | `128`                      | Number of array items retained from the tail when truncating chat log payloads.   |
 | `CHAT_LOG_MAX_DEPTH`                      | `6`                        | Max nesting depth before chat log payloads are truncated.                         |
 | `CHAT_LOG_MAX_OBJECT_KEYS`                | `80`                       | Max object keys retained in chat log payloads (0 = unlimited).                    |
+| `CHAT_LOG_MAX_BODY_KB`                    | `1024`                     | Max request/response body size before `truncateForLog()` summarizes it, in KB.    |
 | `CHAT_DEBUG_FILE`                         | `false`                    | When true, `serializeArtifactForStorage` skips size-based truncation. Debug only. |
 
 ---
@@ -780,13 +763,9 @@ Embedding layer, vector store and reranking knobs for the persistent memory subs
 | `MEMORY_TRANSFORMERS_MODEL`     | `Xenova/all-MiniLM-L6-v2`  | HF repo id for the opt-in `@huggingface/transformers` local MiniLM pipeline (~23 MB int8, ~400 MB RAM).    |
 | `MEMORY_STATIC_MODEL`           | `minishlab/potion-base-8M` | HF repo id for the static potion/Model2Vec lookup-table embedder. Downloaded lazily into the cache dir.    |
 | `MEMORY_STATIC_CACHE_DIR`       | `<DATA_DIR>/embeddings`    | Directory used to cache the static potion model files. Defaults under `DATA_DIR` when unset.               |
-| `HF_HUB_ENDPOINT`               | `https://huggingface.co`   | Override Hugging Face Hub base URL used by `staticPotion.ts` (e.g. mirror endpoint for air-gapped setups). |
 | `MEMORY_VEC_TOP_K`              | `20`                       | Default top-K used by the `sqlite-vec` brute-force vector search inside `src/lib/memory/vectorStore.ts`.   |
 | `MEMORY_RRF_K`                  | `60`                       | Reciprocal Rank Fusion constant `k` for hybrid FTS5 + vector retrieval (sqlite-vec recipe).                |
-| `NOTION_API_KEY`                | _(unset)_                  | API key for Notion backend (used by `genericBackend.ts` known backend preset).                                |
-| `NOTION_API_URL`                | `https://api.notion.com/v1`| Base URL for Notion API (can override for self-hosted Notion alternatives).                                   |
-| `OBSIDIAN_API_KEY`              | _(unset)_                  | API key for Obsidian Vault backend (used by `genericBackend.ts` known backend preset).                        |
-| `OBSIDIAN_API_URL`              | `http://localhost:27123`   | Base URL for Obsidian Vault API (can override for remote vault).                                              |
+| `HF_HUB_ENDPOINT`               | `https://huggingface.co`   | Override Hugging Face Hub base URL used by `staticPotion.ts` (e.g. mirror endpoint for air-gapped setups). |
 | `MEMORY_TYPED_DECAY_ENABLED`    | `false`                    | TV6 typed memory decay master switch. **Opt-in (default off)** — the sweep **deletes** decayed memories. With it off, `access_count`/`last_accessed_at` are pure telemetry and nothing is ever deleted. |
 | `MEMORY_TYPED_DECAY_EPISODIC_DAYS` | `30`                    | TTL (days) after which an unused `episodic` memory decays. `0` makes episodic immune too. Durable types (`factual`/`procedural`/`semantic`) are always immune. The decay clock re-bases on `last_accessed_at`. |
 | `MEMORY_TYPED_DECAY_ACCESS_IMMUNITY` | `3`                   | A memory injected `>=` this many times becomes immune to decay regardless of type. `0` disables access immunity. |
@@ -853,7 +832,6 @@ Reverse-engineered session bridge for hyperagent.com (`src/shared/constants/prov
 
 | Variable                            | Default       | Source File                        | Description                                                                                                                                                                                                                                                                                            |
 | ----------------------------------- | ------------- | ---------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `MODELS_DEV_SYNC_ENABLED`           | `false`       | `src/lib/modelsDevSync.ts`         | Opt-in switch for the models.dev capability sync. Set to anything non-empty it wins over the `modelsDevSyncEnabled` setting (Dashboard > Settings > AI) in either direction, so a deployment can pin the sync on or off without depending on database state surviving a rebuild; unset, it defers to that setting. On for `1`, `true`, `yes` or `on` in any casing; any other value is off.          |
 | `MODELS_DEV_SYNC_INTERVAL`          | `86400` (24h) | `src/lib/modelsDevSync.ts`         | Development-time model catalog sync interval in seconds.                                                                                                                                                                                                                                              |
 | `CONTEXT_WINDOW_RECONCILE_INTERVAL` | `86400` (24h) | `src/lib/contextWindowResolver.ts` | Interval (seconds) for the self-correcting context-window reconciler (5004): pins provider-declared windows from `/models` discovery as `auto:discovery` overrides when they diverge from the catalog. Set to `0` to disable. Reuses already-synced data (no new fetch); never overwrites `manual` overrides. |
 
@@ -869,7 +847,6 @@ Reverse-engineered session bridge for hyperagent.com (`src/shared/constants/prov
 | `NANOBANANA_POLL_INTERVAL_MS`                  | `2500`                                 | `open-sse/handlers/imageGeneration.ts`                                             | NanoBanana job polling frequency.                                                                           |
 | `DESIGNER_WEB_POLL_TIMEOUT_MS`                 | `60000`                                | `open-sse/handlers/imageGeneration/providers/designerWeb.ts`                       | Max wait for microsoft-designer-web image generation jobs.                                                  |
 | `DESIGNER_WEB_POLL_INTERVAL_MS`                | `2000`                                 | `open-sse/handlers/imageGeneration/providers/designerWeb.ts`                       | microsoft-designer-web job polling frequency.                                                               |
-| `ADOBE_FIREFLY_SUBMIT_BASE_DELAY_MS`           | `8000`                                 | `open-sse/services/adobeFireflyUpscale.ts`                                         | Base delay for the Adobe Firefly upscale submit-retry exponential backoff.                                  |
 | `AWS_REGION`                                   | _(unset)_                              | `src/lib/providers/validation.ts`, `open-sse/handlers/audioSpeech.ts`              | Region used to construct AWS Bedrock endpoints (Kiro, audio).                                               |
 | `AWS_DEFAULT_REGION`                           | _(unset)_                              | `src/lib/providers/validation.ts`, `open-sse/handlers/audioSpeech.ts`              | Fallback when `AWS_REGION` is not set.                                                                      |
 | `CLOUDFLARE_ACCOUNT_ID`                        | _(unset)_                              | `open-sse/executors/cloudflare-ai.ts`                                              | Account ID for Cloudflare Workers AI.                                                                       |
@@ -891,10 +868,6 @@ Reverse-engineered session bridge for hyperagent.com (`src/shared/constants/prov
 | `CLIPROXYAPI_PORT`                             | `5544`                                 | `open-sse/executors/cliproxyapi.ts`                                                | CLIProxyAPI bridge port.                                                                                    |
 | `CLIPROXYAPI_CONFIG_DIR`                       | `~/.cli-proxy-api`                     | `src/lib/versionManager/processManager.ts`                                         | CLIProxyAPI config directory.                                                                               |
 | `MUX_SERVICE_PORT`                             | `8322`                                 | `src/lib/services/bootstrap.ts`                                                    | Override the port where the embedded Mux (coder/mux) agent-orchestration daemon listens (always 127.0.0.1). |
-| `DARIO_HOST`                                   | `127.0.0.1`                            | `open-sse/executors/dario.ts`                                                      | Dario embedded-service bind/connect host (loopback only by default).                                        |
-| `DARIO_PORT`                                   | `3456`                                 | `open-sse/executors/dario.ts`                                                      | Dario embedded-service port.                                                                                |
-| `DARIO_HOST`                                   | `127.0.0.1`                            | `open-sse/executors/dario.ts`                                                      | Dario embedded-service bind/connect host (loopback only by default).                                        |
-| `DARIO_PORT`                                   | `3456`                                 | `open-sse/executors/dario.ts`                                                      | Dario embedded-service port.                                                                                |
 | `LOCAL_HOSTNAMES`                              | _(empty)_                              | `open-sse/config/providerRegistry.ts`                                              | Comma-separated additional hostnames treated as "local" (Docker service names, etc.).                       |
 
 `ENABLE_CC_COMPATIBLE_PROVIDER` is only for third-party relays that accept Claude Code clients
@@ -1175,13 +1148,6 @@ Provider quota endpoints, network tunnels (Tailscale, Ngrok, MITM debug proxy),
 | `OMNIROUTE_LOCAL_ENDPOINTS_TOKEN`           | _(unset)_                                                                   | `src/lib/security/localEndpoints.ts`                                      | Bearer token for `/api/local/*` callers that aren't on loopback (e.g. the desktop app). When set, requests from non-loopback IPs must carry `Authorization: Bearer <token>`. Required when `OMNIROUTE_LOCAL_ENDPOINTS_ENABLED=1` in non-loopback deployments.                                                                                                         |
 | `OMNIROUTE_REDIS_CONTAINER_NAME`            | `omniroute-redis`                                                           | `bin/cli/commands/redis.mjs`                                              | Container name for the 1-click Redis launcher (`omniroute redis up`). Used by both the CLI and the `RedisLauncherPanel` GUI.                                                                                                                                                                                                                                          |
 | `OMNIROUTE_REDIS_HOST_PORT`                 | `6379`                                                                      | `bin/cli/commands/redis.mjs`                                              | Host port for the 1-click Redis launcher. Bump if the host already binds 6379. The container's internal port stays 6379.                                                                                                                                                                                                                                              |
-| `OMNIROUTE_REDIS_BIND_HOST`                 | `127.0.0.1`                                                                 | `bin/cli/commands/redis.mjs`                                              | Host interface the 1-click Redis launcher publishes on. The launcher starts Redis WITHOUT a password, so binding `0.0.0.0` hands every host on your LAN an unauthenticated Redis — only widen this if you also set a password on the instance yourself.                                                                                                                |
-| `REDIS_BIND_HOST`                           | `127.0.0.1`                                                                 | `docker-compose.yml`                                                      | Host interface docker-compose publishes the Redis sidecar on (#9286). The compose Redis runs without `requirepass`; app containers reach it over the compose network (`redis:6379`) — the published port exists only for host-side tooling. `0.0.0.0` exposes an unauthenticated Redis to the whole LAN.                                                              |
-| `REDIS_PORT`                                | `6379`                                                                      | `docker-compose.yml`                                                      | Host port for the compose Redis sidecar.                                                                                                                                                                                                                                                                                                                              |
-| `OMNIROUTE_INTERNAL_SERVICE_TOKEN`          | _(unset — mechanism disabled)_                                              | `src/lib/api/internalServiceAuth.ts`                                      | Shared secret for identity-preserving internal REST hops (#9260): OmniRoute components calling other local OmniRoute routes send it as `x-omniroute-internal-service-token` so the original caller identity is preserved. Compared with `timingSafeEqual`.                                                                                                              |
-| `OMNIROUTE_INTERNAL_SERVICE_TOKEN_FILE`     | _(unset)_                                                                   | `src/lib/api/internalServiceAuth.ts`                                      | Secret-file variant of the internal service token: path to a file whose trimmed content is the token. Only consulted when the inline var is unset.                                                                                                                                                                                                                    |
-| `OPENROUTER_PROVIDER_STATS_ENABLED`         | `true`                                                                      | `src/lib/catalog/openrouterProviderStats.ts`                              | Enrich the dashboard providers list with OpenRouter weekly ranking stats (#9324). On by default; set `false` to skip the background fetch entirely (non-blocking, never fatal).                                                                                                                                                                                       |
-| `OPENROUTER_PROVIDER_STATS_TTL_MS`          | `86400000` (24h)                                                            | `src/lib/catalog/openrouterProviderStats.ts`                              | Cache TTL for the OpenRouter provider-stats snapshot, in milliseconds.                                                                                                                                                                                                                                                                                                |
 | `OMNIROUTE_REDIS_IMAGE`                     | `redis:7-alpine`                                                            | `bin/cli/commands/redis.mjs`                                              | Redis image used by the 1-click Redis launcher. Override to `redis:8-alpine` or a private registry mirror as needed.                                                                                                                                                                                                                                                  |
 | `QDRANT_HOST`                               | `qdrant`                                                                    | _(opt-in cluster profile)_                                                | Hostname of the Qdrant sidecar when `--profile memory` is active. Default points to the in-network qdrant service name; override for an external deployment. Only consumed when `qdrantEnabled` is `true` in code (`src/lib/memory/vectorStore.ts:108`).                                                                                                              |
 | `QDRANT_PORT`                               | `6333`                                                                      | _(opt-in cluster profile)_                                                | REST port of the Qdrant sidecar.                                                                                                                                                                                                                                                                                                                                      |
@@ -1207,17 +1173,6 @@ Provider quota endpoints, network tunnels (Tailscale, Ngrok, MITM debug proxy),
 | `OMNIROUTE_ROTATE_400_THRESHOLD`            | `1`                                                                         | `open-sse/services/rotationConfig.ts`                                     | Number of `400` errors within `OMNIROUTE_ROTATE_400_WINDOW_SECONDS` required before the account is rotated (only consulted when `OMNIROUTE_ROTATE_ON_400=true`).                                                                                                                                                                                                     |
 | `OMNIROUTE_ROTATE_400_WINDOW_SECONDS`       | `120`                                                                       | `open-sse/services/rotationConfig.ts`                                     | Sliding window (seconds) over which `400` errors are counted toward `OMNIROUTE_ROTATE_400_THRESHOLD`.                                                                                                                                                                                                                                                                 |
 
-### Claude Warmup Scheduler
-
-Cron-driven warmup for opted-in Anthropic OAuth connections, so the 5-hour rate-limit window is opened by a trivial scheduled request instead of by the first real one (#8848). The scheduler is off unless `OMNIROUTE_WARMUP_ENABLED` is truthy **and** the connection is flagged in `settings.claudeWarmup.connections`; an empty connection list means nothing is warmed even with the env var on.
-
-| Variable                      | Default                                | Source File                  | Description                                                                                                                                                            |
-| ----------------------------- | -------------------------------------- | ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `OMNIROUTE_WARMUP_ENABLED`    | _(unset → off)_                        | `src/lib/warmupScheduler.ts` | Master switch for the warmup scheduler. Accepts `1`/`true`/`yes`/`on` (case-insensitive, trimmed). Any other value, or unset, leaves the scheduler off.                 |
-| `OMNIROUTE_WARMUP_CRON`       | `0 7 * * *`                            | `src/lib/warmupScheduler.ts` | Five-field cron expression for the warmup tick, evaluated in `America/Los_Angeles` (Anthropic's reset timezone) regardless of the host clock.                           |
-| `OMNIROUTE_WARMUP_CONCURRENCY` | `3`                                    | `src/lib/warmupScheduler.ts` | How many connections are warmed in parallel per tick. Clamped to `1`-`10`; a non-numeric value falls back to `3`.                                                       |
-| `OMNIROUTE_WARMUP_MODEL`      | `claude-3-5-haiku-20241022`            | `src/lib/warmupScheduler.ts` | Model used for the warmup request. Override only if the default is unavailable on your plan; pick the cheapest model that still opens the window.                       |
-
 ### Browser-Login VNC Sessions & Data-Dir Alias
 
 Containerized Chromium+VNC used for interactive browser-login credential capture (`/api/vnc-session`), plus a legacy `DATA_DIR` alias. All optional — the VNC defaults target the bundled `omniroute-vnc-chromium:local` image and are only overridden for a custom container image, ports, or lifecycle tuning.
@@ -1282,25 +1237,6 @@ that should be able to run the docs translator.
 
 ---
 
-## 27. Radar Feed (Self-Hosting)
-
-Optional add-on gated by the RADAR_ENABLED feature flag (default off — a feature
-flag toggled via Settings/DB, not an env var; see
-[docs/frameworks/RADAR.md](../frameworks/RADAR.md#flag-radar_enabled-default-off)).
-The four variables below are optional overrides used only to point the client at a
-self-hosted or forked feed / supporter-key flow instead of the default OmniRoute
-Radar service. See [docs/frameworks/RADAR.md](../frameworks/RADAR.md) for the full
-module doc.
-
-| Variable                       | Default                                          | Source File                   | Description                                                                                     |
-| -------------------------------- | --------------------------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------ |
-| `RADAR_FEED_URL`               | `https://radar.omniroute.online`                 | `src/lib/radar/sync.ts`       | Base URL of the Radar feed service. Override to point at a self-hosted or forked feed.          |
-| `RADAR_FEED_PUBKEY`            | _(pinned default key)_                           | `src/lib/radar/pinnedKeys.ts` | Ed25519 public key (base64-DER SPKI or PEM) used to verify feed signatures from a custom feed.   |
-| `RADAR_CONTRIBUTOR_CLAIM_URL`  | `https://radar.omniroute.online/auth/github`     | `src/lib/radar/links.ts`      | URL the "I'm a contributor" dashboard button opens (GitHub OAuth supporter-key claim flow).      |
-| `RADAR_SUPPORTER_PLANS_URL`    | `https://radar.omniroute.online/planos`          | `src/lib/radar/links.ts`      | URL the "Support the project" dashboard button opens (payment/plans page).                       |
-
----
-
 ## Audit: Removed / Dead Variables
 
 The following variables appeared in previous versions of `.env.example` but have **no runtime references** in the current codebase. They have been removed:
@@ -1368,24 +1304,13 @@ Used by `src/lib/vncSession/manifest.ts` to configure Docker-based headless Chro
 | `OMNIROUTE_VNC_HARVEST_MS`            | `20000`                       | `src/lib/vncSession/manifest.ts`  | Harvest/cleanup timeout (ms).                                                  |
 | `VIBEPROXY_DATA_DIR`                  | _(unset)_                     | `open-sse/services/notionThreadSessions.ts` | Directory for Notion thread session persistence.                               |
 
-### Internal service auth
+### Telegram Mini App
 
-| Variable | Default | Description |
-| --- | --- | --- |
-| `OMNIROUTE_INTERNAL_SERVICE_TOKEN` | – | Inline token for management-plane service-to-service authentication. |
-| `OMNIROUTE_INTERNAL_SERVICE_TOKEN_FILE` | – | Path to a file containing the internal service token (preferred in containers; overrides the inline variable). |
+Used by `src/lib/telegram/*` and `src/app/api/telegram/update/route.ts` for the inbound bot webhook and Mini App chat proxy. All optional — the endpoint returns 503 when `TELEGRAM_BOT_TOKEN` is unset.
 
-### OpenRouter provider stats
-
-| Variable | Default | Description |
-| --- | --- | --- |
-| `OPENROUTER_PROVIDER_STATS_ENABLED` | `true` | Set to `false` to skip fetching OpenRouter per-provider stats for catalog enrichment. |
-| `OPENROUTER_PROVIDER_STATS_TTL_MS` | `3600000` | Cache TTL (ms) for the fetched OpenRouter provider stats. |
-
-### Embedded Redis binding
-
-| Variable | Default | Description |
-| --- | --- | --- |
-| `REDIS_BIND_HOST` | `127.0.0.1` | Bind address for the embedded Redis service. |
-| `REDIS_PORT` | `6379` | Port for the embedded Redis service. |
-| `OMNIROUTE_REDIS_BIND_HOST` | – | OmniRoute-scoped override for the embedded Redis bind address. |
+| Variable                       | Default                    | Source File                              | Description                                                                             |
+| ------------------------------ | -------------------------- | ---------------------------------------- | --------------------------------------------------------------------------------------- |
+| `TELEGRAM_BOT_TOKEN`           | _(unset)_                  | `src/lib/telegram/config.ts`             | Bot token from @BotFather (`<numeric_id>:<secret>`). Enables the inbound webhook; doubles as the HMAC secret for Mini App `initData` verification. |
+| `TELEGRAM_DEFAULT_MODEL`       | `auto/chat`                | `src/lib/telegram/chatProxy.ts`          | Model used for Telegram chat replies.                                                    |
+| `TELEGRAM_BOT_API_BASE`        | `https://api.telegram.org` | `src/lib/telegram/config.ts`             | Bot API base URL override (proxies / self-hosted Bot API servers).                       |
+| `TELEGRAM_WEBHOOK_TIMEOUT_MS`  | `60000`                    | `src/lib/telegram/config.ts`             | Timeout (ms) for outbound Bot API calls (`sendMessage`/`setWebhook`).                    |

docs/video-preset-generation.md

@@ -0,0 +1,113 @@
+# Video Generation Through Preset Jobs
+
+Custom provider nodes whose `/videos` surface is an **async submit → poll → fetch-result API** (instead of a synchronous generation endpoint) can be wired into the `/api/v1/videos/generations` route without any new provider code. The model row carries a `generationConfig.preset`, and the dispatcher routes the request through a single job executor that is configured entirely by declarative preset data.
+
+## How dispatch works
+
+1. The route parses `model` as `provider/model` and resolves the provider node's credentials (`POST /api/v1/videos/generations`).
+2. `handleVideoGeneration` (in `open-sse/handlers/videoGeneration.ts`) checks whether the provider is a **custom provider node** (no entry in the static video registry).
+3. For custom nodes it reads the custom model row via `getCustomModelVideoPreset(provider, model)`:
+   - The model row has `generationConfig.preset` set (e.g. `"agnes-video-job"`) → dispatch through the **job executor** (`open-sse/handlers/videoGeneration/job.ts`).
+   - The preset name does not match any known preset → **502** `Unknown video job preset: <preset>` (server-side misconfiguration).
+   - No preset configured → fall back to the generic OpenAI-compatible sync handler, mirroring the images route.
+4. The job executor runs the preset pipeline: **submit** the job, **poll** for terminal status, **read** the finished video URL, and return the standard OpenAI-compatible response shape.
+
+The executor is one handler family; every provider-specific detail (paths, auth, body shape, status/result fields, poll cadence) is data in the preset definition.
+
+## Response contract
+
+Both the sync and job paths return the same shape:
+
+```json
+{
+  "created": 1234567890,
+  "data": [{ "url": "https://…", "format": "mp4" }]
+}
+```
+
+This is the shape the media-generation consumer reads (`data.data[0].url`), so preset-job providers are drop-in replacements for sync providers.
+
+## Presets
+
+Presets live in `open-sse/handlers/videoGeneration/job.ts` (`VIDEO_JOB_PRESETS`). Each preset declares:
+
+| Field                                        | Meaning                                                                                                                                                                                                |
+| -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `authHeaderName` / `authScheme`              | `x-api-key` with `raw` value (Agnes, muapi) or `Authorization` with `Bearer` prefix (Sora). Missing credentials → request goes out without an auth header.                                             |
+| `baseUrlFallback`                            | Default base URL. Overridden by the provider connection's `providerSpecificData.baseUrl` (or top-level `baseUrl`), which wins when set.                                                                |
+| `submit.path` / `submit.buildBody`           | Where and how the job is submitted. `{model}` in the path is substituted with the encoded model id; the body is built from `model`/`prompt`/`duration` plus pass-through of every other request field. |
+| `taskIdPath`                                 | Dot path into the submit response identifying the job (e.g. `task_id`, `request_id`, `id`). Missing job id → **502**.                                                                                  |
+| `poll.pathTemplate`                          | Poll URL template; `{taskId}` is substituted.                                                                                                                                                          |
+| `statusPath` / `statusDone` / `statusFailed` | Where the job status lives and which values are terminal.                                                                                                                                              |
+| `resultPath`                                 | Dot path into the poll response holding the finished video URL: a string, a string array, or an array of `{ url }` objects are all accepted. Completed job with no readable URL → **502**.             |
+| `maxPolls` / `pollIntervalMs`                | Poll budget (default 60 polls × 2000 ms). Exhausted → **504** `Video job timed out`.                                                                                                                   |
+
+### `agnes-video-job` — Agnes Video V2.0
+
+- Auth: `x-api-key: <key>` (raw).
+- Base URL fallback: `https://apihub.agnes-ai.com`.
+- Submit: `POST /v1/videos` with `{ model, prompt, ...extras }` — image, mode, `num_frames`, `frame_rate` and other provider knobs pass through untouched.
+- Job id: `task_id` from the submit response.
+- Poll: `GET /v1/videos/{taskId}`; status at `status` (`completed` / `failed`).
+- Result: `metadata.url` — the completed video URL is returned as JSON metadata, not a binary body.
+
+### `muapi-video-job` — muapi.ai
+
+- Auth: `x-api-key: <key>` (raw).
+- Base URL fallback: `https://api.muapi.ai`.
+- Submit: `POST /api/v1/{model}` with `{ prompt, duration?, ...extras }`.
+- Job id: `request_id` from the submit response.
+- Poll: `GET /api/v1/predictions/{taskId}/result`; status at `status` (`completed` / `failed`).
+- Result: `outputs` — an array of video URLs.
+
+### `sora-job` — OpenAI Sora
+
+- Auth: `Authorization: Bearer <key>`.
+- Base URL fallback: `https://api.openai.com`.
+- Submit: `POST /v1/videos` with `{ model, prompt, seconds?, ...extras }`. `seconds` is a **string** enum (`"4" | "8" | "12"`) in the Sora API, so a numeric `duration` is stringified; size mapping is intentionally not forced.
+- Job id: `id` from the submit response.
+- Poll: `GET /v1/videos/{taskId}`; status at `status` (`completed` / `failed`).
+- Result: `data` — an array whose entries are either a URL string or `{ url: "…" }`.
+
+## Setup
+
+1. **Register the provider node** as an OpenAI-compatible custom provider (`providerSpecificData.baseUrl` optional — the preset's `baseUrlFallback` is used when absent).
+2. **Register a custom model** tagged with the `videos` endpoint and a `generationConfig`:
+
+   ```json
+   {
+     "id": "super-video-v1",
+     "name": "Super Video v1",
+     "source": "manual",
+     "apiFormat": "chat-completions",
+     "supportedEndpoints": ["videos"],
+     "generationConfig": { "preset": "agnes-video-job" }
+   }
+   ```
+
+   `addCustomModel` (in `src/lib/db/models.ts`) accepts `generationConfig?: { preset: string }` as its final parameter and persists it on the model row; `updateCustomModel` forwards it the same way. The provider-models API accepts `generationConfig` on create and update.
+
+3. **Call the route** as usual:
+
+   ```bash
+   curl -X POST http://localhost:8787/api/v1/videos/generations \
+     -H "Content-Type: application/json" \
+     -H "Authorization: Bearer $API_KEY" \
+     -d '{
+       "model": "my-custom-provider/super-video-v1",
+       "prompt": "a cat playing piano",
+       "duration": 5
+     }'
+   ```
+
+## Troubleshooting
+
+| Symptom                                                                        | Cause                                                                                            |
+| ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
+| `400 Unknown video provider: …`                                                | Non-custom provider not in the static registry; preset jobs only apply to custom provider nodes. |
+| `502 Unknown video job preset: …`                                              | `generationConfig.preset` does not match any preset in `VIDEO_JOB_PRESETS`. Fix the model row.   |
+| `502 Video provider did not return a job id (…)`                               | Submit succeeded but the response had no readable value at `taskIdPath`.                         |
+| `502 Video job failed (…)` / `Video job completed but no result URL found (…)` | Poll reached a terminal `statusFailed` state, or `resultPath` held no readable URL.              |
+| `504 Video job timed out after 60 polls (…)`                                   | Job never reached a terminal status within the poll budget.                                      |
+| Upstream 4xx/5xx passthrough                                                   | `fetchJson` returns the upstream status when the submit/poll request itself is not OK.           |
+| Requests go out without auth                                                   | No `apiKey`/`accessToken` on the provider connection; the executor sends `Content-Type` only.    |

electron/package-lock.json

@@ -55,9 +55,9 @@
       "license": "MIT"
     },
     "node_modules/@electron/asar/node_modules/brace-expansion": {
-      "version": "1.1.16",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.16.tgz",
-      "integrity": "sha512-IDw48K2/2kRkg9LdJxurvq3lV3aBgq0REY89duEqFRthjlPdXHKMj7EnQOXVckxzgisinf3nHfrcE2FufFLXMw==",
+      "version": "1.1.18",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz",
+      "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -257,9 +257,9 @@
       "license": "MIT"
     },
     "node_modules/@electron/universal/node_modules/brace-expansion": {
-      "version": "2.1.2",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.2.tgz",
-      "integrity": "sha512-w5JZcKgdhDOgOwm8H+KgbosopHMuGcl6qbulwjtz3SM7I7P3yW1eAjzMPLrIE+NQ9vjgANKHWeMHnrT0OXW1oA==",
+      "version": "2.1.4",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.4.tgz",
+      "integrity": "sha512-hGfVzPxthbf3+2yjg/RBs60cB0FhqBS/zvdV/4wn4/BmN0bNMMHPc4V/BbFieqf1TKAGGAHnY4eSjajCl0f2Xg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -297,6 +297,45 @@
         "url": "https://github.com/sponsors/isaacs"
       }
     },
+    "node_modules/@electron/windows-sign": {
+      "version": "1.2.2",
+      "resolved": "https://registry.npmjs.org/@electron/windows-sign/-/windows-sign-1.2.2.tgz",
+      "integrity": "sha512-dfZeox66AvdPtb2lD8OsIIQh12Tp0GNCRUDfBHIKGpbmopZto2/A8nSpYYLoedPIHpqkeblZ/k8OV0Gy7PYuyQ==",
+      "dev": true,
+      "license": "BSD-2-Clause",
+      "optional": true,
+      "peer": true,
+      "dependencies": {
+        "cross-dirname": "^0.1.0",
+        "debug": "^4.3.4",
+        "fs-extra": "^11.1.1",
+        "minimist": "^1.2.8",
+        "postject": "^1.0.0-alpha.6"
+      },
+      "bin": {
+        "electron-windows-sign": "bin/electron-windows-sign.js"
+      },
+      "engines": {
+        "node": ">=14.14"
+      }
+    },
+    "node_modules/@electron/windows-sign/node_modules/fs-extra": {
+      "version": "11.4.0",
+      "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-11.4.0.tgz",
+      "integrity": "sha512-EQsFzMUJkCKGr1ePqlYADkIUmHW1s3ZXr5Yqy6wbGrfUCphpl2maM/kyOIRA2HpP3AaFQTZXD4ldjek+nccddA==",
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "peer": true,
+      "dependencies": {
+        "graceful-fs": "^4.2.0",
+        "jsonfile": "^6.0.1",
+        "universalify": "^2.0.0"
+      },
+      "engines": {
+        "node": ">=14.14"
+      }
+    },
     "node_modules/@isaacs/fs-minipass": {
       "version": "4.0.1",
       "resolved": "https://registry.npmjs.org/@isaacs/fs-minipass/-/fs-minipass-4.0.1.tgz",
@@ -835,16 +874,16 @@
       "optional": true
     },
     "node_modules/brace-expansion": {
-      "version": "5.0.7",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.7.tgz",
-      "integrity": "sha512-7oFy703dxfY3/NLxC1fh2SUCQ0H9rmAY+5EpDVfXjUTTs+HEwR2nYaqLv+GWcTsumwxPfiz6CzCNkwXwBUwqCA==",
+      "version": "5.0.9",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz",
+      "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "balanced-match": "^4.0.2"
       },
       "engines": {
-        "node": "18 || 20 || >=22"
+        "node": "20 || >=22"
       }
     },
     "node_modules/buffer-from": {
@@ -1091,6 +1130,15 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/cross-dirname": {
+      "version": "0.1.0",
+      "resolved": "https://registry.npmjs.org/cross-dirname/-/cross-dirname-0.1.0.tgz",
+      "integrity": "sha512-+R08/oI0nl3vfPcqftZRpytksBXDzOUveBq/NBVx0sUp1axwzPQrKinNx5yd5sxPu8j1wIy8AfnVQ+5eFdha6Q==",
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "peer": true
+    },
     "node_modules/cross-spawn": {
       "version": "7.0.6",
       "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
@@ -1260,9 +1308,9 @@
       "license": "MIT"
     },
     "node_modules/dir-compare/node_modules/brace-expansion": {
-      "version": "1.1.16",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.16.tgz",
-      "integrity": "sha512-IDw48K2/2kRkg9LdJxurvq3lV3aBgq0REY89duEqFRthjlPdXHKMj7EnQOXVckxzgisinf3nHfrcE2FufFLXMw==",
+      "version": "1.1.18",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz",
+      "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -1411,6 +1459,19 @@
         "node": ">=14.0.0"
       }
     },
+    "node_modules/electron-builder-squirrel-windows": {
+      "version": "26.15.3",
+      "resolved": "https://registry.npmjs.org/electron-builder-squirrel-windows/-/electron-builder-squirrel-windows-26.15.3.tgz",
+      "integrity": "sha512-Jc19XPV9y9+2bAdZPkXuVNGNIEFBq9poHC61l8Kv6FdK7DRG3+Ic0rerC0DXOaeHNz8yW0fg/JnF8GQROOF5MA==",
+      "dev": true,
+      "license": "MIT",
+      "peer": true,
+      "dependencies": {
+        "app-builder-lib": "26.15.3",
+        "builder-util": "26.15.3",
+        "electron-winstaller": "5.4.0"
+      }
+    },
     "node_modules/electron-publish": {
       "version": "26.15.3",
       "resolved": "https://registry.npmjs.org/electron-publish/-/electron-publish-26.15.3.tgz",
@@ -1445,6 +1506,66 @@
         "tiny-typed-emitter": "^2.1.0"
       }
     },
+    "node_modules/electron-winstaller": {
+      "version": "5.4.0",
+      "resolved": "https://registry.npmjs.org/electron-winstaller/-/electron-winstaller-5.4.0.tgz",
+      "integrity": "sha512-bO3y10YikuUwUuDUQRM4KfwNkKhnpVO7IPdbsrejwN9/AABJzzTQ4GeHwyzNSrVO+tEH3/Np255a3sVZpZDjvg==",
+      "dev": true,
+      "hasInstallScript": true,
+      "license": "MIT",
+      "peer": true,
+      "dependencies": {
+        "@electron/asar": "^3.2.1",
+        "debug": "^4.1.1",
+        "fs-extra": "^7.0.1",
+        "lodash": "^4.17.21",
+        "temp": "^0.9.0"
+      },
+      "engines": {
+        "node": ">=8.0.0"
+      },
+      "optionalDependencies": {
+        "@electron/windows-sign": "^1.1.2"
+      }
+    },
+    "node_modules/electron-winstaller/node_modules/fs-extra": {
+      "version": "7.0.1",
+      "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-7.0.1.tgz",
+      "integrity": "sha512-YJDaCJZEnBmcbw13fvdAM9AwNOJwOzrE4pqMqBq5nFiEqXUqHwlK4B+3pUw6JNvfSPtX05xFHtYy/1ni01eGCw==",
+      "dev": true,
+      "license": "MIT",
+      "peer": true,
+      "dependencies": {
+        "graceful-fs": "^4.1.2",
+        "jsonfile": "^4.0.0",
+        "universalify": "^0.1.0"
+      },
+      "engines": {
+        "node": ">=6 <7 || >=8"
+      }
+    },
+    "node_modules/electron-winstaller/node_modules/jsonfile": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/jsonfile/-/jsonfile-4.0.0.tgz",
+      "integrity": "sha512-m6F1R3z8jjlf2imQHS2Qez5sjKWQzbuuhuJ/FKYFRZvPE3PuHcSMVZzfsLhGVOkfd20obL5SWEBew5ShlquNxg==",
+      "dev": true,
+      "license": "MIT",
+      "peer": true,
+      "optionalDependencies": {
+        "graceful-fs": "^4.1.6"
+      }
+    },
+    "node_modules/electron-winstaller/node_modules/universalify": {
+      "version": "0.1.2",
+      "resolved": "https://registry.npmjs.org/universalify/-/universalify-0.1.2.tgz",
+      "integrity": "sha512-rBJeI5CXAlmy1pV+617WB9J63U6XcazHHF2f2dbJix4XzpUF0RS3Zbj0FGIOCAva5P/d/GBOYaACQ1w+0azUkg==",
+      "dev": true,
+      "license": "MIT",
+      "peer": true,
+      "engines": {
+        "node": ">= 4.0.0"
+      }
+    },
     "node_modules/emoji-regex": {
       "version": "8.0.0",
       "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
@@ -1627,9 +1748,9 @@
       "license": "MIT"
     },
     "node_modules/filelist/node_modules/brace-expansion": {
-      "version": "2.1.2",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.2.tgz",
-      "integrity": "sha512-w5JZcKgdhDOgOwm8H+KgbosopHMuGcl6qbulwjtz3SM7I7P3yW1eAjzMPLrIE+NQ9vjgANKHWeMHnrT0OXW1oA==",
+      "version": "2.1.4",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.4.tgz",
+      "integrity": "sha512-hGfVzPxthbf3+2yjg/RBs60cB0FhqBS/zvdV/4wn4/BmN0bNMMHPc4V/BbFieqf1TKAGGAHnY4eSjajCl0f2Xg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -1792,9 +1913,9 @@
       "license": "MIT"
     },
     "node_modules/glob/node_modules/brace-expansion": {
-      "version": "1.1.16",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.16.tgz",
-      "integrity": "sha512-IDw48K2/2kRkg9LdJxurvq3lV3aBgq0REY89duEqFRthjlPdXHKMj7EnQOXVckxzgisinf3nHfrcE2FufFLXMw==",
+      "version": "1.1.18",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz",
+      "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -2113,9 +2234,9 @@
       }
     },
     "node_modules/js-yaml": {
-      "version": "4.3.0",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.3.0.tgz",
-      "integrity": "sha512-1td788aAnnZ5qs7V2QIRl1owjtYpbKt749Y3xauqQgwIIGF/xXWz1wMTEBx5O3LK3lXLVuqXPdPxj2BoFHaW9Q==",
+      "version": "4.3.1",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.3.1.tgz",
+      "integrity": "sha512-CY6crGq313MX8GkwvB7tzgp99vjQxY1++5y10/BKN/GUfHqWaOGQMNZkBvqSzsZKWk/ijwHlWzzkLulsGHhjWQ==",
       "funding": [
         {
           "type": "github",
@@ -2359,6 +2480,20 @@
         "node": ">= 18"
       }
     },
+    "node_modules/mkdirp": {
+      "version": "0.5.6",
+      "resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-0.5.6.tgz",
+      "integrity": "sha512-FP+p8RB8OWpF3YZBCrP5gtADmtXApB5AMLn+vdyA+PyxCjrCs00mjyUozssO33cwDeT3wNGdLxJ5M//YqtHAJw==",
+      "dev": true,
+      "license": "MIT",
+      "peer": true,
+      "dependencies": {
+        "minimist": "^1.2.6"
+      },
+      "bin": {
+        "mkdirp": "bin/cmd.js"
+      }
+    },
     "node_modules/ms": {
       "version": "2.1.3",
       "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
@@ -2622,6 +2757,36 @@
         "node": ">=18"
       }
     },
+    "node_modules/postject": {
+      "version": "1.0.0-alpha.6",
+      "resolved": "https://registry.npmjs.org/postject/-/postject-1.0.0-alpha.6.tgz",
+      "integrity": "sha512-b9Eb8h2eVqNE8edvKdwqkrY6O7kAwmI8kcnBv1NScolYJbo59XUF0noFq+lxbC1yN20bmC0WBEbDC5H/7ASb0A==",
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "peer": true,
+      "dependencies": {
+        "commander": "^9.4.0"
+      },
+      "bin": {
+        "postject": "dist/cli.js"
+      },
+      "engines": {
+        "node": ">=14.0.0"
+      }
+    },
+    "node_modules/postject/node_modules/commander": {
+      "version": "9.5.0",
+      "resolved": "https://registry.npmjs.org/commander/-/commander-9.5.0.tgz",
+      "integrity": "sha512-KRs7WVDKg86PWiuAqhDrAQnTXZKraVcCc6vFdL14qrZ/DcWwuRo7VoiYXalXO7S5GKpqYiVEwCbgFDfxNHKJBQ==",
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "peer": true,
+      "engines": {
+        "node": "^12.20.0 || >=14"
+      }
+    },
     "node_modules/proc-log": {
       "version": "6.1.0",
       "resolved": "https://registry.npmjs.org/proc-log/-/proc-log-6.1.0.tgz",
@@ -2816,6 +2981,21 @@
         "node": ">= 4"
       }
     },
+    "node_modules/rimraf": {
+      "version": "2.6.3",
+      "resolved": "https://registry.npmjs.org/rimraf/-/rimraf-2.6.3.tgz",
+      "integrity": "sha512-mwqeW5XsA2qAejG46gYdENaxXjx9onRNCfn7L0duuP4hCuTIi/QO7PDK07KJfp1d+izWPrzEJDcSqBa0OZQriA==",
+      "deprecated": "Rimraf versions prior to v4 are no longer supported",
+      "dev": true,
+      "license": "ISC",
+      "peer": true,
+      "dependencies": {
+        "glob": "^7.1.3"
+      },
+      "bin": {
+        "rimraf": "bin.js"
+      }
+    },
     "node_modules/roarr": {
       "version": "2.15.4",
       "resolved": "https://registry.npmjs.org/roarr/-/roarr-2.15.4.tgz",
@@ -3045,9 +3225,9 @@
       }
     },
     "node_modules/tar": {
-      "version": "7.5.20",
-      "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.20.tgz",
-      "integrity": "sha512-9FcyK4PA6+WbzlTM9WhQm6vB5W7cP7dUiPsv1g7YDwEQnQ1CGpK3MGlKk/ITVWMk05kHZuBhmVhiv8LZoy/PFQ==",
+      "version": "7.5.22",
+      "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.22.tgz",
+      "integrity": "sha512-MFO/QzvtAOmJbkhOaCTvbGcFN9L9b+JunIsDwaKljSOdcLMea3NJ1k9Usz/rjdfSXTq4dfzfeS7W4p4YOAAHeA==",
       "dev": true,
       "license": "BlueOak-1.0.0",
       "dependencies": {
@@ -3071,6 +3251,21 @@
         "node": ">=18"
       }
     },
+    "node_modules/temp": {
+      "version": "0.9.4",
+      "resolved": "https://registry.npmjs.org/temp/-/temp-0.9.4.tgz",
+      "integrity": "sha512-yYrrsWnrXMcdsnu/7YMYAofM1ktpL5By7vZhf15CrXijWWrEYZks5AXBudalfSWJLlnen/QUJUB5aoB0kqZUGA==",
+      "dev": true,
+      "license": "MIT",
+      "peer": true,
+      "dependencies": {
+        "mkdirp": "^0.5.1",
+        "rimraf": "~2.6.2"
+      },
+      "engines": {
+        "node": ">=6.0.0"
+      }
+    },
     "node_modules/temp-file": {
       "version": "3.4.0",
       "resolved": "https://registry.npmjs.org/temp-file/-/temp-file-3.4.0.tgz",

open-sse/config/audioRegistry.ts

@@ -603,7 +603,7 @@ export interface ProviderNodeRow {
 }
 
 /** Hosts reachable only from the operator's machine/Docker network. */
-function isLoopbackNodeHost(baseUrl: string): boolean {
+export function isLoopbackNodeHost(baseUrl: string): boolean {
   try {
     const hostname = new URL(baseUrl).hostname;
     return (

open-sse/config/constants.ts

@@ -65,27 +65,27 @@ export const PROVIDERS: Record<string, LegacyProvider> = new Proxy(
   {} as Record<string, LegacyProvider>,
   {
     get(_, prop) {
-      if (typeof prop === 'symbol') return undefined;
+      if (typeof prop === "symbol") return undefined;
       return Reflect.get(initProviders(), prop, _providers);
     },
     has(_, prop) {
-      if (typeof prop === 'symbol') return false;
+      if (typeof prop === "symbol") return false;
       return Reflect.has(initProviders(), prop);
     },
     ownKeys() {
       return Reflect.ownKeys(initProviders());
     },
     getOwnPropertyDescriptor(_, prop) {
-      if (typeof prop === 'symbol') return undefined;
+      if (typeof prop === "symbol") return undefined;
       return Object.getOwnPropertyDescriptor(initProviders(), prop);
     },
     set(_, prop, value) {
-      if (typeof prop === 'symbol') return false;
+      if (typeof prop === "symbol") return false;
       (initProviders() as Record<string, LegacyProvider>)[prop] = value;
       return true;
     },
     deleteProperty(_, prop) {
-      if (typeof prop === 'symbol') return false;
+      if (typeof prop === "symbol") return false;
       return Reflect.deleteProperty(initProviders(), prop);
     },
   }
@@ -124,6 +124,11 @@ export const OAUTH_ENDPOINTS = {
     auth: "https://github.com/login/oauth/authorize",
     deviceCode: "https://github.com/login/device/code",
   },
+  openference: {
+    token: "https://openference.com/oauth/token",
+    auth: "https://openference.com/app/oauth/authorize",
+    clientId: "omniroute",
+  },
 };
 
 // Cache TTLs (seconds)

open-sse/config/errorConfig.ts

@@ -149,6 +149,18 @@ export const ERROR_RULES: ErrorRule[] = [
     backoff: true,
     reason: "quota_exhausted",
   },
+  {
+    id: "out_of_extra_usage",
+    text: "out of extra usage",
+    backoff: true,
+    reason: "quota_exhausted",
+  },
+  {
+    id: "extra_usage_required",
+    text: "extra usage required",
+    backoff: true,
+    reason: "quota_exhausted",
+  },
   { id: "capacity", text: "capacity", backoff: true, reason: "model_capacity" },
   { id: "overloaded", text: "overloaded", backoff: true, reason: "model_capacity" },
   { id: "high_demand", text: "high demand", backoff: true, reason: "model_capacity" },

open-sse/config/freeModelCatalog.data.ts

@@ -311,7 +311,6 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
   { provider: "nscale", modelId: "openai/gpt-oss-20b", displayName: "openai/gpt-oss-20b", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
   { provider: "nscale", modelId: "meta-llama/Llama-4-Scout-17B-16E-Instruct", displayName: "meta-llama/Llama-4-Scout-17B-16E-Instruct", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
   { provider: "nscale", modelId: "meta-llama/Llama-3.3-70B-Instruct", displayName: "meta-llama/Llama-3.3-70B-Instruct", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
-  { provider: "nvidia", modelId: "z-ai/glm-5.1", displayName: "GLM 5.1", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "z-ai/glm-5.2", displayName: "GLM 5.2", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "minimaxai/minimax-m2.7", displayName: "MiniMax M2.7", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "google/gemma-4-31b-it", displayName: "Gemma 4 31B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
@@ -321,7 +320,6 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
   { provider: "nvidia", modelId: "qwen/qwen3.5-397b-a17b", displayName: "Qwen3.5-397B-A17B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "qwen/qwen3.5-122b-a10b", displayName: "Qwen3.5-122B-A10B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "stepfun-ai/step-3.5-flash", displayName: "Step 3.5 Flash", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
-  { provider: "nvidia", modelId: "deepseek-ai/deepseek-v4-pro", displayName: "DeepSeek V4 Pro", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "openai/gpt-oss-120b", displayName: "GPT OSS 120B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "openai/gpt-oss-20b", displayName: "GPT OSS 20B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "nvidia/nemotron-3-super-120b-a12b", displayName: "Nemotron 3 Super 120B A12B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },

open-sse/config/imageRegistry.ts

@@ -12,6 +12,10 @@ import { FREEPIK_IMAGE_PROVIDER } from "./providers/registry/freepik/index.ts";
 import { STABILITY_AI_IMAGE_MODELS } from "./providers/registry/stability-ai/imageModels.ts";
 import { GEMINI_IMAGEN_PROVIDER } from "./providers/registry/gemini/imageModels.ts";
 import { CHEAPERINFERENCE_IMAGE_PROVIDER } from "./providers/registry/cheaperinference/imageModels.ts";
+import {
+  ADOBE_FIREFLY_IMAGE_ROUTING_ALIASES,
+  toRegistryImageModels,
+} from "../services/adobeFireflyModels.ts";
 
 interface ImageModelEntry {
   id: string;
@@ -22,6 +26,8 @@ interface ImageModelEntry {
   imageRequired?: boolean;
   description?: string;
   isMarket?: boolean;
+  supportedSizes?: string[];
+  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface ImageProviderConfig {
@@ -35,6 +41,7 @@ interface ImageProviderConfig {
   authHeader: string;
   format: string;
   models: ImageModelEntry[];
+  routingAliases?: readonly string[];
   supportedSizes: string[];
 }
 
@@ -46,6 +53,7 @@ interface ImageModelAliasEntry {
   inputModalities?: string[];
   imageRequired?: boolean;
   description?: string;
+  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface ImageCatalogModelEntry {
@@ -55,6 +63,7 @@ interface ImageCatalogModelEntry {
   supportedSizes: string[];
   inputModalities: string[];
   description?: string;
+  mediaCapabilities?: Record<string, unknown>;
 }
 
 const IMAGE_MODEL_ALIASES: Record<string, ImageModelAliasEntry> = {
@@ -678,55 +687,9 @@ export const IMAGE_PROVIDERS: Record<string, ImageProviderConfig> = {
     authType: "apikey",
     authHeader: "bearer",
     format: "adobe-firefly-image",
-    models: [
-      {
-        id: "nano-banana-pro",
-        name: "Firefly Gemini 3.0 (Nano Banana Pro)",
-        inputModalities: ["text", "image"],
-      },
-      {
-        id: "nano-banana",
-        name: "Firefly Gemini 2.5 (Nano Banana)",
-        inputModalities: ["text", "image"],
-      },
-      {
-        id: "nano-banana-2",
-        name: "Firefly Gemini 3.1 (Nano Banana 2)",
-        inputModalities: ["text", "image"],
-      },
-      { id: "gpt-image-2", name: "Firefly GPT Image 2", inputModalities: ["text", "image"] },
-      { id: "gpt-image", name: "Firefly GPT Image 2", inputModalities: ["text", "image"] },
-      { id: "gpt-image-1.5", name: "Firefly GPT Image 1.5", inputModalities: ["text", "image"] },
-      { id: "flux-2", name: "Firefly Flux 2", inputModalities: ["text", "image"] },
-      { id: "flux-pro", name: "Firefly Flux 1.1 Pro", inputModalities: ["text", "image"] },
-      { id: "flux-ultra", name: "Firefly Flux 1.1 Ultra", inputModalities: ["text", "image"] },
-      { id: "seedream-4", name: "Firefly Seedream 4.0", inputModalities: ["text", "image"] },
-      {
-        id: "seedream-5-lite",
-        name: "Firefly Seedream 5.0 Lite",
-        inputModalities: ["text", "image"],
-      },
-      {
-        id: "runway-gen4-image",
-        name: "Firefly Runway Gen-4 Image",
-        inputModalities: ["text", "image"],
-      },
-      // Topaz Labs upscalers (inputMediaUseCase: ["upscaling"]).
-      // Served by firefly-3p /v2/3p-images/upsample — see config/upscaleRegistry.ts.
-      {
-        id: "topaz-standard",
-        name: "Firefly Topaz Upscale (Standard)",
-        inputModalities: ["image"],
-        imageRequired: true,
-      },
-      {
-        id: "topaz-bloom",
-        name: "Firefly Topaz Bloom (Creative Upscale)",
-        inputModalities: ["image"],
-        imageRequired: true,
-      },
-    ],
-    supportedSizes: ["1:1", "16:9", "9:16", "4:3", "3:4", "1024x1024", "1792x1024", "1024x1792"],
+    models: toRegistryImageModels(),
+    routingAliases: ADOBE_FIREFLY_IMAGE_ROUTING_ALIASES,
+    supportedSizes: [],
   },
 
   // Cheaper Inference (OSS-sponsor gateway). Declared AFTER adobe-firefly on
@@ -887,7 +850,7 @@ export function parseImageModel(modelStr) {
 
   // No provider prefix — try to find the model in every provider
   for (const [providerId, config] of Object.entries(IMAGE_PROVIDERS)) {
-    if (config.models.some((m) => m.id === modelStr)) {
+    if (config.routingAliases?.includes(modelStr) || config.models.some((m) => m.id === modelStr)) {
       return { provider: providerId, model: modelStr };
     }
   }
@@ -906,9 +869,10 @@ function imageProviderCatalogEntries(
     id: `${providerId}/${model.id}`,
     name: model.name,
     provider: providerId,
-    supportedSizes: config.supportedSizes,
+    supportedSizes: model.supportedSizes || config.supportedSizes,
     inputModalities: model.inputModalities || ["text"],
     description: model.description || undefined,
+    mediaCapabilities: model.mediaCapabilities,
   }));
 }
 

open-sse/config/nvidiaHostedModels.snapshot.json

@@ -1,5 +1,4 @@
 [
-  "deepseek-ai/deepseek-v4-pro",
   "google/gemma-4-31b-it",
   "minimaxai/minimax-m2.7",
   "mistralai/devstral-2-123b-instruct-2512",
@@ -13,6 +12,5 @@
   "qwen/qwen3.5-397b-a17b",
   "stepfun-ai/step-3.5-flash",
   "thinkingmachines/inkling",
-  "z-ai/glm-5.1",
   "z-ai/glm-5.2"
 ]

open-sse/config/providerModels.ts

@@ -90,10 +90,65 @@ export function getDefaultModel(aliasOrId: string): string | null {
   return models?.[0]?.id || null;
 }
 
+/** Score a registry entry by how many capability flags it defines. */
+function modelRichness(m: RegistryModel): number {
+  let score = 0;
+  if (m.supportsXHighEffort !== undefined) score += 10; // critical for effort routing
+  if (m.supportsReasoning !== undefined) score += 5;
+  if (m.contextLength !== undefined) score += 3;
+  if (m.maxOutputTokens !== undefined) score += 2;
+  if (m.supportsVision !== undefined) score += 2;
+  if (m.toolCalling !== undefined) score += 2;
+  if (m.interleavedField !== undefined) score += 1;
+  if (m.unsupportedParams !== undefined) score += 1;
+  return score;
+}
+
+function getGlobalModel(modelId: string): RegistryModel | undefined {
+  // 1. Exact match — collect all, pick the richest
+  let candidates: RegistryModel[] = [];
+  for (const models of Object.values(PROVIDER_MODELS)) {
+    const found = models.find((m) => m.id === modelId);
+    if (found) candidates.push(found);
+  }
+  if (candidates.length > 0) {
+    return candidates.sort((a, b) => modelRichness(b) - modelRichness(a))[0];
+  }
+
+  // 2. Strip provider prefix (e.g. moonshotai/kimi-k3-free -> kimi-k3-free)
+  const basename = modelId.split("/").pop() || modelId;
+  candidates = [];
+  for (const models of Object.values(PROVIDER_MODELS)) {
+    const found = models.find((m) => m.id === basename);
+    if (found) candidates.push(found);
+  }
+  if (candidates.length > 0) {
+    return candidates.sort((a, b) => modelRichness(b) - modelRichness(a))[0];
+  }
+
+  // 3. Substring match for base model name (e.g. kimi-k3-free -> kimi-k3)
+  // Finds the longest matching base model ID; on ties, prefers the richer entry.
+  let bestMatch: RegistryModel | undefined;
+  for (const models of Object.values(PROVIDER_MODELS)) {
+    for (const m of models) {
+      if (basename.startsWith(m.id)) {
+        if (
+          !bestMatch ||
+          m.id.length > bestMatch.id.length ||
+          (m.id.length === bestMatch.id.length && modelRichness(m) > modelRichness(bestMatch))
+        ) {
+          bestMatch = m;
+        }
+      }
+    }
+  }
+  return bestMatch;
+}
+
 export function getProviderModel(aliasOrId: string, modelId: string): RegistryModel | undefined {
   const models = PROVIDER_MODELS[aliasOrId];
-  if (!models) return undefined;
-  return models.find((model) => model.id === modelId);
+  if (!models) return getGlobalModel(modelId);
+  return models.find((model) => model.id === modelId) || getGlobalModel(modelId);
 }
 
 export function isValidModel(
@@ -103,26 +158,20 @@ export function isValidModel(
 ): boolean {
   if (passthroughProviders.has(aliasOrId)) return true;
   const models = PROVIDER_MODELS[aliasOrId];
-  if (!models) return false;
-  return models.some((m) => m.id === modelId);
+  if (!models) return !!getGlobalModel(modelId);
+  return models.some((m) => m.id === modelId) || !!getGlobalModel(modelId);
 }
 
 export function findModelName(aliasOrId: string, modelId: string): string {
   const models = PROVIDER_MODELS[aliasOrId];
-  if (!models) return modelId;
-  const found = models.find((m) => m.id === modelId);
+  if (!models) return getGlobalModel(modelId)?.name || modelId;
+  const found = models.find((m) => m.id === modelId) || getGlobalModel(modelId);
   return found?.name || modelId;
 }
 
 export function getModelTargetFormat(aliasOrId: string, modelId: string): string | null {
   const models = PROVIDER_MODELS[aliasOrId];
-  // Strip provider prefix if present: "openai/gpt-5.6-luna" → "gpt-5.6-luna"
-  const prefix = aliasOrId + "/";
-  const bareModelId =
-    typeof modelId === "string" && modelId.startsWith(prefix)
-      ? modelId.slice(prefix.length)
-      : modelId;
-  const found = models?.find((m) => m.id === bareModelId);
+  const found = models?.find((m) => m.id === modelId) || getGlobalModel(modelId);
   if (found?.targetFormat) return found.targetFormat;
   // #5842: OpenAI "*-pro" reasoning models (o1-pro, gpt-5.x-pro) are only served by
   // the native /v1/responses endpoint — /v1/chat/completions 404s ("only supported
@@ -130,14 +179,17 @@ export function getModelTargetFormat(aliasOrId: string, modelId: string): string
   // covers dynamically-synced ids that post-date the catalog (same spirit as the gh
   // executor's /codex/i routing, 9router#102). Scoped to the openai alias so other
   // providers shipping *-pro ids keep their own endpoint semantics.
-  if (aliasOrId === "openai" && /-pro$/i.test(bareModelId)) return "openai-responses";
+  if (aliasOrId === "openai" && /-pro$/i.test(modelId)) return "openai-responses";
   return null;
 }
 
 export function getModelStripTypes(aliasOrId: string, modelId: string): string[] {
   const models = PROVIDER_MODELS[aliasOrId];
-  if (!models) return [];
-  const found = models.find((m) => m.id === modelId);
+  if (!models)
+    return Array.isArray(getGlobalModel(modelId)?.strip)
+      ? [...getGlobalModel(modelId)!.strip!]
+      : [];
+  const found = models.find((m) => m.id === modelId) || getGlobalModel(modelId);
   return Array.isArray(found?.strip) ? [...found.strip] : [];
 }
 
@@ -262,7 +314,7 @@ function resolveProviderModelList(aliasOrId: string): {
 
 export function supportsXHighEffort(aliasOrId: string, modelId: string): boolean {
   const { models: providerModels } = resolveProviderModelList(aliasOrId);
-  const model = providerModels?.find((entry) => entry.id === modelId);
+  const model = providerModels?.find((entry) => entry.id === modelId) || getGlobalModel(modelId);
   if (model?.supportsXHighEffort !== undefined) {
     return model.supportsXHighEffort !== false;
   }

open-sse/config/providers/index.ts

@@ -121,6 +121,8 @@ import { chatgpt_webProvider } from "./registry/chatgpt-web/index.ts";
 import { openrouterProvider } from "./registry/openrouter/index.ts";
 import { cheaperinferenceProvider } from "./registry/cheaperinference/index.ts";
 import { openvectaProvider } from "./registry/openvecta/index.ts";
+import { openferenceProvider } from "./registry/openference/index.ts";
+import { openference_apiProvider } from "./registry/openference-api/index.ts";
 import { orcarouterProvider } from "./registry/orcarouter/index.ts";
 import { copilot_webProvider } from "./registry/copilot-web/index.ts";
 import { copilot_m365_webProvider } from "./registry/copilot-m365-web/index.ts";
@@ -345,6 +347,8 @@ export const REGISTRY: Record<string, RegistryEntry> = {
   openrouter: openrouterProvider,
   cheaperinference: cheaperinferenceProvider,
   openvecta: openvectaProvider,
+  openference: openferenceProvider,
+  "openference-api": openference_apiProvider,
   orcarouter: orcarouterProvider,
   "copilot-web": copilot_webProvider,
   "copilot-m365-web": copilot_m365_webProvider,

open-sse/config/providers/registry/gemini/web/index.ts

@@ -8,9 +8,32 @@ export const gemini_webProvider: RegistryEntry = {
   baseUrl: "https://gemini.google.com/app",
   authType: "apikey",
   authHeader: "cookie",
+  // #9356: `supportsReasoning: false` is a live-behavior statement, not a guess
+  // about the underlying Gemini model. The executor drives the gemini.google.com
+  // web UI by typing a prompt, so it has no thinking-budget control to set and
+  // never surfaces `reasoning_content` — agent routers reading /v1/models must
+  // not select these for reasoning work. `toolCalling: false` is the matching
+  // statement for native function calling; the prompt-emulation shim (#7286)
+  // stays available and is advertised separately as `toolCalling: "emulated"`
+  // on the provider constant (src/shared/constants/providers/web-cookie.ts).
   models: [
-    { id: "gemini-3.1-pro", name: "Gemini 3.1 Pro", toolCalling: false },
-    { id: "gemini-3.5-flash", name: "Gemini 3.5 Flash", toolCalling: false },
-    { id: "gemini-3.1-flash-lite", name: "Gemini 3.1 Flash-Lite", toolCalling: false },
+    {
+      id: "gemini-3.1-pro",
+      name: "Gemini 3.1 Pro",
+      toolCalling: false,
+      supportsReasoning: false,
+    },
+    {
+      id: "gemini-3.5-flash",
+      name: "Gemini 3.5 Flash",
+      toolCalling: false,
+      supportsReasoning: false,
+    },
+    {
+      id: "gemini-3.1-flash-lite",
+      name: "Gemini 3.1 Flash-Lite",
+      toolCalling: false,
+      supportsReasoning: false,
+    },
   ],
 };

open-sse/config/providers/registry/nvidia/index.ts

@@ -32,8 +32,6 @@ export const nvidiaProvider: RegistryEntry = {
     { id: "qwen/qwen3.5-122b-a10b", name: "Qwen3.5-122B-A10B" },
     { id: "stepfun-ai/step-3.5-flash", name: "Step 3.5 Flash" },
     { id: "stepfun-ai/step-3.7-flash", name: "Step 3.7 Flash" },
-    { id: "deepseek-ai/deepseek-v4-pro", name: "DeepSeek V4 Pro", supportsReasoning: true },
-    { id: "deepseek-ai/deepseek-v4-flash", name: "DeepSeek V4 Flash", supportsReasoning: true },
     // Sweep 2026-06-19: verified present in the live NVIDIA NIM /v1/models catalog.
     { id: "moonshotai/kimi-k2.6", name: "Kimi K2.6" },
     { id: "openai/gpt-oss-120b", name: "GPT OSS 120B", toolCalling: false },

open-sse/config/providers/registry/openference-api/index.ts

@@ -0,0 +1,18 @@
+import type { RegistryEntry } from "../../shared.ts";
+import { buildOpenAiCompatibleRegistryEntry } from "../../shared.ts";
+
+/**
+ * Openference API key — OpenAI-compatible gateway (https://openference.com/).
+ *
+ * Bearer API keys (`sk-…`) hit the same api.openference.com/v1/* surface as OAuth
+ * JWTs. Live model discovery uses NAMED_OPENAI_STYLE_PROVIDERS; the seed below is
+ * the offline fallback when the live fetch fails.
+ */
+export const openference_apiProvider: RegistryEntry = buildOpenAiCompatibleRegistryEntry({
+  id: "openference-api",
+  alias: "ofa",
+  baseUrl: "https://api.openference.com/v1/chat/completions",
+  responsesBaseUrl: "https://api.openference.com/v1/responses",
+  passthroughModels: true,
+  models: [{ id: "GLM-5.2", name: "GLM 5.2", contextLength: 850000 }],
+});

open-sse/config/providers/registry/openference/index.ts

@@ -0,0 +1,25 @@
+import type { RegistryEntry } from "../../shared.ts";
+
+/**
+ * Openference — OpenAI-compatible AI inference gateway (https://openference.com/).
+ *
+ * OAuth access tokens are ES256 JWTs accepted as Bearer credentials on
+ * api.openference.com/v1/*. Live model discovery uses NAMED_OPENAI_STYLE_PROVIDERS;
+ * seed models below are the offline fallback when the live fetch fails.
+ */
+export const openferenceProvider: RegistryEntry = {
+  id: "openference",
+  alias: "of",
+  format: "openai",
+  executor: "default",
+  baseUrl: "https://api.openference.com/v1/chat/completions",
+  responsesBaseUrl: "https://api.openference.com/v1/responses",
+  authType: "oauth",
+  authHeader: "bearer",
+  passthroughModels: true,
+  oauth: {
+    clientIdDefault: "omniroute",
+    tokenUrl: "https://openference.com/oauth/token",
+  },
+  models: [{ id: "GLM-5.2", name: "GLM 5.2", contextLength: 850000 }],
+};

open-sse/config/videoRegistry.ts

@@ -5,14 +5,17 @@
  * Supports local providers plus hosted task-based APIs such as Runway.
  */
 
-import { parseModelFromRegistry, getAllModelsFromRegistry } from "./registryUtils.ts";
+import { parseModelFromRegistry } from "./registryUtils.ts";
 import { RUNWAYML_SUPPORTED_VIDEO_MODELS } from "./runway.ts";
 import { SEGMIND_VIDEO_MODELS } from "./providers/registry/segmind/videoModels.ts";
+import { toRegistryVideoModels } from "../services/adobeFireflyModels.ts";
 
 interface VideoModel {
   id: string;
   name: string;
   isMarket?: boolean;
+  supportedSizes?: string[];
+  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface VideoProvider {
@@ -326,8 +329,7 @@ export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
   },
 
   // Adobe Firefly (unofficial) — same IMS/cookie credential as the image entry.
-  // Async 3P video generate + poll (Sora 2, Veo 3.1, Kling …). Fallback list
-  // from models/discovery capture (adobe/get_models.txt).
+  // Exact async video models and capabilities from the verified discovery snapshot.
   "adobe-firefly": {
     id: "adobe-firefly",
     alias: "firefly",
@@ -335,18 +337,7 @@ export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
     authType: "apikey",
     authHeader: "bearer",
     format: "adobe-firefly-video",
-    models: [
-      { id: "sora-2", name: "Firefly Sora 2" },
-      { id: "sora-2-pro", name: "Firefly Sora 2 Pro" },
-      { id: "veo-3.1", name: "Firefly Veo 3.1" },
-      { id: "veo-3.1-fast", name: "Firefly Veo 3.1 Fast" },
-      { id: "veo-3.1-ref", name: "Firefly Veo 3.1 Reference" },
-      { id: "kling-3", name: "Firefly Kling v3 Standard I2V" },
-      { id: "kling-v3-t2v", name: "Firefly Kling v3 Standard T2V" },
-      { id: "kling-v3-pro-i2v", name: "Firefly Kling v3 Pro I2V" },
-      { id: "luma-ray3", name: "Firefly Ray3" },
-      { id: "runway-gen4-turbo", name: "Firefly Runway Gen-4 Video" },
-    ],
+    models: toRegistryVideoModels(),
   },
 };
 
@@ -368,5 +359,17 @@ export function parseVideoModel(modelStr: string | null) {
  * Get all video models as a flat list
  */
 export function getAllVideoModels() {
-  return getAllModelsFromRegistry(VIDEO_PROVIDERS);
+  return Object.entries(VIDEO_PROVIDERS).flatMap(([providerId, config]) =>
+    [providerId, config.alias]
+      .filter((prefix): prefix is string => Boolean(prefix))
+      .flatMap((prefix) =>
+        config.models.map((model) => ({
+          id: `${prefix}/${model.id}`,
+          name: model.name,
+          provider: providerId,
+          supportedSizes: model.supportedSizes || [],
+          mediaCapabilities: model.mediaCapabilities,
+        }))
+      )
+  );
 }

open-sse/executors/azure-ai.ts

@@ -0,0 +1,35 @@
+import { DefaultExecutor } from "./default.ts";
+import type { ProviderCredentials } from "./base.ts";
+import { applyAzureParamRules } from "./azureParamRules.ts";
+
+/**
+ * Azure AI Foundry (`azure-ai`).
+ *
+ * URL building, auth headers and the `responses` vs `chat` apiType switch all
+ * live in `DefaultExecutor`, keyed on the `azure-ai` provider id — this subclass
+ * inherits them unchanged and adds only the Azure request-param rules.
+ *
+ * Before this existed, `azure-ai` fell through to the bare `DefaultExecutor`
+ * while `azure-openai` had the rules inline, so the same Azure deployment
+ * behaved differently depending on which connection served it: `azure-openai`
+ * succeeded and `azure-ai` returned HTTP 400 for `max_tokens` /
+ * `reasoning_effort`.
+ */
+export class AzureAiExecutor extends DefaultExecutor {
+  constructor() {
+    super("azure-ai");
+  }
+
+  override transformRequest(
+    model: string,
+    body: unknown,
+    stream: boolean,
+    credentials: ProviderCredentials
+  ): unknown {
+    return applyAzureParamRules(
+      model,
+      body,
+      super.transformRequest(model, body, stream, credentials)
+    );
+  }
+}

open-sse/executors/azure-openai.ts

@@ -1,9 +1,9 @@
 import { DefaultExecutor } from "./default.ts";
 import type { ProviderCredentials } from "./base.ts";
 import { stripTrailingSlashes } from "../utils/urlSanitize.ts";
+import { applyAzureParamRules } from "./azureParamRules.ts";
 
 const DEFAULT_API_VERSION = "2024-12-01-preview";
-const GPT5_OR_REASONING_DEPLOYMENT = /(?:^|[/_-])(?:gpt-5|o(?:1|3|4))(?:[._-]|$)/i;
 
 function normalizeAzureBaseUrl(rawBaseUrl?: string | null): string {
   const normalized = stripTrailingSlashes((rawBaseUrl || "").trim());
@@ -57,37 +57,10 @@ export class AzureOpenAIExecutor extends DefaultExecutor {
     stream: boolean,
     credentials: ProviderCredentials
   ): unknown {
-    const transformed = super.transformRequest(model, body, stream, credentials);
-    if (!GPT5_OR_REASONING_DEPLOYMENT.test(model)) return transformed;
-    if (!transformed || typeof transformed !== "object" || Array.isArray(transformed)) {
-      return transformed;
-    }
-
-    const original =
-      body && typeof body === "object" && !Array.isArray(body)
-        ? (body as Record<string, unknown>)
-        : null;
-    const normalized = { ...(transformed as Record<string, unknown>) };
-
-    if (original?.max_completion_tokens !== undefined) {
-      normalized.max_completion_tokens = original.max_completion_tokens;
-    } else if (
-      normalized.max_completion_tokens === undefined &&
-      original?.max_tokens !== undefined
-    ) {
-      normalized.max_completion_tokens = original.max_tokens;
-    }
-    delete normalized.max_tokens;
-
-    if (normalized.temperature !== undefined && normalized.temperature !== 1) {
-      delete normalized.temperature;
-    }
-
-    const hasTools = Array.isArray(normalized.tools) && normalized.tools.length > 0;
-    if (hasTools || normalized.reasoning_effort === "none") {
-      delete normalized.reasoning_effort;
-    }
-
-    return normalized;
+    return applyAzureParamRules(
+      model,
+      body,
+      super.transformRequest(model, body, stream, credentials)
+    );
   }
 }

open-sse/executors/azureParamRules.ts

@@ -0,0 +1,76 @@
+/**
+ * Azure Chat Completions param rules, shared by every Azure wire path.
+ *
+ * Azure's newer deployments reject a handful of stock OpenAI Chat Completions
+ * params and return HTTP 400 rather than ignoring them:
+ *
+ *   - `max_tokens`      -> "Unsupported parameter: 'max_tokens' is not supported
+ *                          with this model. Use 'max_completion_tokens' instead."
+ *   - `temperature`     -> only the default (1) is accepted.
+ *   - `reasoning_effort` -> "Function tools with reasoning_effort are not
+ *                          supported ... Please use /v1/responses instead."
+ *
+ * This logic previously lived inline in `AzureOpenAIExecutor`, so it only
+ * covered the `azure-openai` provider. `azure-ai` (Azure AI Foundry) routes
+ * through `DefaultExecutor` and inherited none of it, which meant an identical
+ * deployment 400'd on one connection and succeeded on the other. Extracted here
+ * so both executors apply exactly the same rules.
+ */
+
+/**
+ * Deployments that require `max_completion_tokens` instead of `max_tokens`.
+ *
+ * Matches the GPT-5 family and the o1/o3/o4 reasoning series at a token
+ * boundary, so a deployment named `my-gpt-5-prod` matches while an unrelated
+ * `piston-o4-legacy`-style name does not match by accident. `gpt-chat-latest`
+ * is listed explicitly: it is a moving alias that currently resolves to a
+ * GPT-5-era model and rejects `max_tokens`, but carries no version number for
+ * the boundary pattern to key on.
+ */
+export const AZURE_COMPLETION_TOKEN_DEPLOYMENT =
+  /(?:^|[/_-])(?:gpt-5|o(?:1|3|4))(?:[._-]|$)|^gpt-chat-latest$/i;
+
+/**
+ * Apply the Azure param rules to an already-translated Chat Completions body.
+ *
+ * `originalBody` is the pre-translation request, consulted only to recover a
+ * caller-supplied token budget that translation may have moved or dropped.
+ * Returns `transformed` untouched when the deployment is unaffected or the body
+ * is not a plain object, and never mutates either input.
+ */
+export function applyAzureParamRules(
+  model: string,
+  originalBody: unknown,
+  transformed: unknown
+): unknown {
+  if (!AZURE_COMPLETION_TOKEN_DEPLOYMENT.test(model)) return transformed;
+  if (!transformed || typeof transformed !== "object" || Array.isArray(transformed)) {
+    return transformed;
+  }
+
+  const original =
+    originalBody && typeof originalBody === "object" && !Array.isArray(originalBody)
+      ? (originalBody as Record<string, unknown>)
+      : null;
+  const normalized = { ...(transformed as Record<string, unknown>) };
+
+  if (original?.max_completion_tokens !== undefined) {
+    normalized.max_completion_tokens = original.max_completion_tokens;
+  } else if (normalized.max_completion_tokens === undefined && original?.max_tokens !== undefined) {
+    normalized.max_completion_tokens = original.max_tokens;
+  }
+  delete normalized.max_tokens;
+
+  if (normalized.temperature !== undefined && normalized.temperature !== 1) {
+    delete normalized.temperature;
+  }
+
+  // Azure 400s on reasoning_effort as soon as tools are present, which is every
+  // agentic client (Claude Code, Cursor agent) on every turn.
+  const hasTools = Array.isArray(normalized.tools) && normalized.tools.length > 0;
+  if (hasTools || normalized.reasoning_effort === "none") {
+    delete normalized.reasoning_effort;
+  }
+
+  return normalized;
+}

open-sse/executors/base/reasoningEffort.ts

@@ -2,16 +2,19 @@
 // Extracted verbatim from base.ts. Deps are config/services only (no host import → no cycle).
 import { PROVIDER_CLAUDE } from "../../services/systemTransforms.ts";
 import { isClaudeCodeCompatible } from "../../services/provider.ts";
-import { supportsClaudeMaxEffort, supportsXHighEffort } from "../../config/providerModels.ts";
+import {
+  supportsClaudeMaxEffort,
+  supportsXHighEffort,
+  getProviderModel,
+} from "../../config/providerModels.ts";
 
 /**
  * Sanitize reasoning_effort for providers that don't accept all values.
  *
- * The claude→openai translator passes output_config.effort through verbatim
- * (including max) and only performs form conversion; provider-aware effort
- * policy is owned here. Combined with runtime alias remapping (e.g.
- * claude-opus-4-6 → mimo/mimo-v2.5-pro), this routes a client's effort value
- * to OpenAI-shape providers that don't accept it:
+ * The claude→openai translator may emit reasoning_effort=max/xhigh when the
+ * client sends output_config.effort=max on a Claude-shape request. Combined with
+ * runtime alias remapping (e.g. claude-opus-4-6 → mimo/mimo-v2.5-pro), this
+ * routes xhigh to OpenAI-shape providers that don't accept the value:
  *
  *   xiaomi-mimo : low|medium|high only — 400 literal_error on xhigh
  *   mistral     : devstral models reject reasoning_effort entirely
@@ -140,9 +143,11 @@ export function mapNvidiaGlm52ReasoningParams(
 }
 
 export function supportsMaxEffortForProvider(provider: string, model: string): boolean {
+  const resolvedModelId = getProviderModel(provider, model)?.id || model;
+
   const isClaude =
     (provider === PROVIDER_CLAUDE || isClaudeCodeCompatible(provider)) &&
-    supportsClaudeMaxEffort(model);
+    supportsClaudeMaxEffort(resolvedModelId);
   // opencode-go proxies DeepSeek with the native DeepSeek API contract, which
   // accepts {high, max} literally. Without this opt-in, max would be
   // normalized to xhigh (the OmniRoute-internal top tier) and rejected by the
@@ -151,11 +156,12 @@ export function supportsMaxEffortForProvider(provider: string, model: string): b
   // Ollama Cloud also accepts literal max (for example GLM 5.2 supports
   // low|medium|high|max|none) and rejects xhigh.
   const isOpencodeGoDeepSeek =
-    (provider === "opencode-go" || provider === "opencode-zen") &&
-    model.toLowerCase().includes("deepseek");
+    provider === "opencode-go" && resolvedModelId.toLowerCase().includes("deepseek");
   const isOllamaCloud = provider === "ollama-cloud";
-  const isMoonshotK3 =
-    (provider === "moonshot" || provider === "kimi") && /^kimi-k3(?:$|-)/i.test(model);
+  // Kimi K3 only accepts literal max and rejects xhigh natively. Apply this mapping
+  // regardless of provider so that OpenAI-compatible proxies (e.g. TokenRouter)
+  // correctly pass max instead of the internal xhigh top tier.
+  const isMoonshotK3 = /^kimi-k3(?:$|-)/i.test(resolvedModelId);
   return isClaude || isOpencodeGoDeepSeek || isOllamaCloud || isMoonshotK3;
 }
 
@@ -253,16 +259,6 @@ export function sanitizeReasoningEffortForProvider(
   const effortStr = typeof c.effort === "string" ? c.effort.toLowerCase() : "";
   const modelStr = model || "";
 
-  // Oh My Pi exposes `minimal`, while Codex's Responses API starts at `low`.
-  // Normalize every carrier before the Codex executor sends the upstream request.
-  if (provider === "codex" && effortStr === "minimal") {
-    log?.info?.(
-      "REASONING_SANITIZE",
-      `${provider}/${modelStr}: normalized reasoning_effort minimal → low`
-    );
-    return writeEffortValue(b, "low", c);
-  }
-
   const githubOptIn =
     provider === "github" && GITHUB_REASONING_EFFORT_OPT_IN_PATTERN.test(modelStr);
   const rejecting =
@@ -298,27 +294,48 @@ export function sanitizeReasoningEffortForProvider(
   }
 
   const supportsXHigh = supportsXHighEffort(provider, modelStr);
-  const shouldDowngradeXHigh = effortStr === "xhigh" && !supportsXHigh;
-  const supportsXHighForMax = supportsXHigh;
   const supportsMax = supportsMaxEffortForProvider(provider, modelStr);
-  const shouldNormalizeMaxToXHigh = effortStr === "max" && !supportsMax && supportsXHighForMax;
-  const shouldDowngradeMax = effortStr === "max" && !supportsMax && !supportsXHighForMax;
 
-  if (shouldNormalizeMaxToXHigh) {
+  // ── xhigh handling ──────────────────────────────────────────────────────
+  // xhigh is OmniRoute-internal. Map it to the best effort the model accepts.
+  if (effortStr === "xhigh") {
+    if (supportsXHigh) return body; // model accepts xhigh natively
+    if (supportsMax) {
+      log?.info?.(
+        "REASONING_SANITIZE",
+        `${provider}/${modelStr}: mapped reasoning_effort xhigh → max`
+      );
+      return writeEffortValue(b, "max", c);
+    }
+    // Model explicitly rejects xhigh — gracefully degrade to high (its highest standard tier)
     log?.info?.(
       "REASONING_SANITIZE",
-      `${provider}/${modelStr}: normalized reasoning_effort max → xhigh`
-    );
-    return writeEffortValue(b, "xhigh", c);
-  }
-
-  if (shouldDowngradeXHigh || shouldDowngradeMax) {
-    log?.info?.(
-      "REASONING_SANITIZE",
-      `${provider}/${modelStr}: downgraded reasoning_effort ${effortStr} → high`
+      `${provider}/${modelStr}: downgraded reasoning_effort xhigh → high`
     );
     return writeEffortValue(b, "high", c);
   }
 
+  // ── max handling ────────────────────────────────────────────────────────
+  // NEW DEFAULT: pass max through unchanged. Most reasoning-capable APIs
+  // accept max natively. Only degrade when we KNOW the model rejects it
+  // (registry has supportsXHighEffort explicitly set to false AND it's not
+  // in the supportsMax whitelist). Unknown models pass through — trust the
+  // upstream, and if it 400s the user gets a clear signal. This prevents
+  // new models from being unusable for weeks until they're whitelisted (#8057).
+  if (effortStr === "max") {
+    if (supportsMax) return body; // explicitly known to accept max
+    if (!supportsXHigh) {
+      // Model is explicitly flagged as rejecting xhigh (and not in supportsMax) —
+      // it likely only accepts standard tiers. Degrade to its highest: high.
+      log?.info?.(
+        "REASONING_SANITIZE",
+        `${provider}/${modelStr}: downgraded reasoning_effort max → high (model rejects max/xhigh)`
+      );
+      return writeEffortValue(b, "high", c);
+    }
+    // Default: pass max through unchanged — trust the upstream
+    return body;
+  }
+
   return body;
 }

open-sse/executors/cliproxyapi.ts

@@ -408,12 +408,13 @@ export class CliproxyapiExecutor extends BaseExecutor {
 
     input.log?.info?.("CPA", `CLIProxyAPI → ${url} (model: ${input.model}, shape: ${shape})`);
 
-    // _toolNameMap is an in-memory channel to chatCore for response-side
-    // tool name restoration; never send it over the wire.
+    // _toolNameMap and _namespaceToolIdentityMap are in-memory channels to
+    // chatCore for response-side tool name restoration; never send them over
+    // the wire.
     const wireBody =
       transformedBody && typeof transformedBody === "object"
         ? JSON.stringify(transformedBody, (key, value) =>
-            key === "_toolNameMap" ? undefined : value
+            key === "_toolNameMap" || key === "_namespaceToolIdentityMap" ? undefined : value
           )
         : JSON.stringify(transformedBody);
 

open-sse/executors/codebuddy-cn.ts

@@ -1,5 +1,82 @@
 import { DefaultExecutor } from "./default.ts";
-import type { ProviderCredentials } from "./base.ts";
+import type { ExecuteInput, ExecutorExecuteResult, ProviderCredentials } from "./base.ts";
+
+const SENSITIVE_CONTENT_REJECTION =
+  "抱歉，系统检测到您当前输入的信息存在敏感内容，我无法响应您的请求，请检查后重新输入";
+const LARGE_TOOL_METADATA_BYTES = 64 * 1024;
+
+function responseFromResult(result: ExecutorExecuteResult): Response {
+  return result instanceof Response ? result : result.response;
+}
+
+function credentialsFromResult(
+  result: ExecutorExecuteResult,
+  fallback: ProviderCredentials
+): ProviderCredentials {
+  if (result instanceof Response || !result.headers) return fallback;
+
+  const authorization = Object.entries(result.headers).find(
+    ([name]) => name.toLowerCase() === "authorization"
+  )?.[1];
+  if (!authorization?.startsWith("Bearer ")) return fallback;
+
+  return {
+    ...fallback,
+    accessToken: authorization.slice("Bearer ".length),
+    expiresAt: undefined,
+  };
+}
+
+function compactToolDescriptions(body: unknown): unknown | null {
+  if (!body || typeof body !== "object" || Array.isArray(body)) return null;
+
+  const request = body as Record<string, unknown>;
+  if (!Array.isArray(request.tools) || request.tools.length === 0) return null;
+
+  const originalTools = request.tools;
+  try {
+    const serializedTools = JSON.stringify(originalTools);
+    if (new TextEncoder().encode(serializedTools).byteLength < LARGE_TOOL_METADATA_BYTES) {
+      return null;
+    }
+  } catch {
+    return null;
+  }
+
+  let tools: unknown[] | null = null;
+  originalTools.forEach((tool, index) => {
+    if (!tool || typeof tool !== "object" || Array.isArray(tool)) return;
+
+    const declaration = tool as Record<string, unknown>;
+    if (
+      declaration.type !== "function" ||
+      !declaration.function ||
+      typeof declaration.function !== "object" ||
+      Array.isArray(declaration.function)
+    ) {
+      return;
+    }
+
+    const toolFunction = declaration.function as Record<string, unknown>;
+    if (!Object.prototype.hasOwnProperty.call(toolFunction, "description")) return;
+
+    const compactFunction = { ...toolFunction };
+    delete compactFunction.description;
+    tools ??= originalTools.slice();
+    tools[index] = { ...declaration, function: compactFunction };
+  });
+
+  return tools ? { ...request, tools } : null;
+}
+
+async function isSensitiveContentRejection(response: Response): Promise<boolean> {
+  if (response.status !== 400) return false;
+  const responseText = await response
+    .clone()
+    .text()
+    .catch(() => "");
+  return responseText.includes(SENSITIVE_CONTENT_REJECTION);
+}
 
 /**
  * CodeBuddyCnExecutor — talks to https://copilot.tencent.com/v2/chat/completions
@@ -21,6 +98,26 @@ export class CodeBuddyCnExecutor extends DefaultExecutor {
     super("codebuddy-cn");
   }
 
+  async execute(input: ExecuteInput): Promise<ExecutorExecuteResult> {
+    const result = await super.execute(input);
+    if (!(await isSensitiveContentRejection(responseFromResult(result)))) {
+      return result;
+    }
+
+    const compactBody = compactToolDescriptions(input.body);
+    if (!compactBody) return result;
+
+    input.log?.debug?.(
+      "CODEBUDDY_CN",
+      "Upstream rejected an oversized tool request as sensitive content; retrying with compact tool descriptions"
+    );
+    return super.execute({
+      ...input,
+      body: compactBody,
+      credentials: credentialsFromResult(result, input.credentials),
+    });
+  }
+
   transformRequest(
     model: string,
     body: unknown,

open-sse/executors/codex.ts

@@ -32,6 +32,7 @@ import {
 } from "../config/codexIdentity.ts";
 import { getAccessToken } from "../services/tokenRefresh.ts";
 import { sanitizeResponsesInputItems } from "../services/responsesInputSanitizer.ts";
+import { applyResponsesInputPolicy } from "../services/responsesInputPolicy.ts";
 import { normalizeCodexVerbosity } from "../services/codexVerbosity.ts";
 import { getThinkingBudgetConfig, ThinkingMode } from "../services/thinkingBudget.ts";
 import { CORS_HEADERS } from "../utils/cors.ts";
@@ -222,90 +223,6 @@ function convertSystemToDeveloperRole(body: Record<string, unknown>): void {
   }
 }
 
-/**
- * Strip server-generated item IDs from the input array.
- *
- * The Codex /codex/responses endpoint does not persist response items even when
- * store=true is sent. When proxy clients (e.g. OpenClaw) include response items
- * from previous turns in the input array, those items carry server-assigned IDs
- * (prefixed with "rs_", "fc_", "resp_", "msg_"). The Codex backend tries to
- * validate these IDs against its persistence store and returns 404 when the items
- * are not found (because store was effectively false).
- *
- * This function:
- *   1. Removes bare string references ("rs_abc123") from the input array
- *   2. Removes object items with type "item_reference" (explicit stored-item refs)
- *   3. Strips the "id" field from any object in input whose id matches a
- *      server-generated prefix (rs_, fc_, resp_, msg_) — so the content is
- *      preserved but the backend won't try to look it up
- */
-export function stripStoredItemReferences(body: Record<string, unknown>): void {
-  if (Array.isArray(body.input) && body.input.length === 0) {
-    body.input = [
-      {
-        type: "message",
-        role: "user",
-        content: [{ type: "input_text", text: "continue" }],
-      },
-    ];
-  }
-
-  if (!Array.isArray(body.input)) return;
-
-  const SERVER_ID_PATTERN = /^(rs|fc|resp|msg)_/;
-  let strippedCount = 0;
-
-  body.input = body.input.filter((item) => {
-    // Bare string references: "rs_abc123", "resp_abc123"
-    if (typeof item === "string" && SERVER_ID_PATTERN.test(item)) {
-      strippedCount++;
-      return false;
-    }
-
-    // Object references: { type: "item_reference", id: "rs_..." }
-    if (
-      item &&
-      typeof item === "object" &&
-      !Array.isArray(item) &&
-      (item as Record<string, unknown>).type === "item_reference"
-    ) {
-      strippedCount++;
-      return false;
-    }
-
-    // Reasoning blobs (encrypted_content) are unusable with store=false since
-    // previous_response_id is deleted — strip them to avoid wasting context
-    // tokens (O(n^2) growth across agentic turns).
-    if (
-      item &&
-      typeof item === "object" &&
-      !Array.isArray(item) &&
-      (item as Record<string, unknown>).type === "reasoning"
-    ) {
-      strippedCount++;
-      return false;
-    }
-
-    // Object items with server-generated IDs: strip the id field but keep the item.
-    // e.g. { id: "rs_...", type: "reasoning", summary: [...] } → keep content, remove id
-    // e.g. { id: "fc_...", type: "function_call", ... } → keep content, remove id
-    if (item && typeof item === "object" && !Array.isArray(item)) {
-      const record = item as Record<string, unknown>;
-      if (typeof record.id === "string" && SERVER_ID_PATTERN.test(record.id)) {
-        delete record.id;
-        strippedCount++;
-      }
-    }
-
-    return true;
-  });
-
-  if (strippedCount > 0) {
-    console.debug(
-      `[Codex] stripStoredItemReferences: sanitized ${strippedCount} server-generated ID(s) from input`
-    );
-  }
-}
 
 function stripOrphanedCodexFunctionCallOutputs(body: Record<string, unknown>): void {
   if (!Array.isArray(body.input)) return;
@@ -1296,7 +1213,7 @@ export class CodexExecutor extends BaseExecutor {
     }
 
     // Issue #1832 & #1853: Map messages to input for clients like Cursor 5.5 that use responses/compact but send messages instead of input.
-    // This MUST run before convertSystemToDeveloperRole and stripStoredItemReferences.
+    // This MUST run before convertSystemToDeveloperRole.
     if (!body.input && Array.isArray(body.messages)) {
       body.input = body.messages.map((msg: ResponsesMessageInput) => ({
         type: "message",
@@ -1419,11 +1336,6 @@ export class CodexExecutor extends BaseExecutor {
       preserveCustomTools: nativeCodexPassthrough,
     });
 
-    // Strip stored response item references (rs_, resp_, msg_ IDs) from input.
-    // The /codex/responses endpoint does not persist responses even with store=true,
-    // so any references to previous response items would cause 404 errors.
-    stripStoredItemReferences(body);
-
     // Issue #806: Even for native passthrough, some clients (purist completions) might indiscriminately inject
     // a `messages` or `prompt` array which the strict Codex Responses schema rejects.
     delete body.messages;
@@ -1515,6 +1427,11 @@ export class CodexExecutor extends BaseExecutor {
     delete body.session_id;
     delete body.conversation_id;
 
+    applyResponsesInputPolicy(
+      body,
+      credentials?.providerSpecificData?.preserveEncryptedReasoning === true
+    );
+
     if (nativeCodexPassthrough) {
       return body;
     }

open-sse/executors/codex/tools.ts

@@ -30,6 +30,114 @@ export function isCodexFreePlan(providerSpecificData: unknown): boolean {
   return typeof plan === "string" && plan.trim().toLowerCase() === "free";
 }
 
+type JsonRecord = Record<string, unknown>;
+
+const REDUNDANT_ONEOF_OBJECT_MAP_FIELDS = [
+  "properties",
+  "patternProperties",
+  "$defs",
+  "definitions",
+] as const;
+
+const REDUNDANT_ONEOF_ARRAY_SCHEMA_FIELDS = ["prefixItems", "oneOf", "anyOf", "allOf"] as const;
+
+const REDUNDANT_ONEOF_SINGLE_SCHEMA_FIELDS = [
+  "items",
+  "additionalProperties",
+  "not",
+  "if",
+  "then",
+  "else",
+] as const;
+
+const REDUNDANT_ONEOF_ANNOTATION_KEYS = new Set(["const", "description", "title", "$comment"]);
+
+/**
+ * Remove a redundant `oneOf` when it is fully covered by a sibling `enum`.
+ *
+ * The Codex private Responses endpoint (`chatgpt.com/backend-api/codex/responses`)
+ * intermittently returns a 502 `upstream_empty_response` when a tool parameter
+ * carries the JSON-Schema pattern `oneOf: [{const, ...annotations}]` together
+ * with a sibling `enum` whose value set exactly matches the `const` set. In that
+ * case `oneOf` adds no constraint beyond `enum`, so dropping it is semantically
+ * safe and eliminates the trigger.
+ *
+ * Only the exact-match redundant case is stripped. Bare `oneOf[const]` without
+ * a sibling `enum`, narrowing const sets, non-matching enums, type-discriminated
+ * `oneOf`, and `anyOf`/`allOf` are all preserved.
+ */
+export function stripRedundantOneOfConstEnum(schema: unknown): unknown {
+  if (Array.isArray(schema)) {
+    return schema.map((entry) => stripRedundantOneOfConstEnum(entry));
+  }
+  if (!isPlainObject(schema)) return schema;
+
+  const result: JsonRecord = { ...schema };
+
+  maybeStripRedundantOneOf(result);
+
+  for (const field of REDUNDANT_ONEOF_OBJECT_MAP_FIELDS) {
+    const map = result[field];
+    if (isPlainObject(map)) {
+      result[field] = Object.fromEntries(
+        Object.entries(map).map(([key, value]) => [key, stripRedundantOneOfConstEnum(value)])
+      );
+    }
+  }
+
+  for (const field of REDUNDANT_ONEOF_ARRAY_SCHEMA_FIELDS) {
+    if (Array.isArray(result[field])) {
+      result[field] = (result[field] as unknown[]).map((entry) =>
+        stripRedundantOneOfConstEnum(entry)
+      );
+    }
+  }
+
+  for (const field of REDUNDANT_ONEOF_SINGLE_SCHEMA_FIELDS) {
+    if (result[field] !== undefined) {
+      result[field] = stripRedundantOneOfConstEnum(result[field]);
+    }
+  }
+
+  return result;
+}
+
+function maybeStripRedundantOneOf(node: JsonRecord): void {
+  const branches = node.oneOf;
+  if (!Array.isArray(branches) || branches.length === 0) return;
+
+  const enumValues = Array.isArray(node.enum) ? node.enum : null;
+  if (!enumValues || enumValues.length === 0) return;
+
+  // Every branch must be {const, ...annotations only}.
+  const constValues: unknown[] = [];
+  for (const branch of branches) {
+    if (!isPlainObject(branch)) return;
+    const branchKeys = Object.keys(branch);
+    if (!branchKeys.includes("const")) return;
+    if (!branchKeys.every((key) => REDUNDANT_ONEOF_ANNOTATION_KEYS.has(key))) return;
+    constValues.push((branch as JsonRecord).const);
+  }
+
+  // Restrict to string consts and string enums (confirmed production shape).
+  if (!constValues.every((value) => typeof value === "string")) return;
+  if (!enumValues.every((value) => typeof value === "string")) return;
+
+  // All const values must be unique.
+  if (new Set(constValues).size !== constValues.length) return;
+
+  // The const set must exactly match the enum set.
+  const enumSet = new Set(enumValues);
+  if (enumSet.size !== constValues.length) return;
+  if (!constValues.every((value) => enumSet.has(value))) return;
+
+  delete node.oneOf;
+}
+
+function isPlainObject(value: unknown): value is JsonRecord {
+  return typeof value === "object" && value !== null && !Array.isArray(value);
+}
+
 export function normalizeCodexTools(
   body: Record<string, unknown>,
   options?: { dropImageGeneration?: boolean; preserveCustomTools?: boolean }
@@ -138,7 +246,9 @@ export function normalizeCodexTools(
     // Codex/OpenAI Responses API rejects `pattern` fields using regex lookaround
     // (e.g. `^(?=.*@).+$`) with a 400 "regex lookaround is not supported" error.
     // Strip those before the schema reaches upstream (9router#1556).
-    const sanitizedParameters = stripUnsupportedRegexPatterns(parameters);
+    const sanitizedParameters = stripRedundantOneOfConstEnum(
+      stripUnsupportedRegexPatterns(parameters)
+    );
 
     // Rewrite in-place to Responses format
     for (const key of Object.keys(tool)) {

open-sse/executors/commandCode.ts

@@ -48,6 +48,21 @@ function recordOrEmpty(value: unknown): JsonRecord {
   return {};
 }
 
+/**
+ * Build the `arguments` field for an assistant tool-call part that Command
+ * Code's /alpha/generate schema REQUIRES (rejects a missing field with
+ * `missing required field 'arguments'`). Valid source values round-trip:
+ *   - object arguments  -> JSON string of the object
+ *   - string arguments  -> the string as-is (already valid JSON)
+ *   - missing / empty / invalid JSON -> "{}" (a valid empty-object string)
+ */
+function toolCallArgumentsString(value: unknown): string {
+  const parsed = recordOrEmpty(value);
+  if (isRecord(value)) return JSON.stringify(parsed);
+  if (typeof value === "string" && value.trim()) return value;
+  return JSON.stringify(parsed);
+}
+
 function normalizeContentText(content: unknown): string {
   if (typeof content === "string") return content;
   return asRecordArray(content)
@@ -244,11 +259,15 @@ function convertMessages(
         const id = stringValue(call.id) || "";
         if (!id || !pairedToolCallIds.has(id)) continue;
         const fn = isRecord(call.function) ? call.function : {};
+        const parsedInput = recordOrEmpty(fn.arguments);
         parts.push({
           type: "tool-call",
           toolCallId: id,
           toolName: stringValue(fn.name) || "",
-          input: recordOrEmpty(fn.arguments),
+          input: parsedInput,
+          // /alpha/generate requires this field on assistant tool-call parts;
+          // a missing one is rejected with `missing required field 'arguments'`.
+          arguments: toolCallArgumentsString(fn.arguments),
         });
       }
 
@@ -420,7 +439,61 @@ type AggregateState = {
   usage: JsonRecord | null;
 };
 
+function firstRecord(record: JsonRecord, keys: readonly string[]): JsonRecord {
+  for (const key of keys) {
+    const value = record[key];
+    if (isRecord(value)) return value;
+  }
+  return {};
+}
+
+function firstNumber(record: JsonRecord, keys: readonly string[]): number | undefined {
+  for (const key of keys) {
+    const value = numberValue(record[key]);
+    if (value !== undefined) return value;
+  }
+  return undefined;
+}
+
+/** Keep earlier finish-step usage when the terminal finish event omits it. */
+function mergeCommandCodeUsage(previous: JsonRecord | null, next: unknown): JsonRecord | null {
+  if (!isRecord(next)) return previous;
+
+  const merged: JsonRecord = { ...(previous || {}), ...next };
+  for (const key of [
+    "inputTokenDetails",
+    "input_token_details",
+    "input_tokens_details",
+    "prompt_tokens_details",
+    "outputTokenDetails",
+    "output_token_details",
+    "output_tokens_details",
+    "completion_tokens_details",
+    "reasoningTokenDetails",
+    "reasoning_token_details",
+  ]) {
+    const before = isRecord(previous?.[key]) ? previous[key] : {};
+    const after = isRecord(next[key]) ? next[key] : {};
+    if (Object.keys(before).length > 0 || Object.keys(after).length > 0) {
+      merged[key] = { ...before, ...after };
+    }
+  }
+  return merged;
+}
+
+function rememberCommandCodeUsage(state: AggregateState, event: JsonRecord): void {
+  const usage =
+    event.type === "finish-step"
+      ? (event.usage ?? event.totalUsage)
+      : (event.totalUsage ?? event.usage);
+  state.usage = mergeCommandCodeUsage(state.usage, usage);
+}
+
 function applyEventToAggregate(event: JsonRecord, state: AggregateState): void {
+  // Some Command Code protocol revisions attach usage to the terminal payload
+  // without preserving the event type. Capture it before event-specific handling.
+  rememberCommandCodeUsage(state, event);
+
   switch (event.type) {
     case "text-delta":
       state.content += stringValue(event.text) || "";
@@ -440,9 +513,10 @@ function applyEventToAggregate(event: JsonRecord, state: AggregateState): void {
       });
       break;
     }
+    case "finish-step":
+      break;
     case "finish":
       state.finishReason = mapFinishReason(event.finishReason);
-      state.usage = isRecord(event.totalUsage) ? event.totalUsage : null;
       break;
   }
 }
@@ -460,30 +534,72 @@ function applyEventToAggregateOrThrow(event: JsonRecord, state: AggregateState):
 
 function usageFromCommandCode(usage: JsonRecord | null) {
   if (!usage) return undefined;
-  const details = isRecord(usage.inputTokenDetails) ? usage.inputTokenDetails : {};
-  const cacheRead = numberValue(details.cacheReadTokens) || 0;
-  const noCache = numberValue(details.noCacheTokens) || 0;
+  const inputDetails = firstRecord(usage, [
+    "inputTokenDetails",
+    "input_token_details",
+    "input_tokens_details",
+    "prompt_tokens_details",
+  ]);
+  const outputDetails = firstRecord(usage, [
+    "outputTokenDetails",
+    "output_token_details",
+    "output_tokens_details",
+    "completion_tokens_details",
+  ]);
+  const reasoningDetails = firstRecord(usage, [
+    "reasoningTokenDetails",
+    "reasoning_token_details",
+    "reasoning_tokens_details",
+  ]);
+  const cacheRead =
+    firstNumber(usage, [
+      "cachedInputTokens",
+      "cached_input_tokens",
+      "cacheReadInputTokens",
+      "cache_read_input_tokens",
+      "cacheReadTokens",
+      "cache_read_tokens",
+      "cached_tokens",
+    ]) ??
+    firstNumber(inputDetails, [
+      "cachedTokens",
+      "cached_tokens",
+      "cacheReadTokens",
+      "cache_read_tokens",
+    ]);
+  const noCache = firstNumber(inputDetails, ["noCacheTokens", "no_cache_tokens"]);
   // Command Code's totalUsage.inputTokens is the FULL prompt total and already
   // includes the cached portion (noCacheTokens + cacheReadTokens = inputTokens),
   // so we must NOT add cacheRead back — that would double-count. There is no
   // cache-write field in the upstream payload, so cache creation stays unset.
-  const inputTokens = numberValue(usage.inputTokens) || 0;
-  const prompt = inputTokens;
-  const completion = numberValue(usage.outputTokens) || 0;
+  const prompt =
+    firstNumber(usage, ["inputTokens", "input_tokens", "promptTokens", "prompt_tokens"]) ??
+    (noCache ?? 0) + (cacheRead ?? 0);
+  const reasoning =
+    firstNumber(usage, ["reasoningTokens", "reasoning_tokens"]) ??
+    firstNumber(outputDetails, ["reasoningTokens", "reasoning_tokens"]) ??
+    firstNumber(reasoningDetails, ["reasoningTokens", "reasoning_tokens"]);
+  const textOutput = firstNumber(outputDetails, ["textTokens", "text_tokens"]);
+  const completion =
+    firstNumber(usage, [
+      "outputTokens",
+      "output_tokens",
+      "completionTokens",
+      "completion_tokens",
+    ]) ?? (textOutput ?? 0) + (reasoning ?? 0);
+  const total = firstNumber(usage, ["totalTokens", "total_tokens"]) ?? prompt + completion;
   const result: JsonRecord = {
     prompt_tokens: prompt,
+    prompt_tokens_details: { cached_tokens: cacheRead ?? 0 },
     completion_tokens: completion,
-    total_tokens: prompt + completion,
+    completion_tokens_details: { reasoning_tokens: reasoning ?? 0 },
+    total_tokens: total,
   };
   // Surface the cache breakdown as informational fields so logUsage prints
   // `| cache_read=X | no_cache=Y` and appendRequestLog persists them. These are
   // NOT added to prompt_tokens (already included) — metering stays accurate.
-  if (cacheRead > 0) result.cache_read_input_tokens = cacheRead;
-  if (noCache > 0) result.no_cache_tokens = noCache;
-  // Keep reasoning_token_details (reasoningTokens) when present so stream.ts's
-  // extractUsage can surface it as reasoning_tokens.
-  const reasoningDetails = isRecord(usage.reasoningTokenDetails) ? usage.reasoningTokenDetails : {};
-  const reasoning = numberValue(reasoningDetails.reasoningTokens);
+  if (cacheRead !== undefined && cacheRead > 0) result.cache_read_input_tokens = cacheRead;
+  if (noCache !== undefined && noCache > 0) result.no_cache_tokens = noCache;
   if (reasoning !== undefined && reasoning > 0) result.reasoning_tokens = reasoning;
   return result;
 }
@@ -523,6 +639,7 @@ function createStreamResponse(
 
       const emitEvent = (event: unknown) => {
         if (!isRecord(event) || closed) return;
+        rememberCommandCodeUsage(state, event);
         if (!sentRole) {
           sentRole = true;
           controller.enqueue(sse(chatCompletionChunk(id, model, { role: "assistant" })));
@@ -562,9 +679,10 @@ function createStreamResponse(
           }
           case "reasoning-end":
             break;
+          case "finish-step":
+            break;
           case "finish": {
             state.finishReason = mapFinishReason(event.finishReason);
-            state.usage = isRecord(event.totalUsage) ? event.totalUsage : null;
             controller.enqueue(sse(chatCompletionChunk(id, model, {}, state.finishReason)));
             // Emit a standards-compliant usage-only chunk (choices: []) before
             // [DONE] when upstream reported usage. stream.ts's extractUsage

open-sse/executors/deepseek-web.ts

@@ -515,7 +515,6 @@ export function messagesToPrompt(
   historyWindow = 0
 ): string {
   if (messages.length === 0) return "";
-
   const systemParts: string[] = [];
   const conversation: Array<{ role: string; text: string }> = [];
   const callNameById = new Map<string, string>();
@@ -527,8 +526,9 @@ export function messagesToPrompt(
     } else if (m.role === "user" || m.role === "assistant") {
       if (text) conversation.push({ role: m.role, text });
       if (m.role === "user") lastUserContent = text;
-      const calls = Array.isArray((m as { tool_calls?: unknown }).tool_calls)
-        ? (m as { tool_calls: Array<{ id?: string; function?: { name?: string } }> }).tool_calls
+      const toolCalls = (m as { tool_calls?: unknown }).tool_calls;
+      const calls = Array.isArray(toolCalls)
+        ? (toolCalls as Array<{ id?: string; function?: { name?: string } }>)
         : [];
       for (const c of calls) {
         if (c?.id && typeof c.function?.name === "string") callNameById.set(c.id, c.function.name);

open-sse/executors/default.ts

@@ -61,12 +61,11 @@ import {
 } from "@/lib/providers/validation/urlHelpers";
 import { forwardOpencodeClientHeaders } from "../utils/opencodeHeaders.ts";
 import { resolveZaiUrl } from "./default/zaiFormatOverride.ts";
+import { normalizePoolConfig } from "./default/poolConfig.ts";
 import { acquireNvidiaConcurrencySlot } from "./default/nvidiaConcurrencyGate.ts";
 import { resolveAlibabaProviderBaseUrl } from "@/shared/constants/alibabaProviderRegions";
 import { usesCcWireImage } from "../services/ccWireImageBuiltins.ts";
 
-import type { PoolConfig } from "../services/sessionPool/types.ts";
-
 const NVIDIA_TOOL_CALL_ID_PATTERN = /^[A-Za-z0-9]{9}$/;
 
 function normalizeNvidiaToolCallId(id: unknown): unknown {
@@ -146,7 +145,7 @@ export class DefaultExecutor extends BaseExecutor {
     super(provider, PROVIDERS[provider] || PROVIDERS.openai);
     const registryEntry = getRegistryEntry(provider);
     if (registryEntry?.poolConfig) {
-      this.poolConfig = registryEntry.poolConfig as PoolConfig;
+      this.poolConfig = normalizePoolConfig(registryEntry.poolConfig) ?? undefined;
     }
   }
 

open-sse/executors/default/poolConfig.ts

@@ -0,0 +1,33 @@
+import type { PoolConfig } from "../../services/sessionPool/types.ts";
+
+export function normalizePoolConfig(value: Record<string, unknown>): PoolConfig | null {
+  const {
+    minSessions,
+    maxSessions,
+    cooldownBase,
+    cooldownMax,
+    cooldownJitter,
+    requestTimeout,
+    requestJitter,
+  } = value;
+  if (
+    typeof minSessions !== "number" ||
+    typeof maxSessions !== "number" ||
+    typeof cooldownBase !== "number" ||
+    typeof cooldownMax !== "number" ||
+    typeof cooldownJitter !== "number" ||
+    typeof requestTimeout !== "number" ||
+    typeof requestJitter !== "number"
+  ) {
+    return null;
+  }
+  return {
+    minSessions,
+    maxSessions,
+    cooldownBase,
+    cooldownMax,
+    cooldownJitter,
+    requestTimeout,
+    requestJitter,
+  };
+}

open-sse/executors/duckduckgo-web.ts

@@ -137,8 +137,23 @@ interface DuckDuckGoModelCapabilities {
   reasoningEffort: string | null;
 }
 
+type DuckDuckGoRequestMessage = Record<string, unknown> & {
+  role: string;
+  content: unknown;
+};
+
 let durablePublicKey: JsonWebKey | null = null;
 
+export function normalizeDuckDuckGoMessages(value: unknown): DuckDuckGoRequestMessage[] {
+  if (!Array.isArray(value)) return [];
+  return value.flatMap((message) => {
+    if (!message || typeof message !== "object" || Array.isArray(message)) return [];
+    const record = message as Record<string, unknown>;
+    if (typeof record.role !== "string") return [];
+    return [{ ...record, role: record.role, content: record.content }];
+  });
+}
+
 function extractDuckDuckGoContent(data: unknown): string {
   if (!data || typeof data !== "object") return "";
   const record = data as Record<string, unknown>;
@@ -251,11 +266,14 @@ export function normalizeDuckDuckGoModel(model: string | undefined): string {
 }
 
 function getDuckDuckGoModelCapabilities(model: string): DuckDuckGoModelCapabilities {
-  // Per duckchat/v1/models (2026-07-22): claude-haiku-4-5 and gpt-oss-120b take a "low"
-  // reasoningEffort on the free tier; the others omit it (duck.ai applies its own default).
+  // `reasoningEffort` is REQUIRED on every duckchat/v1/chat request. Omitting it
+  // returns 400 ERR_BAD_REQUEST — A/B verified live against duck.ai with an
+  // otherwise byte-identical payload (200 with the field, 400 without, repeated).
+  // The live duck.ai bundle always sends one, so there is no "let the server
+  // pick a default" path any more.
   if (model === "claude-haiku-4-5") return { reasoningEffort: "low" };
   if (model === "tinfoil/gpt-oss-120b") return { reasoningEffort: "low" };
-  return { reasoningEffort: null };
+  return { reasoningEffort: "none" };
 }
 
 function extractDuckDuckGoFeVersion(html: string): string | null {
@@ -353,7 +371,6 @@ export class DuckDuckGoWebExecutor extends BaseExecutor {
   }
 
   private warmed = false;
-  private seeded = false;
   private feVersion = DEFAULT_FE_VERSION;
   private pendingVqdHash1: string | null = null;
   private readonly cookieJar = new Map<string, string>();
@@ -440,14 +457,12 @@ export class DuckDuckGoWebExecutor extends BaseExecutor {
     const { model, body, stream, signal, upstreamExtraHeaders } = input;
     const upstreamModel = normalizeDuckDuckGoModel(model);
     const bodyObj = (body || {}) as Record<string, unknown>;
-    const rawMessages = Array.isArray((body as { messages?: unknown[] } | null)?.messages)
-      ? ((body as { messages: unknown[] }).messages as Array<Record<string, unknown>>)
-      : [];
+    const rawMessages = normalizeDuckDuckGoMessages(bodyObj.messages);
     const { hasTools, requestedTools, effectiveMessages } = prepareToolMessages(
       bodyObj,
       rawMessages
     );
-    const messages = effectiveMessages as Array<Record<string, unknown>>;
+    const messages = effectiveMessages;
     const isStreaming = stream !== false;
     const upstreamHeaders = upstreamExtraHeaders || {};
 
@@ -561,7 +576,12 @@ export class DuckDuckGoWebExecutor extends BaseExecutor {
       }
 
       await this.warmSession(mergedSignal);
-      await this.seedChallengeChain(upstreamModel, mergedSignal);
+      // NOTE: the throwaway "seed" chat POST that used to run here has been removed.
+      // It existed to coax a usable challenge out of the upstream while the solver
+      // was broken; now that the solver reproduces a real browser's probe vectors
+      // exactly, the first real request succeeds on its own. Keeping it only doubled
+      // the chat calls per user request against an IP-rate-limited endpoint, which
+      // showed up as spurious 429 ERR_RATE_LIMIT.
       const vqdHeaders = await this.acquireAuthHeaders(mergedSignal);
       if (!vqdHeaders.vqd4 && !vqdHeaders.vqdHash1) {
         clearTimeout(timeout);
@@ -770,41 +790,6 @@ export class DuckDuckGoWebExecutor extends BaseExecutor {
     );
   }
 
-  private async seedChallengeChain(model: string, signal: AbortSignal): Promise<void> {
-    if (this.seeded || signal.aborted) return;
-    this.seeded = true;
-    const seedMessages = [{ role: "user", content: "hi" }];
-    const previousPending = this.pendingVqdHash1;
-    try {
-      const vqdHeaders = await this.acquireAuthHeaders(signal);
-      if (!vqdHeaders.vqd4 && !vqdHeaders.vqdHash1) {
-        this.pendingVqdHash1 = previousPending;
-        return;
-      }
-      const response = await fetch(CHAT_URL, {
-        method: "POST",
-        headers: mergeHeadersCaseInsensitive(this.buildRequestHeaders(), {
-          Accept: "text/event-stream",
-          "Content-Type": "application/json",
-          "x-ddg-journey-id": randomUUID().replaceAll("-", ""),
-          "x-fe-signals": makeDuckDuckGoFeSignals(),
-          "x-fe-version": this.feVersion,
-          ...(vqdHeaders.vqd4 ? { "x-vqd-4": vqdHeaders.vqd4 } : {}),
-          ...(vqdHeaders.vqdHash1 ? { "x-vqd-hash-1": vqdHeaders.vqdHash1 } : {}),
-        }),
-        body: JSON.stringify(buildDuckDuckGoPayload(model, seedMessages, false)),
-        signal,
-      });
-      this.rememberResponseCookies(response);
-      if (response.ok) this.rememberChallengeHeader(response);
-      else this.pendingVqdHash1 = previousPending;
-      await response.body?.cancel().catch(() => {});
-    } catch (error) {
-      void error;
-      this.pendingVqdHash1 = previousPending;
-    }
-  }
-
   private async processResponse(
     response: Response,
     streaming: boolean,

open-sse/executors/duckduckgo-web/challenge.ts

@@ -5,12 +5,38 @@ import { createHash } from "node:crypto";
 import vm from "node:vm";
 import { parseFragment, serialize } from "parse5";
 
+// WARNING: the contents of this template literal are NOT TypeScript — they are plain
+// script-mode JavaScript executed via `vm.runInContext`. `vm.runInContext` compiles in
+// script (non-module) mode, so an `export` keyword anywhere in here is a hard
+// SyntaxError that kills the whole solver. A refactor that mass-added `export` to the
+// five `function` declarations below silently broke every DuckDuckGo chat request
+// (solve threw -> unsolved challenge sent -> HTTP 418 ERR_CHALLENGE). Do not add
+// `export`/`import` to this string; `duckduckgo-challenge-split.test.ts` guards this.
 export const CHALLENGE_STUBS = String.raw`
 var __ua = __DDG_REAL_UA__;
 var __HTML_LOOKUP = __DDG_HTML_LOOKUP__;
-export function __makeHtmlElement(tag) {
+// Browser-fidelity shims for the DDG "am I a real browser" probes.
+// In a browser every built-in stringifies as native code; under a plain vm
+// context the user-land re-declarations below would otherwise leak their source.
+function __nativeFn(fn, name){
+  Object.defineProperty(fn, 'name', { value: name, configurable: true });
+  fn.toString = function(){ return 'function ' + name + '() { [native code] }'; };
+  return fn;
+}
+__nativeFn(parseInt, 'parseInt');
+__nativeFn(parseFloat, 'parseFloat');
+__nativeFn(isNaN, 'isNaN');
+__nativeFn(encodeURIComponent, 'encodeURIComponent');
+__nativeFn(decodeURIComponent, 'decodeURIComponent');
+// NOTE: do NOT seal Math. Real Chromium reports Object.isSealed(Math) === false,
+// and at least one challenge variant probes exactly that; sealing it here made
+// the vector differ from the browser by one and failed the challenge.
+function __makeHtmlElement(tag) {
   var state = { _innerHTML: '', _qsaCount: 0, _cssText: '' };
-  var el = {
+  // Instantiate against the real per-tag constructor so
+  // document.createElement('div') instanceof HTMLDivElement holds.
+  var el = Object.create(__ctorForTag(tag).prototype);
+  Object.assign(el, {
     tagName: String(tag).toUpperCase(), nodeName: String(tag).toUpperCase(), nodeType: 1,
     children: [], childNodes: [], classList: [], dataset: {},
     offsetWidth: 1, offsetHeight: 1, clientWidth: 1, clientHeight: 1, scrollHeight: 1, scrollWidth: 1,
@@ -19,9 +45,9 @@ export function __makeHtmlElement(tag) {
     getAttribute: function(a){ if(a==='srcdoc') return state._srcdoc||''; return null; },
     hasAttribute: function(){ return false; }, appendChild: function(c){ return c; }, removeChild: function(c){ return c; },
     addEventListener: function(){}, removeEventListener: function(){}, querySelector: function(){ return null; },
-    querySelectorAll: function(s){ if (s === '*') { var arr = []; arr.length = state._qsaCount; return arr; } return []; },
+    querySelectorAll: function(s){ if (s === '*') { return __makeNodeList(state._qsaCount); } return __makeNodeList(0); },
     cloneNode: function(){ return __makeHtmlElement(tag); }
-  };
+  });
   Object.defineProperty(el, 'style', { value: new Proxy({}, { set: function(t, k, v){ t[k] = v; if (k === 'cssText') state._cssText = String(v); return true; }, get: function(t, k){ if (k === 'cssText') return state._cssText; return t[k] || ''; } }), enumerable: true, configurable: true });
   Object.defineProperty(el, 'innerHTML', { get: function(){ return state._innerHTML; }, set: function(v){ var key = String(v); var entry = __HTML_LOOKUP && __HTML_LOOKUP[key]; if (entry) { state._innerHTML = String(entry.html); state._qsaCount = entry.count|0; } else { state._innerHTML = key; state._qsaCount = 0; } }, enumerable: true, configurable: true });
   Object.defineProperty(el, 'outerHTML', { get: function(){ return '<' + tag + '>' + state._innerHTML + '</' + tag + '>'; }, enumerable: true });
@@ -30,7 +56,7 @@ export function __makeHtmlElement(tag) {
   Object.defineProperty(el, 'contentDocument', { get: function(){ return __ifDoc; }, enumerable: true });
   return el;
 }
-export function __mkObj(name, base) {
+function __mkObj(name, base) {
   base = base || {};
   return new Proxy(base, {
     get: function(t, k) {
@@ -54,18 +80,105 @@ export function __mkObj(name, base) {
     has: function(t, k){ return k in t; }, set: function(t, k, v){ t[k] = v; return true; }
   });
 }
-export function __parseCssDisplay(cssText){ if(!cssText) return ''; var m = String(cssText).match(/(?:^|;)\\s*display\\s*:\\s*([^;]+)/i); return m ? String(m[1]).trim() : ''; }
-export function __getComputedStyle(el){ var cssText = el && el.style && el.style.cssText || ''; var display = __parseCssDisplay(cssText); return { getPropertyValue: function(name){ if(String(name).toLowerCase()==='display') return display; return ''; }, cssText: cssText, display: display }; }
+function __parseCssDisplay(cssText){ if(!cssText) return ''; var m = String(cssText).match(/(?:^|;)\s*display\s*:\s*([^;]+)/i); return m ? String(m[1]).trim() : ''; }
+function __getComputedStyle(el){ var cssText = el && el.style && el.style.cssText || ''; var display = __parseCssDisplay(cssText); return { getPropertyValue: function(name){ if(String(name).toLowerCase()==='display') return display; return ''; }, cssText: cssText, display: display }; }
 var __ifMeta = __mkObj('meta', { getAttribute: function(a){ return a==='content' ? "default-src 'none'; script-src 'unsafe-inline';" : null; }, hasAttribute: function(a){ return a==='content'; }, tagName: 'META', nodeName: 'META' });
 var __ifDoc = __mkObj('iframeDoc', { querySelector: function(s){ if (s && s.indexOf('Content-Security-Policy') !== -1) return __ifMeta; if (s === 'meta') return __ifMeta; return null; }, querySelectorAll: function(s){ if (s && s.indexOf('Content-Security-Policy') !== -1) return [__ifMeta]; if (s === 'meta') return [__ifMeta]; return []; }, getElementsByTagName: function(t){ return t && t.toLowerCase()==='meta' ? [__ifMeta] : []; }, body: __mkObj('iframeBody'), head: __mkObj('iframeHead'), documentElement: __mkObj('iframeRoot'), createElement: function(){ return __mkObj('elem', {setAttribute:function(){}, appendChild:function(){}, removeChild:function(){}, getAttribute:function(){return null;}, hasAttribute:function(){return false;}}); }, cookie: '', readyState: 'complete' });
 var __iframeEl = __mkObj('iframe', { contentDocument: __ifDoc, contentWindow: __mkObj('iframeWin', { document: __ifDoc, top: undefined, parent: undefined }), document: __ifDoc, getAttribute: function(a){ if (a==='sandbox') return 'allow-scripts allow-same-origin'; if (a==='srcdoc') return ''; if (a==='id') return 'jsa'; return null; }, hasAttribute: function(a){ return a==='sandbox'||a==='id'; }, tagName: 'IFRAME', nodeName: 'IFRAME', id: 'jsa' });
-var document = __mkObj('document', { querySelector: function(s){ if (s === '#jsa') return __iframeEl; if (s && s.indexOf('Content-Security-Policy') !== -1) return __ifMeta; return null; }, querySelectorAll: function(s){ if (s === '#jsa') return [__iframeEl]; if (s && s.indexOf('Content-Security-Policy') !== -1) return [__ifMeta]; return []; }, getElementById: function(id){ return id==='jsa' ? __iframeEl : null; }, getElementsByTagName: function(t){ if(t&&t.toLowerCase()==='iframe') return [__iframeEl]; return []; }, getElementsByClassName: function(){ return []; }, body: __mkObj('body', {appendChild:function(){}, removeChild:function(){}, querySelector:function(s){return s==='#jsa'?__iframeEl:null;}, querySelectorAll:function(s){return s==='#jsa'?[__iframeEl]:[];}}), head: __mkObj('head'), documentElement: __mkObj('root'), createElement: function(tag){ return __makeHtmlElement(tag||'div'); }, createTextNode: function(t){ return {nodeType:3, nodeValue:String(t||''), textContent:String(t||'')}; }, cookie: '', readyState: 'complete', title: '', addEventListener: function(){}, removeEventListener: function(){} });
+// document.body keeps a LIVE children collection: challenges append a node and
+// assert body.children.length grew by exactly 1, then remove it again.
+var __bodyKids = [];
+Object.defineProperty(__bodyKids, 'constructor', { value: HTMLCollection, enumerable: false, configurable: true });
+var __body = __mkObj('body', {
+  appendChild: function(c){ __bodyKids.push(c); return c; },
+  removeChild: function(c){ var i = __bodyKids.indexOf(c); if (i !== -1) __bodyKids.splice(i, 1); return c; },
+  contains: function(c){ return __bodyKids.indexOf(c) !== -1; },
+  querySelector: function(s){ return s === '#jsa' ? __iframeEl : null; },
+  querySelectorAll: function(s){ return s === '#jsa' ? [__iframeEl] : __makeNodeList(0); },
+  children: __bodyKids, childNodes: __bodyKids,
+  tagName: 'BODY', nodeName: 'BODY', nodeType: 1
+});
+var document = __mkObj('document', { querySelector: function(s){ if (s === '#jsa') return __iframeEl; if (s && s.indexOf('Content-Security-Policy') !== -1) return __ifMeta; return null; }, querySelectorAll: function(s){ if (s === '#jsa') return [__iframeEl]; if (s && s.indexOf('Content-Security-Policy') !== -1) return [__ifMeta]; return __makeNodeList(__bodyKids.length + 3); }, getElementById: function(id){ return id==='jsa' ? __iframeEl : null; }, getElementsByTagName: function(t){ if(t&&t.toLowerCase()==='iframe') return [__iframeEl]; return []; }, getElementsByClassName: function(){ return []; }, body: __body, head: __mkObj('head'), documentElement: __mkObj('root'), createElement: function(tag){ return __makeHtmlElement(tag||'div'); }, createTextNode: function(t){ return {nodeType:3, nodeValue:String(t||''), textContent:String(t||'')}; }, cookie: '', readyState: 'complete', title: '', addEventListener: function(){}, removeEventListener: function(){} });
   var window = __mkObj('window', { document: document, __DDG_BE_VERSION__: 1, __DDG_FE_CHAT_HASH__: 1, navigator: __mkObj('navigator', { userAgent: __ua, webdriver: false, language: 'en-US', languages: ['en-US','en'], platform: 'Linux x86_64', vendor: 'Google Inc.', appVersion: '5.0 (X11)', cookieEnabled: true, onLine: true, hardwareConcurrency: 8, deviceMemory: 8 }), innerWidth: 1280, innerHeight: 800, outerWidth: 1280, outerHeight: 800, devicePixelRatio: 1, screen: __mkObj('screen', { width:1920, height:1080, availWidth:1920, availHeight:1080, colorDepth:24, pixelDepth:24 }), location: __mkObj('location', { href:'https://duck.ai/', origin:'https://duck.ai', host:'duck.ai', hostname:'duck.ai', protocol:'https:', pathname:'/' }), performance: __mkObj('perf', { now: function(){ return 0; }, timeOrigin: 0 }), history: __mkObj('history', { length: 1, state: null }), addEventListener: function(){}, removeEventListener: function(){}, dispatchEvent: function(){return true;}, setTimeout: function(fn){ try{fn();}catch(e){} return 0; }, clearTimeout: function(){}, hasOwnProperty: function(k){ if (k==='__DDG_BE_VERSION__'||k==='__DDG_FE_CHAT_HASH__') return true; return Object.prototype.hasOwnProperty.call(this,k); } });
 window.top = window; window.self = window; window.window = window; window.parent = window; window.globalThis = window;
+// Object.prototype.toString.call(window) must be "[object Window]".
+try { window[Symbol.toStringTag] = 'Window'; } catch (e) {}
+// In a browser a sloppy-mode function called with no receiver gets the global
+// object, and challenges assert (function(){return this;})() === window.
+// In a vm context that is the context's own global, so alias it to window.
+try {
+  var __g = (function(){ return this; })();
+  if (__g && __g !== window) {
+    Object.defineProperty(__g, Symbol.toStringTag, { value: 'Window', configurable: true });
+    // Copy by VALUE, not via accessors. Two reasons:
+    //  1) the var top/self/navigator/... declarations further down are hoisted,
+    //     so those names already exist on the vm global and an "in" guard would
+    //     skip them, leaving window.navigator undefined;
+    //  2) accessors closing over the window binding would recurse once it is
+    //     rebound to __g below.
+    // The stub window is static, so a value copy is equivalent.
+    var __winStub = window;
+    for (var __k in __winStub) {
+      try { __g[__k] = __winStub[__k]; } catch (e) {}
+    }
+    // hasOwnProperty is probed for the __DDG_* markers; keep the stub's version.
+    try { __g.hasOwnProperty = function(k){ return __winStub.hasOwnProperty(k); }; } catch (e) {}
+    window = __g;
+    window.top = window; window.self = window; window.window = window; window.parent = window; window.globalThis = window;
+  }
+} catch (e) {}
 var top = window, self = window, parent = window, navigator = window.navigator, location = window.location, screen = window.screen, performance = window.performance, history = window.history;
 var __R = null, __E = null;
-export function __HTMLClass(name){ var c = function(){}; c.prototype = __mkObj(name+'.proto'); return c; }
-var HTMLElement = __HTMLClass('HTMLElement'), HTMLDivElement = __HTMLClass('HTMLDivElement'), HTMLIFrameElement = __HTMLClass('HTMLIFrameElement'), HTMLDocument = __HTMLClass('HTMLDocument'), Document = __HTMLClass('Document'), Element = __HTMLClass('Element'), Node = __HTMLClass('Node'), Window = __HTMLClass('Window'), Event = __HTMLClass('Event'), MouseEvent = __HTMLClass('MouseEvent'), KeyboardEvent = __HTMLClass('KeyboardEvent'), TouchEvent = __HTMLClass('TouchEvent'), XMLHttpRequest = __HTMLClass('XMLHttpRequest'), WebSocket = __HTMLClass('WebSocket'), Image = __HTMLClass('Image'), FormData = __HTMLClass('FormData'), Blob = __HTMLClass('Blob'), File = __HTMLClass('File'), FileReader = __HTMLClass('FileReader'), URL = __HTMLClass('URL'), URLSearchParams = __HTMLClass('URLSearchParams'), Headers = __HTMLClass('Headers'), Request = __HTMLClass('Request'), Response = __HTMLClass('Response');
+// Real DOM constructor chain. Some DDG challenge variants assert
+// HTMLDivElement.prototype instanceof HTMLElement and
+// HTMLElement.prototype instanceof Element, so these cannot be flat
+// unrelated stubs — the prototype links have to be real.
+function __DomClass(name, parent){
+  var c = function(){};
+  if (parent) c.prototype = Object.create(parent.prototype);
+  c.prototype.constructor = c;
+  Object.defineProperty(c, 'name', { value: name, configurable: true });
+  c.toString = function(){ return 'function ' + name + '() { [native code] }'; };
+  return c;
+}
+var EventTarget = __DomClass('EventTarget', null);
+var Node = __DomClass('Node', EventTarget);
+var Element = __DomClass('Element', Node);
+var HTMLElement = __DomClass('HTMLElement', Element);
+var HTMLDivElement = __DomClass('HTMLDivElement', HTMLElement);
+var HTMLIFrameElement = __DomClass('HTMLIFrameElement', HTMLElement);
+var HTMLLIElement = __DomClass('HTMLLIElement', HTMLElement);
+var HTMLUnknownElement = __DomClass('HTMLUnknownElement', HTMLElement);
+var Document = __DomClass('Document', Node);
+var HTMLDocument = __DomClass('HTMLDocument', Document);
+var NodeList = __DomClass('NodeList', null);
+var HTMLCollection = __DomClass('HTMLCollection', null);
+// Map a tag name to the constructor a browser would use, so
+// document.createElement('div') instanceof HTMLDivElement holds.
+function __ctorForTag(tag){
+  var t = String(tag||'div').toLowerCase();
+  if (t === 'div') return HTMLDivElement;
+  if (t === 'iframe') return HTMLIFrameElement;
+  if (t === 'li') return HTMLLIElement;
+  return HTMLElement;
+}
+// A NodeList-like: array-shaped but NOT a real Array, with .constructor.name
+// === 'NodeList' — challenges check both !Array.isArray(x) and the ctor name.
+function __makeNodeList(length){
+  var nl = Object.create(NodeList.prototype);
+  var n = length|0;
+  for (var i = 0; i < n; i++) nl[i] = __makeHtmlElement('div');
+  Object.defineProperty(nl, 'length', { value: n, enumerable: false, configurable: true });
+  nl.item = function(i){ return this[i] || null; };
+  nl.forEach = function(fn, thisArg){ for (var i = 0; i < n; i++) fn.call(thisArg, this[i], i, this); };
+  nl[Symbol.iterator] = function(){ var i = 0, self = this; return { next: function(){ return i < n ? { value: self[i++], done: false } : { value: undefined, done: true }; } }; };
+  return nl;
+}
+function __HTMLClass(name){ var c = function(){}; c.prototype = __mkObj(name+'.proto'); return c; }
+// NOTE: HTMLElement / HTMLDivElement / HTMLIFrameElement / Element / Node /
+// Document / HTMLDocument / NodeList are defined above via __DomClass with a
+// REAL prototype chain — do not redeclare them here or the instanceof probes break.
+var Window = __HTMLClass('Window'), Event = __HTMLClass('Event'), MouseEvent = __HTMLClass('MouseEvent'), KeyboardEvent = __HTMLClass('KeyboardEvent'), TouchEvent = __HTMLClass('TouchEvent'), XMLHttpRequest = __HTMLClass('XMLHttpRequest'), WebSocket = __HTMLClass('WebSocket'), Image = __HTMLClass('Image'), FormData = __HTMLClass('FormData'), Blob = __HTMLClass('Blob'), File = __HTMLClass('File'), FileReader = __HTMLClass('FileReader'), URL = __HTMLClass('URL'), URLSearchParams = __HTMLClass('URLSearchParams'), Headers = __HTMLClass('Headers'), Request = __HTMLClass('Request'), Response = __HTMLClass('Response');
 var fetch = function(){ return Promise.resolve(__mkObj('resp', {ok:true, status:200, json:function(){return Promise.resolve({});}, text:function(){return Promise.resolve('');}})); };
 var getComputedStyle = __getComputedStyle;
 `;
@@ -90,9 +203,16 @@ export function buildHtmlLookup(js: string): Record<string, { html: string; coun
     if (seen.has(html)) continue;
     seen.add(html);
     const fragment = parseFragment(html);
+    // `count` backs `element.querySelectorAll('*').length` for an element whose
+    // innerHTML is `html`. `querySelectorAll('*')` on a container returns its
+    // DESCENDANTS, and `countHtmlElements` already excludes the `#document-fragment`
+    // root, so the fragment's element count IS the descendant count. The former
+    // `- 1` undercounted by one (verified against a real browser: for
+    // `<li><div></li><li></div` Chromium reports 3, this returned 2), which
+    // corrupted every probe that multiplies by that length.
     lookup[html] = {
       html: serialize(fragment),
-      count: Math.max(0, countHtmlElements(fragment) - 1),
+      count: countHtmlElements(fragment),
     };
   }
   return lookup;
@@ -102,14 +222,33 @@ export function sha256Base64(value: string): string {
   return createHash("sha256").update(value, "utf8").digest("base64");
 }
 
+// Shape of the object a DDG challenge program resolves to.
 type DuckDuckGoChallengeResult = {
   client_hashes?: unknown;
+  meta?: unknown;
   [key: string]: unknown;
 };
 
+/**
+ * Origin the solved challenge claims to come from. The duck.ai frontend stamps
+ * `meta.origin` with its own origin and the upstream cross-checks it.
+ */
+export const DUCKDUCKGO_CHALLENGE_ORIGIN = "https://duck.ai";
+
+/**
+ * `meta.stack` mimics the frontend's captured Error stack. The upstream only
+ * requires a plausible stack that points at the duck.ai bundle — verified by
+ * ablation: a generic bundle path is accepted, omitting the field is not.
+ */
+function buildChallengeStack(origin: string, bundlePath: string): string {
+  const url = `${origin}${bundlePath}`;
+  return `Error\nat l (${url}:2:1695625)\nat async ${url}:2:1519117`;
+}
+
 export async function solveDuckDuckGoChallenge(
   challenge: string,
-  userAgent: string
+  userAgent: string,
+  options: { origin?: string; bundlePath?: string } = {}
 ): Promise<string> {
   // SECURITY NOTE: This function executes base64-decoded JavaScript from duck.ai via vm.runInContext.
   // The challenge code is upstream-supplied (supply-chain surface). It is sandboxed with a 5s timeout
@@ -121,14 +260,31 @@ export async function solveDuckDuckGoChallenge(
   );
   const context = vm.createContext({});
   vm.runInContext(stubs, context, { timeout: 5000 });
+  const startedAt = Date.now();
   const result = (await vm.runInContext(js, context, {
     timeout: 5000,
   })) as DuckDuckGoChallengeResult;
+  const elapsedMs = Date.now() - startedAt;
   const clientHashes = Array.isArray(result.client_hashes) ? result.client_hashes : [];
   if (clientHashes.length === 0)
     throw new Error("DuckDuckGo challenge returned empty client_hashes");
   clientHashes[0] = userAgent;
   result.client_hashes = clientHashes.map((hash) => sha256Base64(String(hash)));
+
+  // The real frontend augments the challenge's own `meta` with origin / stack /
+  // duration before sending it back. Omitting them yields 418 ERR_CHALLENGE even
+  // when every client_hash is correct (confirmed by capturing a real browser's
+  // x-vqd-hash-1 header, which always carries all three).
+  const origin = options.origin ?? DUCKDUCKGO_CHALLENGE_ORIGIN;
+  const bundlePath = options.bundlePath ?? "/dist/duckai-dist/entry.duckai.js";
+  const meta = (result.meta ?? {}) as Record<string, unknown>;
+  result.meta = {
+    ...meta,
+    origin,
+    stack: buildChallengeStack(origin, bundlePath),
+    duration: String(elapsedMs),
+  };
+
   return Buffer.from(JSON.stringify(result), "utf8").toString("base64");
 }
 

open-sse/executors/gemini-business.ts

@@ -80,16 +80,7 @@ export class GeminiBusinessExecutor extends BaseExecutor {
     // Extract cookies from credentials — check apiKey/cookie first, then
     // try each __Secure-1PSID* key in providerSpecificData individually.
     // A user with only __Secure-1PSID (no PSIDTS) is still valid.
-    const directCookie =
-      readCredentialString(credentials?.apiKey) || readCredentialString(credentials?.cookie);
-    const psid = readProviderSpecificString(credentials?.providerSpecificData, [
-      "__Secure-1PSID",
-      "cookie",
-    ]);
-    const psidts = readProviderSpecificString(credentials?.providerSpecificData, [
-      "__Secure-1PSIDTS",
-    ]);
-    const cookie = directCookie || [psid, psidts].filter(Boolean).join("; ");
+    const cookie = resolveGeminiBusinessCookie(credentials);
 
     if (!cookie) {
       return makeErrorResult(
@@ -380,6 +371,15 @@ function readProviderSpecificString(providerSpecificData: unknown, keys: string[
   return "";
 }
 
+export function resolveGeminiBusinessCookie(credentials: unknown): string {
+  if (!credentials || typeof credentials !== "object") return "";
+  const data = credentials as Record<string, unknown>;
+  const directCookie = readCredentialString(data.apiKey) || readCredentialString(data.cookie);
+  const psid = readProviderSpecificString(data.providerSpecificData, ["__Secure-1PSID", "cookie"]);
+  const psidts = readProviderSpecificString(data.providerSpecificData, ["__Secure-1PSIDTS"]);
+  return directCookie || [psid, psidts].filter(Boolean).join("; ");
+}
+
 function extractTextContent(content: unknown): string {
   if (typeof content === "string") return content.trim();
   if (Array.isArray(content)) {

open-sse/executors/gemini-web.ts

@@ -14,9 +14,13 @@
  */
 
 import { BaseExecutor, type ExecuteInput } from "./base.ts";
-import { sanitizeErrorMessage } from "../utils/error.ts";
+import { buildErrorBody, sanitizeErrorMessage } from "../utils/error.ts";
 import { prepareToolMessages } from "../translator/webTools.ts";
 import { buildToolModeResponse } from "./chatgptWebTools.ts";
+import {
+  checkGeminiWebUnsupportedControls,
+  GEMINI_WEB_UNSUPPORTED_CONTROL_CODE,
+} from "./gemini-web/capabilities.ts";
 
 // ─── Constants ──────────────────────────────────────────────────────────────
 
@@ -406,6 +410,33 @@ export class GeminiWebExecutor extends BaseExecutor {
     const { model, body, stream, credentials, signal, log, onCredentialsRefreshed } = input;
     const requestBody = body as GeminiRequestBody;
 
+    // #9356: fail fast on controls this provider cannot honor (reasoning_effort
+    // above "minimal", forced tool_choice). Runs before the credential check and
+    // before Playwright launches — the request is unservable no matter which
+    // cookie is used, and answering 200 with ordinary prose made agents believe
+    // their reasoning/tool requirements had been met. See ./gemini-web/capabilities.ts.
+    const violation = checkGeminiWebUnsupportedControls(body as Record<string, unknown>);
+    if (violation) {
+      log?.warn?.(
+        "GEMINI-WEB",
+        `Rejected request: "${violation.param}" is not supported by this provider`
+      );
+      return {
+        response: new Response(
+          JSON.stringify(
+            buildErrorBody(400, violation.message, null, {
+              type: "invalid_request_error",
+              code: GEMINI_WEB_UNSUPPORTED_CONTROL_CODE,
+            })
+          ),
+          { status: 400, headers: { "Content-Type": "application/json" } }
+        ),
+        url: GEMINI_URL,
+        headers: {},
+        transformedBody: body,
+      };
+    }
+
     const cookie = resolveGeminiWebCookie(credentials);
     if (!cookie) {
       return {

open-sse/executors/gemini-web/capabilities.ts

@@ -0,0 +1,121 @@
+/**
+ * Request-contract guards for the Gemini Web executor (#9356).
+ *
+ * gemini-web is not an API client. It launches Playwright, types ONE flat
+ * prompt string into the gemini.google.com `.ql-editor` contenteditable,
+ * presses Enter, and captures the first `StreamGenerate` response off the page
+ * (see ../gemini-web.ts). There is no JSON request body on the wire, which
+ * makes two OpenAI controls structurally impossible to honor:
+ *
+ *   • `reasoning_effort` — no field exists to carry a thinking budget. Unlike
+ *     deepseek-web or perplexity-web, which post a real payload and can flip a
+ *     `thinking_enabled` flag or swap the model preference, there is nothing
+ *     here to set.
+ *   • forced `tool_choice` — the tools support gemini-web does have is the
+ *     prompt-emulation shim (`translator/webTools.ts`, #7286): it ASKS the
+ *     model, in prose, to answer with `<tool>{...}</tool>` and parses whatever
+ *     comes back. That is best-effort by construction. "required" / "any" /
+ *     a named function is a GUARANTEE, and a prompt cannot make one.
+ *
+ * Before this module both were accepted and quietly ignored, so an agent got a
+ * 200 with `finish_reason: "stop"`, no `reasoning_content`, and `tool_calls: []`
+ * and concluded its requirements had been met (#9356). Failing the request is
+ * the honest answer: the caller can drop the control, or route to a model that
+ * actually implements it.
+ *
+ * Deliberately NOT rejected — these are already satisfied or already work:
+ *   • `reasoning_effort: "none" | "minimal"` — asking for as little reasoning as
+ *     possible is something a non-thinking provider trivially complies with.
+ *   • `tool_choice: "auto" | "none"` and plain `tools[]` — the #7286 emulation
+ *     path, which several shipped combos depend on (#5240, #8488). Untouched.
+ *
+ * Pure and dependency-free so the whole contract is unit-testable without a
+ * browser.
+ */
+
+/** `error.code` on every compatibility rejection raised here. */
+export const GEMINI_WEB_UNSUPPORTED_CONTROL_CODE = "unsupported_control_for_provider";
+
+/** Effort levels a non-thinking provider already complies with. */
+const SATISFIED_EFFORT_LEVELS = new Set(["none", "minimal"]);
+
+/** `tool_choice` strings that demand a tool call rather than merely offering one. */
+const FORCING_TOOL_CHOICE_STRINGS = new Set(["required", "any"]);
+
+/** `tool_choice: { type }` values that pin the model to a specific/any tool. */
+const FORCING_TOOL_CHOICE_TYPES = new Set(["function", "tool", "any"]);
+
+export interface GeminiWebCapabilityViolation {
+  /** Which request field could not be honored. */
+  param: "reasoning_effort" | "tool_choice";
+  /** Client-facing explanation — already safe to put in a response body. */
+  message: string;
+}
+
+function normalizeString(value: unknown): string | null {
+  return typeof value === "string" && value.trim().length > 0 ? value.trim().toLowerCase() : null;
+}
+
+/**
+ * True when `tool_choice` demands a tool call. Covers the OpenAI strings
+ * ("required"), the Anthropic-flavored ones the translators also emit ("any"),
+ * and the object forms that name a function or force any tool. "auto" / "none"
+ * and every unrecognized shape are treated as non-forcing — this guard only
+ * blocks contracts it is certain gemini-web cannot keep.
+ */
+export function isForcingToolChoice(toolChoice: unknown): boolean {
+  const asString = normalizeString(toolChoice);
+  if (asString) return FORCING_TOOL_CHOICE_STRINGS.has(asString);
+
+  if (toolChoice && typeof toolChoice === "object" && !Array.isArray(toolChoice)) {
+    const type = normalizeString((toolChoice as Record<string, unknown>).type);
+    return type !== null && FORCING_TOOL_CHOICE_TYPES.has(type);
+  }
+
+  return false;
+}
+
+/** True when `reasoning_effort` asks for MORE thinking than "none at all". */
+export function requestsThinkingBudget(reasoningEffort: unknown): boolean {
+  const effort = normalizeString(reasoningEffort);
+  if (effort === null) return false;
+  return !SATISFIED_EFFORT_LEVELS.has(effort);
+}
+
+/**
+ * Inspect an OpenAI-shaped request body for controls gemini-web cannot honor.
+ * Returns the first violation found, or `null` when the request is servable.
+ *
+ * `reasoning_effort` is checked before `tool_choice` only for determinism; a
+ * request carrying both is rejected either way.
+ */
+export function checkGeminiWebUnsupportedControls(
+  body: Record<string, unknown> | null | undefined
+): GeminiWebCapabilityViolation | null {
+  if (!body || typeof body !== "object") return null;
+
+  if (requestsThinkingBudget(body.reasoning_effort)) {
+    return {
+      param: "reasoning_effort",
+      message:
+        'Model provider "gemini-web" does not support "reasoning_effort". It drives the ' +
+        "gemini.google.com web UI through a typed prompt and has no thinking-budget control " +
+        'to set, so any effort above "minimal" would be silently ignored. Remove ' +
+        '"reasoning_effort" (or send "none"/"minimal") or route to a reasoning-capable model.',
+    };
+  }
+
+  if (isForcingToolChoice(body.tool_choice)) {
+    return {
+      param: "tool_choice",
+      message:
+        'Model provider "gemini-web" cannot guarantee a forced tool call. Its tool support is ' +
+        "prompt-emulated — the model is asked to emit a tool block and may answer with prose " +
+        'instead — so "tool_choice" values that require one ("required", "any", or a named ' +
+        'function) cannot be honored. Use "auto" to keep best-effort tool calling, or route to ' +
+        "a model with native function calling.",
+    };
+  }
+
+  return null;
+}

open-sse/executors/index.ts

@@ -25,6 +25,7 @@ import { ChatGptWebExecutor } from "./chatgpt-web.ts";
 import { BlackboxWebExecutor } from "./blackbox-web.ts";
 import { MuseSparkWebExecutor } from "./muse-spark-web.ts";
 import { AzureOpenAIExecutor } from "./azure-openai.ts";
+import { AzureAiExecutor } from "./azure-ai.ts";
 import { CommandCodeExecutor } from "./commandCode.ts";
 import { GitlabExecutor } from "./gitlab.ts";
 import { NlpCloudExecutor } from "./nlpcloud.ts";
@@ -89,6 +90,7 @@ const executors = {
   glmt: new GlmExecutor("glmt"),
   cu: new CursorExecutor(), // Alias for cursor
   "azure-openai": new AzureOpenAIExecutor(),
+  "azure-ai": new AzureAiExecutor(),
   "command-code": new CommandCodeExecutor(),
   cmd: new CommandCodeExecutor(), // Alias
   gitlab: new GitlabExecutor(),
@@ -263,6 +265,7 @@ export { ChatGptWebExecutor } from "./chatgpt-web.ts";
 export { BlackboxWebExecutor } from "./blackbox-web.ts";
 export { MuseSparkWebExecutor } from "./muse-spark-web.ts";
 export { AzureOpenAIExecutor } from "./azure-openai.ts";
+export { AzureAiExecutor } from "./azure-ai.ts";
 export { CommandCodeExecutor } from "./commandCode.ts";
 export { GitlabExecutor } from "./gitlab.ts";
 export { NlpCloudExecutor } from "./nlpcloud.ts";

open-sse/executors/lmarena/response.ts

@@ -7,6 +7,8 @@ import { isCloudflareChallenge } from "../../services/lmarenaTlsClient.ts";
 import { markLMArenaCatalogModelDead } from "./models.ts";
 import { parseArenaSSE } from "./stream.ts";
 
+const encoder = new TextEncoder();
+
 export function errorResponse(
   status: number,
   message: string,
@@ -165,7 +167,7 @@ function baseChunk(model: string) {
 }
 
 function enqueueSse(controller: ReadableStreamDefaultController, chunk: Record<string, unknown>) {
-  controller.enqueue(new TextEncoder().encode(`data: ${JSON.stringify(chunk)}\n\n`));
+  controller.enqueue(encoder.encode(`data: ${JSON.stringify(chunk)}\n\n`));
 }
 
 function emitStopAndDone(controller: ReadableStreamDefaultController, model: string) {
@@ -173,7 +175,8 @@ function emitStopAndDone(controller: ReadableStreamDefaultController, model: str
     ...baseChunk(model),
     choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
   });
-  controller.enqueue(new TextEncoder().encode("data: [DONE]\n\n"));
+
+  controller.enqueue(encoder.encode("data: [DONE]\n\n"));
   controller.close();
 }
 

open-sse/executors/theoldllm.ts

@@ -108,13 +108,9 @@ export function mapModel(model: string): string {
 const TOKEN_SEED = "oldllm-client-2026";
 const UA_PREFIX = CHROME_UA.slice(0, 20); // "Mozilla/5.0 (Windows"
 
-type TheOldLlmProxy = {
-  type?: string;
-  host: string;
-  port: number;
-  username?: string | null;
-  password?: string | null;
-} | null;
+type TheOldLlmProxy = Awaited<
+  ReturnType<typeof import("../../src/lib/db/proxies").resolveProxyForProvider>
+>;
 
 interface TheOldLlmFetchDependencies {
   resolveProxy: () => Promise<TheOldLlmProxy>;

open-sse/handlers/chatCore.ts

@@ -21,6 +21,7 @@ import { assembleStreamingResponseHeaders } from "./chatCore/streamingResponseHe
 import { storeStreamingSemanticCacheResponse } from "./chatCore/streamingSemanticCacheStore.ts";
 import { assembleStreamingPipeline } from "./chatCore/streamingPipeline.ts";
 import { sanitizeChatRequestBody } from "./chatCore/sanitization.ts";
+import { applyResponsesInputPolicy } from "../services/responsesInputPolicy.ts";
 import {
   getHeaderValueCaseInsensitive,
   isNoMemoryRequested,
@@ -207,7 +208,6 @@ import { stageTrace } from "./chatCore/stageTrace.ts";
 import { attachCompressionUsageReceiptAfterAnalytics as attachCompressionUsageReceiptAfterAnalyticsFor } from "./chatCore/compressionUsageReceipt.ts";
 import { prepareUpstreamBody } from "./chatCore/upstreamBody.ts";
 import { getQuotaScopeLabelForProvider } from "../services/antigravityQuotaFamily.ts";
-
 import {
   getCallLogPipelineCaptureStreamChunks,
   getCallLogPipelineMaxSizeBytes,
@@ -367,9 +367,7 @@ import {
   isTpmExhausted,
   isRpmExhausted,
 } from "../services/geminiRateLimitTracker.ts";
-
 import { isSmallEnoughForSemanticCache } from "../utils/estimateSize.ts";
-
 /**
  * Core chat handler - shared between SSE and Worker
  * Returns { success, response, status, error } for caller to handle fallback
@@ -389,10 +387,8 @@ import { isSmallEnoughForSemanticCache } from "../utils/estimateSize.ts";
  * @param {boolean} options.isCombo - Whether this request is from a combo
  * @param {string} options.connectionId - Connection ID for settings lookup
  */
-
 // extractSystemRoleMessages extracted to chatCore/claudeSystemRole.ts (#3501); re-exported above so
 // existing importers (e.g. tests/unit/system-role-extraction.test.ts) keep resolving it from here.
-
 export async function handleChatCore({
   body,
   modelInfo,
@@ -428,7 +424,6 @@ export async function handleChatCore({
       /* fail open */
     }
   }
-
   // Per-request model-routing metadata (first extracted slice of the request-setup phase).
   const { apiFormat, customModelTargetFormat, requestedModel } = resolveChatCoreRequestSetup(
     modelInfo,
@@ -442,7 +437,6 @@ export async function handleChatCore({
   // (not Math.random) purely to satisfy CodeQL js/insecure-randomness — this id
   // is a log-correlation token, not a security secret.
   const traceId = globalThis.crypto.randomUUID().slice(0, 6);
-
   // Emit request.started event for real-time dashboard
   setImmediate(() => {
     emit("request.started", {
@@ -526,7 +520,6 @@ export async function handleChatCore({
       `long-running goal mode enabled: readinessMax=${agentGoalPolicy.readinessMaxTimeoutMs}ms streamRecovery=${agentGoalPolicy.streamRecoveryEnabled}`
     );
   }
-
   let effectiveServiceTier: EffectiveServiceTier = "standard";
   // Codex service-tier resolvers extracted to chatCore/serviceTier.ts (#3501); bind the per-request
   // provider/credentials once and delegate so the existing call sites stay byte-identical.
@@ -555,7 +548,6 @@ export async function handleChatCore({
       })
     ).catch(() => {});
   };
-
   // Key-health updater extracted to chatCore/keyHealth.ts (#3501); bind the per-request log once
   // and delegate so the existing call sites stay byte-identical.
   const recordKeyHealthStatus = (
@@ -563,11 +555,9 @@ export async function handleChatCore({
     creds: Record<string, unknown> | null | undefined,
     transport?: string
   ): void => recordKeyHealthStatusFor(status, creds, log, transport);
-
   const persistCodexQuotaState = async (headers: Record<string, string> | null, status = 0) => {
     const currentConnectionId = getCurrentConnectionId();
     if (provider !== "codex" || !currentConnectionId || !headers) return;
-
     try {
       const existingProviderData =
         credentials?.providerSpecificData && typeof credentials.providerSpecificData === "object"
@@ -582,28 +572,23 @@ export async function handleChatCore({
         status,
       });
       if (!built) return;
-
       if (built.exhaustionLog) {
         log?.debug?.("CODEX", built.exhaustionLog);
       }
-
       // Invalidate the preflight cache for this connection so the next
       // isModelAvailable check fetches fresh quota data.
       if (status === 429) {
         invalidateCodexQuotaCache(currentConnectionId);
       }
-
       await updateProviderConnection(currentConnectionId, {
         providerSpecificData: built.nextProviderData,
       });
-
       credentials.providerSpecificData = built.nextProviderData;
     } catch (err) {
       const errMessage = err instanceof Error ? err.message : String(err);
       log?.debug?.("CODEX", `Failed to persist codex quota state: ${errMessage}`);
     }
   };
-
   // ── Phase 9.2: Idempotency check ──
   // Resolve the idempotency key once here and reuse it at the Phase 9.2 save site below,
   // rather than re-deriving it. (#3821-review LEDGER-6)
@@ -622,13 +607,11 @@ export async function handleChatCore({
   if (idempotencyHit) {
     return idempotencyHit;
   }
-
   // T07: Inject connectionId into credentials so executors can rotate API keys
   // using providerSpecificData.extraApiKeys (API Key Round-Robin feature)
   if (connectionId && credentials && !credentials.connectionId) {
     credentials.connectionId = connectionId;
   }
-
   // Endpoint/format resolution extracted to chatCore/requestFormat.ts (#3501); pure derivation
   // from the inbound request, destructured so every downstream use stays byte-identical.
   const {
@@ -1071,6 +1054,13 @@ export async function handleChatCore({
     return cacheHit;
   }
 
+  if (targetFormat === FORMATS.OPENAI_RESPONSES && body && typeof body === "object") {
+    applyResponsesInputPolicy(
+      body as Record<string, unknown>,
+      credentials?.providerSpecificData?.preserveEncryptedReasoning === true
+    );
+  }
+
   body = sanitizeChatRequestBody(body, sourceFormat, targetFormat);
   // Per-request opt-out: clients that manage their own context send
   // `x-omniroute-no-memory: true` to skip memory+skills injection (a null owner
@@ -2264,8 +2254,19 @@ export async function handleChatCore({
   // the latter is a Kiro/Claude passthrough alias channel with string values,
   // while namespace identities carry `{namespace, name}` for the #7936 response
   // seam. Extract first because Kiro merge may reuse `_toolNameMap` below.
+  //
+  // #9780 — prefer the dedicated channel: on a pivot the openai->claude/gemini
+  // step publishes its own alias map on `_toolNameMap`, so that property alone
+  // yields aliases here. The `_toolNameMap` read stays as the fallback for the
+  // non-pivot producers (executors/base.ts, cliproxyapi.ts, antigravity).
+  const namespaceIdentityMap = translatedBody._namespaceToolIdentityMap;
   const requestToolIdentityMap =
-    translatedBody._toolNameMap instanceof Map ? translatedBody._toolNameMap : null;
+    namespaceIdentityMap instanceof Map
+      ? namespaceIdentityMap
+      : translatedBody._toolNameMap instanceof Map
+        ? translatedBody._toolNameMap
+        : null;
+  delete translatedBody._namespaceToolIdentityMap;
   delete translatedBody._toolNameMap;
 
   // Kiro: sanitize tool schemas before dispatch. Kiro returns 400 "Improperly
@@ -4333,9 +4334,14 @@ export async function handleChatCore({
     try {
       const firstChoice = translatedResponse?.choices?.[0];
       const msg = firstChoice?.message;
+      // The response being cached now will be replayed as history on the *next*
+      // turn, where the read side (translator/index.ts) keys the lookup by the
+      // message's real position in that future `messages` array — i.e. right
+      // after everything the client sent this turn.
+      const bodyMessages = (body as { messages?: unknown[] } | null | undefined)?.messages;
       cacheReasoningFromAssistantMessage(msg, provider, model, {
         requestId: skillRequestId,
-        messageIndex: 0,
+        messageIndex: Array.isArray(bodyMessages) ? bodyMessages.length : 0,
       });
     } catch {
       // Cache capture is non-critical — never block the response
@@ -4760,12 +4766,15 @@ export async function handleChatCore({
     // with tool_calls so it can be replayed on subsequent turns (DeepSeek V4, Kimi K2, etc.)
     if (normalizedStreamStatus === 200 && streamResponseBody) {
       try {
-        const body = streamResponseBody as Record<string, unknown>;
-        const choices = body.choices as { message?: Record<string, unknown> }[] | undefined;
+        const streamBody = streamResponseBody as Record<string, unknown>;
+        const choices = streamBody.choices as { message?: Record<string, unknown> }[] | undefined;
         const msg = choices?.[0]?.message;
+        // See the non-streaming capture above: messageIndex must match the
+        // position this message will occupy in the *next* turn's history.
+        const bodyMessages = (body as { messages?: unknown[] } | null | undefined)?.messages;
         cacheReasoningFromAssistantMessage(msg, provider, model, {
           requestId: skillRequestId,
-          messageIndex: 0,
+          messageIndex: Array.isArray(bodyMessages) ? bodyMessages.length : 0,
         });
       } catch {
         // Cache capture is non-critical — never block the stream
@@ -5025,7 +5034,6 @@ export async function handleChatCore({
     }),
   };
 }
-
 export function isTokenExpiringSoon(expiresAt, bufferMs = 5 * 60 * 1000) {
   if (!expiresAt) return false;
   const expiresAtMs = new Date(expiresAt).getTime();

open-sse/handlers/chatCore/logTruncation.ts

@@ -3,11 +3,11 @@ import {
   getChatLogMaxDepth,
   getChatLogArrayTailItems,
   getChatLogMaxObjectKeys,
+  getChatLogMaxBodyBytes,
 } from "@/lib/logEnv";
 import { estimateSizeFast } from "../../utils/estimateSize.ts";
 
 export const MEMORY_EXTRACTION_TEXT_LIMIT = 64 * 1024;
-const MAX_LOG_BODY_CHARS = 8 * 1024; // 8KB cap for logged request/response bodies
 
 export function capMemoryExtractionText(value: string): string {
   if (value.length <= MEMORY_EXTRACTION_TEXT_LIMIT) return value;
@@ -60,9 +60,10 @@ export function cloneBoundedChatLogPayload(value: unknown, depth = 0): unknown {
 
 /**
  * Truncate a large object for logging. If its JSON representation exceeds
- * MAX_LOG_BODY_CHARS, return a lightweight summary instead of the full clone.
- * This prevents persistAttemptLogs from holding multi-MB references to
- * translatedBody across 17 call sites per request.
+ * the configured max body size (getChatLogMaxBodyBytes()), return a
+ * lightweight summary instead of the full clone. This prevents
+ * persistAttemptLogs from holding multi-MB references to translatedBody
+ * across 17 call sites per request.
  *
  * When the summarized object carries a `tools` definition, re-attach it
  * (bounded via `cloneBoundedChatLogPayload`) so the request-details view can
@@ -75,8 +76,9 @@ export function cloneBoundedChatLogPayload(value: unknown, depth = 0): unknown {
 export function truncateForLog(value: unknown): Record<string, unknown> | null | undefined {
   if (value === null || value === undefined) return value as null | undefined;
   if (typeof value !== "object") return value as unknown as Record<string, unknown>;
-  const estimatedSize = estimateSizeFast(value);
-  if (estimatedSize <= MAX_LOG_BODY_CHARS) return value as Record<string, unknown>;
+  const maxBodyBytes = getChatLogMaxBodyBytes();
+  const estimatedSize = estimateSizeFast(value, maxBodyBytes);
+  if (estimatedSize <= maxBodyBytes) return value as Record<string, unknown>;
   // Object is too large — return a summary instead of a deep clone
   const obj = value as Record<string, unknown>;
   const summary: Record<string, unknown> = {

open-sse/handlers/imageGeneration/providers/adobeFirefly.ts

@@ -16,11 +16,11 @@ import {
   AdobeFireflyError,
   adobeFireflyGenerateImage,
   adobeFireflyImageTimeoutMs,
-  adobeFireflyMaxImageRefs,
   resolveAdobeAccessToken,
-  resolveAdobeSourceImageIds,
+  resolveAdobeSourceImageReferences,
   resolveAdobeImageModel,
 } from "../../../services/adobeFireflyClient.ts";
+import { getAdobeReferenceUploadLimit } from "../../../services/adobeFireflyModels.ts";
 import { isAdobeFireflyUpscaleModel } from "../../../services/adobeFireflyUpscale.ts";
 import { handleAdobeFireflyImageUpscale } from "../../imageUpscale/adobeFirefly.ts";
 
@@ -90,7 +90,8 @@ export async function handleAdobeFireflyImageGeneration({
 
     // Keep the raw credential blob for Cookie + sherlockToken (x-arp-session-id).
     // JWT may be embedded in the same paste as cookies (HAR / multi-line).
-    const psd = (credentials as { providerSpecificData?: { cookie?: string } })?.providerSpecificData;
+    const psd = (credentials as { providerSpecificData?: { cookie?: string } })
+      ?.providerSpecificData;
     const sessionCookie =
       (typeof psd?.cookie === "string" && psd.cookie.trim()) ||
       (typeof credentials?.apiKey === "string" && credentials.apiKey.trim()) ||
@@ -98,15 +99,11 @@ export async function handleAdobeFireflyImageGeneration({
         ? credentials.accessToken
         : undefined);
 
-    // Cap uploads by model family. gpt-image: 2 subject refs max (3–4+ stalls colligo → 504).
-    // nano: 4 general refs for multi-panel composition.
-    const { id: resolvedId } = resolveAdobeImageModel(model);
-    const maxRefs = adobeFireflyMaxImageRefs(resolvedId);
-
-    const sourceImageIds = await resolveAdobeSourceImageIds({
+    const { spec } = resolveAdobeImageModel(model);
+    const references = await resolveAdobeSourceImageReferences({
       accessToken,
       body,
-      max: maxRefs,
+      max: getAdobeReferenceUploadLimit(spec, "image"),
       sessionCookie,
       prompt,
       fetchImpl,
@@ -121,13 +118,13 @@ export async function handleAdobeFireflyImageGeneration({
           : undefined;
     const timeoutMs = adobeFireflyImageTimeoutMs({
       timeoutMs: explicitTimeout,
-      refCount: sourceImageIds.length,
+      refCount: references.length,
     });
 
     log?.info?.(
       "IMAGE",
       `${provider}/${model} (adobe-firefly) | prompt: "${prompt.slice(0, 60)}${prompt.length > 60 ? "..." : ""}"` +
-        (sourceImageIds.length ? ` | refs: ${sourceImageIds.length}/${maxRefs}` : "") +
+        (references.length ? ` | refs: ${references.length}` : "") +
         ` | pollTimeoutMs=${timeoutMs}`
     );
 
@@ -139,9 +136,8 @@ export async function handleAdobeFireflyImageGeneration({
       aspectRatio: body.aspect_ratio ?? body.aspectRatio ?? body.size,
       quality: body.quality,
       seed: Number.isFinite(seed as number) ? (seed as number) : undefined,
-      negativePrompt:
-        typeof body.negative_prompt === "string" ? body.negative_prompt : undefined,
-      sourceImageIds: sourceImageIds.length ? sourceImageIds : undefined,
+      negativePrompt: typeof body.negative_prompt === "string" ? body.negative_prompt : undefined,
+      references: references.length ? references : undefined,
       sessionCookie,
       timeoutMs,
       fetchImpl,

open-sse/handlers/videoGeneration.ts

@@ -4,7 +4,7 @@
  * Handles POST /v1/videos/generations requests. Proxies to upstream video
  * generation providers (ComfyUI AnimateDiff/SVD, SD WebUI AnimateDiff, and
  * more — see the per-format handlers below). Response format (OpenAI-like):
- * { "created": 1234567890, "data": [{ "b64_json": "...", "format": "mp4" }] }
+ * { "created": 1234567890, "data": [{ "url": "https://…", "format": "mp4" }] }
  */
 
 import { getVideoProvider, parseVideoModel } from "../config/videoRegistry.ts";
@@ -18,6 +18,16 @@ import { handleNovitaVideoGeneration } from "./videoGeneration/novitaHandler.ts"
 import { handleXaiVideoGeneration } from "./videoGeneration/xaiGrokImagineHandler.ts";
 import { handleSegmindVideoGeneration } from "./videoGeneration/providers/segmind.ts";
 import { handleAdobeFireflyVideoGeneration } from "./videoGeneration/adobeFireflyHandler.ts";
+import { handleOpenAIVideoGeneration } from "./videoGeneration/openai.ts";
+import { getVideoJobPreset, handleVideoJobGeneration } from "./videoGeneration/job.ts";
+import {
+  extractRunwayFailureMessage,
+  normalizeRunwayVideoResult,
+  resolvePositiveInteger,
+  resolveRunwayDuration,
+  resolveRunwayPromptImage,
+  resolveRunwayRatio,
+} from "./videoGeneration/runwayHelpers.ts";
 import { getExecutor } from "../executors/index.ts";
 import { getKieTaskId, isJsonObject, parseKieResultJson } from "../utils/kieTask.ts";
 import {
@@ -33,13 +43,94 @@ import {
   resolveComfyUiBaseUrl,
 } from "../utils/comfyuiClient.ts";
 import { saveCallLog } from "@/lib/usageDb";
+import { getAllCustomModels } from "@/lib/db/models";
 import { sanitizeErrorMessage } from "../utils/error.ts";
+import {
+  FetchTimeoutError,
+  fetchWithTimeout,
+  getConfiguredTimeout,
+} from "@/shared/utils/fetchTimeout";
+
+/**
+ * Resolve the base URL for OpenAI-compatible video generation endpoints.
+ * Prefers providerSpecificData.baseUrl (from custom node config), falls back to
+ * top-level credentials.baseUrl, then to the provided fallback.
+ */
+export function resolveVideoBaseUrl(
+  credentials:
+    { baseUrl?: unknown; providerSpecificData?: { baseUrl?: unknown } | null } | null | undefined,
+  fallback: string
+): string {
+  const psd = credentials?.providerSpecificData;
+  const psdBaseUrl =
+    psd && typeof psd === "object" && typeof psd.baseUrl === "string" && psd.baseUrl.trim()
+      ? psd.baseUrl.trim()
+      : null;
+  const topLevelBaseUrl =
+    typeof credentials?.baseUrl === "string" && credentials.baseUrl.trim()
+      ? credentials.baseUrl.trim()
+      : null;
+  const nodeBaseUrl = psdBaseUrl || topLevelBaseUrl;
+
+  if (!nodeBaseUrl) return fallback;
+
+  // Trim trailing slashes
+  let normalized = nodeBaseUrl;
+  while (normalized.endsWith("/")) normalized = normalized.slice(0, -1);
+  if (normalized.endsWith("/videos/generations")) return normalized;
+  const stripped = normalized.replace(/\/videos\/generations$/, "");
+  return `${stripped}/videos/generations`;
+}
+
+/**
+ * Read generationConfig.preset from the custom model row for the given
+ * provider/model id. Returns null when the model has no preset configured (or
+ * the registry is unreadable), so callers can fall back to the sync path.
+ */
+async function getCustomModelVideoPreset(
+  providerId: string,
+  modelId: string
+): Promise<string | null> {
+  try {
+    const customModelsMap = (await getAllCustomModels()) as Record<
+      string,
+      Array<Record<string, unknown>>
+    >;
+    const models = customModelsMap[providerId];
+    if (!Array.isArray(models)) return null;
+    for (const model of models) {
+      if (!model || typeof model !== "object" || model.id !== modelId) continue;
+      const generationConfig = model.generationConfig;
+      if (
+        generationConfig &&
+        typeof generationConfig === "object" &&
+        typeof (generationConfig as Record<string, unknown>).preset === "string"
+      ) {
+        return (generationConfig as Record<string, unknown>).preset as string;
+      }
+      return null;
+    }
+    return null;
+  } catch {
+    return null;
+  }
+}
 
 /**
  * Handle video generation request
  */
-export async function handleVideoGeneration({ body, credentials, log }) {
-  const { provider, model } = parseVideoModel(body.model);
+
+/**
+ * Handle video generation request
+ */
+export async function handleVideoGeneration({ body, credentials, log, resolvedProvider = null }) {
+  let { provider, model } = parseVideoModel(body.model);
+  if (resolvedProvider) {
+    provider = resolvedProvider;
+    model = body.model.startsWith(provider + "/")
+      ? body.model.slice(provider.length + 1)
+      : body.model;
+  }
 
   if (!provider) {
     return {
@@ -51,11 +142,59 @@ export async function handleVideoGeneration({ body, credentials, log }) {
 
   const providerConfig = getVideoProvider(provider);
   if (!providerConfig) {
-    return {
-      success: false,
-      status: 400,
-      error: `Unknown video provider: ${provider}`,
+    if (!resolvedProvider) {
+      return {
+        success: false,
+        status: 400,
+        error: `Unknown video provider: ${provider}`,
+      };
+    }
+    // Custom provider node. When the custom model row carries a
+    // generationConfig.preset (e.g. "agnes-video-job"), dispatch through the
+    // submit → poll job pipeline; otherwise mirror the images route and use the
+    // generic OpenAI-compatible handler with a synthetic config.
+    const presetName = await getCustomModelVideoPreset(provider, model);
+    if (presetName !== null) {
+      if (!getVideoJobPreset(presetName)) {
+        return {
+          success: false,
+          status: 502,
+          error: `Unknown video job preset: ${presetName}`,
+        };
+      }
+      if (log)
+        log.info("VIDEO", `Custom model ${provider}/${model} — using job preset ${presetName}`);
+      return handleVideoJobGeneration({
+        model,
+        presetName,
+        body,
+        credentials,
+        log,
+      });
+    }
+    if (log)
+      log.info("VIDEO", `Custom model ${provider}/${model} — using OpenAI-compatible handler`);
+    const syntheticConfig = {
+      id: provider,
+      baseUrl: resolveVideoBaseUrl(
+        credentials,
+        "http://generative.language.googleapis.com/v1beta/openai/videos/generations"
+      ),
+      authType: "apikey",
+      authHeader: "bearer",
+      format: "openai-video",
     };
+    return handleOpenAIVideoGeneration({
+      model,
+      body,
+      credentials,
+      provider,
+      providerConfig: syntheticConfig,
+      log,
+    });
+  }
+  if (providerConfig.format === "openai-video") {
+    return handleOpenAIVideoGeneration({ model, provider, providerConfig, body, credentials, log });
   }
 
   if (providerConfig.format === "vertex-veo") {
@@ -158,7 +297,10 @@ export async function handleVideoGeneration({ body, credentials, log }) {
       log,
     });
   }
-
+  if (resolvedProvider) {
+    // Custom provider with no matching built-in format — use OpenAI-compatible fallback
+    return handleOpenAIVideoGeneration({ model, provider, providerConfig, body, credentials, log });
+  }
   return {
     success: false,
     status: 400,
@@ -832,148 +974,6 @@ const RUNWAY_TERMINAL_FAILURE_STATUSES = new Set([
   "DELETED",
 ]);
 
-function resolveRunwayPromptImage(body) {
-  const directCandidates = [
-    body.promptImage,
-    body.prompt_image,
-    body.image,
-    body.image_url,
-    body.imageUrl,
-    body.provider_options?.promptImage,
-    body.provider_options?.prompt_image,
-  ];
-
-  for (const candidate of directCandidates) {
-    if (typeof candidate === "string" && candidate.trim()) return candidate.trim();
-    if (candidate && typeof candidate === "object") return candidate;
-    if (Array.isArray(candidate) && candidate.length > 0) return candidate;
-  }
-
-  const arrayCandidates = [
-    body.imageUrls,
-    body.image_urls,
-    body.provider_options?.imageUrls,
-    body.provider_options?.image_urls,
-  ];
-  for (const candidate of arrayCandidates) {
-    if (Array.isArray(candidate) && candidate.length > 0) return candidate;
-  }
-
-  return null;
-}
-
-function resolveRunwayRatio(body) {
-  const aspectRatio = typeof body.aspect_ratio === "string" ? body.aspect_ratio : body.aspectRatio;
-  if (aspectRatio === "1280:720" || aspectRatio === "720:1280") return aspectRatio;
-  if (aspectRatio === "16:9") return "1280:720";
-  if (aspectRatio === "9:16") return "720:1280";
-
-  const size = typeof body.size === "string" ? body.size : "";
-  const [widthRaw, heightRaw] = size.split("x");
-  const width = Number(widthRaw);
-  const height = Number(heightRaw);
-  if (Number.isFinite(width) && Number.isFinite(height) && width > 0 && height > 0) {
-    return width >= height ? "1280:720" : "720:1280";
-  }
-
-  return "1280:720";
-}
-
-function resolveRunwayDuration(body) {
-  if (Number.isFinite(body.duration)) {
-    return clampRunwayDuration(body.duration);
-  }
-
-  if (Number.isFinite(body.frames) && Number.isFinite(body.fps) && Number(body.fps) > 0) {
-    return clampRunwayDuration(Number(body.frames) / Number(body.fps));
-  }
-
-  return 5;
-}
-
-function clampRunwayDuration(value) {
-  const duration = Math.round(Number(value));
-  if (!Number.isFinite(duration)) return 5;
-  return Math.min(10, Math.max(2, duration));
-}
-
-function resolvePositiveInteger(value, fallback) {
-  const numeric = Number(value);
-  if (!Number.isFinite(numeric) || numeric <= 0) return fallback;
-  return Math.floor(numeric);
-}
-
-function extractRunwayOutputUrls(task) {
-  const rawOutput = Array.isArray(task?.output)
-    ? task.output
-    : Array.isArray(task?.result)
-      ? task.result
-      : [];
-
-  return rawOutput
-    .map((entry) => {
-      if (typeof entry === "string") return entry;
-      if (!entry || typeof entry !== "object") return null;
-      return entry.url || entry.uri || entry.videoUrl || entry.video_url || null;
-    })
-    .filter((value) => typeof value === "string" && value.length > 0);
-}
-
-function extractRunwayFailureMessage(task) {
-  const directCandidates = [
-    task?.failure,
-    task?.failureReason,
-    task?.error,
-    task?.errorMessage,
-    task?.message,
-  ];
-  for (const candidate of directCandidates) {
-    if (typeof candidate === "string" && candidate.trim()) return candidate.trim();
-  }
-
-  if (task?.failure && typeof task.failure === "object") {
-    const nestedCandidates = [
-      task.failure.message,
-      task.failure.reason,
-      task.failure.error,
-      task.failure.code,
-    ];
-    for (const candidate of nestedCandidates) {
-      if (typeof candidate === "string" && candidate.trim()) return candidate.trim();
-    }
-  }
-
-  return null;
-}
-
-async function normalizeRunwayVideoResult(task, body) {
-  const urls = extractRunwayOutputUrls(task);
-  if (urls.length === 0) {
-    throw new Error(
-      `Runway task completed without output URLs: ${JSON.stringify(task).slice(0, 400)}`
-    );
-  }
-
-  if (body.response_format === "url") {
-    return urls.map((url) => ({ url, format: "mp4" }));
-  }
-
-  const videos = [];
-  for (const url of urls) {
-    const response = await fetch(url);
-    if (!response.ok) {
-      throw new Error(`Runway output fetch failed (${response.status})`);
-    }
-    const arrayBuffer = await response.arrayBuffer();
-    videos.push({
-      b64_json: Buffer.from(arrayBuffer).toString("base64"),
-      format: "mp4",
-    });
-  }
-
-  return videos;
-}
-
 async function handleHaiperVideoGeneration({
   model,
   provider,

open-sse/handlers/videoGeneration/adobeFireflyHandler.ts

@@ -10,9 +10,10 @@ import {
   AdobeFireflyError,
   adobeFireflyGenerateVideo,
   resolveAdobeAccessToken,
-  resolveAdobeSourceImageIds,
+  resolveAdobeSourceImageReferences,
   resolveAdobeVideoModel,
 } from "../../services/adobeFireflyClient.ts";
+import { getAdobeReferenceUploadLimit } from "../../services/adobeFireflyModels.ts";
 
 function normalizePositiveNumber(value: unknown, fallback: number): number {
   const n = Number(value);
@@ -55,7 +56,8 @@ export async function handleAdobeFireflyVideoGeneration({
           ? Number(body.seed)
           : undefined;
     // Keep raw paste for Cookie + sherlockToken (x-arp-session-id).
-    const psd = (credentials as { providerSpecificData?: { cookie?: string } })?.providerSpecificData;
+    const psd = (credentials as { providerSpecificData?: { cookie?: string } })
+      ?.providerSpecificData;
     const sessionCookie =
       (typeof psd?.cookie === "string" && psd.cookie.trim()) ||
       (typeof credentials?.apiKey === "string" && credentials.apiKey.trim()) ||
@@ -63,13 +65,11 @@ export async function handleAdobeFireflyVideoGeneration({
         ? credentials.accessToken
         : undefined);
 
-    // Kling i2v / Veo ref / Sora frame: upload reference images first.
-    const { id: videoModelId } = resolveAdobeVideoModel(String(model));
-    const maxFrames = videoModelId.includes("kling") || videoModelId.includes("sora") ? 2 : 3;
-    const sourceImageIds = await resolveAdobeSourceImageIds({
+    const { spec } = resolveAdobeVideoModel(String(model));
+    const references = await resolveAdobeSourceImageReferences({
       accessToken,
       body,
-      max: maxFrames,
+      max: getAdobeReferenceUploadLimit(spec, "image"),
       sessionCookie,
       prompt,
       fetchImpl,
@@ -79,7 +79,7 @@ export async function handleAdobeFireflyVideoGeneration({
     log?.info?.(
       "VIDEO",
       `${provider}/${model} (adobe-firefly) | prompt: "${prompt.slice(0, 60)}${prompt.length > 60 ? "..." : ""}"` +
-        (sourceImageIds.length ? ` | frames: ${sourceImageIds.length}` : "")
+        (references.length ? ` | refs: ${references.length}` : "")
     );
 
     const result = await adobeFireflyGenerateVideo({
@@ -99,7 +99,7 @@ export async function handleAdobeFireflyVideoGeneration({
             ? body.negativePrompt
             : undefined,
       generateAudio: body.generate_audio !== false && body.generateAudio !== false,
-      sourceImageIds: sourceImageIds.length ? sourceImageIds : undefined,
+      references: references.length ? references : undefined,
       sessionCookie,
       timeoutMs,
       fetchImpl,