feat(dashboard): Conductor panel — fleet live view, task detail and cancel over /api/conductor proxy

feat(dashboard): /api/conductor proxy routes (fleet, task detail, cancel) behind management auth
feat(dashboard): server-side hub proxy for the Conductor panel (whitelisted shapes, fail-open)
2026-08-09 08:42:15 +03:00 · 2026-07-22 20:55:19 -03:00 · 2026-07-22 20:44:03 -03:00 · 2026-07-22 20:41:46 -03:00 · 2026-07-22 08:36:51 -03:00 · 2026-07-22 08:35:16 -03:00
1439 changed files with 67130 additions and 297606 deletions
--- a/.env.example
+++ b/.env.example
@@ -80,21 +80,8 @@ PORT=20128

 # Base path (URL subpath) when serving OmniRoute behind a reverse proxy under a subpath.
 # Used by: next.config.mjs — sets Next.js `basePath`; auth redirects are basePath-aware.
-# Also mirrored to NEXT_PUBLIC_OMNIROUTE_BASE_PATH at build time so the dashboard
-# endpoint display (useDisplayBaseUrl) shows https://host/omniroute/v1 instead of
-# https://host/v1. Rebuild after changing this value (Next basePath is build-time).
 # Default: "" (served at the domain root). Example: /omniroute to serve under https://host/omniroute
 # OMNIROUTE_BASE_PATH=
-#
-# Browser-visible mirror of OMNIROUTE_BASE_PATH, inlined at build time so the
-# dashboard endpoint display can read it client-side. Set it to the same value
-# as OMNIROUTE_BASE_PATH; when unset the hook falls back to OMNIROUTE_BASE_PATH.
-# Used by: src/shared/hooks/useDisplayBaseUrl.ts
-# NEXT_PUBLIC_OMNIROUTE_BASE_PATH=
-#
-# Optional: set the public origin *with* the same path so OAuth and display URLs
-# stay consistent without relying on window.location.origin alone:
-# NEXT_PUBLIC_BASE_URL=https://host/omniroute

 # Split-port mode: serve Dashboard and API on separate ports for network isolation.
 # Used by: src/lib/runtime/ports.ts — overrides PORT for each service.
@@ -325,14 +312,6 @@ ALLOW_API_KEY_REVEAL=false
 # OMNIROUTE_CHAT_HARD_MAX_BODY_BYTES=52428800
 # Maximum heavyweight requests simultaneously admitted in one process. Default 1.
 # OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT=1
-# Message count that classifies an otherwise small body as heavyweight. Default 200.
-# OMNIROUTE_CHAT_HEAVY_MESSAGE_COUNT=200
-# Tool count that classifies an otherwise small body as heavyweight. Default 64.
-# 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
-# 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
@@ -373,14 +352,11 @@ ALLOW_API_KEY_REVEAL=false
 # ── Request-Side: Prompt Injection Guard ──
 # Scans incoming messages for prompt injection patterns before routing.
 # Used by: src/middleware/promptInjectionGuard.ts
-# Default ON when unset. Set to false/0/no/off to disable. Truthy: true/1/yes/on.
-# INPUT_SANITIZER_ENABLED=false
-# INPUT_SANITIZER_MODE=warn    # warn = log only | block = reject request | redact = legacy (does NOT strip injection; use PII_REDACTION_ENABLED for request PII)
-# INPUT_SANITIZER_BLOCK_THRESHOLD=high  # high (default) | medium | low — severities at/above this are blocked in block mode
+# INPUT_SANITIZER_ENABLED=true
+# INPUT_SANITIZER_MODE=warn    # warn = log only | block = reject request | redact = strip patterns

-# Legacy aliases for INPUT_SANITIZER_MODE / INPUT_SANITIZER_BLOCK_THRESHOLD (same effect).
+# Legacy alias for INPUT_SANITIZER_MODE (same effect).
 # INJECTION_GUARD_MODE=warn
-# INJECTION_GUARD_BLOCK_THRESHOLD=high

 # PII detection in incoming requests (emails, phone numbers, SSNs, etc.).
 # Used by: src/middleware/promptInjectionGuard.ts — extends injection guard.
@@ -867,11 +843,10 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
 # Used by: open-sse/executors/antigravity.ts — escape hatch for multi-project setups.
 # OMNIROUTE_ALLOW_BODY_PROJECT_OVERRIDE=0

-# Control Antigravity Google One AI credit usage. Used by:
-# open-sse/services/antigravityCredits.ts — accepts off, retry, or always.
-# off (default): never use credits; retry: use credits once after eligible quota 429;
-# always: use credits on the first request (higher account and spend risk).
-#ANTIGRAVITY_CREDITS=off
+# Adjust how Antigravity advertises remaining credits.  Used by:
+# open-sse/services/antigravityCredits.ts — accepts forced override strings.
+# Default: empty (use upstream-reported credits).
+#ANTIGRAVITY_CREDITS=

 # Override the path to the Antigravity CLI (agy) token file read by the
 # "auto-detect local login" import. Used by:
@@ -1040,7 +1015,7 @@ GITHUB_OAUTH_CLIENT_ID=Iv1.b507a08c87ecfe98
 # Used by: open-sse/executors/base.ts — buildHeaders() dynamic lookup.
 # Update these when providers release new CLI versions to avoid blocks.

-CLAUDE_USER_AGENT="claude-cli/2.1.219 (external, cli)"
+CLAUDE_USER_AGENT="claude-cli/2.1.207 (external, cli)"

 # Disable the deterministic tool-name cloak applied on both Anthropic-bound paths
 # (executors/base.ts native OAuth + executors/cliproxyapi.ts CLIProxyAPI) —
@@ -1189,20 +1164,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # OMNIROUTE_GROK_TLS_TIMEOUT_MS=60000
 # OMNIROUTE_GROK_TLS_GRACE_MS=10000

-# ── Notion web TLS sidecar (Chrome-fingerprinted client) ──
-# Used by: open-sse/services/notionTlsClient.ts — wire-level timeout for the
-# bogdanfinn/tls-client koffi binding and the JS-side grace window layered on
-# top of it when the native library is wedged. The notion-web executor raises
-# the wire timeout per-request to 180000 for long generations.
-# OMNIROUTE_NOTION_TLS_TIMEOUT_MS=30000
-# OMNIROUTE_NOTION_TLS_GRACE_MS=10000
-
-# ── Grok web quota fetcher (auth.json override) ──
-# Used by: open-sse/services/grokQuotaFetcher.ts — path of the Grok CLI
-# auth.json used to fetch the grok-web weekly quota. Defaults to
-# ~/.grok/auth.json; override for tests or a non-standard CLI install.
-# GROK_AUTH_PATH=
-
 # ── Browser-backed web-cookie chat (Playwright shared pool) ──
 # Used by: open-sse/services/browserPool.ts + browserBackedChat.ts. The shared
 # browser pool warms a headless context for web-cookie providers (e.g. claude-web)
@@ -1950,11 +1911,6 @@ APP_LOG_TO_FILE=true
 # Used by: src/lib/db/backup.ts.
 # DB_BACKUP_MAX_FILES=20
 # DB_BACKUP_RETENTION_DAYS=0
-# Tick interval (ms) of the server-side job that executes backup-schedule.json.
-# Must stay well under the 1-minute cron granularity; values below 5000 (or
-# unparseable) fall back to the 30000 default.
-# Used by: src/lib/jobs/backupScheduleJob.ts
-# OMNIROUTE_BACKUP_SCHEDULE_JOB_INTERVAL_MS=30000

 # ── TLS sidecar override ──
 # Used by: open-sse/services/chatgptTlsClient.ts tests. Production deployments
@@ -2117,15 +2073,6 @@ QUOTA_STORE_DRIVER=sqlite              # sqlite | redis
 # the full (unfiltered) pool with a warning. Source: open-sse/services/autoCombo/virtualFactory.ts
 # OMNIROUTE_AUTO_FREE_FALLBACK_TO_FULL_POOL=false

-# ─── Auto-Combo chaos panel (broadcast variant) ────────────────────────────
-# Tuning for the `auto/*:chaos` variant, which fans a single request out to a
-# panel of provider-diverse models. Panel size is clamped to 1..10 (default 5);
-# min-panel and the panel hard-timeout fall back to the engine defaults when
-# unset. Source: open-sse/services/autoCombo/virtualFactory.ts
-# OMNIROUTE_CHAOS_MAX_PANEL=5
-# OMNIROUTE_CHAOS_MIN_PANEL=
-# OMNIROUTE_CHAOS_PANEL_TIMEOUT_MS=
-
 # ─── OpenCode config regeneration (scripts/ad-hoc/regen-opencode-config.ts) ───
 # Base URL of the OmniRoute instance to query for /v1/models when regenerating
 # an opencode.json with accurate limit.context values. Used by:
@@ -2276,38 +2223,11 @@ QUOTA_STORE_DRIVER=sqlite              # sqlite | redis
 # PROMPTQL_TOKEN_REFRESH_URL=https://auth.pro.ql.app/ddn/project/token
 # PROMPTQL_POLL_TIMEOUT_MS=180000

-# ─────────────────────────────────────────────────────────────────────────────
-# HyperAgent web provider (Unofficial/Experimental — src/shared/constants/providers/web-cookie.ts)
-# Reverse-engineered session bridge for hyperagent.com. Optional — defaults
-# point at the public billing/usage endpoint; override only for a
-# self-hosted/alternate HyperAgent deployment.
-# Used by: open-sse/services/usage/hyperagent.ts
-# ─────────────────────────────────────────────────────────────────────────────
-# HYPERAGENT_USAGE_URL=https://hyperagent.com/api/settings/billing/usage
-
-# ─────────────────────────────────────────────────────────────────────────────
-# Browser-login VNC sessions (optional — src/lib/vncSession/manifest.ts)
-# Containerized Chromium+VNC used for interactive browser-login credential
-# capture via /api/vnc-session. All optional — defaults target the bundled
-# `omniroute-vnc-chromium:local` image; override only for a custom image, ports,
-# or lifecycle tuning.
-# ─────────────────────────────────────────────────────────────────────────────
-# OMNIROUTE_VNC_IMAGE=omniroute-vnc-chromium:local
-# OMNIROUTE_DOCKER_BIN=docker
-# OMNIROUTE_VNC_CONTAINER_VNC_PORT=3000
-# OMNIROUTE_VNC_CONTAINER_CDP_PORT=9223
-# OMNIROUTE_VNC_CONTAINER_PROFILE_DIR=/config
-# OMNIROUTE_VNC_PROFILE_DIR=
-# OMNIROUTE_VNC_IDLE_MS=600000
-# OMNIROUTE_VNC_MAX_MS=1800000
-# OMNIROUTE_VNC_MAX_SESSIONS=4
-# OMNIROUTE_VNC_READY_MS=45000
-# OMNIROUTE_VNC_HARVEST_MS=20000
-# OMNIROUTE_VNC_CHROMIUM_ARGS=--remote-debugging-port=9222 --no-first-run --no-default-browser-check
-
-# ─────────────────────────────────────────────────────────────────────────────
-# Data-dir alias (optional — open-sse/services/notionThreadSessions.ts)
-# Legacy fallback for DATA_DIR, checked only after DATA_DIR and
-# OMNIROUTE_DATA_DIR are both unset. Locates the Notion web-thread session cache.
-# ─────────────────────────────────────────────────────────────────────────────
-# VIBEPROXY_DATA_DIR=
+# ── OmniConductor bridge (Conductor PRD RF1) ──────────────────────────────────
+# Mirrors the OmniConductor hub's tasks into the local A2A TaskManager via SSE.
+# Opt-in: the bridge only starts when CONDUCTOR_HUB_URL is set.
+# Token: emit a `spokesperson`-kind credential on the hub (POST /v1/peers, admin) —
+# server-side only, never exposed to the browser.
+# Used by: src/lib/conductor/boot.ts, src/lib/conductor/bridge.ts
+# CONDUCTOR_HUB_URL=http://127.0.0.1:7910
+# CONDUCTOR_HUB_TOKEN=
--- a/.github/pull_request_template.md
+++ b/.github/pull_request_template.md
@@ -9,12 +9,10 @@

 ## Validation

-Run only the focused loop for what you changed — the full unit suite, Vitest, the
-60% coverage gate, and the production build all run in CI on this PR (#8329):
-
- [ ] Focused tests for the change: `node --import tsx/esm --test tests/unit/<file>.test.ts`
 - [ ] `npm run lint`
- [ ] Production-code changes include a new or updated automated test in this PR
+- [ ] `npm run test:unit`
+- [ ] `npm run test:coverage`
+- [ ] Coverage is still `>= 60%` for statements, lines, functions, and branches
 - [ ] SonarQube PR analysis is green or any remaining issues are explicitly documented below

 ## Tests Added Or Updated
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -459,26 +459,6 @@ jobs:
      - uses: ./.github/actions/npm-ci-retry
      - run: node scripts/i18n/check-ui-keys-coverage.mjs --threshold=65

-  # #8038: cheap single-locale glossary/protected-terms consistency gate —
-  # complements i18n-ui-coverage (key parity) and the ICU `i18n` job below
-  # without needing app-boot/Playwright infra. Same gating as i18n-ui-coverage.
-  i18n-glossary-zhcn:
-    name: i18n Glossary (zh-CN)
-    runs-on: ubuntu-latest
-    needs: changes
-    if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && (needs.changes.outputs.i18n == 'true' || needs.changes.outputs.code == 'true')) }}
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v7
-        with:
-          node-version: ${{ env.CI_NODE_VERSION }}
-          cache: npm
-      - uses: ./.github/actions/npm-ci-retry
-      - run: node scripts/i18n/check-glossary-consistency.mjs --locale=zh-CN
-      - run: node scripts/i18n/check-glossary-consistency.mjs --locale=zh-TW
-
  # D4 (plano mestre testes+CI): a matrix de ~40 jobs de <1min por idioma saturava sozinha
  # a concorrência de jobs da conta (Free = 20 slots, compartilhados entre TODOS os repos)
  # e pagava spin-up + arredondamento de billing por idioma. Um único job itera os idiomas
@@ -497,7 +477,7 @@ jobs:
      - uses: actions/checkout@v7
        with:
          persist-credentials: false
-      - uses: actions/setup-python@v7
+      - uses: actions/setup-python@v6
        with:
          python-version: "3.12"
      - name: Validate all languages
@@ -908,7 +888,7 @@ jobs:
      # (if-no-files-found: warn) — Sonar consumes the same file.
      - name: Upload coverage to Codecov (informational)
        if: always()
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f # v7.0.0
+        uses: codecov/codecov-action@0fb7174895f61a3b6b78fc075e0cd60383518dac # v5
        with:
          files: coverage/lcov.info
          token: ${{ secrets.CODECOV_TOKEN }}
@@ -1192,7 +1172,6 @@ jobs:
      - lint
      - docs-sync-strict
      - i18n-ui-coverage
-      - i18n-glossary-zhcn
      - i18n
      - pr-test-policy
      - build
@@ -1238,7 +1217,6 @@ jobs:
          echo "| Lint | $(status '${{ needs.lint.result }}') |" >> "$GITHUB_STEP_SUMMARY"
          echo "| Docs Sync (Strict) | $(status '${{ needs.docs-sync-strict.result }}') |" >> "$GITHUB_STEP_SUMMARY"
          echo "| i18n UI Coverage | $(status '${{ needs.i18n-ui-coverage.result }}') |" >> "$GITHUB_STEP_SUMMARY"
-          echo "| i18n Glossary (zh-CN) | $(status '${{ needs.i18n-glossary-zhcn.result }}') |" >> "$GITHUB_STEP_SUMMARY"
          echo "| PR Test Policy | $(status '${{ needs.pr-test-policy.result }}') |" >> "$GITHUB_STEP_SUMMARY"
          echo "| SonarQube | $(status '${{ needs.sonarqube.result }}') |" >> "$GITHUB_STEP_SUMMARY"

--- a/.github/workflows/codeql.yml
+++ b/.github/workflows/codeql.yml
@@ -22,10 +22,10 @@ jobs:
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
-      - uses: github/codeql-action/init@e4fba868fa4b1b91e1fdab776edc8cfbe6e9fb81 # v4.37.3
+      - uses: github/codeql-action/init@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
        with:
          languages: javascript-typescript
          queries: security-extended
-      - uses: github/codeql-action/analyze@e4fba868fa4b1b91e1fdab776edc8cfbe6e9fb81 # v4.37.3
+      - uses: github/codeql-action/analyze@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
        with:
          category: "/language:javascript-typescript"
--- a/.github/workflows/dast-smoke.yml
+++ b/.github/workflows/dast-smoke.yml
@@ -2,20 +2,8 @@ name: DAST smoke (PR)
 on:
  pull_request:
    branches: ["main", "release/**"]
-    # Runner-cost guard (#8084): the CLI-bundle build alone is 6-11min; a docs-only PR
-    # cannot change DAST behavior, so skip the whole workflow for pure docs/markdown
-    # changes. Any code path in the diff still runs the full smoke.
-    paths-ignore:
-      - "docs/**"
-      - "**/*.md"
 permissions:
  contents: read
-
-# Superseded runs on the same PR must not stack 25-minute advisory builds
-# (force-push storms were holding 2-3 runners each). Same group rule as quality.yml.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
 jobs:
  dast-smoke:
    runs-on: ubuntu-latest
@@ -53,7 +41,7 @@ jobs:
            if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
            sleep 2
          done
-      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
        with:
          python-version: "3.12"
      - run: pip install schemathesis
--- a/.github/workflows/nightly-llm-security.yml
+++ b/.github/workflows/nightly-llm-security.yml
@@ -90,7 +90,7 @@ jobs:
            if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
            sleep 2
          done
-      - uses: actions/setup-python@v7
+      - uses: actions/setup-python@v6
        if: steps.gate.outputs.run == 'true'
        with: { python-version: "3.12" }
      - run: pip install garak
--- a/.github/workflows/nightly-schemathesis.yml
+++ b/.github/workflows/nightly-schemathesis.yml
@@ -35,7 +35,7 @@ jobs:
            if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo "server up"; break; fi
            sleep 2
          done
-      - uses: actions/setup-python@v7
+      - uses: actions/setup-python@v6
        with: { python-version: "3.12" }
      - name: Install schemathesis
        run: pip install schemathesis
--- a/.github/workflows/quality.yml
+++ b/.github/workflows/quality.yml
@@ -177,26 +177,17 @@ jobs:
          git fetch --no-tags origin "$GITHUB_BASE_REF" || true
          node scripts/quality/build-test-impact-map.mjs
          SEL="$(node scripts/quality/select-impacted-tests.mjs)"
-          # Shadow evidence (#8084): persist every selection so TIA false negatives can
-          # be measured against fast-unit's full-suite verdict across releases BEFORE
-          # any gate authority moves off ordinary PRs. Artifact uploaded below.
-          printf '%s\n' "$SEL" > tia-selection.txt
-          if [ -z "$SEL" ]; then
-            echo "TIA selection: empty (no source/test changes)" >> "$GITHUB_STEP_SUMMARY"
-            echo "No source/test changes — skipping unit tests"; exit 0
-          fi
+          if [ -z "$SEL" ]; then echo "No source/test changes — skipping unit tests"; exit 0; fi
          # CI runners are 4-vCPU; run at --test-concurrency=4 (matching the ci.yml unit
          # job) rather than test:unit's local-tuned concurrency=20. Oversubscribing the
          # runner makes timing-sensitive tests (db-backup, upstream-timeout, ...) flake,
          # which must not happen on a blocking gate. DATA_DIR isolation keeps the parallel
          # run race-free regardless of concurrency.
          if echo "$SEL" | grep -q "__RUN_ALL__"; then
-            echo "TIA selection: __RUN_ALL__ (fail-safe) — full-suite authority stays with fast-unit" >> "$GITHUB_STEP_SUMMARY"
            echo "Fail-safe: __RUN_ALL__ — deferring FULL unit suite to fast-unit (4-shard)."
            echo "Not re-running unsharded test:unit:ci here (duplicate of fast-unit coverage)."
            exit 0
          fi
-          echo "TIA selection: $(grep -c . tia-selection.txt) impacted test file(s) — full suite still runs in fast-unit (shadow-evidence phase, #8084)" >> "$GITHUB_STEP_SUMMARY"
          echo "Running impacted tests:"; echo "$SEL"
          mapfile -t FILES <<< "$SEL"
          # Loader parity with test:unit:ci:shard (#6787): tests/unit/dashboard/** runs
@@ -219,16 +210,6 @@ jobs:
            node --import tsx --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${DASH[@]}" || RC=$?
          fi
          exit $RC
-      # #8084 shadow evidence: keep the raw selection downloadable so TIA misses can be
-      # audited against fast-unit failures on the same run (gate moves need this data).
-      - name: Upload TIA selection (shadow evidence)
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: tia-selection
-          path: tia-selection.txt
-          if-no-files-found: ignore
-          retention-days: 30

  fast-vitest:
    name: Vitest (fast-path)
--- a/.github/workflows/scorecard.yml
+++ b/.github/workflows/scorecard.yml
@@ -26,7 +26,7 @@ jobs:
          persist-credentials: false

      - name: Run analysis
-        uses: ossf/scorecard-action@v2.4.4
+        uses: ossf/scorecard-action@v2.4.3
        with:
          results_file: results.sarif
          results_format: sarif
--- a/.github/workflows/semgrep.yml
+++ b/.github/workflows/semgrep.yml
@@ -6,12 +6,6 @@ on:
    branches: ["main"]
 permissions:
  contents: read
-
-# Cancel superseded PR runs (same rule as quality.yml). No paths filter on purpose:
-# p/secrets must keep scanning docs-only diffs too — credentials leak in .md files.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
 jobs:
  semgrep:
    runs-on: ubuntu-latest
--- a/.prettierignore
+++ b/.prettierignore
@@ -3,9 +3,3 @@ docs/reference/ENVIRONMENT.md

 # Dense auto-generated free-tier budget rows (one object per line) — prettier multi-line expand blows past file-size cap 800.
 open-sse/config/freeModelCatalog.data.ts
-
-# Generated by scripts/skills/generate-agent-skills.mjs; the generator is their
-# formatter of record and check:agent-skills-sync diffs its output byte-for-byte.
-# Prettier reformats the frontmatter (blank line after ---), which makes the gate
-# fail on any skill that happens to pass through lint-staged.
-skills/*/SKILL.md
--- a/@omniroute/opencode-plugin/README.md
+++ b/@omniroute/opencode-plugin/README.md
@@ -10,8 +10,7 @@ This plugin solves that by:

 - Fetching `/v1/models` and `/api/combos` **at OpenCode startup, in Node.js** — no CORS, no WebView restrictions
 - Emitting the provider block **dynamically** in the plugin's `config`/`provider` hook — so `opencode.json` only needs the plugin entry, not a static `provider.omniroute`
- Re-fetching on a configurable TTL (default 5 min) **and** background auto-discovery while OpenCode is running (`autoSyncIntervalMs`, default 5 min), so new models / combo changes appear without restarting OpenCode
- Exposing a force-refresh path (`omniroute_sync_models` tool + `/omni-sync` command template) equivalent to Pi `/omni sync`
+- Re-fetching on a configurable TTL (default 5 min), so new models / combo changes in the OmniRoute UI appear without restarting OpenCode
 - Computing `limit.context` for combos as `min(member.context_length)` from the live catalog (no more `null` values that cause 4K-token truncation)
 - **Auto-pickup of `interleaved` capability** for thinking models (merged via PR #3138)

@@ -74,9 +73,6 @@ Peer dep: `@opencode-ai/plugin` (managed by your OpenCode install).
      {
        "providerId": "omniroute",
        "baseURL": "https://or.example.com",
-        // Background re-discovery while OpenCode is running (Pi parity).
-        // Default 300000 (5 min). Minimum 60000. Set 0 to disable.
-        "autoSyncIntervalMs": 300000,
      },
    ],
  ],
@@ -92,27 +88,6 @@ opencode auth login --provider omniroute

 Restart OpenCode. `/models` lists the full live catalog. Variants (`-low`, `-medium`, `-high`, `-thinking`) and combos appear as first-class IDs — OmniRoute is the source of truth, no client-side synthesis.

-### Live catalog refresh (auto + force)
-
-While OpenCode is running, the plugin keeps the model catalog fresh in two ways:
-
-| Mechanism | Default | What it does |
-| --- | --- | --- |
-| `modelCacheTtl` | `300000` (5 min) | On-demand TTL: next provider/models hook after expiry re-fetches `/v1/models` |
-| `autoSyncIntervalMs` | `300000` (5 min) | Background timer: proactively invalidates + re-fetches while the harness is running. Min `60000`. Set `0` to disable background polling (TTL still applies) |
-
-**Force sync now** (Pi `/omni sync` equivalent) — OpenCode has no Pi-style slash-command registration API, so the plugin wires both a tool and command templates:
-
-1. **Tool:** `omniroute_sync_models` — invalidates in-memory + disk caches, re-fetches `GET /v1/models` (and combos/enrichment when enabled), returns `{ ok, count, ... }`.
-2. **Command templates** (type these in OpenCode):
-   - `/omni-sync` — asks the agent to call `omniroute_sync_models` and report the result
-   - `/omni-autosync` — asks the agent to report current `autoSyncIntervalMs` / `modelCacheTtl` status
-
-```text
-/omni-sync
-/omni-autosync
-```
-
 ## Multi-instance (prod + preprod side-by-side)

 > ⚠ OC ≤1.15.5 dedupes plugin loads by absolute module path. Two `plugin:` entries pointing at the same `dist/index.js` collapse into one (last-listed options win). Workaround: install the plugin twice into separate directories so each entry resolves to a distinct module file. v0.2.x will introduce an `instances: [...]` shape that registers N providers from a single load.
--- a/@omniroute/opencode-plugin/package.json
+++ b/@omniroute/opencode-plugin/package.json
@@ -1,6 +1,6 @@
 {
  "name": "@omniroute/opencode-plugin",
-  "version": "0.2.1",
+  "version": "0.2.0",
  "description": "OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @opencode-ai/plugin contract.",
  "type": "module",
  "main": "./dist/index.js",
@@ -23,7 +23,7 @@
  "scripts": {
    "build": "tsup",
    "clean": "rm -rf dist",
-    "test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts tests/auto-sync.test.ts",
+    "test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts",
    "prepublishOnly": "npm run clean && npm run build && npm test"
  },
  "keywords": [
--- a/@omniroute/opencode-plugin/src/index.ts
+++ b/@omniroute/opencode-plugin/src/index.ts
@@ -46,7 +46,7 @@
 */

 import { createHash } from "node:crypto";
-import { mkdir, readFile, unlink, writeFile } from "node:fs/promises";
+import { mkdir, readFile, writeFile } from "node:fs/promises";
 import * as os from "node:os";
 import * as path from "node:path";
 import { appendFileSync, existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
@@ -54,7 +54,6 @@ import { homedir } from "node:os";
 import { join } from "node:path";
 import { randomUUID } from "node:crypto";
 import type { AuthHook, Config, Plugin, PluginOptions, ProviderHook } from "@opencode-ai/plugin";
-import { tool } from "@opencode-ai/plugin";
 import type { Model as ModelV2 } from "@opencode-ai/sdk/v2";
 import { z } from "zod";
 import { logger as _logger, setLogLevel, type LogLevel as _LogLevel } from "./logger.js";
@@ -89,10 +88,6 @@ import {
 *                     from providerId.
 *  - `modelCacheTtl`  `/v1/models` TTL cache duration in milliseconds.
 *                     Default: 300_000 (5 min).
- *  - `autoSyncIntervalMs` Background catalog re-discovery while OpenCode is
- *                     running. Default: 300_000 (5 min). Minimum: 60_000.
- *                     Set `0` to disable background auto-sync (TTL on-demand
- *                     discovery still applies via `modelCacheTtl`).
 *  - `baseURL`        Override base URL for this OmniRoute instance. When
 *                     absent, the loader falls back to a credential-attached
 *                     baseURL set by `/connect`.
@@ -195,12 +190,6 @@ const optionsSchema = z
      .optional(),
    displayName: z.string().min(1).optional(),
    modelCacheTtl: z.number().positive().optional(),
-    /**
-     * Background auto-discovery interval while the harness is running.
-     * `0` disables background polling. Values in (0, 60000) are clamped up
-     * to 60000. Default when unset: 300000.
-     */
-    autoSyncIntervalMs: z.number().int().nonnegative().optional(),
    baseURL: z.string().url().optional(),
    managementReadToken: z.string().min(1).optional(),
    features: featuresSchema.optional(),
@@ -228,29 +217,6 @@ export const PLUGIN_GIT_HASH: string =

 export const DEFAULT_MODEL_CACHE_TTL_MS = 300_000 as const;

-/** Default background auto-discovery interval (matches modelCacheTtl default). */
-export const DEFAULT_AUTO_SYNC_INTERVAL_MS = 300_000 as const;
-
-/** Minimum positive background auto-discovery interval. */
-export const MIN_AUTO_SYNC_INTERVAL_MS = 60_000 as const;
-
-/**
- * Sanitize background auto-sync interval.
- *  - unset/invalid → default 300_000
- *  - explicit 0 → disabled
- *  - (0, 60000) → clamped to 60000
- *  - ≥ 60000 → kept as integer ms
- */
-export function sanitizeAutoSyncIntervalMs(value: unknown): number {
-  if (value === undefined || value === null) return DEFAULT_AUTO_SYNC_INTERVAL_MS;
-  if (typeof value !== "number" || !Number.isFinite(value)) return DEFAULT_AUTO_SYNC_INTERVAL_MS;
-  const n = Math.trunc(value);
-  if (n === 0) return 0;
-  if (n < 0) return DEFAULT_AUTO_SYNC_INTERVAL_MS;
-  if (n < MIN_AUTO_SYNC_INTERVAL_MS) return MIN_AUTO_SYNC_INTERVAL_MS;
-  return n;
-}
-
 // Manual trim helpers avoid polynomial-regex CodeQL warnings on
 // user-supplied baseURL strings (string.replace(/\/+$/, "")). The same
 // behaviour, no backtracking.
@@ -277,7 +243,7 @@ function trimLeadingDashes(value: string): string {
 * sees a consistent identifier.
 */
 export function resolveOmniRoutePluginOptions(opts?: OmniRoutePluginOptions): Required<
-  Pick<OmniRoutePluginOptions, "providerId" | "displayName" | "modelCacheTtl" | "autoSyncIntervalMs">
+  Pick<OmniRoutePluginOptions, "providerId" | "displayName" | "modelCacheTtl">
 > & {
  /**
   * #6859: the UNPREFIXED provider id ("omniroute", "omniroute-preprod", …).
@@ -311,22 +277,17 @@ export function resolveOmniRoutePluginOptions(opts?: OmniRoutePluginOptions): Re
    typeof opts?.modelCacheTtl === "number" && opts.modelCacheTtl > 0
      ? opts.modelCacheTtl
      : DEFAULT_MODEL_CACHE_TTL_MS;
-  const autoSyncIntervalMs = sanitizeAutoSyncIntervalMs(opts?.autoSyncIntervalMs);
  return {
    providerId,
    omnirouteProviderId,
    displayName,
    modelCacheTtl,
-    autoSyncIntervalMs,
    baseURL: opts?.baseURL,
    managementReadToken: opts?.managementReadToken,
    features: opts?.features,
  };
 }

-/** Fully resolved plugin options (defaults applied). */
-export type ResolvedOmniRoutePluginOptions = ReturnType<typeof resolveOmniRoutePluginOptions>;
-
 /**
 * Strip a leading "opencode-" prefix (added only for the OC native-adapter
 * gate — see `resolveOmniRoutePluginOptions`) so the returned id is safe to
@@ -562,378 +523,8 @@ export function createOmniRouteAuthHook(opts?: OmniRoutePluginOptions): AuthHook
 * opencode.json), NOT as a closure binding. Multi-instance support follows
 * from each plugin tuple invoking the factory with its own opts.
 */
-/**
- * Invalidate in-memory fetch cache entries for a baseURL (all credential keys).
- * Returns number of entries removed.
- */
-export function invalidateOmniRouteFetchCache(
-  cache: OmniRouteFetchCache,
-  baseURL?: string,
-): number {
-  if (!baseURL) {
-    const n = cache.size;
-    cache.clear();
-    return n;
-  }
-  const prefix = `${baseURL}::`;
-  let removed = 0;
-  for (const key of [...cache.keys()]) {
-    if (key.startsWith(prefix) || key === baseURL) {
-      cache.delete(key);
-      removed += 1;
-    }
-  }
-  return removed;
-}
-
-/**
- * Resolve API credentials for force-sync / background refresh without
- * depending on the provider.models auth context.
- */
-export async function resolveOmniRouteRuntimeAuth(
-  resolved: ResolvedOmniRoutePluginOptions,
-  readAuthJson?: OmniRouteReadAuthJson,
-): Promise<{ apiKey: string; baseURL: string; managementReadToken: string } | null> {
-  const reader = readAuthJson ?? defaultReadAuthJson;
-  let authJson: AuthJsonShape | undefined | null;
-  try {
-    authJson = await reader();
-  } catch {
-    authJson = undefined;
-  }
-  if (authJson === null) authJson = undefined;
-
-  const bareKey = resolved.providerId.startsWith("opencode-")
-    ? resolved.providerId.slice("opencode-".length)
-    : resolved.providerId;
-  const lookupKeys = [resolved.providerId];
-  if (bareKey !== resolved.providerId) lookupKeys.push(bareKey);
-  if (resolved.omnirouteProviderId && !lookupKeys.includes(resolved.omnirouteProviderId)) {
-    lookupKeys.push(resolved.omnirouteProviderId);
-  }
-
-  let entry: AuthJsonApiEntry | undefined;
-  for (const k of lookupKeys) {
-    const e = authJson?.[k];
-    if (
-      e &&
-      (e as { type?: unknown }).type === "api" &&
-      typeof (e as { key?: unknown }).key === "string" &&
-      ((e as { key: string }).key).length > 0
-    ) {
-      entry = e as AuthJsonApiEntry;
-      break;
-    }
-  }
-  const apiKey = entry?.key ?? "";
-  if (!apiKey) return null;
-
-  const authBaseURL =
-    entry && typeof (entry as { baseURL?: unknown }).baseURL === "string"
-      ? (entry as { baseURL: string }).baseURL
-      : "";
-  const baseURL = resolved.baseURL ?? (authBaseURL || "");
-  if (!baseURL) return null;
-  const managementReadToken = resolved.managementReadToken ?? apiKey;
-  return { apiKey, baseURL, managementReadToken };
-}
-
-/**
- * Force-refresh OmniRoute catalog: clear memory + disk cache, re-fetch /v1/models
- * (and optional management endpoints), and repopulate the shared cache.
- * OpenCode equivalent of Pi `/omni sync`.
- */
-export async function forceSyncOmniRouteModels(args: {
-  resolved: ResolvedOmniRoutePluginOptions;
-  cache: OmniRouteFetchCache;
-  readAuthJson?: OmniRouteReadAuthJson;
-  fetcher?: OmniRouteModelsFetcher;
-  combosFetcher?: OmniRouteCombosFetcher;
-  autoCombosFetcher?: OmniRouteAutoCombosFetcher;
-  enrichmentFetcher?: OmniRouteEnrichmentFetcher;
-  compressionMetaFetcher?: OmniRouteCompressionMetaFetcher;
-  providersFetcher?: OmniRouteProvidersFetcher;
-  now?: () => number;
-}): Promise<{
-  ok: boolean;
-  count: number;
-  combos: number;
-  provider: string;
-  baseURL?: string;
-  clearedMemory: number;
-  clearedDisk: boolean;
-  error?: string;
-}> {
-  const resolved = args.resolved;
-  const cache = args.cache;
-  const now = args.now ?? Date.now;
-  const fetcher = args.fetcher ?? defaultOmniRouteModelsFetcher;
-  const combosFetcher = args.combosFetcher ?? defaultOmniRouteCombosFetcher;
-  const autoCombosFetcher = args.autoCombosFetcher ?? defaultOmniRouteAutoCombosFetcher;
-  const enrichmentFetcher = args.enrichmentFetcher ?? defaultOmniRouteEnrichmentFetcher;
-  const compressionMetaFetcher =
-    args.compressionMetaFetcher ?? defaultOmniRouteCompressionMetaFetcher;
-  const providersFetcher = args.providersFetcher ?? defaultOmniRouteProvidersFetcher;
-  const features = resolved.features ?? {};
-  const wantCombos = features.combos !== false;
-  const wantAutoCombos = features.autoCombos !== false;
-  const wantEnrichment = features.enrichment !== false;
-  const wantCompressionMeta = features.compressionMetadata === true;
-  const wantUsableOnly = features.usableOnly === true;
-  const wantDiskCache = features.diskCache !== false;
-
-  const auth = await resolveOmniRouteRuntimeAuth(
-    resolved,
-    args.readAuthJson ?? defaultReadAuthJson,
-  );
-  if (!auth) {
-    return {
-      ok: false,
-      count: 0,
-      combos: 0,
-      provider: resolved.omnirouteProviderId,
-      clearedMemory: 0,
-      clearedDisk: false,
-      error:
-        "No OmniRoute credentials/baseURL available. Run `opencode connect omniroute` or set plugin baseURL.",
-    };
-  }
-
-  const clearedMemory = invalidateOmniRouteFetchCache(cache, auth.baseURL);
-  // Clear residual entries from prior baseURL history as well.
-  const clearedAll = invalidateOmniRouteFetchCache(cache);
-  let clearedDisk = false;
-  if (wantDiskCache) {
-    clearedDisk = await clearDiskSnapshot(resolved.providerId);
-    if (resolved.omnirouteProviderId !== resolved.providerId) {
-      clearedDisk = (await clearDiskSnapshot(resolved.omnirouteProviderId)) || clearedDisk;
-    }
-  }
-
-  try {
-    const rawModels = await fetcher(auth.baseURL, auth.apiKey, 10_000);
-    let rawCombos: OmniRouteRawCombo[] = [];
-    if (wantCombos) {
-      try {
-        rawCombos = await combosFetcher(auth.baseURL, auth.managementReadToken, 10_000);
-      } catch (err) {
-        console.warn("[omniroute-plugin] force sync: combos fetch failed", err);
-      }
-    }
-    let rawAutoCombos: OmniRouteRawAutoCombo[] = [];
-    if (wantAutoCombos) {
-      try {
-        rawAutoCombos = await autoCombosFetcher(auth.baseURL, auth.managementReadToken, 5_000);
-      } catch {
-        /* soft-fail */
-      }
-    }
-    let rawEnrichment: OmniRouteEnrichmentMap = new Map();
-    if (wantEnrichment) {
-      try {
-        rawEnrichment = await enrichmentFetcher(auth.baseURL, auth.managementReadToken, 10_000);
-      } catch {
-        rawEnrichment = new Map();
-      }
-    }
-    let rawCompressionCombos: OmniRouteCompressionCombo[] = [];
-    if (wantCompressionMeta) {
-      try {
-        rawCompressionCombos = await compressionMetaFetcher(
-          auth.baseURL,
-          auth.managementReadToken,
-          10_000,
-        );
-      } catch {
-        rawCompressionCombos = [];
-      }
-    }
-    let rawConnections: OmniRouteProviderConnection[] = [];
-    if (wantUsableOnly) {
-      try {
-        rawConnections = await providersFetcher(auth.baseURL, auth.managementReadToken, 10_000);
-      } catch {
-        rawConnections = [];
-      }
-    }
-
-    const t = now();
-    const entry = {
-      rawModels,
-      rawCombos,
-      rawAutoCombos,
-      rawEnrichment,
-      rawCompressionCombos,
-      rawConnections,
-      expiresAt: t + resolved.modelCacheTtl,
-    };
-    const cacheKey = modelsCacheKey(
-      auth.baseURL,
-      `${auth.apiKey}\0${auth.managementReadToken}`,
-    );
-    cache.set(cacheKey, entry);
-
-    if (wantDiskCache) {
-      try {
-        const fingerprint = diskSnapshotIdentityFingerprint(
-          auth.baseURL,
-          auth.apiKey,
-          auth.managementReadToken,
-        );
-        const { expiresAt: _expiresAt, ...diskEntry } = entry;
-        await defaultDiskSnapshotWriter(resolved.providerId, diskEntry, fingerprint);
-      } catch {
-        /* soft-fail disk write */
-      }
-    }
-
-    console.warn(
-      `[omniroute-plugin] force sync ok providerId=${resolved.providerId} ` +
-        `models=${rawModels.length} combos=${rawCombos.length} ` +
-        `clearedMemory=${clearedMemory + clearedAll} disk=${clearedDisk}`,
-    );
-
-    return {
-      ok: true,
-      count: rawModels.length,
-      combos: rawCombos.length,
-      provider: resolved.omnirouteProviderId,
-      baseURL: auth.baseURL,
-      clearedMemory: clearedMemory + clearedAll,
-      clearedDisk,
-    };
-  } catch (err) {
-    const message = err instanceof Error ? err.message : String(err);
-    return {
-      ok: false,
-      count: 0,
-      combos: 0,
-      provider: resolved.omnirouteProviderId,
-      baseURL: auth.baseURL,
-      clearedMemory: clearedMemory + clearedAll,
-      clearedDisk,
-      error: message,
-    };
-  }
-}
-
-export function createOmniRouteSyncModelsTool(args: {
-  resolved: ResolvedOmniRoutePluginOptions;
-  cache: OmniRouteFetchCache;
-}): ReturnType<typeof tool> {
-  const { resolved, cache } = args;
-  return tool({
-    description:
-      "Force-refresh the OmniRoute model catalog (OpenCode equivalent of Pi `/omni sync`). " +
-      "Invalidates in-memory and disk caches, then re-fetches GET /v1/models (and combos when enabled).",
-    args: {
-      reason: tool.schema
-        .string()
-        .optional()
-        .describe("Optional reason for the sync (logging only)"),
-    },
-    async execute(toolArgs) {
-      const result = await forceSyncOmniRouteModels({ resolved, cache });
-      const reason = toolArgs.reason ? ` reason=${toolArgs.reason}` : "";
-      if (!result.ok) {
-        return {
-          title: "OmniRoute sync failed",
-          output:
-            `OmniRoute model sync failed for provider=${result.provider}.${reason}\n` +
-            `${result.error ?? "unknown error"}`,
-          metadata: result,
-        };
-      }
-      return {
-        title: `OmniRoute sync: ${result.count} models`,
-        output:
-          `OmniRoute models synced.` +
-          `\nprovider: ${result.provider}` +
-          `\nbaseURL: ${result.baseURL}` +
-          `\nmodels: ${result.count}` +
-          `\ncombos: ${result.combos}` +
-          `\nclearedMemoryEntries: ${result.clearedMemory}` +
-          `\nclearedDiskSnapshot: ${result.clearedDisk}` +
-          `\nTTL: ${resolved.modelCacheTtl}ms` +
-          `\nautoSyncIntervalMs: ${resolved.autoSyncIntervalMs}` +
-          reason,
-        metadata: result,
-      };
-    },
-  });
-}
-
-/**
- * Start background auto-discovery while the harness is running.
- * Quiet: only logs when the model count changes or on errors.
- * Returns a stop function.
- */
-export function startOmniRouteAutoSync(args: {
-  resolved: ResolvedOmniRoutePluginOptions;
-  cache: OmniRouteFetchCache;
-  intervalMs?: number;
-}): () => void {
-  const resolved = args.resolved;
-  const cache = args.cache;
-  const intervalMs = args.intervalMs ?? resolved.autoSyncIntervalMs;
-  if (!intervalMs || intervalMs <= 0) {
-    return () => {};
-  }
-
-  let stopped = false;
-  let inFlight: Promise<void> | null = null;
-  let lastCount: number | undefined;
-
-  const tick = () => {
-    if (stopped) return;
-    if (inFlight) return;
-    inFlight = (async () => {
-      const result = await forceSyncOmniRouteModels({ resolved, cache });
-      if (!result.ok) {
-        console.warn(
-          `[omniroute-plugin] auto-sync failed providerId=${resolved.providerId}: ${result.error}`,
-        );
-        return;
-      }
-      if (lastCount === undefined) {
-        lastCount = result.count;
-        return;
-      }
-      if (result.count !== lastCount) {
-        console.warn(
-          `[omniroute-plugin] auto-sync catalog size changed ${lastCount} → ${result.count} ` +
-            `(providerId=${resolved.providerId})`,
-        );
-        lastCount = result.count;
-      }
-    })()
-      .catch((err) => {
-        console.warn("[omniroute-plugin] auto-sync tick error", err);
-      })
-      .finally(() => {
-        inFlight = null;
-      });
-  };
-
-  // Delay first background tick by one interval so session start is not doubled
-  // with the normal provider.models cold fetch. Manual tool remains immediate.
-  const timer = setInterval(tick, intervalMs);
-  if (typeof timer === "object" && timer && "unref" in timer && typeof timer.unref === "function") {
-    timer.unref();
-  }
-
-  console.warn(
-    `[omniroute-plugin] auto-sync enabled intervalMs=${intervalMs} providerId=${resolved.providerId}`,
-  );
-
-  return () => {
-    stopped = true;
-    clearInterval(timer);
-  };
-}
-
 export const OmniRoutePlugin: Plugin = async (_input, options) => {
-  const resolved = resolveOmniRoutePluginOptions(coercePluginOptions(options));
+  const resolved = coercePluginOptions(options);
  // T-07: a single per-plugin-instance cache shared between the provider
  // hook (T-03/T-05) and the config-shim hook (T-07). On OC ≥1.14.49 both
  // hooks fire within the same Plugin invocation, so a shared cache keeps
@@ -962,53 +553,10 @@ export const OmniRoutePlugin: Plugin = async (_input, options) => {

  // Wire log level: startupDebug:true → "debug", explicit logLevel wins.
  setLogLevel(resolved.features?.startupDebug ? "debug" : (resolved.features?.logLevel ?? "warn"));
-
-  // Background auto-discovery while the harness is running (Pi parity).
-  // Interval 0 disables. TTL on-demand discovery still works via modelCacheTtl.
-  startOmniRouteAutoSync({ resolved, cache: sharedCache });
-
-  const syncTool = createOmniRouteSyncModelsTool({ resolved, cache: sharedCache });
-  const bareProviderId = resolved.omnirouteProviderId;
-
-  // Config hook: keep existing catalog shim, and register slash command
-  // templates that ask the agent to call the force-sync tool (OpenCode has no
-  // Pi-style registerCommand API; tools + command templates are the native path).
-  const baseConfigHook = createOmniRouteConfigHook(resolved, { cache: sharedCache });
-  const configWithSyncCommand = async (input: Config) => {
-    await baseConfigHook(input);
-    const cfg = input as Config & {
-      command?: Record<
-        string,
-        { template: string; description?: string; agent?: string; model?: string; subtask?: boolean }
-      >;
-    };
-    if (!cfg.command) cfg.command = {};
-    if (!cfg.command["omni-sync"]) {
-      cfg.command["omni-sync"] = {
-        description: "Force-refresh OmniRoute model catalog (like Pi /omni sync)",
-        template:
-          `Force-refresh the OmniRoute model catalog now using the omniroute_sync_models tool ` +
-          `(provider ${bareProviderId}). After the tool returns, briefly report model count and whether the sync succeeded.`,
-      };
-    }
-    if (!cfg.command["omni-autosync"]) {
-      cfg.command["omni-autosync"] = {
-        description: "Show OmniRoute auto-sync / cache status",
-        template:
-          `Report OmniRoute discovery status for provider ${bareProviderId}: ` +
-          `autoSyncIntervalMs=${resolved.autoSyncIntervalMs}, modelCacheTtl=${resolved.modelCacheTtl}. ` +
-          `If the user asked to refresh now, call omniroute_sync_models.`,
-      };
-    }
-  };
-
  return {
    auth: createOmniRouteAuthHook(resolved),
    provider: createOmniRouteProviderHook(resolved, { cache: sharedCache }),
-    config: configWithSyncCommand,
-    tool: {
-      omniroute_sync_models: syncTool,
-    },
+    config: createOmniRouteConfigHook(resolved, { cache: sharedCache }),
  };
 };

@@ -4513,19 +4061,6 @@ export function diskSnapshotPath(providerId: string): string {
  return path.join(dir, "plugins", `omniroute-${providerId}.json`);
 }

-/** Best-effort delete of the disk snapshot for a provider (force-sync). */
-export async function clearDiskSnapshot(providerId: string): Promise<boolean> {
-  const file = diskSnapshotPath(providerId);
-  try {
-    await unlink(file);
-    return true;
-  } catch (err) {
-    const code = (err as NodeJS.ErrnoException | undefined)?.code;
-    if (code === "ENOENT") return false;
-    return false;
-  }
-}
-
 export type OmniRouteDiskSnapshotWriter = (
  providerId: string,
  entry: Omit<OmniRouteFetchCacheEntry, "expiresAt">,
--- a/@omniroute/opencode-plugin/tests/auto-sync.test.ts
+++ b/@omniroute/opencode-plugin/tests/auto-sync.test.ts
@@ -1,130 +0,0 @@
-/**
- * Auto-discovery + force-sync (OpenCode parity with Pi `/omni sync`).
- */
-import test from "node:test";
-import assert from "node:assert/strict";
-import {
-  sanitizeAutoSyncIntervalMs,
-  DEFAULT_AUTO_SYNC_INTERVAL_MS,
-  MIN_AUTO_SYNC_INTERVAL_MS,
-  parseOmniRoutePluginOptions,
-  resolveOmniRoutePluginOptions,
-  invalidateOmniRouteFetchCache,
-  forceSyncOmniRouteModels,
-  type OmniRouteFetchCache,
-} from "../src/index.js";
-
-test("sanitizeAutoSyncIntervalMs: unset → default 300000", () => {
-  assert.equal(sanitizeAutoSyncIntervalMs(undefined), DEFAULT_AUTO_SYNC_INTERVAL_MS);
-  assert.equal(sanitizeAutoSyncIntervalMs(null), DEFAULT_AUTO_SYNC_INTERVAL_MS);
-});
-
-test("sanitizeAutoSyncIntervalMs: 0 disables", () => {
-  assert.equal(sanitizeAutoSyncIntervalMs(0), 0);
-});
-
-test("sanitizeAutoSyncIntervalMs: clamps below min to 60000", () => {
-  assert.equal(sanitizeAutoSyncIntervalMs(1), MIN_AUTO_SYNC_INTERVAL_MS);
-  assert.equal(sanitizeAutoSyncIntervalMs(59_999), MIN_AUTO_SYNC_INTERVAL_MS);
-});
-
-test("sanitizeAutoSyncIntervalMs: keeps valid values", () => {
-  assert.equal(sanitizeAutoSyncIntervalMs(60_000), 60_000);
-  assert.equal(sanitizeAutoSyncIntervalMs(300_000), 300_000);
-});
-
-test("parseOmniRoutePluginOptions accepts autoSyncIntervalMs including 0", () => {
-  assert.equal(parseOmniRoutePluginOptions({ autoSyncIntervalMs: 0 }).autoSyncIntervalMs, 0);
-  assert.equal(parseOmniRoutePluginOptions({ autoSyncIntervalMs: 120_000 }).autoSyncIntervalMs, 120_000);
-});
-
-test("resolveOmniRoutePluginOptions defaults autoSyncIntervalMs to 300000", () => {
-  const r = resolveOmniRoutePluginOptions({});
-  assert.equal(r.autoSyncIntervalMs, DEFAULT_AUTO_SYNC_INTERVAL_MS);
-});
-
-test("resolveOmniRoutePluginOptions clamps low positive autoSyncIntervalMs", () => {
-  const r = resolveOmniRoutePluginOptions({ autoSyncIntervalMs: 5000 });
-  assert.equal(r.autoSyncIntervalMs, MIN_AUTO_SYNC_INTERVAL_MS);
-});
-
-test("invalidateOmniRouteFetchCache clears by baseURL prefix", () => {
-  const cache: OmniRouteFetchCache = new Map();
-  cache.set("https://a.example/v1::abc", {
-    rawModels: [],
-    rawCombos: [],
-    rawAutoCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-    expiresAt: Date.now() + 1000,
-  });
-  cache.set("https://b.example/v1::def", {
-    rawModels: [],
-    rawCombos: [],
-    rawAutoCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-    expiresAt: Date.now() + 1000,
-  });
-  const removed = invalidateOmniRouteFetchCache(cache, "https://a.example/v1");
-  assert.equal(removed, 1);
-  assert.equal(cache.size, 1);
-  assert.equal(cache.has("https://b.example/v1::def"), true);
-});
-
-test("forceSyncOmniRouteModels: fetches, populates cache, returns count", async () => {
-  const cache: OmniRouteFetchCache = new Map();
-  const resolved = resolveOmniRoutePluginOptions({
-    providerId: "omniroute",
-    baseURL: "https://omniroute.example/v1",
-    autoSyncIntervalMs: 0,
-    features: {
-      combos: false,
-      autoCombos: false,
-      enrichment: false,
-      compressionMetadata: false,
-      usableOnly: false,
-      diskCache: false,
-    },
-  });
-
-  const result = await forceSyncOmniRouteModels({
-    resolved,
-    cache,
-    readAuthJson: async () => ({
-      omniroute: { type: "api", key: "test-key" },
-    }),
-    fetcher: async () => [
-      { id: "model-a", object: "model" },
-      { id: "model-b", object: "model" },
-    ],
-    now: () => 1_000_000,
-  });
-
-  assert.equal(result.ok, true);
-  assert.equal(result.count, 2);
-  assert.equal(result.provider, "omniroute");
-  assert.equal(cache.size, 1);
-  const entry = [...cache.values()][0];
-  assert.equal(entry.rawModels.length, 2);
-  assert.equal(entry.expiresAt, 1_000_000 + resolved.modelCacheTtl);
-});
-
-test("forceSyncOmniRouteModels: missing auth returns error", async () => {
-  const cache: OmniRouteFetchCache = new Map();
-  const resolved = resolveOmniRoutePluginOptions({
-    providerId: "omniroute",
-    baseURL: "https://omniroute.example/v1",
-    autoSyncIntervalMs: 0,
-    features: { diskCache: false },
-  });
-  const result = await forceSyncOmniRouteModels({
-    resolved,
-    cache,
-    readAuthJson: async () => ({}),
-  });
-  assert.equal(result.ok, false);
-  assert.match(result.error ?? "", /credentials|baseURL|connect/i);
-});
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -3,12 +3,12 @@
 ## Project

 Unified AI proxy/router — route any LLM through one endpoint. Multi-provider support
-with **290 provider entries** (OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Fireworks,
+with **271 provider entries** (OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Fireworks,
 Cohere, NVIDIA, Cerebras, Pollinations, Puter, Cloudflare AI, HuggingFace, DeepInfra,
 SambaNova, Meta Llama API, Moonshot AI, AI21 Labs, Databricks, Snowflake, and many more)
 with **MCP Server** (104 tools), **A2A v0.3 Protocol**, and **Electron desktop app**.

-> **Live counts (v3.8.49)**: providers 290 · MCP tools 104 · MCP scopes 30 · A2A skills 6 ·
+> **Live counts (v3.8.49)**: providers 271 · MCP tools 104 · MCP scopes 30 · A2A skills 6 ·
 > open-sse services 134 · routing strategies 17 · auto-combo scoring factors 12 ·
 > DB modules 95 · DB migrations 110 · base tables 17 · search providers 11 ·
 > i18n locales 42. **Refresh with `npm run check:docs-all`.**
@@ -570,16 +570,12 @@ This repository is a fork of `diegosouzapw/OmniRoute`. Keep fork-only operationa
 changes (for example GHCR image publishing, personal deployment workflows, or local
 automation) out of upstream contribution PRs.

-When preparing a PR for upstream, always start the work branch from the upstream
-**default branch** — the active `release/vX.Y.Z` line (today `release/v3.8.49`).
-Never branch from `main`: `main` only receives release squash-merges, so a branch
-cut there is weeks behind and produces conflict-heavy PRs
-(see `CONTRIBUTING.md` and `docs/ops/BRANCHING_MODEL.md`):
+When preparing a PR for upstream, always start the work branch from `upstream/main`,
+not from this fork's `main`:

 ```bash
 git fetch upstream
-# the default branch is the active release line, e.g. release/v3.8.49
-git switch -c <branch-name> upstream/release/vX.Y.Z
+git switch -c <branch-name> upstream/main
 ```

 Only cherry-pick or reapply the changes intended for the upstream PR.
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -90,71 +90,6 @@ _Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62
 - **feat(providers):** Speechmatics STT, gTTS, VibeProxy preset (#6659, #6667, #6874) ([#7655](https://github.com/diegosouzapw/OmniRoute/pull/7655))
 - **feat(api):** route Google AI Studio Imagen through /v1/images/generations ([#7656](https://github.com/diegosouzapw/OmniRoute/pull/7656)) — thanks @danscMax

- **feat(auth):** OIDC as optional dashboard admin login gate (password fallback preserved) ([#6973](https://github.com/diegosouzapw/OmniRoute/pull/6973)) — thanks @mikolaj92
- **feat(api):** add pagination params to 8 DB modules + recharts code-split ([#7046](https://github.com/diegosouzapw/OmniRoute/pull/7046)) — thanks @oyi77
- **feat(proxy):** operator-level proxy subscriptions (Karing-style) — hardened, ready for review ([#7299](https://github.com/diegosouzapw/OmniRoute/pull/7299)) — thanks @xier2012
- **feat(grok-cli):** align with official Grok Build client ([#7358](https://github.com/diegosouzapw/OmniRoute/pull/7358)) — thanks @backryun
- **feat(providers):** Complete GHE Copilot OAuth provider implementation ([#7546](https://github.com/diegosouzapw/OmniRoute/pull/7546)) — thanks @hppsc1215
- **feat(guardrails):** add CredentialMaskerGuardrail for API key/secret redaction ([#7683](https://github.com/diegosouzapw/OmniRoute/pull/7683)) — thanks @Securiteru
- **feat(perplexity):** refresh provider integrations ([#7687](https://github.com/diegosouzapw/OmniRoute/pull/7687)) — thanks @backryun
- **feat(providers):** notion-web live model discovery via getAvailableModels ([#7696](https://github.com/diegosouzapw/OmniRoute/pull/7696)) — thanks @artickc
- **feat(providers):** add proactive cf_clearance/User-Agent hint to grok-web connection dialog (#7567) ([#7713](https://github.com/diegosouzapw/OmniRoute/pull/7713))
- **feat:** add live gRPC-web quota fetcher for grok-cli (#6844) ([#7714](https://github.com/diegosouzapw/OmniRoute/pull/7714))
- **feat(api):** add opt-in auto-sync scheduler for free-proxy sources (#7079) ([#7716](https://github.com/diegosouzapw/OmniRoute/pull/7716))
- **feat(dashboard):** show proxy name in badge, sort saved-proxy picker, default to Saved tab (#7643) ([#7720](https://github.com/diegosouzapw/OmniRoute/pull/7720))
- **feat(cli):** add auth export command for decrypted provider credentials (#6683) ([#7724](https://github.com/diegosouzapw/OmniRoute/pull/7724))
- **feat(oauth):** accept full ChatGPT session JSON for Codex manual import (#6636) ([#7725](https://github.com/diegosouzapw/OmniRoute/pull/7725))
- **feat(sse):** add nvidia NIM local RPM budget + concurrency cap (#6846) ([#7726](https://github.com/diegosouzapw/OmniRoute/pull/7726))
- **feat(gemini-web):** emulate OpenAI tool calling via the webTools prompt shim (#7286) ([#7727](https://github.com/diegosouzapw/OmniRoute/pull/7727))
- **feat(services):** introduce pluggable service-provider contract, migrate 9router (#7333) ([#7730](https://github.com/diegosouzapw/OmniRoute/pull/7730))
- **feat(mitm):** root-CA + per-host leaf certs for AgentBridge static server (#6684) ([#7731](https://github.com/diegosouzapw/OmniRoute/pull/7731))
- **feat(providers):** add hailuo-web (MiniMax web) chat provider (#6673) ([#7734](https://github.com/diegosouzapw/OmniRoute/pull/7734))
- **feat:** browser login for Grok Build provider (#7013) ([#7735](https://github.com/diegosouzapw/OmniRoute/pull/7735))
- **feat(routing):** wire interceptFetch tool interception into the chat pipeline (#7339) ([#7736](https://github.com/diegosouzapw/OmniRoute/pull/7736))
- **feat(sse):** add X-OmniRoute-Decision routing trace header (#6022) ([#7765](https://github.com/diegosouzapw/OmniRoute/pull/7765))
- **feat(providers):** zai-web live model discovery with local-catalog fallback (#7678) ([#7766](https://github.com/diegosouzapw/OmniRoute/pull/7766))
- **feat(api):** sync upstream reasoning.supported_efforts into synced-model catalog (#7694) ([#7767](https://github.com/diegosouzapw/OmniRoute/pull/7767))
- **feat(dashboard):** pin Kimi providers first in category + official supporter card accent ([#7775](https://github.com/diegosouzapw/OmniRoute/pull/7775))
- **feat(chaos+ponytail):** parallel chaos-mode dispatch + ponytail output … ([#7781](https://github.com/diegosouzapw/OmniRoute/pull/7781)) — thanks @Moseyuh333
- **feat(perf):** IC2 — cache provider connections by ID + lazy-decrypt credentials ([#7787](https://github.com/diegosouzapw/OmniRoute/pull/7787)) — thanks @oyi77
- **feat(quality):** gate the free-tier headline so it can never silently drift again ([#7798](https://github.com/diegosouzapw/OmniRoute/pull/7798))
- **feat(providers):** expose an explicit tier override for any provider connection (#7818) ([#7838](https://github.com/diegosouzapw/OmniRoute/pull/7838))
- **feat(routing):** read-only auto/* candidate transparency + per-API-key exclusions (#7819) ([#7839](https://github.com/diegosouzapw/OmniRoute/pull/7839))
- **feat(catalog):** map unmapped free tiers, add navy + aihorde, surface keyless providers ([#7840](https://github.com/diegosouzapw/OmniRoute/pull/7840))
- **feat(providers):** add OpenRouter speech-to-text (audio transcription) provider ([#7861](https://github.com/diegosouzapw/OmniRoute/pull/7861)) — thanks @Tasogarre
- **feat(qwen):** add Qwen3.8 Max Preview catalogs [Part 2/3] ([#7874](https://github.com/diegosouzapw/OmniRoute/pull/7874)) — thanks @backryun
- **feat:** support Bun bundled SQLite runtime ([#7878](https://github.com/diegosouzapw/OmniRoute/pull/7878)) — thanks @Arul-
- **feat(providers):** add 5 free-tier providers (ainative, aion, sealion, routeway, nara) ([#7887](https://github.com/diegosouzapw/OmniRoute/pull/7887))
- **feat(vnc-session):** persistent noVNC browser login for web-cookie providers ([#7892](https://github.com/diegosouzapw/OmniRoute/pull/7892)) — thanks @Capslockb
- **feat(sse):** add PromptQL playground provider (unofficial) ([#7911](https://github.com/diegosouzapw/OmniRoute/pull/7911)) — thanks @artickc
- **feat(cline):** align ClinePass catalog and request protocol ([#7914](https://github.com/diegosouzapw/OmniRoute/pull/7914)) — thanks @backryun
- **feat:** narrow mcp:connect scope + per-key HTTP tool-scope binding (#7895) ([#7967](https://github.com/diegosouzapw/OmniRoute/pull/7967))
- **feat:** provider tab account search + mirrored top pagination (#7937) ([#7968](https://github.com/diegosouzapw/OmniRoute/pull/7968))
- **feat:** canonical numeric helpers + tier-1 (analytics) migration (#7879) ([#7969](https://github.com/diegosouzapw/OmniRoute/pull/7969))
- **feat(sse):** add HyperAgent (hyperagent.com) unofficial web provider ([#7994](https://github.com/diegosouzapw/OmniRoute/pull/7994)) — thanks @artickc
- **feat:** copilot-m365-web tone-selected model variants (#7872) ([#7997](https://github.com/diegosouzapw/OmniRoute/pull/7997))
- **feat(media):** Adobe Firefly image + video generation provider ([#8006](https://github.com/diegosouzapw/OmniRoute/pull/8006)) — thanks @artickc
- **feat(routing):** add prompt-cache affinity ([#8008](https://github.com/diegosouzapw/OmniRoute/pull/8008)) — thanks @JxnLexn
- **feat(compression):** select model-aware tokenizers ([#8009](https://github.com/diegosouzapw/OmniRoute/pull/8009)) — thanks @JxnLexn
- **feat(compression):** add Responses tool-output engine ([#8010](https://github.com/diegosouzapw/OmniRoute/pull/8010)) — thanks @JxnLexn
- **feat(dashboard):** Kimi sponsor banner, Kimi Coding preset, official logomarks and partner links ([#8039](https://github.com/diegosouzapw/OmniRoute/pull/8039))
- **feat(dashboard):** make Codex quota card windows reflect reality ([#8054](https://github.com/diegosouzapw/OmniRoute/pull/8054)) — thanks @insoln
- **feat(compression):** teach the model the CCR retrieve protocol on first marker (#8033) ([#8063](https://github.com/diegosouzapw/OmniRoute/pull/8063))
- **feat(compression):** per-model/endpoint compression exclusion filter (#8034) ([#8064](https://github.com/diegosouzapw/OmniRoute/pull/8064))
- **feat(providers):** add CLOVA Studio, InternLM and Ant Ling API-key providers ([#8077](https://github.com/diegosouzapw/OmniRoute/pull/8077)) — thanks @alvaretto
- **feat(codex):** support reference image edits ([#8122](https://github.com/diegosouzapw/OmniRoute/pull/8122)) — thanks @xiaoyaner0201
- **feat(providers):** add weekly quota tracking for grok-web ([#8127](https://github.com/diegosouzapw/OmniRoute/pull/8127)) — thanks @apoapostolov
- **feat(providers):** add Sarvam AI, Writer Palmyra and PLaMo API-key providers ([#8161](https://github.com/diegosouzapw/OmniRoute/pull/8161)) — thanks @alvaretto
- **feat:** native Fish Audio TTS provider on /v1/audio/speech (#8099) ([#8164](https://github.com/diegosouzapw/OmniRoute/pull/8164))
- **feat:** zh-CN terminology glossary + consistency gate + normalization pass (#8038) ([#8166](https://github.com/diegosouzapw/OmniRoute/pull/8166))
- **feat(providers):** add Typhoon (Thailand) and Inception Mercury diffusion LLM ([#8170](https://github.com/diegosouzapw/OmniRoute/pull/8170)) — thanks @alvaretto
- **feat(sse):** restrict auto-combo no-auth pool to allowlist (opencode, felo) + docs ([#8183](https://github.com/diegosouzapw/OmniRoute/pull/8183))
- **feat(sre):** add tcp-close-analyzer.py for debugging client-vs-server TCP close order ([#8208](https://github.com/diegosouzapw/OmniRoute/pull/8208)) — thanks @hartmark
- **feat(settings):** configurable model catalog cache TTL ([#8219](https://github.com/diegosouzapw/OmniRoute/pull/8219)) — thanks @oyi77
- **feat(github-models):** refresh catalog and compatibility ([#8225](https://github.com/diegosouzapw/OmniRoute/pull/8225)) — thanks @backryun
- **feat(github):** refresh Copilot model catalog ([#8226](https://github.com/diegosouzapw/OmniRoute/pull/8226)) — thanks @backryun
- **feat:** classify grok-web Cloudflare anti-bot blocks + gated browser-backed cf_clearance path (#8019) ([#8241](https://github.com/diegosouzapw/OmniRoute/pull/8241))
- **feat(providers):** weekly quota for xAI OAuth (Grok) (`xai-oauth` / `xao`) via shared cli-chat-proxy billing (`creditUsagePercent`), with fail-open self-tracked fallback ([#8471](https://github.com/diegosouzapw/OmniRoute/pull/8471)) — thanks @allanvb
 ### ⚡ Performance

 - **perf(db):** project columns + composite index in getProviderConnections ([#6918](https://github.com/diegosouzapw/OmniRoute/pull/6918)) — thanks @oyi77
@@ -164,10 +99,6 @@ _Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62
 - **perf(db):** cap modelLockouts eviction at 1000 entries ([#6923](https://github.com/diegosouzapw/OmniRoute/pull/6923)) — thanks @oyi77
 - **perf:** wrap ComboCard, HeroSection in React.memo ([#7070](https://github.com/diegosouzapw/OmniRoute/pull/7070)) — thanks @oyi77

- **perf:** Date.now hoist, hasActiveDeltaValue hoist, buffer.split guard in SSE stream ([#7066](https://github.com/diegosouzapw/OmniRoute/pull/7066)) — thanks @oyi77
- **perf(memory):** mitigate event-loop starvation under 3000+ provider connections ([#7719](https://github.com/diegosouzapw/OmniRoute/pull/7719)) — thanks @oyi77
- **perf:** reduce long-context request copies ([#7862](https://github.com/diegosouzapw/OmniRoute/pull/7862)) — thanks @RaviTharuma
- **perf:** lazy provider init, P2C quota cache, structuredClone elimination, getSettings→getCachedSettings (batch 2) ([#7893](https://github.com/diegosouzapw/OmniRoute/pull/7893)) — thanks @oyi77
 ### 🐛 Bug Fixes

 - **fix:** add re-entrancy guard to token health check sweep ([#6917](https://github.com/diegosouzapw/OmniRoute/pull/6917)) — thanks @oyi77
@@ -328,180 +259,6 @@ _Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62
 - **fix(stryker):** add Microsoft Designer test to tap.testFiles ([#7659](https://github.com/diegosouzapw/OmniRoute/pull/7659))
 - **fix(dashboard):** cut UI import chain from connection persist module (CI shard base-red) ([#7677](https://github.com/diegosouzapw/OmniRoute/pull/7677))

- **fix(perplexity-web):** stop empty-content responses from live schematized SSE ([#6955](https://github.com/diegosouzapw/OmniRoute/pull/6955)) — thanks @artickc
- **fix(dashboard):** make quota cards container responsive ([#7027](https://github.com/diegosouzapw/OmniRoute/pull/7027)) — thanks @xz-dev
- **fix(nvidia):** restore GLM-5.2 reasoning on NIM (#7215) ([#7296](https://github.com/diegosouzapw/OmniRoute/pull/7296)) — thanks @backryun
- **fix(i18n):** complete Vietnamese dashboard localization and runtime fixes ([#7493](https://github.com/diegosouzapw/OmniRoute/pull/7493)) — thanks @nguyenha935
- **fix(providers):** migrate muse-spark-web from GraphQL to WebSocket protocol ([#7528](https://github.com/diegosouzapw/OmniRoute/pull/7528)) — thanks @Ajeesh25353646
- **fix(combo):** expose computed context_length via /api/combos for accurate OC plugin display ([#7633](https://github.com/diegosouzapw/OmniRoute/pull/7633)) — thanks @herjarsa
- **fix(api):** enumerate tiered auto combo endpoints in /api/combos/auto ([#7662](https://github.com/diegosouzapw/OmniRoute/pull/7662)) — thanks @ekinnee
- **fix(dashboard):** topology reflects connection health + clears finished requests ([#7672](https://github.com/diegosouzapw/OmniRoute/pull/7672)) — thanks @danscMax
- **fix(kimi-coding):** capture and replay reasoning for thinking-mode turns ([#7673](https://github.com/diegosouzapw/OmniRoute/pull/7673)) — thanks @xz-dev
- **fix(ci):** merge-train --fast mirrors test:unit subdir allowlist ([#7688](https://github.com/diegosouzapw/OmniRoute/pull/7688))
- **fix(sse):** start credential-health sweep at boot so stale web sessions recover ([#7689](https://github.com/diegosouzapw/OmniRoute/pull/7689)) — thanks @danscMax
- **fix(cursor):** discover models via official CLI command ([#7692](https://github.com/diegosouzapw/OmniRoute/pull/7692)) — thanks @makcimbx
- **fix(quota):** fix antigravity/agy multi-model quota skipping in combos ([#7695](https://github.com/diegosouzapw/OmniRoute/pull/7695)) — thanks @irvandikky
- **fix(usage):** preserve account identity history ([#7700](https://github.com/diegosouzapw/OmniRoute/pull/7700)) — thanks @xz-dev
- **fix(db):** update proxies on password rotation ([#7707](https://github.com/diegosouzapw/OmniRoute/pull/7707)) — thanks @floze-the-genius
- **fix(providers):** correct Chutes registry baseUrl (#7621) ([#7708](https://github.com/diegosouzapw/OmniRoute/pull/7708))
- **fix(routing):** strip prompt_cache_key for NVIDIA NIM (#7617) ([#7709](https://github.com/diegosouzapw/OmniRoute/pull/7709))
- **fix(providers):** degrade Arena (lmarena) cookie validation redirect to unsupported (#7542) ([#7710](https://github.com/diegosouzapw/OmniRoute/pull/7710))
- **fix(claude-web):** unify Turnstile/executor/fast-path User-Agents behind one fingerprint (#7548) ([#7711](https://github.com/diegosouzapw/OmniRoute/pull/7711))
- **fix(sse):** authenticate CLIProxyAPI fallback/passthrough legs with a dedicated credential (#7645) ([#7712](https://github.com/diegosouzapw/OmniRoute/pull/7712))
- **fix(sse):** proactively refresh Grok Build OAuth token before dispatch (#7610) ([#7715](https://github.com/diegosouzapw/OmniRoute/pull/7715))
- **fix(providers):** classify ambiguous Mistral 401 instead of hard auth error (#7638) ([#7718](https://github.com/diegosouzapw/OmniRoute/pull/7718))
- **fix(security):** bump adm-zip >=0.6.0 + exact host matching in mitm DNS test ([#7732](https://github.com/diegosouzapw/OmniRoute/pull/7732))
- **fix(icons):** fall back to Stepfun Mono when Color component is absent … ([#7743](https://github.com/diegosouzapw/OmniRoute/pull/7743)) — thanks @Dan-ex-hub
- **fix(stream):** suppress `</think>` close marker for Responses API clients ([#7747](https://github.com/diegosouzapw/OmniRoute/pull/7747)) — thanks @xz-dev
- **fix(sse):** wire settings.wildcardAliases into model resolution (#7693) ([#7748](https://github.com/diegosouzapw/OmniRoute/pull/7748))
- **fix(authz):** classify forge/jcode CLI settings routes as LOCAL_ONLY (#7263) ([#7749](https://github.com/diegosouzapw/OmniRoute/pull/7749))
- **fix(routing):** honor eye-icon hidden models for no-auth providers in auto-combo (#7620) ([#7750](https://github.com/diegosouzapw/OmniRoute/pull/7750))
- **fix(sse):** persist rotated Gemini web-session cookies via onCredentialsRefreshed (#7676) ([#7751](https://github.com/diegosouzapw/OmniRoute/pull/7751))
- **fix(docs):** heal release-green docs drift + eslint any-suppression drift (#7253) ([#7755](https://github.com/diegosouzapw/OmniRoute/pull/7755))
- **fix(mcp):** copy undici into dist/node_modules to prevent hollow-package shadowing crash (#7701) ([#7756](https://github.com/diegosouzapw/OmniRoute/pull/7756))
- **fix(packaging):** move fumadocs-mdx to devDependencies (#7661) ([#7757](https://github.com/diegosouzapw/OmniRoute/pull/7757))
- **fix(ci):** build API-only smoke workflows backend-only to fix dast-smoke timeouts (#7226) ([#7758](https://github.com/diegosouzapw/OmniRoute/pull/7758))
- **fix(cli):** load DATA_DIR/server.env as fallback for .env on Electron migration (#7302) ([#7759](https://github.com/diegosouzapw/OmniRoute/pull/7759))
- **fix(cli):** split outboundUrlGuard's DB helpers so setup-opencode packages cleanly (#7682) ([#7760](https://github.com/diegosouzapw/OmniRoute/pull/7760))
- **fix(notion-web):** production-ready labels, multi-workspace, inference, usage (FINAL) ([#7768](https://github.com/diegosouzapw/OmniRoute/pull/7768)) — thanks @artickc
- **fix(kimi):** expose K3 reasoning effort levels ([#7776](https://github.com/diegosouzapw/OmniRoute/pull/7776)) — thanks @xz-dev
- **fix(compression):** apply compression combo assignments to routing combos ([#7779](https://github.com/diegosouzapw/OmniRoute/pull/7779)) — thanks @ekinnee
- **fix(i18n):** regenerate Polish UI locale from English ([#7782](https://github.com/diegosouzapw/OmniRoute/pull/7782)) — thanks @leszek3737
- **fix(combo):** retry transient errors in pipeline strategy ([#7794](https://github.com/diegosouzapw/OmniRoute/pull/7794)) — thanks @AndrianBalanescu
- **fix(quality):** register nvidia-quota-phase1 and service-provider-plugin-registry in stryker tap.testFiles ([#7796](https://github.com/diegosouzapw/OmniRoute/pull/7796))
- **fix(stream):** synthesize terminal finish_reason chunk when upstream omits it (#7800) ([#7804](https://github.com/diegosouzapw/OmniRoute/pull/7804)) — thanks @AndrianBalanescu
- **fix(plugins):** 5 bugs on the plugin path (3 Windows-only, 2 all-platform) ([#7806](https://github.com/diegosouzapw/OmniRoute/pull/7806)) — thanks @tmone
- **fix(cli):** register ESM alias resolver for @/ paths under global install ([#7808](https://github.com/diegosouzapw/OmniRoute/pull/7808)) — thanks @rafaumeu
- **fix(auth):** gate invalid-key check on isRequireApiKeyEnabled for embeddings and web-fetch (#7785) ([#7810](https://github.com/diegosouzapw/OmniRoute/pull/7810)) — thanks @AndrianBalanescu
- **fix(ci):** repair release regressions exposed by clean runs ([#7812](https://github.com/diegosouzapw/OmniRoute/pull/7812)) — thanks @backryun
- **fix(rerank):** add voyage format adapter for request/response translation (#7809) ([#7813](https://github.com/diegosouzapw/OmniRoute/pull/7813)) — thanks @AndrianBalanescu
- **fix(antigravity):** attempt onboarding when projectId is empty (#5193 regression of #2541) ([#7815](https://github.com/diegosouzapw/OmniRoute/pull/7815)) — thanks @rafaumeu
- **fix(stream):** emit terminal SSE frames on mid-stream upstream failure (#7699) ([#7816](https://github.com/diegosouzapw/OmniRoute/pull/7816)) — thanks @AndrianBalanescu
- **fix(sse):** strip orphaned tool_use before antigravity/Vertex Claude dispatch (#7752) ([#7822](https://github.com/diegosouzapw/OmniRoute/pull/7822))
- **fix(translator):** sanitize tool_result.tool_use_id symmetrically with tool_use.id (#7705) ([#7823](https://github.com/diegosouzapw/OmniRoute/pull/7823))
- **fix(oauth):** require chatgptUserId agreement for Codex account dedup (#7737) ([#7825](https://github.com/diegosouzapw/OmniRoute/pull/7825))
- **fix(db):** purge in-memory key-health state when a provider connection is deleted (#7740) ([#7826](https://github.com/diegosouzapw/OmniRoute/pull/7826))
- **fix(compression):** keep a retrievable preamble instead of a bare CCR marker (#7746) ([#7827](https://github.com/diegosouzapw/OmniRoute/pull/7827))
- **fix(db):** log fatal boot-time SQLite driver-cascade failure before propagating (#7773) ([#7828](https://github.com/diegosouzapw/OmniRoute/pull/7828))
- **fix(docker):** repair tls-client-node native binary after --ignore-scripts (#7802) ([#7829](https://github.com/diegosouzapw/OmniRoute/pull/7829))
- **fix(auth):** restore TICK_MS in tokenHealthCheck (ReferenceError on startup) ([#7830](https://github.com/diegosouzapw/OmniRoute/pull/7830))
- **fix(cli):** fix Windows CLI detection false negatives (#7753, #7774) ([#7831](https://github.com/diegosouzapw/OmniRoute/pull/7831))
- **fix(docs):** document CREDENTIAL_REDACTION_ENABLED and GHE_COPILOT_OAUTH_CLIENT_ID (#7793) ([#7833](https://github.com/diegosouzapw/OmniRoute/pull/7833))
- **fix(dashboard):** fix collapsed quota card session/weekly order (#7764) ([#7834](https://github.com/diegosouzapw/OmniRoute/pull/7834))
- **fix(dashboard):** mirror connection-row action-icon spacing under RTL (#7680) ([#7835](https://github.com/diegosouzapw/OmniRoute/pull/7835))
- **fix:** avoid cmd.exe spawn on Windows by using os.hostname() before execSync fallback ([#7841](https://github.com/diegosouzapw/OmniRoute/pull/7841)) — thanks @tientien17
- **fix(usage):** harden account identity reconciliation ([#7843](https://github.com/diegosouzapw/OmniRoute/pull/7843)) — thanks @xz-dev
- **fix(cli):** use rundll32 instead of cmd.exe for Windows browser fallback in dashboard command ([#7844](https://github.com/diegosouzapw/OmniRoute/pull/7844)) — thanks @tientien17
- **fix:** add native lifecycle-aware health endpoint ([#7852](https://github.com/diegosouzapw/OmniRoute/pull/7852)) — thanks @RaviTharuma
- **fix:** reserve chat admission before body parsing ([#7853](https://github.com/diegosouzapw/OmniRoute/pull/7853)) — thanks @RaviTharuma
- **fix:** bound quadratic session-dedup memory growth ([#7855](https://github.com/diegosouzapw/OmniRoute/pull/7855)) — thanks @RaviTharuma
- **fix(compression):** enable OmniGlyph for Claude Fable 5 ([#7863](https://github.com/diegosouzapw/OmniRoute/pull/7863)) — thanks @enjoyer-hub
- **fix(notion-web):** add browser fingerprint headers to reduce Cloudflare challenges ([#7864](https://github.com/diegosouzapw/OmniRoute/pull/7864)) — thanks @HassiyYT
- **fix(mitm):** gate Agent Bridge Repair on sudo password (#7836) ([#7865](https://github.com/diegosouzapw/OmniRoute/pull/7865)) — thanks @skutanjir
- **fix(rerank):** honor the connection's pinned proxy on rerank calls (#7350) ([#7867](https://github.com/diegosouzapw/OmniRoute/pull/7867))
- **fix(compression):** skip CCR on tool outputs to preserve agent loop ([#7869](https://github.com/diegosouzapw/OmniRoute/pull/7869)) — thanks @herjarsa
- **fix(vision-bridge):** reroute auto/ prefix to vision model when images present ([#7871](https://github.com/diegosouzapw/OmniRoute/pull/7871)) — thanks @herjarsa
- **fix(opencode-plugin):** support separate management read token ([#7885](https://github.com/diegosouzapw/OmniRoute/pull/7885)) — thanks @RaviTharuma
- **fix(sse):** CC bridge loses OpenAI-format image input (OpenCode/Kilo/Cline → AgentRouter) ([#7888](https://github.com/diegosouzapw/OmniRoute/pull/7888))
- **fix(combo):** strip boolean reasoning field for opencode-go providers ([#7891](https://github.com/diegosouzapw/OmniRoute/pull/7891)) — thanks @AndrianBalanescu
- **fix(notion-web):** accept OpenAI content-parts arrays in transcript ([#7896](https://github.com/diegosouzapw/OmniRoute/pull/7896)) — thanks @artickc
- **fix(notion-web):** reuse threadId across OpenAI multi-turn (no new chat each request) ([#7900](https://github.com/diegosouzapw/OmniRoute/pull/7900)) — thanks @artickc
- **fix(gemini):** strip OpenAI "strict" tool-schema keyword for Antigravity ([#7901](https://github.com/diegosouzapw/OmniRoute/pull/7901)) — thanks @Witroch4
- **fix(antigravity):** collect native functionCall parts in SSE collector ([#7902](https://github.com/diegosouzapw/OmniRoute/pull/7902)) — thanks @Witroch4
- **fix(sse):** recover invalid Anthropic thinking signatures once ([#7906](https://github.com/diegosouzapw/OmniRoute/pull/7906)) — thanks @insoln
- **fix(resilience):** don't cool down accounts or trip the breaker on client aborts ([#7908](https://github.com/diegosouzapw/OmniRoute/pull/7908)) — thanks @insoln
- **fix(dashboard):** preserve quota cutoff drafts ([#7909](https://github.com/diegosouzapw/OmniRoute/pull/7909)) — thanks @hydraxman
- **fix(providers):** treat public-host 302 as valid in Gemini Web connection test (#7859) ([#7917](https://github.com/diegosouzapw/OmniRoute/pull/7917))
- **fix(providers):** read reasoning_text in Claude-format response translator (#7856) ([#7919](https://github.com/diegosouzapw/OmniRoute/pull/7919))
- **fix(dashboard):** safely render structured error objects in Request Logs detail (#7845) ([#7920](https://github.com/diegosouzapw/OmniRoute/pull/7920))
- **fix(dashboard):** repair monaco deep import broken by 0.56 exports map (#7897) ([#7922](https://github.com/diegosouzapw/OmniRoute/pull/7922))
- **fix(autostart):** adopt 9Router VBS startup to suppress console flash on Windows ([#7925](https://github.com/diegosouzapw/OmniRoute/pull/7925)) — thanks @tientien17
- **fix(translators):** normalize TitleCase tool names for non-Anthropic models ([#7926](https://github.com/diegosouzapw/OmniRoute/pull/7926)) — thanks @nramabad
- **fix(api):** resolve local provider models via dashboard catalog fallback ([#7927](https://github.com/diegosouzapw/OmniRoute/pull/7927)) — thanks @ekinnee
- **fix(auto):** pool accounts by provider model ([#7928](https://github.com/diegosouzapw/OmniRoute/pull/7928)) — thanks @adrianaryaputra
- **fix(perplexity-web):** multi-step empty content + advanced-quota cooldown ([#7930](https://github.com/diegosouzapw/OmniRoute/pull/7930)) — thanks @artickc
- **fix(ccr):** resolve principal via OMNIROUTE_API_KEY env var on stdio MCP transport ([#7932](https://github.com/diegosouzapw/OmniRoute/pull/7932)) — thanks @ekinnee
- **fix(combo):** context-aware fallback ignores model_context_override ([#7933](https://github.com/diegosouzapw/OmniRoute/pull/7933)) — thanks @tmone
- **fix(i18n):** preserve remaining Vietnamese localization ([#7935](https://github.com/diegosouzapw/OmniRoute/pull/7935)) — thanks @nguyenha935
- **fix(mitm):** gate Agent Bridge DNS and Trust Cert on sudo password (#7938) ([#7939](https://github.com/diegosouzapw/OmniRoute/pull/7939)) — thanks @skutanjir
- **fix(providers):** route iflytek/sparkdesk to Spark's OpenAI-compatible host ([#7942](https://github.com/diegosouzapw/OmniRoute/pull/7942)) — thanks @FenjuFu
- **fix(sse):** preserve parallel_tool_calls for GPT-5.6 delegation under Codex Responses Lite (#7821) ([#7957](https://github.com/diegosouzapw/OmniRoute/pull/7957))
- **fix(providers):** copilot-m365-web fails loudly on empty turns + tier-aware enterprise invocation (#7858, #7870) ([#7958](https://github.com/diegosouzapw/OmniRoute/pull/7958))
- **fix(providers):** treat unreliable web-cookie /models probe status as unsupported, not valid (#7857) ([#7959](https://github.com/diegosouzapw/OmniRoute/pull/7959))
- **fix(api):** add amazon-q to the static model catalog (#7820) ([#7960](https://github.com/diegosouzapw/OmniRoute/pull/7960))
- **fix:** parse Gemini 429 RetryInfo.retryDelay for model lockout (#7940) ([#7961](https://github.com/diegosouzapw/OmniRoute/pull/7961))
- **fix(quality):** tolerate ESLint's trailing unpruned-suppressions text in validate-release-green (#7837) ([#7962](https://github.com/diegosouzapw/OmniRoute/pull/7962))
- **fix(cli):** translate missing sqlite bindings error into actionable guidance (#7868) ([#7963](https://github.com/diegosouzapw/OmniRoute/pull/7963))
- **fix(cli):** spawn opencode.cmd shim with shell:true on win32 (#7913) ([#7964](https://github.com/diegosouzapw/OmniRoute/pull/7964))
- **fix(dashboard):** correct block-extra-Claude-usage toggle copy to match quarantine behavior (#7918) ([#7965](https://github.com/diegosouzapw/OmniRoute/pull/7965))
- **fix(api):** classify /api/acp/agents as loopback-only (#7948) ([#7966](https://github.com/diegosouzapw/OmniRoute/pull/7966))
- **fix(auth):** restore configurable HEALTHCHECK_BATCH_SIZE dropped by #7719 (#7875) ([#7970](https://github.com/diegosouzapw/OmniRoute/pull/7970))
- **fix(test):** widen ratelimit-admission pollUntil deadline to 10s (#7842) ([#7971](https://github.com/diegosouzapw/OmniRoute/pull/7971))
- **fix(pricing):** clarify disabled automatic sync status ([#7972](https://github.com/diegosouzapw/OmniRoute/pull/7972)) — thanks @RaviTharuma
- **fix(combo):** exempt content_filter from empty-content detection ([#7973](https://github.com/diegosouzapw/OmniRoute/pull/7973)) — thanks @HouMinXi
- **fix(embeddings):** support secure multimodal inputs ([#7978](https://github.com/diegosouzapw/OmniRoute/pull/7978)) — thanks @RaviTharuma
- **fix(resilience):** cap exactCooldownMs against maxCooldownMs (#7940) ([#7980](https://github.com/diegosouzapw/OmniRoute/pull/7980)) — thanks @ekinnee
- **fix(electron):** derive macOS Helper name from execPath to remove 2nd Dock icon (#7941) ([#8002](https://github.com/diegosouzapw/OmniRoute/pull/8002))
- **fix(chatcore):** report string-reason client aborts as 499, not 502 (#7907) ([#8011](https://github.com/diegosouzapw/OmniRoute/pull/8011)) — thanks @Long-Feeds
- **fix(models):** drop generic catalog siblings of specialty surfaces (#8015) ([#8021](https://github.com/diegosouzapw/OmniRoute/pull/8021)) — thanks @RaviTharuma
- **fix(models):** stop inventing chat capabilities for specialty surfaces (#8016) ([#8022](https://github.com/diegosouzapw/OmniRoute/pull/8022)) — thanks @RaviTharuma
- **fix(capabilities):** resolve models.dev specialty rows across provider keys (#8017) ([#8023](https://github.com/diegosouzapw/OmniRoute/pull/8023)) — thanks @RaviTharuma
- **fix(models):** attach models.dev pricing to GET /v1/models entries (#8018) ([#8025](https://github.com/diegosouzapw/OmniRoute/pull/8025)) — thanks @RaviTharuma
- **fix(grok-cli):** require full auth.json on OAuth paste import (#7610) ([#8027](https://github.com/diegosouzapw/OmniRoute/pull/8027)) — thanks @RaviTharuma
- **fix(grok-cli):** sanitize function_call_output before Grok Build dispatch (#7611) ([#8030](https://github.com/diegosouzapw/OmniRoute/pull/8030)) — thanks @RaviTharuma
- **fix(sse):** bound forwarded response headers ([#8041](https://github.com/diegosouzapw/OmniRoute/pull/8041)) — thanks @insoln
- **fix(sse):** replace spoofable .includes() PromptQL issuer check with hostname comparison (#8029) ([#8042](https://github.com/diegosouzapw/OmniRoute/pull/8042))
- **fix(sse):** bound Codex SSE peek read with per-read timeout (#8020) ([#8043](https://github.com/diegosouzapw/OmniRoute/pull/8043))
- **fix(cli):** stop double-prefixing combo model ids in opencode plugin static catalog (#7976) ([#8047](https://github.com/diegosouzapw/OmniRoute/pull/8047))
- **fix(antigravity):** scope 404 model-not-found lockout to exact model + bare-model autopick ([#8050](https://github.com/diegosouzapw/OmniRoute/pull/8050)) — thanks @AndrianBalanescu
- **fix:** repair pre-existing red gates on the release/v3.8.49 tip ([#8055](https://github.com/diegosouzapw/OmniRoute/pull/8055))
- **fix(oauth):** honor connectionId on token refresh so email-less providers don't duplicate ([#8062](https://github.com/diegosouzapw/OmniRoute/pull/8062)) — thanks @insoln
- **fix:** classify Google quota exhaustion responses ([#8071](https://github.com/diegosouzapw/OmniRoute/pull/8071)) — thanks @rafaumeu
- **fix(providers):** refresh duckduckgo-web catalog to current Duck.ai wire ids (#8000) ([#8079](https://github.com/diegosouzapw/OmniRoute/pull/8079))
- **fix(security):** decouple request PII redaction from injection mode ([#8102](https://github.com/diegosouzapw/OmniRoute/pull/8102)) — thanks @RaviTharuma
- **fix(providers):** discover live AGY models ([#8123](https://github.com/diegosouzapw/OmniRoute/pull/8123)) — thanks @adevwithpurpose
- **fix(guardrails):** align INPUT_SANITIZER request masking gate (#8093) ([#8124](https://github.com/diegosouzapw/OmniRoute/pull/8124)) — thanks @RaviTharuma
- **fix(providers):** refresh Baidu ERNIE and Qianfan website URLs (#6271) ([#8128](https://github.com/diegosouzapw/OmniRoute/pull/8128)) — thanks @TrackCrewGalore
- **fix(stream):** add logging to empty catch blocks in stream error handling ([#8143](https://github.com/diegosouzapw/OmniRoute/pull/8143)) — thanks @chirag127
- **fix(sse):** stop Codex/Responses sanitizer turning system image_url into output_text (#8089) ([#8147](https://github.com/diegosouzapw/OmniRoute/pull/8147))
- **fix(db):** register SIGHUP handler and stop force-killing server on win32 stop paths (#8045) ([#8148](https://github.com/diegosouzapw/OmniRoute/pull/8148))
- **fix(providers):** add missing poe registry baseUrl entry (#8082) ([#8149](https://github.com/diegosouzapw/OmniRoute/pull/8149))
- **fix(routing):** anchor quota cache on globalThis for cross-chunk consistency (#8065) ([#8150](https://github.com/diegosouzapw/OmniRoute/pull/8150))
- **fix(responses):** close namespace round-trip for Responses-Chat translation (#7936) ([#8151](https://github.com/diegosouzapw/OmniRoute/pull/8151)) — thanks @RCrushMe
- **fix(oauth):** warn instead of silently opening unreachable localhost redirect for LAN-IP Codex/xAI/Grok OAuth (#8046) ([#8152](https://github.com/diegosouzapw/OmniRoute/pull/8152))
- **fix(db):** stop closing the sql.js singleton in getDbInstance() probe/reopen (#7494) ([#8153](https://github.com/diegosouzapw/OmniRoute/pull/8153))
- **fix(sse):** run compression pipeline per turn in Codex Responses WS bridge (#8052) ([#8154](https://github.com/diegosouzapw/OmniRoute/pull/8154))
- **fix(cli):** merge node bin dir into CLI healthcheck PATH for codex detection (#8036) ([#8156](https://github.com/diegosouzapw/OmniRoute/pull/8156))
- **fix(sse):** anonymous fingerprint fallback for keyless Pollinations image gen (#8085) ([#8157](https://github.com/diegosouzapw/OmniRoute/pull/8157))
- **fix(cli):** surface the real spawn error in process supervisor (#8091) ([#8158](https://github.com/diegosouzapw/OmniRoute/pull/8158))
- **fix:** strip internal reasoning placeholder from user-visible content (#8081) ([#8162](https://github.com/diegosouzapw/OmniRoute/pull/8162)) — thanks @Dingding-leo
- **fix(combos):** expose synced reasoning-effort variants in Combo Builder model picker (#8072) ([#8165](https://github.com/diegosouzapw/OmniRoute/pull/8165)) — thanks @Dingding-leo
- **fix(windows):** add windowsHide to all child process spawns (#8131) ([#8167](https://github.com/diegosouzapw/OmniRoute/pull/8167)) — thanks @Dingding-leo
- **fix(cursor):** bridge native tools to client calls ([#8171](https://github.com/diegosouzapw/OmniRoute/pull/8171)) — thanks @makcimbx
- **fix(security):** bound JWT-extraction regexes to prevent polynomial ReDoS (CodeQL #754/#755/#756) ([#8173](https://github.com/diegosouzapw/OmniRoute/pull/8173))
- **fix(#8141):** log pending request counter decrement failures ([#8179](https://github.com/diegosouzapw/OmniRoute/pull/8179)) — thanks @rafaumeu
- **fix(#8135):** suppress sql.js build warning via non-analyzable dynamic import ([#8184](https://github.com/diegosouzapw/OmniRoute/pull/8184)) — thanks @rafaumeu
- **fix(#8093):** align INPUT_SANITIZER_ENABLED default to true across all docs ([#8185](https://github.com/diegosouzapw/OmniRoute/pull/8185)) — thanks @rafaumeu
- **fix(combo):** skip remaining same-provider targets on 401/403 auth failure ([#8195](https://github.com/diegosouzapw/OmniRoute/pull/8195)) — thanks @rafaumeu
- **fix(compression):** make memo key model-independent for non-vision engines ([#8196](https://github.com/diegosouzapw/OmniRoute/pull/8196)) — thanks @rafaumeu
- **fix(resilience):** add max/step to NumberField for provider cooldown inputs (#8107) ([#8203](https://github.com/diegosouzapw/OmniRoute/pull/8203)) — thanks @rafaumeu
- **fix(providers):** fix Azure AI Foundry multi-model discovery and per-deployment connection testing (#8174) ([#8206](https://github.com/diegosouzapw/OmniRoute/pull/8206)) — thanks @not-knope
- **fix(logs):** stop the async-EPIPE log-flood loop at its ignition point ([#8207](https://github.com/diegosouzapw/OmniRoute/pull/8207)) — thanks @Tasogarre
- **fix(sse):** surface OpenRouter mid-stream error chunks instead of a false empty success ([#8210](https://github.com/diegosouzapw/OmniRoute/pull/8210)) — thanks @hartmark
- **fix(sse):** Gemini malformed function-call handling + tool_choice translation ([#8211](https://github.com/diegosouzapw/OmniRoute/pull/8211)) — thanks @hartmark
- **fix(sse):** tool-incapable provider handling (AI Horde + Responses content-collapse scoping) ([#8212](https://github.com/diegosouzapw/OmniRoute/pull/8212)) — thanks @hartmark
- **fix(sse):** Gemini TPM/RPD quota classification + combo cooldown-wait resilience ([#8213](https://github.com/diegosouzapw/OmniRoute/pull/8213)) — thanks @hartmark
- **fix(services):** resolve and record a real pid when adopting a service ([#8218](https://github.com/diegosouzapw/OmniRoute/pull/8218)) — thanks @seanford
- **fix(memory):** resolve remote embedding dimensions for reindex (#8074) ([#8220](https://github.com/diegosouzapw/OmniRoute/pull/8220)) — thanks @Prudhvivuda
- **fix(dashboard):** correct machine-translated Korean UI strings in ko.json ([#8224](https://github.com/diegosouzapw/OmniRoute/pull/8224)) — thanks @MichaelYcJo
- **fix(devin-cli):** refresh shared model catalog ([#8227](https://github.com/diegosouzapw/OmniRoute/pull/8227)) — thanks @backryun
- **fix(claude-web):** align session transport and fallback ([#8230](https://github.com/diegosouzapw/OmniRoute/pull/8230)) — thanks @backryun
- **fix:** restore OAuth auto-refresh for gemini-cli connections ([#8232](https://github.com/diegosouzapw/OmniRoute/pull/8232)) — thanks @seanford
- **fix:** normalize Codex URLs and dashboard regressions ([#8233](https://github.com/diegosouzapw/OmniRoute/pull/8233)) — thanks @nguyenha935
- **fix(api):** narrow claudeClassifierCompat auto trigger so stop_sequences alone no longer short-circuits (#8189) ([#8236](https://github.com/diegosouzapw/OmniRoute/pull/8236))
- **fix(gemini):** drop HARM_CATEGORY_CIVIC_INTEGRITY from the default Gemini safety settings (#8231) ([#8238](https://github.com/diegosouzapw/OmniRoute/pull/8238))
- **fix(backend):** word-boundary-safe tool-result truncation in lite compression mode (#8169) ([#8239](https://github.com/diegosouzapw/OmniRoute/pull/8239))
- **fix(providers):** filter unsupported family-fallback candidates against the provider catalog (#8134) ([#8240](https://github.com/diegosouzapw/OmniRoute/pull/8240))
 ### 📚 Docs

 - **docs(quality):** codify retry policy per runner + release-level drift rule (WS5.4/WS5.5) ([#7107](https://github.com/diegosouzapw/OmniRoute/pull/7107))
@@ -515,24 +272,6 @@ _Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62
 - **docs(readme):** replace free-tier budget mockup with animated SMIL card ([#7665](https://github.com/diegosouzapw/OmniRoute/pull/7665))
 - **docs(readme):** standardize all README tables to full content width ([#7666](https://github.com/diegosouzapw/OmniRoute/pull/7666))

- **docs:** fix three stale references failing the fabricated-docs gate ([#7728](https://github.com/diegosouzapw/OmniRoute/pull/7728))
- **docs(readme):** unified animated card system — audited v3.8.49 numbers, style contract across all cards, 5 new cards + rebuilt terminal ([#7769](https://github.com/diegosouzapw/OmniRoute/pull/7769))
- **docs(readme):** add Kimi (Moonshot AI) official supporter section ([#7770](https://github.com/diegosouzapw/OmniRoute/pull/7770))
- **docs(getting-started):** reorder Verify It Works before IDE/CLI setup + add examples ([#7790](https://github.com/diegosouzapw/OmniRoute/pull/7790)) — thanks @swingtempo
- **docs(readme):** audit every number against the live code + refresh contributors and acknowledgments ([#7795](https://github.com/diegosouzapw/OmniRoute/pull/7795))
- **docs(readme):** evolve supporter section into sub2api-style Sponsors section ([#7799](https://github.com/diegosouzapw/OmniRoute/pull/7799))
- **docs(readme):** contributors 360+ -> 350+ (audited) ([#7803](https://github.com/diegosouzapw/OmniRoute/pull/7803))
- **docs(i18n):** refresh Polish README and fix relative links ([#7807](https://github.com/diegosouzapw/OmniRoute/pull/7807)) — thanks @leszek3737
- **docs:** add general Web Cookie provider setup guide ([#7881](https://github.com/diegosouzapw/OmniRoute/pull/7881)) — thanks @arpit-jaiswal-dev
- **docs(guides):** document Kaspersky PDM behavioral false positive on the Desktop installer (#7903) ([#7923](https://github.com/diegosouzapw/OmniRoute/pull/7923))
- **docs:** document npm install ERESOLVE/peer/deprecated warnings as harmless (fixes #7951) ([#7988](https://github.com/diegosouzapw/OmniRoute/pull/7988)) — thanks @Dingding-leo
- **docs:** fix Docker IPv6 connection reset with -p 127.0.0.1 bind (fixes #7722) ([#7989](https://github.com/diegosouzapw/OmniRoute/pull/7989)) — thanks @Dingding-leo
- **docs(readme):** Kimi partner tracking links (aff=omniroute) + first-Brazilian-project line + disclosure ([#8028](https://github.com/diegosouzapw/OmniRoute/pull/8028))
- **docs:** add AgentRouter multi-provider routing troubleshooting ([#8049](https://github.com/diegosouzapw/OmniRoute/pull/8049)) — thanks @leninejunior
- **docs(security):** correct prompt-injection severity table + heuristic-limitations disclaimer (#8097) ([#8113](https://github.com/diegosouzapw/OmniRoute/pull/8113)) — thanks @rafaumeu
- **docs(ops):** publish public branching and release model (#7627) ([#8129](https://github.com/diegosouzapw/OmniRoute/pull/8129)) — thanks @c4usal
- **docs(i18n):** full Russian README rewrite ([#8217](https://github.com/diegosouzapw/OmniRoute/pull/8217)) — thanks @MonteNegroX
- **docs(readme):** re-audit numbers, fix table scroll, refresh contributors ([#8243](https://github.com/diegosouzapw/OmniRoute/pull/8243))
 ### 🧪 Tests & Quality

 - **test(build):** derive pack-artifact closures for all npm-shipped entrypoints (#7065 class) ([#7081](https://github.com/diegosouzapw/OmniRoute/pull/7081))
@@ -542,9 +281,6 @@ _Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62
 - **test(ci):** static body in codex e2e mock route bridge (CodeQL #737) ([#7558](https://github.com/diegosouzapw/OmniRoute/pull/7558))
 - **test(ci):** exact-line assert in grok-build config test (CodeQL #740/#741) ([#7628](https://github.com/diegosouzapw/OmniRoute/pull/7628))

- **test(codex):** cover image tool output replay (#7698) ([#7704](https://github.com/diegosouzapw/OmniRoute/pull/7704)) — thanks @dongwook-chan
- **test(security):** exact SAN-entry match in mitm leaf-cert test (CodeQL #746) ([#7824](https://github.com/diegosouzapw/OmniRoute/pull/7824))
- **test(#8140):** verify keepalive interval cleanup on disconnect, resolve, and reject ([#8190](https://github.com/diegosouzapw/OmniRoute/pull/8190)) — thanks @rafaumeu
 ### 🔧 Chores / CI

 - **chore(release):** gate the sync-back push on release-green --quick (WS0.3) ([#7083](https://github.com/diegosouzapw/OmniRoute/pull/7083))
@@ -563,26 +299,6 @@ _Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62
 - **chore(quality):** register #6672 test in stryker tap.testFiles (base-red unblock) ([#7652](https://github.com/diegosouzapw/OmniRoute/pull/7652))
 - **chore(release):** merge-train box-speed suite + --fast mode ([#7670](https://github.com/diegosouzapw/OmniRoute/pull/7670))

- **chore:** [defer] fix embedded CLIProxyAPI config handling ([#6877](https://github.com/diegosouzapw/OmniRoute/pull/6877)) — thanks @professional-ALFIE
- **chore:** [defer] fix(grok): align responses tool-call shape for grok models ([#6937](https://github.com/diegosouzapw/OmniRoute/pull/6937)) — thanks @CitrusIce
- **chore:** [needs-vps] feat(dashboard): add per-operator quota row visibility on usage tab ([#7251](https://github.com/diegosouzapw/OmniRoute/pull/7251))
- **chore:** [defer] feat(combo): universal cooldown-aware retry & auto-strategy combo-ref guard ([#7301](https://github.com/diegosouzapw/OmniRoute/pull/7301)) — thanks @ViFigueiredo
- **chore:** Completing Arabic language ([#7686](https://github.com/diegosouzapw/OmniRoute/pull/7686)) — thanks @mustafa-phd
- **chore:** IC2: Cache provider connections by ID + provider nodes ([#7744](https://github.com/diegosouzapw/OmniRoute/pull/7744)) — thanks @oyi77
- **chore:** [Emergency Fix] fix(build): repair release build blockers ([#7772](https://github.com/diegosouzapw/OmniRoute/pull/7772)) — thanks @backryun
- **chore:** [Part 1/3]refactor(qwen): replace legacy Qwen Code and remove OAuth provider ([#7866](https://github.com/diegosouzapw/OmniRoute/pull/7866)) — thanks @backryun
- **chore:** [Part 3/3] feat(qwen): add regional Alibaba and Qwen Cloud providers ([#7882](https://github.com/diegosouzapw/OmniRoute/pull/7882)) — thanks @backryun
- **chore:** Preserve supported Responses behavior in Chat translation ([#7894](https://github.com/diegosouzapw/OmniRoute/pull/7894)) — thanks @JxnLexn
- **chore:** Restore Responses API custom tool calls ([#7905](https://github.com/diegosouzapw/OmniRoute/pull/7905)) — thanks @JxnLexn
- **chore:** Hide internal reasoning replay placeholders ([#7912](https://github.com/diegosouzapw/OmniRoute/pull/7912)) — thanks @JxnLexn
- **chore(deps):** bump js-yaml, brace-expansion, shell-quote, tar (security) ([#7915](https://github.com/diegosouzapw/OmniRoute/pull/7915))
- **chore:** i18n(zh-TW): complete Traditional Chinese (Taiwan) translation overhaul ([#8024](https://github.com/diegosouzapw/OmniRoute/pull/8024)) — thanks @lunkerchen
- **chore:** i18n: bring 40 locales to full parity with en.json ([#8031](https://github.com/diegosouzapw/OmniRoute/pull/8031)) — thanks @nguyenha935
- **chore(deps):** resolve 7 open Dependabot alerts via npm overrides ([#8066](https://github.com/diegosouzapw/OmniRoute/pull/8066))
- **chore(deps):** resolve 3 more Dependabot alerts (dompurify, fast-xml-parser, sharp) ([#8069](https://github.com/diegosouzapw/OmniRoute/pull/8069))
- **chore(dashboard):** reframe Kimi partnership as "Open Source Friends" ([#8117](https://github.com/diegosouzapw/OmniRoute/pull/8117))
- **chore(quality):** fix 2 pre-existing lint/suppression drift issues ([#8209](https://github.com/diegosouzapw/OmniRoute/pull/8209)) — thanks @hartmark
- **chore:** add K3banner-1.png banner asset ([#8242](https://github.com/diegosouzapw/OmniRoute/pull/8242))
 ### 🔀 Other

 - [needs-vps] fix(electron): materialize Turbopack hashed-module symlinks during packaging (#6724, #6594) ([#6794](https://github.com/diegosouzapw/OmniRoute/pull/6794)) — thanks @huohua-dev
@@ -606,107 +322,10 @@ _Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62
 - Expose proxy controls for no-auth providers ([#7419](https://github.com/diegosouzapw/OmniRoute/pull/7419)) — thanks @JxnLexn
 - Add reasoning-based model and effort routing ([#7607](https://github.com/diegosouzapw/OmniRoute/pull/7607)) — thanks @JxnLexn

- **refactor(sse):** extract per-provider token-refresh functions from tokenRefresh.ts ([#7817](https://github.com/diegosouzapw/OmniRoute/pull/7817))
- **deps:** bump the production group with 8 updates ([#7897](https://github.com/diegosouzapw/OmniRoute/pull/7897)) — thanks @dependabot[bot]
- **deps:** bump the development group with 5 updates ([#7898](https://github.com/diegosouzapw/OmniRoute/pull/7898)) — thanks @dependabot[bot]
- **refactor(antigravity):** align official clients and callable catalog ([#8013](https://github.com/diegosouzapw/OmniRoute/pull/8013)) — thanks @backryun
- **refactor(compression):** extract resolveHeadroomDetail to keep dispatchCompression under the complexity gate ([#8058](https://github.com/diegosouzapw/OmniRoute/pull/8058))
- **deps:** bump next from 16.2.10 to 16.2.11 ([#8235](https://github.com/diegosouzapw/OmniRoute/pull/8235)) — thanks @dependabot[bot]
 ### 🩹 Direct release-branch fixes (no PR — authorized base-red sweep, 2026-07-18)

 - **fix(base-red):** full-suite realignment after the 102-PR merge campaign: two real production fixes (legacy `refresh_token` column healed before its index is created; `shouldSkipCloudSyncInitialization` no longer swaps its `(env, argv)` arguments) plus 13 test files, goldens, provider counts, and env docs realigned to the live-validated behavior of the merged PRs.

-### 🙌 Contributors
-
-Thanks to everyone whose work landed in v3.8.49:
-
-| Contributor | PRs / Issues |
-| --- | --- |
-| [@adevwithpurpose](https://github.com/adevwithpurpose) | #8123 |
-| [@adrianaryaputra](https://github.com/adrianaryaputra) | #7928 |
-| [@Ajeesh25353646](https://github.com/Ajeesh25353646) | #7528 |
-| [@alltomatos](https://github.com/alltomatos) | #7041, #7042, #7164, #7277, #7490, #7492, #7644 |
-| [@alvaretto](https://github.com/alvaretto) | #8077, #8161, #8170 |
-| [@AndrianBalanescu](https://github.com/AndrianBalanescu) | #7794, #7804, #7810, #7813, #7816, #7891, #8050 |
-| [@apoapostolov](https://github.com/apoapostolov) | #8127 |
-| [@arpit-jaiswal-dev](https://github.com/arpit-jaiswal-dev) | #7881 |
-| [@artickc](https://github.com/artickc) | #6955, #7204, #7696, #7768, #7896, #7900, #7911, #7930, #7994, #8006 |
-| [@Arul-](https://github.com/Arul-) | #7878 |
-| [@backryun](https://github.com/backryun) | #7296, #7314, #7358, #7531, #7687, #7772, #7812, #7866, #7874, #7882, #7914, #8013, #8225, #8226, #8227, #8230 |
-| [@c4usal](https://github.com/c4usal) | #8129 |
-| [@Capslockb](https://github.com/Capslockb) | #7892 |
-| [@Chewji9875](https://github.com/Chewji9875) | #7545 |
-| [@chirag127](https://github.com/chirag127) | #7520, #8143 |
-| [@CitrusIce](https://github.com/CitrusIce) | #6937, #6938 |
-| [@Dan-ex-hub](https://github.com/Dan-ex-hub) | #7743 |
-| [@danscMax](https://github.com/danscMax) | #7359, #7511, #7517, #7648, #7656, #7672, #7689 |
-| [@dependabot](https://github.com/dependabot) | #7897, #7898, #8235 |
-| [@Dingding-leo](https://github.com/Dingding-leo) | #7988, #7989, #8162, #8165, #8167 |
-| [@DKotsyuba](https://github.com/DKotsyuba) | #7500 |
-| [@dongwook-chan](https://github.com/dongwook-chan) | #7574, #7582, #7704 |
-| [@ekinnee](https://github.com/ekinnee) | #7613, #7614, #7662, #7779, #7927, #7932, #7980 |
-| [@enjoyer-hub](https://github.com/enjoyer-hub) | #7863 |
-| [@fenix007](https://github.com/fenix007) | #7171, #7399 |
-| [@FenjuFu](https://github.com/FenjuFu) | #7942 |
-| [@floze-the-genius](https://github.com/floze-the-genius) | #7707 |
-| [@growab](https://github.com/growab) | #7062 |
-| [@guanbear](https://github.com/guanbear) | #7028 |
-| [@hartmark](https://github.com/hartmark) | #8208, #8209, #8210, #8211, #8212, #8213 |
-| [@HassiyYT](https://github.com/HassiyYT) | #7864 |
-| [@herjarsa](https://github.com/herjarsa) | #7612, #7625, #7633, #7869, #7871 |
-| [@HouMinXi](https://github.com/HouMinXi) | #7035, #7129, #7290, #7398, #7408, #7973 |
-| [@hppsc1215](https://github.com/hppsc1215) | #7546 |
-| [@huohua-dev](https://github.com/huohua-dev) | #6794 |
-| [@hydraxman](https://github.com/hydraxman) | #7909 |
-| [@insoln](https://github.com/insoln) | #7906, #7908, #8041, #8054, #8062 |
-| [@irvandikky](https://github.com/irvandikky) | #7695 |
-| [@isiahw1](https://github.com/isiahw1) | #7555 |
-| [@JxnLexn](https://github.com/JxnLexn) | #6993, #7154, #7177, #7269, #7273, #7280, #7281, #7282, #7323, #7360, #7377, #7378, #7379, #7380, #7381, #7419, #7607, #7894, #7905, #7912, #8008, #8009, #8010 |
-| [@KooshaPari](https://github.com/KooshaPari) | #7008, #7087, #7093, #7128, #7130, #7136, #7315, #7318, #7334, #7336 |
-| [@leninejunior](https://github.com/leninejunior) | #8049 |
-| [@leszek3737](https://github.com/leszek3737) | #7782, #7807 |
-| [@Long-Feeds](https://github.com/Long-Feeds) | #8011 |
-| [@loulanyue](https://github.com/loulanyue) | #7540 |
-| [@lunkerchen](https://github.com/lunkerchen) | #8024 |
-| [@makcimbx](https://github.com/makcimbx) | #7692, #8171 |
-| [@megamen32](https://github.com/megamen32) | #7313 |
-| [@MichaelYcJo](https://github.com/MichaelYcJo) | #8224 |
-| [@mikolaj92](https://github.com/mikolaj92) | #6973 |
-| [@MonteNegroX](https://github.com/MonteNegroX) | #8217 |
-| [@Moseyuh333](https://github.com/Moseyuh333) | #7781 |
-| [@MrFadiAi](https://github.com/MrFadiAi) | #7073 |
-| [@mustafa-phd](https://github.com/mustafa-phd) | #7686 |
-| [@nguyenha935](https://github.com/nguyenha935) | #7493, #7547, #7552, #7553, #7629, #7935, #8031, #8233 |
-| [@not-knope](https://github.com/not-knope) | #8206 |
-| [@nramabad](https://github.com/nramabad) | #7926 |
-| [@oyi77](https://github.com/oyi77) | #6917, #6918, #6919, #6920, #6921, #6923, #7032, #7045, #7046, #7066, #7070, #7178, #7719, #7744, #7787, #7893, #8219 |
-| [@professional-ALFIE](https://github.com/professional-ALFIE) | #6877 |
-| [@Prudhvivuda](https://github.com/Prudhvivuda) | #8220 |
-| [@rafaumeu](https://github.com/rafaumeu) | #6979, #6982, #6983, #6987, #6988, #7001, #7808, #7815, #8071, #8113, #8179, #8184, #8185, #8190, #8195, #8196, #8203 |
-| [@RaviTharuma](https://github.com/RaviTharuma) | #7852, #7853, #7855, #7862, #7885, #7972, #7978, #8021, #8022, #8023, #8025, #8027, #8030, #8102, #8124 |
-| [@RCrushMe](https://github.com/RCrushMe) | #8151 |
-| [@rushsinging](https://github.com/rushsinging) | #7256 |
-| [@seanford](https://github.com/seanford) | #8218, #8232 |
-| [@SeaXen](https://github.com/SeaXen) | #7063, #7264, #7294 |
-| [@Securiteru](https://github.com/Securiteru) | #7683 |
-| [@skutanjir](https://github.com/skutanjir) | #7865, #7939 |
-| [@swingtempo](https://github.com/swingtempo) | #7790 |
-| [@Tasogarre](https://github.com/Tasogarre) | #7861, #8207 |
-| [@thepigdestroyer](https://github.com/thepigdestroyer) | #7497 |
-| [@tianrking](https://github.com/tianrking) | #7353 |
-| [@tientien17](https://github.com/tientien17) | #7841, #7844, #7925 |
-| [@tmone](https://github.com/tmone) | #7806, #7933 |
-| [@TrackCrewGalore](https://github.com/TrackCrewGalore) | #8128 |
-| [@ViFigueiredo](https://github.com/ViFigueiredo) | #7301 |
-| [@vzts](https://github.com/vzts) | #7390 |
-| [@webmasterarbez](https://github.com/webmasterarbez) | #7504 |
-| [@Wibias](https://github.com/Wibias) | #7125 |
-| [@Witroch4](https://github.com/Witroch4) | #7901, #7902 |
-| [@xiaoyaner0201](https://github.com/xiaoyaner0201) | #8122 |
-| [@xier2012](https://github.com/xier2012) | #7036, #7050, #7052, #7053, #7056, #7059, #7060, #7061, #7166, #7299 |
-| [@xz-dev](https://github.com/xz-dev) | #7004, #7012, #7027, #7673, #7700, #7747, #7776, #7843 |
-| [@diegosouzapw](https://github.com/diegosouzapw) | maintainer |
-
 ---

 ## [3.8.48] — 2026-07-13
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -35,7 +35,7 @@ For full test matrix, see `CONTRIBUTING.md` → "Running Tests". For deep archit

 ## Project at a Glance

-**OmniRoute** — unified AI proxy/router. One endpoint, 290 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 271 LLM providers, auto-fallback.

 | Layer         | Location                | Purpose                                                                                                                                                 |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -103,19 +103,13 @@ Default URLs:
 ## Git Workflow

 > ⚠️ **NEVER commit directly to `main`.** Always use feature branches.
->
-> **PR base:** target the active `release/vX.Y.Z` branch (not `main`). See
-> [`docs/ops/BRANCHING_MODEL.md`](docs/ops/BRANCHING_MODEL.md) for the
-> release-per-branch + tag-at-ship model.

 ```bash
-# Branch from the active release tip (example: release/v3.8.49)
-git fetch origin
-git checkout -b feat/your-feature-name origin/release/v3.8.49
+git checkout -b feat/your-feature-name
 # ... make changes ...
 git commit -m "feat: describe your change"
 git push -u origin feat/your-feature-name
-# Open a Pull Request with base = release/v3.8.49
+# Open a Pull Request on GitHub
 ```

 ### Branch Naming
@@ -198,14 +192,11 @@ Coverage notes:

 ### Pull Request Requirements

-Before opening a PR, run the focused loop for what you changed. The full unit suite
-(4 CI shards), Vitest, the **60%+** coverage gate, and the production build are CI's
-responsibility — running them locally adds no signal the PR checks will not already
-give you, and on smaller machines it can saturate the host (#8084):
+Before opening or merging a PR:

- Run the test files that cover your change: `node --import tsx/esm --test tests/unit/<file>.test.ts`
- Run `npm run lint`
- Include or update automated tests in the same PR whenever production code changes
+- Run `npm run test:unit`
+- Run `npm run test:coverage`
+- Ensure the coverage gate stays at **60%+** statements/lines/functions/branches
 - Include the changed or added test files in the PR description when production code changed
 - Check the SonarQube result on the PR when the project secrets are configured in CI

@@ -231,31 +222,6 @@ Current test status: **122 unit test files** covering:
 - **Zod validation** — Use Zod v4 schemas for all API input validation
 - **Naming**: Files = camelCase/kebab-case, components = PascalCase, constants = UPPER_SNAKE

-### Error handling / empty catch blocks
-
-Never leave a `catch` unexplained. Classify it into one of two buckets (operationalizes
-the hard rule "never silently swallow errors in SSE streams"):
-
- **Intentional (our own best-effort cleanup/telemetry)** — a failure here is expected and
-  harmless; add a one-line rationale comment, no logging (logging on every request is the
-  noise this convention avoids).
-
-  ```ts
-  } catch {} // closing an already-closed controller after client disconnect is expected
-  ```
-
- **Should log (external/caller-supplied code, or the swallow changes control flow)** — keep
-  the catch (never let it break the stream) but emit a contextual `console.debug`/`warn` so the
-  failure is discoverable.
-
-  ```ts
-  } catch (e) {
-    console.debug("[STREAM] onFailure callback error:", e);
-  }
-  ```
-
-See `open-sse/utils/stream.ts` and `open-sse/utils/streamHandler.ts` for applied examples.
-
 ---

 ## Project Structure
--- a/GEMINI.md
+++ b/GEMINI.md
@@ -27,7 +27,7 @@ When creating _any_ validation tests or one-off logic scripts, default to using
 7. **Never bypass Husky hooks** (`--no-verify`, `--no-gpg-sign`) without explicit operator approval.
 8. **Always validate inputs with Zod schemas** from `src/shared/validation/schemas.ts`.
 9. **Always include tests when changing production code** (`src/`, `open-sse/`, `electron/`, `bin/`).
-10. **Coverage must stay** ≥ 60 % statements / lines / functions / branches — the official CI gate (`npm run test:coverage`). The ratchet baseline in `quality-baseline.json` may freeze a higher floor; never regress it.
+10. **Coverage must stay** ≥ 75 % statements / 75 % lines / 75 % functions / 70 % branches (real measured: ~82 %).

 ## 3. Codebase navigation

--- a/README.md
+++ b/README.md
--- a/SECURITY.md
+++ b/SECURITY.md
@@ -77,28 +77,21 @@ Custom guardrails register via `registerGuardrail(new MyGuardrail())`. The model

 ### 🧠 Prompt Injection Guard

-Best-effort heuristic middleware that detects prompt injection patterns in LLM requests.
-**Not a complete prompt-injection firewall** — can produce false positives (benign
-persona/RPG prompts) and false negatives (leetspeak, spacing, non-English patterns).
+Middleware that detects and blocks prompt injection attacks in LLM requests:

 | Pattern Type        | Severity | Example                                        |
 | ------------------- | -------- | ---------------------------------------------- |
 | System Override     | High     | "ignore all previous instructions"             |
-| Role Hijack         | Medium   | "you are now DAN, you can do anything"         |
-| Delimiter Injection | High     | Encoded separators to break context boundaries |
-| DAN/Jailbreak       | Medium   | Known jailbreak prompt patterns                |
-| Instruction Leak    | High     | "show me your system prompt"                   |
-| Encoding Evasion    | Medium   | base64/rot13/hex decode + instruction keywords |
-
-Only **High** severity detections are blocked in `block` mode. Medium-severity
-families are logged but never blocked by `sanitizeRequest`.
+| Role Hijack         | High     | "you are now DAN, you can do anything"         |
+| Delimiter Injection | Medium   | Encoded separators to break context boundaries |
+| DAN/Jailbreak       | High     | Known jailbreak prompt patterns                |
+| Instruction Leak    | Medium   | "show me your system prompt"                   |

 Configure via dashboard (Settings → Security) or `.env`:

 ```env
 INPUT_SANITIZER_ENABLED=true
-INPUT_SANITIZER_MODE=block    # warn | block (injection policy; legacy "redact" does not strip injection text)
-INPUT_SANITIZER_BLOCK_THRESHOLD=high  # high (default) | medium | low — severities at/above this are blocked in block mode
+INPUT_SANITIZER_MODE=block    # warn | block | redact
 ```

 ### 🔒 PII Redaction
@@ -115,8 +108,7 @@ Automatic detection and optional redaction of personally identifiable informatio
 | SSN (US)      | `123-45-6789`         | `[SSN_REDACTED]`   |

 ```env
-PII_REDACTION_ENABLED=true   # request PII rewrite; independent of INPUT_SANITIZER_MODE
-PII_RESPONSE_SANITIZATION=true  # optional: redact PII in provider responses returned to clients
+PII_REDACTION_ENABLED=true
 ```

 ### 🌐 Network Security
--- a/bin/cli/commands/backup.mjs
+++ b/bin/cli/commands/backup.mjs
@@ -78,15 +78,18 @@ export function registerBackup(program) {
      if (exitCode !== 0) process.exit(exitCode);
    });

-  // Legacy: `omniroute backup` without a subcommand still creates a backup
-  // (documented as the canonical usage in USER_GUIDE.md / CLI-TOOLS.md /
-  // AGENT-SKILLS.md). No flags are declared here — declaring the same
-  // option names as `create`/`auto enable` here previously shadowed them
-  // (#8512), and no doc shows `omniroute backup` invoked with flags.
+  // Legacy: `omniroute backup` without subcommand still creates a backup
  backup.action(async (opts) => {
    const exitCode = await runBackupCommand(opts);
    if (exitCode !== 0) process.exit(exitCode);
  });
+  backup
+    .option("--name <name>", t("backup.nameOpt"))
+    .option("--cloud", t("backup.cloudOpt"))
+    .option("--encrypt", t("backup.encryptOpt"))
+    .option("--key-file <path>", t("backup.keyFileOpt"))
+    .option("--exclude <pattern>", t("backup.excludeOpt"), (v, prev = []) => [...prev, v], [])
+    .option("--retention <n>", t("backup.retentionOpt"), parseInt);
 }

 export function registerRestore(program) {
--- a/bin/cli/commands/launch.mjs
+++ b/bin/cli/commands/launch.mjs
@@ -106,10 +106,10 @@ export async function runLaunchCommand(opts = {}, claudeArgs = []) {
    if (!res.ok) throw new Error(`status ${res.status}`);
  } catch {
    console.error(
-      (
-        t("launch.notRunning") ||
-        "OmniRoute is not reachable at {port}. Start it with 'omniroute serve'."
-      ).replace("{port}", baseUrl)
+      (t("launch.notRunning") || "OmniRoute is not reachable at {port}. Start it with 'omniroute serve'.").replace(
+        "{port}",
+        baseUrl
+      )
    );
    return 1;
  }
@@ -120,14 +120,7 @@ export async function runLaunchCommand(opts = {}, claudeArgs = []) {
  const env = buildClaudeEnv(process.env, baseUrl, authToken, { configDir });

  return await new Promise((resolve) => {
-    // #8246: on Windows, npm installs claude as a .cmd shim — spawn() without
-    // shell:true cannot resolve PATHEXT shims and fails with ENOENT.
-    const claudeCommand = process.platform === "win32" ? "claude.cmd" : "claude";
-    const child = spawn(claudeCommand, claudeArgs, {
-      env,
-      stdio: "inherit",
-      ...(process.platform === "win32" ? { shell: true, windowsHide: true } : {}),
-    });
+    const child = spawn("claude", claudeArgs, { env, stdio: "inherit" });
    child.on("error", (err) => {
      if (err && err.code === "ENOENT") {
        console.error(t("launch.notFound") || "The 'claude' CLI was not found in PATH.");
@@ -149,10 +142,7 @@ export function registerLaunch(program) {
    )
    .option("--port <port>", t("serve.port") || "Proxy port", "20128")
    .option("--remote <url>", "Remote OmniRoute base URL (overrides --port and the active context)")
-    .option(
-      "--profile <name>",
-      "Claude Code profile to use (CLAUDE_CONFIG_DIR ~/.claude/profiles/<name>)"
-    )
+    .option("--profile <name>", "Claude Code profile to use (CLAUDE_CONFIG_DIR ~/.claude/profiles/<name>)")
    .option("--token <token>", t("launch.token") || "Token Claude sends (ANTHROPIC_AUTH_TOKEN)")
    .option("--api-key <key>", "Alias for --token (OmniRoute access token / API key)")
    .allowUnknownOption(true)
--- a/bin/cli/commands/setup.mjs
+++ b/bin/cli/commands/setup.mjs
@@ -26,7 +26,6 @@ function wantsProviderSetup(opts) {

 async function resolvePassword(opts, prompt, nonInteractive) {
  if (opts.password) return opts.password;
-  if (process.env.INITIAL_PASSWORD) return process.env.INITIAL_PASSWORD;
  if (nonInteractive) return "";

  const answer = await prompt.ask("Set an admin password now? [y/N]", "N");
--- a/bin/cli/commands/stop.mjs
+++ b/bin/cli/commands/stop.mjs
@@ -8,7 +8,6 @@ import {
  sleep,
 } from "../utils/pid.mjs";
 import { t } from "../i18n.mjs";
-import { stopProcessGracefully } from "../../../src/shared/platform/windowsProcess.ts";

 const execFileAsync = promisify(execFile);

@@ -28,11 +27,18 @@ export async function runStopCommand(opts = {}) {
  if (pid && isPidRunning(pid)) {
    console.log(t("stop.stopping", { pid }));
    try {
-      // #8045: on win32, process.kill(pid, "SIGTERM") unconditionally force-terminates
-      // the target instead of delivering an interceptable signal, racing (and beating)
-      // the server's own async graceful shutdown / WAL checkpoint. stopProcessGracefully
-      // skips the immediate SIGTERM on win32 and just polls before escalating to SIGKILL.
-      await stopProcessGracefully({ pid, timeoutMs: 5000, isPidRunning, sleep });
+      process.kill(pid, "SIGTERM");
+
+      let waited = 0;
+      while (waited < 5000 && isPidRunning(pid)) {
+        await sleep(100);
+        waited += 100;
+      }
+
+      if (isPidRunning(pid)) {
+        process.kill(pid, "SIGKILL");
+        await sleep(500);
+      }

      killAllSubprocesses();
      cleanupPidFile("server");
--- a/bin/cli/locales/zh-CN.json
+++ b/bin/cli/locales/zh-CN.json
@@ -29,16 +29,16 @@
  "setup": {
    "title": "OmniRoute 设置",
    "passwordPrompt": "管理员密码",
-    "providerPrompt": "默认提供者（留空跳过）",
+    "providerPrompt": "默认提供商（留空跳过）",
    "done": "设置完成",
    "passwordSet": "管理员密码已配置",
-    "providerSet": "提供者已配置：{name}",
-    "testingProvider": "正在测试提供者连接：{name}",
-    "testPassed": "提供者测试通过",
-    "testFailed": "提供者测试失败：{error}",
+    "providerSet": "提供商已配置：{name}",
+    "testingProvider": "正在测试提供商连接：{name}",
+    "testPassed": "提供商测试通过",
+    "testFailed": "提供商测试失败：{error}",
    "loginEnabled": "登录：已启用（密码已更新）",
    "loginDisabled": "登录：已禁用",
-    "providerInfo": "提供者：{info}"
+    "providerInfo": "提供商：{info}"
  },
  "doctor": {
    "title": "OmniRoute 诊断",
@@ -52,29 +52,29 @@
    "warnings": "{count} 个警告 — 见上文。"
  },
  "providers": {
-    "title": "提供者",
-    "noProviders": "未配置提供者。运行：omniroute setup",
+    "title": "提供商",
+    "noProviders": "未配置提供商。运行：omniroute setup",
    "testing": "正在测试 {name}...",
-    "available": "{count} 个提供者可用",
+    "available": "{count} 个提供商可用",
    "connected": "已连接",
    "disconnected": "未连接",
    "validationFailed": "验证失败：{error}",
    "metrics": {
-      "description": "显示提供者性能指标（延迟、成功率、成本）",
-      "provider": "按提供者 ID 筛选",
+      "description": "显示提供商性能指标（延迟、成功率、成本）",
+      "provider": "按提供商 ID 筛选",
      "connection_id": "按连接 ID 筛选",
      "period": "时间范围：1h|6h|24h|7d|30d（默认：24h）",
      "metric": "关注特定指标字段",
      "sort": "按字段排序（降序）",
      "limit": "最大行数（默认：50）",
      "watch": "每 5 秒刷新（实时模式）",
-      "compare": "逗号分隔的提供者 ID，并排比较"
+      "compare": "逗号分隔的提供商 ID，并排比较"
    },
    "metric_single": {
      "description": "获取特定连接的单个指标值"
    },
    "rotate": {
-      "description": "轮换提供者连接的上游 API 密钥",
+      "description": "轮换提供商连接的上游 API 密钥",
      "newKeyOpt": "新 API 密钥值（避免使用：优先使用 --from-env）",
      "fromEnvOpt": "从环境变量 VAR 读取新密钥",
      "oauthOpt": "改为触发 OAuth 重新认证流程",
@@ -89,18 +89,18 @@
      "testFailed": "轮换后测试失败：{error}"
    },
    "status": {
-      "description": "显示所有提供者连接的密钥健康状态（期限、过期、冷却）",
-      "providerOpt": "按提供者名称筛选",
-      "header": "ID         提供者       名称                     过期状态  测试状态  冷却至",
-      "noData": "没有可用的提供者连接数据。",
+      "description": "显示所有提供商连接的密钥健康状态（期限、过期、冷却）",
+      "providerOpt": "按提供商名称筛选",
+      "header": "ID         提供商       名称                     过期状态  测试状态  冷却至",
+      "noData": "没有可用的提供商连接数据。",
      "requiresServer": "providers status 需要 OmniRoute 服务器正在运行。"
    }
  },
  "keys": {
    "title": "API 密钥",
-    "addDescription": "为提供者添加或更新 API 密钥",
+    "addDescription": "为提供商添加或更新 API 密钥",
    "listDescription": "列出所有已配置的 API 密钥",
-    "removeDescription": "移除提供者的 API 密钥",
+    "removeDescription": "移除提供商的 API 密钥",
    "regenerateDescription": "重新生成 OmniRoute API 密钥",
    "revokeDescription": "撤销 OmniRoute API 密钥",
    "revealDescription": "显示未掩码的 API 密钥值",
@@ -122,10 +122,10 @@
    "revoked": "密钥 {id} 已撤销。",
    "rotated": "密钥 {id} 已轮换。新密钥 ID：{newId}",
    "revealWarning": "⚠ 这将显示完整的未掩码密钥。请确保您的屏幕不被人看到。",
-    "providerRequired": "需要提供者。",
+    "providerRequired": "需要提供商。",
    "keyRequired": "需要 API 密钥。",
    "stdinEmpty": "未通过标准输入提供 API 密钥。",
-    "unknownProvider": "未知提供者：{provider}",
+    "unknownProvider": "未知提供商：{provider}",
    "policy": {
      "title": "密钥策略",
      "showDescription": "显示密钥的速率/成本策略",
@@ -165,7 +165,7 @@
    "analytics": {
      "description": "显示汇总使用分析",
      "period": "时间范围：1d|7d|30d|90d|ytd|all（默认：30d）",
-      "provider": "按提供者 ID 筛选"
+      "provider": "按提供商 ID 筛选"
    },
    "budget": {
      "description": "管理成本预算",
@@ -175,8 +175,8 @@
      }
    },
    "quota": {
-      "description": "显示提供者配额使用情况",
-      "provider": "按提供者 ID 筛选",
+      "description": "显示提供商配额使用情况",
+      "provider": "按提供商 ID 筛选",
      "check": "显示新请求是否有可用配额"
    },
    "logs": {
@@ -201,7 +201,7 @@
    }
  },
  "cost": {
-    "description": "按提供者、模型、组合或 API 密钥显示成本报告",
+    "description": "按提供商、模型、组合或 API 密钥显示成本报告",
    "period": "时间范围：1d|7d|30d|90d|ytd|all（默认：30d）",
    "since": "开始日期（ISO 格式，例如 2026-01-01）— 覆盖 --period",
    "until": "结束日期（ISO 格式）",
@@ -210,7 +210,7 @@
    "limit": "显示的最大行数（默认：100）"
  },
  "simulate": {
-    "description": "模拟路由（空运行）— 显示将选择哪些提供者而不调用上游",
+    "description": "模拟路由（空运行）— 显示将选择哪些提供商而不调用上游",
    "file": "从 JSON 文件加载完整请求体",
    "model": "模型 ID（默认：auto）",
    "combo": "强制指定组合名称",
@@ -301,7 +301,7 @@
    "cost": "成本（24h）："
  },
  "quota": {
-    "description": "显示提供者配额使用情况",
+    "description": "显示提供商配额使用情况",
    "noServer": "服务器未运行。启动：omniroute serve",
    "noData": "没有可用的配额信息。"
  },
@@ -315,12 +315,12 @@
    "description": "一键启动本地 Redis 容器（Podman 或 Docker），用于 OmniRoute 缓存和配额跟踪"
  },
  "test": {
-    "description": "测试提供者连接",
+    "description": "测试提供商连接",
    "noServer": "服务器未运行。启动：omniroute serve",
    "testing": "正在测试 {provider} / {model}...",
    "passed": "连接成功！",
    "failed": "连接失败：{error}",
-    "allProvidersOpt": "测试所有已配置的提供者",
+    "allProvidersOpt": "测试所有已配置的提供商",
    "latencyOpt": "显示延迟测量值（平均/最小/最大 毫秒）",
    "repeatOpt": "重复测试 N 次并汇总结果",
    "compareOpt": "逗号分隔的要比较的模型（例如 gpt-4o,claude-3-5-sonnet）",
@@ -328,7 +328,7 @@
    "saved": "结果已保存至 {path}",
    "compareTitle": "模型比较",
    "compareMinTwo": "--compare 需要至少两个模型（逗号分隔）",
-    "noProviders": "未配置提供者。添加：omniroute keys add"
+    "noProviders": "未配置提供商。添加：omniroute keys add"
  },
  "update": {
    "checking": "正在检查更新...",
@@ -509,7 +509,7 @@
  },
  "models": {
    "description": "列出可用模型（需要服务器）",
-    "search": "按 ID、名称、提供者或描述筛选模型",
+    "search": "按 ID、名称、提供商或描述筛选模型",
    "noServer": "服务器未运行。启动：omniroute serve",
    "noModels": "未找到模型。"
  },
@@ -656,25 +656,25 @@
    }
  },
  "oauth": {
-    "description": "管理 OAuth 提供者连接",
+    "description": "管理 OAuth 提供商连接",
    "providers": {
-      "description": "列出支持 OAuth 的提供者及其流程类型"
+      "description": "列出支持 OAuth 的提供商及其流程类型"
    },
    "start": {
-      "description": "为提供者启动 OAuth 授权流程",
-      "provider": "提供者 ID（gemini, copilot, cursor, ...）",
+      "description": "为提供商启动 OAuth 授权流程",
+      "provider": "提供商 ID（gemini, copilot, cursor, ...）",
      "no_browser": "仅打印 URL — 不打开浏览器",
      "import_system": "从本地系统配置自动导入凭据",
-      "social": "社交登录提供者（google|github）— kiro 需要",
+      "social": "社交登录提供商（google|github）— kiro 需要",
      "timeout": "等待授权超时时间（毫秒，默认：300000）"
    },
    "status": {
      "description": "列出活动的 OAuth 连接",
-      "provider": "按提供者 ID 筛选"
+      "provider": "按提供商 ID 筛选"
    },
    "revoke": {
      "description": "撤销 OAuth 连接",
-      "provider": "要撤销的提供者 ID",
+      "provider": "要撤销的提供商 ID",
      "connection_id": "按 ID 撤销特定连接",
      "yes": "跳过确认提示"
    }
@@ -884,11 +884,11 @@
    "description": "管理模型定价数据",
    "sync": {
      "description": "从上游同步价格",
-      "provider": "按提供者筛选",
+      "provider": "按提供商筛选",
      "force": "强制重新同步"
    },
    "list": {
-      "provider": "按提供者筛选",
+      "provider": "按提供商筛选",
      "model": "按模型筛选",
      "limit": "最大结果数"
    },
@@ -907,25 +907,25 @@
  "resilience": {
    "description": "检查和管理弹性机制",
    "status": {
-      "provider": "按提供者筛选"
+      "provider": "按提供商筛选"
    },
    "breakers": {
-      "provider": "按提供者筛选"
+      "provider": "按提供商筛选"
    },
    "cooldowns": {
-      "provider": "按提供者筛选",
+      "provider": "按提供商筛选",
      "connectionId": "按连接 ID 筛选"
    },
    "lockouts": {
-      "provider": "按提供者筛选",
+      "provider": "按提供商筛选",
      "model": "按模型筛选"
    },
    "reset": {
      "description": "重置断路器/冷却状态",
-      "provider": "要重置的提供者",
+      "provider": "要重置的提供商",
      "connectionId": "要重置的连接 ID",
      "model": "要重置锁定状态的模型",
-      "allCooldowns": "重置提供者的所有冷却",
+      "allCooldowns": "重置提供商的所有冷却",
      "yes": "跳过确认"
    },
    "profile": {
@@ -940,13 +940,13 @@
    }
  },
  "nodes": {
-    "description": "管理提供者节点（端点）",
+    "description": "管理提供商节点（端点）",
    "list": {
-      "provider": "按提供者筛选",
+      "provider": "按提供商筛选",
      "enabled": "仅显示已启用的节点"
    },
    "add": {
-      "provider": "提供者名称",
+      "provider": "提供商名称",
      "baseUrl": "节点的基础 URL",
      "name": "节点名称",
      "weight": "负载均衡权重",
@@ -965,7 +965,7 @@
    },
    "validate": {
      "baseUrl": "要验证的 URL",
-      "provider": "要验证的提供者"
+      "provider": "要验证的提供商"
    },
    "test": {
      "description": "向节点发送测试请求"
@@ -1091,7 +1091,7 @@
  "oneproxy": {
    "description": "管理 OneProxy 上游代理池",
    "stats": {
-      "provider": "按提供者筛选",
+      "provider": "按提供商筛选",
      "period": "时间范围（默认：24h）"
    },
    "fetch": {
@@ -1101,14 +1101,14 @@
    },
    "rotate": {
      "description": "强制轮换代理",
-      "provider": "要轮换的提供者",
+      "provider": "要轮换的提供商",
      "connectionId": "要轮换的特定连接 ID"
    },
    "config": {
      "description": "显示或更新 OneProxy 配置",
      "enabled": "启用代理池（true|false）",
      "poolSize": "池大小",
-      "providerSource": "代理提供者的 URL",
+      "providerSource": "代理提供商的 URL",
      "rotationPolicy": "轮换策略：sticky|per-request|periodic"
    },
    "pool": {
@@ -1201,7 +1201,7 @@
    "bash": "打印 bash 补全脚本",
    "fish": "打印 fish 补全脚本",
    "install": "为检测到的 Shell 全局安装补全脚本",
-    "refresh": "刷新组合/提供者/模型缓存"
+    "refresh": "刷新组合/提供商/模型缓存"
  },
  "logs": {
    "description": "流式传输或导出请求日志",
--- a/bin/cli/locales/zh-TW.json
+++ b/bin/cli/locales/zh-TW.json
@@ -29,16 +29,16 @@
  "setup": {
    "title": "OmniRoute 設定",
    "passwordPrompt": "管理員密碼",
-    "providerPrompt": "預設提供者（留空跳過）",
+    "providerPrompt": "預設提供商（留空跳過）",
    "done": "設定完成",
    "passwordSet": "管理員密碼已配置",
-    "providerSet": "提供者已配置：{name}",
-    "testingProvider": "正在測試提供者連線：{name}",
-    "testPassed": "提供者測試通過",
-    "testFailed": "提供者測試失敗：{error}",
+    "providerSet": "提供商已配置：{name}",
+    "testingProvider": "正在測試提供商連線：{name}",
+    "testPassed": "提供商測試通過",
+    "testFailed": "提供商測試失敗：{error}",
    "loginEnabled": "登入：已啟用（密碼已更新）",
    "loginDisabled": "登入：已停用",
-    "providerInfo": "提供者：{info}"
+    "providerInfo": "提供商：{info}"
  },
  "doctor": {
    "title": "OmniRoute 診斷",
@@ -52,29 +52,29 @@
    "warnings": "{count} 個警告 — 見上文。"
  },
  "providers": {
-    "title": "提供者",
-    "noProviders": "未配置提供者。執行：omniroute setup",
+    "title": "提供商",
+    "noProviders": "未配置提供商。執行：omniroute setup",
    "testing": "正在測試 {name}...",
-    "available": "{count} 個提供者可用",
+    "available": "{count} 個提供商可用",
    "connected": "已連線",
    "disconnected": "未連線",
    "validationFailed": "驗證失敗：{error}",
    "metrics": {
-      "description": "顯示提供者效能指標（延遲、成功率、成本）",
-      "provider": "按提供者 ID 篩選",
+      "description": "顯示提供商效能指標（延遲、成功率、成本）",
+      "provider": "按提供商 ID 篩選",
      "connection_id": "按連線 ID 篩選",
      "period": "時間範圍：1h|6h|24h|7d|30d（預設：24h）",
      "metric": "關注特定指標欄位",
      "sort": "按欄位排序（降序）",
      "limit": "最大行數（預設：50）",
      "watch": "每 5 秒重新整理（即時模式）",
-      "compare": "逗號分隔的提供者 ID，並排比較"
+      "compare": "逗號分隔的提供商 ID，並排比較"
    },
    "metric_single": {
      "description": "獲取特定連線的單個指標值"
    },
    "rotate": {
-      "description": "輪換提供者連線的上游 API 金鑰",
+      "description": "輪換提供商連線的上游 API 金鑰",
      "newKeyOpt": "新 API 金鑰值（避免使用：優先使用 --from-env）",
      "fromEnvOpt": "從環境變數 VAR 讀取新金鑰",
      "oauthOpt": "改為觸發 OAuth 重新認證流程",
@@ -89,18 +89,18 @@
      "testFailed": "輪換後測試失敗：{error}"
    },
    "status": {
-      "description": "顯示所有提供者連線的金鑰健康狀態（期限、過期、冷卻）",
-      "providerOpt": "按提供者名稱篩選",
-      "header": "ID         提供者       名稱                     過期狀態  測試狀態  冷卻至",
-      "noData": "沒有可用的提供者連線資料。",
+      "description": "顯示所有提供商連線的金鑰健康狀態（期限、過期、冷卻）",
+      "providerOpt": "按提供商名稱篩選",
+      "header": "ID         提供商       名稱                     過期狀態  測試狀態  冷卻至",
+      "noData": "沒有可用的提供商連線資料。",
      "requiresServer": "providers status 需要 OmniRoute 伺服器正在執行。"
    }
  },
  "keys": {
    "title": "API 金鑰",
-    "addDescription": "為提供者新增或更新 API 金鑰",
+    "addDescription": "為提供商新增或更新 API 金鑰",
    "listDescription": "列出所有已配置的 API 金鑰",
-    "removeDescription": "移除提供者的 API 金鑰",
+    "removeDescription": "移除提供商的 API 金鑰",
    "regenerateDescription": "重新生成 OmniRoute API 金鑰",
    "revokeDescription": "撤銷 OmniRoute API 金鑰",
    "revealDescription": "顯示未掩碼的 API 金鑰值",
@@ -122,10 +122,10 @@
    "revoked": "金鑰 {id} 已撤銷。",
    "rotated": "金鑰 {id} 已輪換。新金鑰 ID：{newId}",
    "revealWarning": "⚠ 這將顯示完整的未掩碼金鑰。請確保您的螢幕不被人看到。",
-    "providerRequired": "需要提供者。",
+    "providerRequired": "需要提供商。",
    "keyRequired": "需要 API 金鑰。",
    "stdinEmpty": "未通過標準輸入提供 API 金鑰。",
-    "unknownProvider": "未知提供者：{provider}",
+    "unknownProvider": "未知提供商：{provider}",
    "policy": {
      "title": "金鑰策略",
      "showDescription": "顯示金鑰的速率/成本策略",
@@ -151,7 +151,7 @@
    "model": "模型 ID（預設：auto）",
    "system": "系統提示",
    "combo": "強制指定組合名稱",
-    "max_tokens": "響應最大權杖數",
+    "max_tokens": "響應最大令牌數",
    "responses_api": "使用 /v1/responses 而不是 /v1/chat/completions",
    "raw": "列印接收到的原始 SSE 行",
    "debug": "在 stderr 中列印每塊的時間資訊",
@@ -165,7 +165,7 @@
    "analytics": {
      "description": "顯示彙總使用分析",
      "period": "時間範圍：1d|7d|30d|90d|ytd|all（預設：30d）",
-      "provider": "按提供者 ID 篩選"
+      "provider": "按提供商 ID 篩選"
    },
    "budget": {
      "description": "管理成本預算",
@@ -175,8 +175,8 @@
      }
    },
    "quota": {
-      "description": "顯示提供者配額使用情況",
-      "provider": "按提供者 ID 篩選",
+      "description": "顯示提供商配額使用情況",
+      "provider": "按提供商 ID 篩選",
      "check": "顯示新請求是否有可用配額"
    },
    "logs": {
@@ -201,7 +201,7 @@
    }
  },
  "cost": {
-    "description": "按提供者、模型、組合或 API 金鑰顯示成本報告",
+    "description": "按提供商、模型、組合或 API 金鑰顯示成本報告",
    "period": "時間範圍：1d|7d|30d|90d|ytd|all（預設：30d）",
    "since": "開始日期（ISO 格式，例如 2026-01-01）— 覆蓋 --period",
    "until": "結束日期（ISO 格式）",
@@ -210,12 +210,12 @@
    "limit": "顯示的最大行數（預設：100）"
  },
  "simulate": {
-    "description": "模擬路由（空執行）— 顯示將選擇哪些提供者而不呼叫上游",
+    "description": "模擬路由（空執行）— 顯示將選擇哪些提供商而不呼叫上游",
    "file": "從 JSON 檔案載入完整請求體",
    "model": "模型 ID（預設：auto）",
    "combo": "強制指定組合名稱",
    "reasoning": "推理努力級別（low|medium|high）",
-    "thinking": "擴充套件思維權杖預算",
+    "thinking": "擴充套件思維令牌預算",
    "explain": "在 stderr 中列印回退樹和成本範圍",
    "noCombo": "未找到匹配的組合。使用以下命令配置：omniroute combo create"
  },
@@ -225,11 +225,11 @@
    "stdin": "從標準輸入讀取提示",
    "system": "系統提示",
    "model": "模型 ID（預設：auto）",
-    "max_tokens": "響應最大權杖數",
+    "max_tokens": "響應最大令牌數",
    "temperature": "取樣溫度（0–2）",
    "top_p": "Top-p 核取樣",
    "reasoning_effort": "推理努力級別（low|medium|high）",
-    "thinking_budget": "擴充套件思維權杖預算",
+    "thinking_budget": "擴充套件思維令牌預算",
    "combo": "強制指定組合名稱",
    "responses_api": "使用 /v1/responses 而不是 /v1/chat/completions",
    "stream": "增量流式傳輸響應",
@@ -301,7 +301,7 @@
    "cost": "成本（24h）："
  },
  "quota": {
-    "description": "顯示提供者配額使用情況",
+    "description": "顯示提供商配額使用情況",
    "noServer": "伺服器未執行。啟動：omniroute serve",
    "noData": "沒有可用的配額資訊。"
  },
@@ -315,12 +315,12 @@
    "description": "一鍵啟動本地 Redis 容器（Podman 或 Docker），用於 OmniRoute 快取和配額跟蹤"
  },
  "test": {
-    "description": "測試提供者連線",
+    "description": "測試提供商連線",
    "noServer": "伺服器未執行。啟動：omniroute serve",
    "testing": "正在測試 {provider} / {model}...",
    "passed": "連線成功！",
    "failed": "連線失敗：{error}",
-    "allProvidersOpt": "測試所有已配置的提供者",
+    "allProvidersOpt": "測試所有已配置的提供商",
    "latencyOpt": "顯示延遲測量值（平均/最小/最大 毫秒）",
    "repeatOpt": "重複測試 N 次並彙總結果",
    "compareOpt": "逗號分隔的要比較的模型（例如 gpt-4o,claude-3-5-sonnet）",
@@ -328,7 +328,7 @@
    "saved": "結果已儲存至 {path}",
    "compareTitle": "模型比較",
    "compareMinTwo": "--compare 需要至少兩個模型（逗號分隔）",
-    "noProviders": "未配置提供者。新增：omniroute keys add"
+    "noProviders": "未配置提供商。新增：omniroute keys add"
  },
  "update": {
    "checking": "正在檢查更新...",
@@ -445,7 +445,7 @@
      "description": "配置壓縮設定",
      "engine": "壓縮引擎（caveman|rtk|hybrid|none）",
      "caveman_agg": "Caveman 激程序度 0.0–1.0",
-      "rtk_budget": "RTK 權杖預算",
+      "rtk_budget": "RTK 令牌預算",
      "language_pack": "要啟用的語言包"
    },
    "engine": {
@@ -509,7 +509,7 @@
  },
  "models": {
    "description": "列出可用模型（需要伺服器）",
-    "search": "按 ID、名稱、提供者或描述篩選模型",
+    "search": "按 ID、名稱、提供商或描述篩選模型",
    "noServer": "伺服器未執行。啟動：omniroute serve",
    "noModels": "未找到模型。"
  },
@@ -621,7 +621,7 @@
      "type": "按記憶型別篩選（user|feedback|project|reference）",
      "limit": "最大結果數（預設：20）",
      "api_key": "按 API 金鑰篩選",
-      "token_budget": "限制結果中的總權杖數"
+      "token_budget": "限制結果中的總令牌數"
    },
    "add": {
      "description": "新增新的記憶條目",
@@ -656,25 +656,25 @@
    }
  },
  "oauth": {
-    "description": "管理 OAuth 提供者連線",
+    "description": "管理 OAuth 提供商連線",
    "providers": {
-      "description": "列出支援 OAuth 的提供者及其流程型別"
+      "description": "列出支援 OAuth 的提供商及其流程型別"
    },
    "start": {
-      "description": "為提供者啟動 OAuth 授權流程",
-      "provider": "提供者 ID（gemini, copilot, cursor, ...）",
+      "description": "為提供商啟動 OAuth 授權流程",
+      "provider": "提供商 ID（gemini, copilot, cursor, ...）",
      "no_browser": "僅列印 URL — 不開啟瀏覽器",
      "import_system": "從本地系統配置自動匯入憑據",
-      "social": "社交登入提供者（google|github）— kiro 需要",
+      "social": "社交登入提供商（google|github）— kiro 需要",
      "timeout": "等待授權超時時間（毫秒，預設：300000）"
    },
    "status": {
      "description": "列出活動的 OAuth 連線",
-      "provider": "按提供者 ID 篩選"
+      "provider": "按提供商 ID 篩選"
    },
    "revoke": {
      "description": "撤銷 OAuth 連線",
-      "provider": "要撤銷的提供者 ID",
+      "provider": "要撤銷的提供商 ID",
      "connection_id": "按 ID 撤銷特定連線",
      "yes": "跳過確認提示"
    }
@@ -884,20 +884,20 @@
    "description": "管理模型定價資料",
    "sync": {
      "description": "從上游同步價格",
-      "provider": "按提供者篩選",
+      "provider": "按提供商篩選",
      "force": "強制重新同步"
    },
    "list": {
-      "provider": "按提供者篩選",
+      "provider": "按提供商篩選",
      "model": "按模型篩選",
      "limit": "最大結果數"
    },
    "defaults": {
      "description": "管理預設定價",
-      "input": "每 1M 權杖的輸入成本（美元）",
-      "output": "每 1M 權杖的輸出成本（美元）",
-      "cacheRead": "每 1M 權杖的快取讀取成本（美元）",
-      "cacheWrite": "每 1M 權杖的快取寫入成本（美元）"
+      "input": "每 1M 令牌的輸入成本（美元）",
+      "output": "每 1M 令牌的輸出成本（美元）",
+      "cacheRead": "每 1M 令牌的快取讀取成本（美元）",
+      "cacheWrite": "每 1M 令牌的快取寫入成本（美元）"
    },
    "diff": {
      "description": "顯示與上游價格的差異",
@@ -907,25 +907,25 @@
  "resilience": {
    "description": "檢查和管理彈性機制",
    "status": {
-      "provider": "按提供者篩選"
+      "provider": "按提供商篩選"
    },
    "breakers": {
-      "provider": "按提供者篩選"
+      "provider": "按提供商篩選"
    },
    "cooldowns": {
-      "provider": "按提供者篩選",
+      "provider": "按提供商篩選",
      "connectionId": "按連線 ID 篩選"
    },
    "lockouts": {
-      "provider": "按提供者篩選",
+      "provider": "按提供商篩選",
      "model": "按模型篩選"
    },
    "reset": {
      "description": "重置斷路器/冷卻狀態",
-      "provider": "要重置的提供者",
+      "provider": "要重置的提供商",
      "connectionId": "要重置的連線 ID",
      "model": "要重置鎖定狀態的模型",
-      "allCooldowns": "重置提供者的所有冷卻",
+      "allCooldowns": "重置提供商的所有冷卻",
      "yes": "跳過確認"
    },
    "profile": {
@@ -940,13 +940,13 @@
    }
  },
  "nodes": {
-    "description": "管理提供者節點（端點）",
+    "description": "管理提供商節點（端點）",
    "list": {
-      "provider": "按提供者篩選",
+      "provider": "按提供商篩選",
      "enabled": "僅顯示已啟用的節點"
    },
    "add": {
-      "provider": "提供者名稱",
+      "provider": "提供商名稱",
      "baseUrl": "節點的基礎 URL",
      "name": "節點名稱",
      "weight": "負載均衡權重",
@@ -965,7 +965,7 @@
    },
    "validate": {
      "baseUrl": "要驗證的 URL",
-      "provider": "要驗證的提供者"
+      "provider": "要驗證的提供商"
    },
    "test": {
      "description": "向節點發送測試請求"
@@ -993,7 +993,7 @@
      "description": "管理 RTK 上下文最佳化器",
      "config": {
        "description": "顯示或更新 RTK 配置",
-        "tokenBudget": "RTK 權杖預算",
+        "tokenBudget": "RTK 令牌預算",
        "reservePct": "保留百分比"
      },
      "filters": {
@@ -1091,7 +1091,7 @@
  "oneproxy": {
    "description": "管理 OneProxy 上游代理池",
    "stats": {
-      "provider": "按提供者篩選",
+      "provider": "按提供商篩選",
      "period": "時間範圍（預設：24h）"
    },
    "fetch": {
@@ -1101,14 +1101,14 @@
    },
    "rotate": {
      "description": "強制輪換代理",
-      "provider": "要輪換的提供者",
+      "provider": "要輪換的提供商",
      "connectionId": "要輪換的特定連線 ID"
    },
    "config": {
      "description": "顯示或更新 OneProxy 配置",
      "enabled": "啟用代理池（true|false）",
      "poolSize": "池大小",
-      "providerSource": "代理提供者的 URL",
+      "providerSource": "代理提供商的 URL",
      "rotationPolicy": "輪換策略：sticky|per-request|periodic"
    },
    "pool": {
@@ -1163,11 +1163,11 @@
      "fromCloud": "從雲備份初始化"
    },
    "tokens": {
-      "description": "管理同步權杖",
+      "description": "管理同步令牌",
      "create": {
-        "name": "權杖名稱",
-        "scope": "權杖作用域",
-        "ttl": "權杖有效期（例如 30d）"
+        "name": "令牌名稱",
+        "scope": "令牌作用域",
+        "ttl": "令牌有效期（例如 30d）"
      },
      "revoke": {
        "yes": "跳過確認"
@@ -1201,7 +1201,7 @@
    "bash": "列印 bash 補全指令碼",
    "fish": "列印 fish 補全指令碼",
    "install": "為檢測到的 Shell 全域性安裝補全指令碼",
-    "refresh": "重新整理組合/提供者/模型快取"
+    "refresh": "重新整理組合/提供商/模型快取"
  },
  "logs": {
    "description": "流式傳輸或匯出請求日誌",
--- a/bin/cli/runtime/processSupervisor.mjs
+++ b/bin/cli/runtime/processSupervisor.mjs
@@ -1,6 +1,6 @@
 import { spawn } from "node:child_process";
 import { dirname } from "node:path";
-import { writePidFile, cleanupPidFile, killAllSubprocesses, isPidRunning } from "../utils/pid.mjs";
+import { writePidFile, cleanupPidFile, killAllSubprocesses } from "../utils/pid.mjs";
 import {
  RESTART_RESET_MS,
  DEFAULT_MAX_RESTARTS,
@@ -9,7 +9,6 @@ import {
  waitUntilPortFree,
 } from "./supervisorPolicy.mjs";
 import { buildNodeHeapArgs } from "../../../scripts/build/runtime-env.mjs";
-import { stopProcessGracefully } from "../../../src/shared/platform/windowsProcess.ts";

 const CRASH_LOG_LINES = 50;

@@ -73,32 +72,12 @@ export class ServerSupervisor {
    return this.child;
  }

-  handleExit(code, err) {
+  handleExit(code) {
    // Node.js v24+ requires process.exit() to receive a number. Spawn-error events
    // deliver err.code (a string like 'ENOENT') via the 'error' listener; normalise here.
    const exitCode = typeof code === "number" ? code : null;
    cleanupPidFile("server");

-    // #8091: the child's spawn 'error' listener passes `err` through as a second
-    // argument, but it used to be silently dropped — the user only ever saw the
-    // hardcoded "code=-1" with a permanently empty crash log, with no way to
-    // diagnose why the child never started (ENOENT/EACCES/bad path/etc.). Surface
-    // the real reason immediately, both on the console and in the crash-log buffer
-    // so `dumpCrashLog()` shows it too.
-    if (err) {
-      const detail = [
-        err.code && `code=${err.code}`,
-        err.syscall && `syscall=${err.syscall}`,
-        err.path && `path=${err.path}`,
-        err.message,
-      ]
-        .filter(Boolean)
-        .join(" ");
-      const line = `⚠ Spawn error: ${detail || String(err)}`;
-      console.error(line);
-      this.crashLog.push(line);
-    }
-
    // #4425: only exit on an intentional shutdown. A spontaneous code-0 exit (e.g. a
    // systemd MemoryMax cgroup kill, which reports the process exited cleanly) is anomalous
    // and must be restarted, not treated as a graceful stop that leaves the gateway dead.
@@ -156,13 +135,14 @@ export class ServerSupervisor {
  stop() {
    this.isShuttingDown = true;
    if (this.child?.pid) {
-      // #8045: on win32, process.kill(pid, "SIGTERM") unconditionally force-terminates
-      // the target — it is never a real, interceptable signal there. The child already
-      // receives the real CTRL_C_EVENT/CTRL_CLOSE_EVENT independently (it shares the
-      // console) and runs its own async graceful shutdown (WAL checkpoint). Sending
-      // SIGTERM immediately on win32 races and beats that cleanup. Fire-and-forget:
-      // stop() itself stays sync so callers keep their existing control flow.
-      void stopProcessGracefully({ pid: this.child.pid, timeoutMs: 5000, isPidRunning });
+      try {
+        process.kill(this.child.pid, "SIGTERM");
+      } catch {}
+      setTimeout(() => {
+        try {
+          process.kill(this.child.pid, "SIGKILL");
+        } catch {}
+      }, 5000);
    }
    killAllSubprocesses();
  }
--- a/bin/cli/sqlite.mjs
+++ b/bin/cli/sqlite.mjs
@@ -5,32 +5,13 @@ import { ensureSettingsSchema, hashManagementPassword, updateSettings } from "./

 async function loadSqlite() {
  if (process.versions.bun) {
-    return { Database: (await import("bun:sqlite")).Database };
+    return (await import("bun:sqlite")).Database;
  }
  try {
-    return { Database: (await import("better-sqlite3")).default };
-  } catch (error) {
-    return { error };
-  }
-}
-
-// #7586: unlike the real server (src/lib/db/adapters/driverFactory.ts::tryOpenSync),
-// this CLI helper historically had NO fallback beyond better-sqlite3 — so on any
-// machine where better-sqlite3's native binary is unavailable (Windows without a
-// prebuilt addon, etc.), every `omniroute doctor` DB check reported a false FAIL
-// even when the actual server was healthy via its own (correct) driver cascade.
-// Reuse that same cascade here instead of re-deriving it.
-async function openWithSyncDriverFallback(dbPath, options, importError) {
-  try {
-    const { tryOpenSync } = await import("../../src/lib/db/adapters/driverFactory.ts");
-    const adapter = tryOpenSync(dbPath, options);
-    if (adapter) {
-      return adapter;
-    }
+    return (await import("better-sqlite3")).default;
  } catch {
-    // fall through to the original better-sqlite3 error below
+    throw new Error("better-sqlite3 is not installed. Run npm install before using setup.");
  }
-  throw createSqliteNativeError(importError);
 }

 function openBunSqlite(Database, dbPath, options) {
@@ -110,25 +91,19 @@ export function createSqliteNativeError(error) {
 }

 async function openSqliteDatabase(dbPath, options = {}) {
-  const loaded = await loadSqlite();
+  const Database = await loadSqlite();
  if (process.versions.bun) {
    if (options.fileMustExist && !fs.existsSync(dbPath)) {
      throw new Error(`SQLite file does not exist: ${dbPath}`);
    }
-    const bunOptions = options.readonly
+    options = options.readonly
      ? { readonly: true }
      : { readwrite: true, create: options.fileMustExist !== true };
-    try {
-      return openBunSqlite(loaded.Database, dbPath, bunOptions);
-    } catch (error) {
-      throw createSqliteNativeError(error);
-    }
-  }
-  if (loaded.error) {
-    return openWithSyncDriverFallback(dbPath, options, loaded.error);
  }
  try {
-    return new loaded.Database(dbPath, options);
+    return process.versions.bun
+      ? openBunSqlite(Database, dbPath, options)
+      : new Database(dbPath, options);
  } catch (error) {
    throw createSqliteNativeError(error);
  }
--- a/changelog.d/features/7013-grok-build-browser-login.md
+++ b/changelog.d/features/7013-grok-build-browser-login.md
@@ -1 +0,0 @@
- **feat(oauth):** Add a one-click browser (PKCE) login for Grok Build (`grok-cli`) ALONGSIDE the existing device-code flow — reusing the same `auth.x.ai` authorize/token endpoints and public client id as the sibling `xai-oauth` provider on its own loopback port — while keeping the pre-existing device-code method and the paste-token/`auth.json` import flow both available; the connect modal lets the user pick "Device Code", "Browser Login", or "JWT Token" ([#7013](https://github.com/diegosouzapw/OmniRoute/issues/7013))
--- a/changelog.d/features/7872-m365-tone-model-variants.md
+++ b/changelog.d/features/7872-m365-tone-model-variants.md
@@ -1 +0,0 @@
- feat(providers): copilot-m365-web tone-selected model variants (#7872)
--- a/changelog.d/features/7879-numeric-helpers-foundation.md
+++ b/changelog.d/features/7879-numeric-helpers-foundation.md
@@ -1 +0,0 @@
- **feat(shared):** Add canonical numeric coercion helpers (`toNumber`, `toNumberOrNull`, `toNumberArray`) in `src/shared/utils/numeric.ts` with table-driven tests and a lint rule barring new local `toNumber` definitions, then migrate the report/analytics tier (usage analytics route, provider metrics route, usage stats, usage history helpers, call-log formatting, cost-analysis A2A skill) off their local duplicates ([#7879](https://github.com/diegosouzapw/OmniRoute/issues/7879))
--- a/changelog.d/features/7895-mcp-connect-scope-binding.md
+++ b/changelog.d/features/7895-mcp-connect-scope-binding.md
@@ -1 +0,0 @@
- feat(mcp): add a narrow `mcp:connect` API-key scope for the `/api/mcp/` LOCAL_ONLY carve-out (separate from `manage`/`admin`) and populate `authInfo.scopes` from the caller's real per-key scopes over HTTP/SSE so `scopeEnforcement.ts` prefers per-key scopes over the `OMNIROUTE_MCP_SCOPES` env fallback when enforcement is enabled (#7895).
--- a/changelog.d/features/7937-provider-account-search-pagination.md
+++ b/changelog.d/features/7937-provider-account-search-pagination.md
@@ -1 +0,0 @@
- feat(dashboard): provider tab account search (id/tag/name/email substring, cross-page) + mirrored top pagination bar + pagination for the tagged/grouped connections view (#7937)
--- a/changelog.d/features/8019-grok-web-cloudflare-classification.md
+++ b/changelog.d/features/8019-grok-web-cloudflare-classification.md
@@ -1 +0,0 @@
- feat(sse): classify grok-web Cloudflare anti-bot blocks + gated browser-backed cf_clearance path (#8019)
--- a/changelog.d/features/8033-ccr-protocol-instruction.md
+++ b/changelog.d/features/8033-ccr-protocol-instruction.md
@@ -1 +0,0 @@
- Teach the model the CCR retrieve protocol (marker → `omniroute_ccr_retrieve`, verbatim 24-char hash, `dedup:ref` look-back) on the first marker, gated on MCP-tool capability (#8033)
--- a/changelog.d/features/8034-compression-exclusions.md
+++ b/changelog.d/features/8034-compression-exclusions.md
@@ -1 +0,0 @@
- Add a per-model/endpoint compression exclusion filter: name model ids or `provider/model` patterns (`*` wildcard) that must never be compressed, checked before any engine runs so the request passes through byte-identical; configurable from a new Dashboard → Compression → Exclusions tab (#8034)
--- a/changelog.d/features/8038-zhcn-terminology-visual-qa.md
+++ b/changelog.d/features/8038-zhcn-terminology-visual-qa.md
@@ -1 +0,0 @@
- **feat(i18n):** zh-CN terminology glossary + consistency gate + 提供商→提供者 normalization — one-shot pass across `src/i18n/messages/zh-CN.json` (679 substitutions) and `bin/cli/locales/zh-CN.json` (54) mirroring #8024's zh-TW pass, a new versioned glossary (`scripts/i18n/glossary/zh-CN.json`) and protected-terms list (`scripts/i18n/glossary/protected-terms.json`), a pure-function consistency check (`scripts/i18n/check-glossary-consistency.mjs`, `npm run i18n:check-glossary`) wired into CI as `i18n-glossary-zhcn`, and zh-CN added to the visual-QA harness default locales (#8038).
--- a/changelog.d/features/8051-codex-quota-latent-windows.md
+++ b/changelog.d/features/8051-codex-quota-latent-windows.md
@@ -1 +0,0 @@
- **feat(dashboard):** The Codex quota card no longer shows latent, never-used per-feature rate-limit ceilings (e.g. `GPT-5.3-Codex-Spark`) as permanent 100% rows with a meaningless always-full reset — they now appear only once the feature is actually used. Per-feature window labels track the payload's `limit_name`, and each window is labeled by its real `limit_window_seconds` (so a 7-day `primary_window` shows "Weekly" instead of "Session"). ([#8051](https://github.com/diegosouzapw/OmniRoute/issues/8051))
--- a/changelog.d/features/8099-fishaudio-tts-provider.md
+++ b/changelog.d/features/8099-fishaudio-tts-provider.md
@@ -1 +0,0 @@
- feat(providers): native Fish Audio TTS provider on /v1/audio/speech (#8099)
--- a/changelog.d/features/8122-codex-reference-image-edits.md
+++ b/changelog.d/features/8122-codex-reference-image-edits.md
@@ -1 +0,0 @@
- **feat(codex):** add bounded multi-reference PNG/JPEG/WebP image editing (up to 8 references and 20 MiB decoded in aggregate) through the OpenAI-compatible `/v1/images/edits` route by reusing Codex Responses hosted-image tooling, OAuth, proxies, sanitized logs/errors, and OpenAI Images response formatting ([#8122](https://github.com/diegosouzapw/OmniRoute/pull/8122)) — thanks @xiaoyaner0201
--- a/changelog.d/features/8142-empty-catch-convention.md
+++ b/changelog.d/features/8142-empty-catch-convention.md
@@ -1 +0,0 @@
- refactor(sse): classify SSE critical-path empty catches + add CONTRIBUTING convention (#8142)
--- a/changelog.d/features/8249-call-logs-session-tag.md
+++ b/changelog.d/features/8249-call-logs-session-tag.md
@@ -1 +0,0 @@
- feat(db): persist caller session tag into call_logs for per-session cost attribution (#8249)
--- a/changelog.d/features/8297-web-fetch-quota-aware-fallback.md
+++ b/changelog.d/features/8297-web-fetch-quota-aware-fallback.md
@@ -1 +0,0 @@
- feat(api): quota-aware fallback routing for web-fetch providers (#8297)
--- a/changelog.d/features/8347-cliproxy-reasoning-levels.md
+++ b/changelog.d/features/8347-cliproxy-reasoning-levels.md
@@ -1 +0,0 @@
- feat(providers): map upstream reasoning-level metadata in openai-compatible discovery (#8347)
--- a/changelog.d/features/8471-xai-oauth-weekly-quota.md
+++ b/changelog.d/features/8471-xai-oauth-weekly-quota.md
@@ -1 +0,0 @@
- **feat(providers):** weekly quota for xAI OAuth (Grok) (`xai-oauth` / `xao`) via shared cli-chat-proxy billing (`creditUsagePercent`), with fail-open self-tracked fallback ([#8471](https://github.com/diegosouzapw/OmniRoute/pull/8471)) — thanks @allanvb
--- a/changelog.d/features/8513-backup-schedule-execution.md
+++ b/changelog.d/features/8513-backup-schedule-execution.md
@@ -1 +0,0 @@
- feat(jobs): `backup auto enable` schedule is now executed server-side — the cron expression, cloud/encrypt/retention settings written by the CLI are consumed by a new `startBackupScheduleJob()` tick registered alongside `startBudgetResetJob()` in `instrumentation-node.ts`; includes a zero-dependency 5-field cron matcher
--- a/changelog.d/features/adobe-firefly-reference-images.md
+++ b/changelog.d/features/adobe-firefly-reference-images.md
@@ -1 +0,0 @@
- **feat(adobe-firefly):** reference-image attach for generate + OpenAI `/v1/images/edits` support (follow-up to #8006). Uploads sources to Firefly storage (`POST /v2/storage/image`), then submits `referenceBlobs` on 3P generate-async (nano multi-ref `usage:general`; gpt-image `usage:subject`). Wire matches live `firefly.adobe.com` captures. Also routes built-in edits to the same path (up to 4 refs).
--- a/changelog.d/features/conductor-agent-card.md
+++ b/changelog.d/features/conductor-agent-card.md
@@ -0,0 +1 @@
+- feat(a2a): the Agent Card (`/.well-known/agent.json`) now announces skills derived from the OmniConductor fleet (`GET /v1/runners` OASF capabilities — one skill per online CLI profile + declared fleet skills), cached ~60s and fail-open when the hub is unset/offline
--- a/changelog.d/features/conductor-bridge.md
+++ b/changelog.d/features/conductor-bridge.md
@@ -0,0 +1 @@
+- feat(a2a): Conductor bridge — long-lived SSE consumer that mirrors OmniConductor hub tasks into the A2A TaskManager (explicit `canceled→cancelled` mapping with tests, persisted `last_event_id` cursor in the `key_value` table, exponential-backoff reconnection; opt-in via `CONDUCTOR_HUB_URL`/`CONDUCTOR_HUB_TOKEN`)
--- a/changelog.d/features/conductor-panel.md
+++ b/changelog.d/features/conductor-panel.md
@@ -0,0 +1 @@
+- feat(dashboard): "Conductor" panel — OmniConductor fleet (runners + task queue) live via server-side proxy routes (`/api/conductor/*`, management auth, hub token never reaches the browser), task detail with manifest/council and cancel-with-confirmation; sidebar entry under Tools
--- a/changelog.d/features/local-corpus-context.md
+++ b/changelog.d/features/local-corpus-context.md
@@ -1 +0,0 @@
- **feat(mcp):** add a read-only Local Corpus context source with bounded incremental text indexing, path-containment controls, an authenticated settings API, and three scoped MCP tools.
--- a/changelog.d/features/ru-readme-full-translation.md
+++ b/changelog.d/features/ru-readme-full-translation.md
@@ -1 +0,0 @@
- docs(i18n): rewrite Russian README as a full native manual (structure aligned with modern EN/zh-CN, fixed relative asset links).
--- a/changelog.d/fixes/6271-baidu-qianfan-website-urls.md
+++ b/changelog.d/fixes/6271-baidu-qianfan-website-urls.md
@@ -1 +0,0 @@
- **fix(providers):** refresh Baidu ERNIE + Qianfan provider website URLs to current developer landing pages ([#6271](https://github.com/diegosouzapw/OmniRoute/issues/6271)) — thanks @TrackCrewGalore
--- a/changelog.d/fixes/6914-antigravity-server-side-tool-invocations.md
+++ b/changelog.d/fixes/6914-antigravity-server-side-tool-invocations.md
@@ -0,0 +1 @@
+- fix(sse): set includeServerSideToolInvocations on Antigravity tool cloak decoys (#6914)
--- a/changelog.d/fixes/7447-kimi-cn-key-format.md
+++ b/changelog.d/fixes/7447-kimi-cn-key-format.md
@@ -1 +0,0 @@
- fix(providers): expose a base-URL override for Kimi/Moonshot so CN-region API keys (issued on platform.kimi.com / moonshot.cn) can be pointed at api.moonshot.cn instead of being rejected by the international host (#7447)
--- a/changelog.d/fixes/7494-sqljs-close-poison.md
+++ b/changelog.d/fixes/7494-sqljs-close-poison.md
@@ -1 +0,0 @@
- fix(db): stop closing the single sql.js singleton during getDbInstance()'s probe/reopen sequence, which poisoned every boot with "Database closed" once both sync SQLite drivers were unavailable (#7494)
--- a/changelog.d/fixes/7503-empty-choices-stream-readiness.md
+++ b/changelog.d/fixes/7503-empty-choices-stream-readiness.md
@@ -1 +0,0 @@
- fix(sse): stop stream readiness from treating a choices-less mid-stream error frame as a successful stream, so combo can fail over instead of returning zero `choices` (#7503)
--- a/changelog.d/fixes/7586-windows-sqlite-launch.md
+++ b/changelog.d/fixes/7586-windows-sqlite-launch.md
@@ -1 +0,0 @@
- fix(cli): fall back to the node:sqlite driver cascade in `bin/cli/sqlite.mjs` so `omniroute doctor` no longer reports a false "FAIL Database"/"FAIL Storage/encryption" on machines without a working better-sqlite3 native binary (#7586)
--- a/changelog.d/fixes/7587-vscode-models-missing-openai.md
+++ b/changelog.d/fixes/7587-vscode-models-missing-openai.md
@@ -1 +0,0 @@
- fix(api): expose Responses-API-format (OpenAI/Codex) chat models on every VS Code Ollama-compatible listing route, not just `/models` (#7587)
--- a/changelog.d/fixes/7610-grok-cli-auth-json-paste.md
+++ b/changelog.d/fixes/7610-grok-cli-auth-json-paste.md
@@ -1 +0,0 @@
- **grok-cli:** OAuth paste-import now requires the full `~/.grok/auth.json` (with `refresh_token`) instead of a bare JWT `key`, preventing connections that can never auto-refresh (#7610).
--- a/changelog.d/fixes/7611-grok-cli-function-call-output-sanitize.md
+++ b/changelog.d/fixes/7611-grok-cli-function-call-output-sanitize.md
@@ -1 +0,0 @@
- **grok-cli:** sanitize Responses `function_call_output.output` values before dispatch so incomplete `\u` escapes / malformed tool results no longer cause intermittent 400 body-parse failures on cli-chat-proxy (#7611).
--- a/changelog.d/fixes/7847-bound-client-raw-request.md
+++ b/changelog.d/fixes/7847-bound-client-raw-request.md
@@ -1 +0,0 @@
- fix(backend): stop `buildClientRawRequest` deep-cloning the whole request body on every chat request (#7847) — every consumer of `clientRawRequest.body` is observability and keeps at most a bounded copy, so the unbounded clone retained ~41x more than anything used it (3.19 MiB vs 0.08 MiB on a 3.05 MiB / 729-message agent request). Also makes `cloneBoundedForLog` idempotent: arrays, objects and strings all exceeded their own bounds once the truncation marker was added, so re-bounding an already bounded payload silently dropped a further item and misreported the original length
--- a/changelog.d/fixes/7847-combo-attempt-body-cow.md
+++ b/changelog.d/fixes/7847-combo-attempt-body-cow.md
@@ -1 +0,0 @@
- fix(sse): copy the combo attempt body shallowly instead of deep-cloning it per target (#7847) — the deep clone cost 9.53 MiB at 3 targets and scaled linearly with the target count (31.78 MiB at 10) on a 3.05 MiB agent request, while the isolation it provided only ever needed to contain top-level scalar writes. Also fixes a real cross-target leak in round-robin, which copied the body only when the reasoning buffer changed `max_tokens` and otherwise shared the caller's object, so a Background Task Redirection on one target rewrote `body.model` for the next
--- a/changelog.d/fixes/7847-structural-json-size.md
+++ b/changelog.d/fixes/7847-structural-json-size.md
@@ -1 +0,0 @@
- fix(sse): estimate the combo fallback-compression trigger from the request object instead of `JSON.stringify(...)` (#7847) — the string path charged an inline base64 image as if every character were prose (~50k tokens instead of ~1.2k on a 200 KB image), falsely tripping compression on requests nowhere near the context window; the same over-count #8368/#8401 fixed elsewhere. Adds `jsonLength()`, an exact serialized-length walker (property-tested against `JSON.stringify`), and uses it for the readiness-timeout and token estimates so a multi-megabyte body is no longer materialized as a string just to be measured
--- a/changelog.d/fixes/7907-chatcore-499-string-abort.md
+++ b/changelog.d/fixes/7907-chatcore-499-string-abort.md
@@ -1 +0,0 @@
- **Chat Core**: client aborts that reject the upstream fetch with a raw string reason (e.g. `request_signal_aborted`, `Client disconnected`) are now reported as `499 Request aborted` in the response, request logs, and usage records instead of `FAILED 502 / Bad Gateway`. Follow-up to #7908 for #7907.
--- a/changelog.d/fixes/7993-noauth-proxy-routing.md
+++ b/changelog.d/fixes/7993-noauth-proxy-routing.md
@@ -1 +0,0 @@
- fix(providers): route noauth opencode-zen connections through their assigned proxy
--- a/changelog.d/fixes/8000-duckduckgo-catalog.md
+++ b/changelog.d/fixes/8000-duckduckgo-catalog.md
@@ -1 +0,0 @@
- fix(providers): refresh duckduckgo-web free model catalog to Duck.ai's current wire ids, fixing 400 ERR_BAD_REQUEST (#8000)
--- a/changelog.d/fixes/8014-zai-web-auth.md
+++ b/changelog.d/fixes/8014-zai-web-auth.md
@@ -1 +0,0 @@
- fix(providers): repoint the zai-web executor at chat.z.ai's current v2 chat-completions endpoint, fixing model-independent 404s (#8014)
--- a/changelog.d/fixes/8032-path-shaped-vision.md
+++ b/changelog.d/fixes/8032-path-shaped-vision.md
@@ -1 +0,0 @@
- **fix(providers):** path-shaped multimodal model ids (e.g. `cp/cline-pass/kimi-k3`) resolve native vision via leaf/registry metadata instead of triggering Vision Bridge ([#8032](https://github.com/diegosouzapw/OmniRoute/issues/8032)) — thanks @Prudhvivuda
--- a/changelog.d/fixes/8036-codex-cli-detect.md
+++ b/changelog.d/fixes/8036-codex-cli-detect.md
@@ -1 +0,0 @@
- fix(cli): merge Node's own bin dir into the CLI healthcheck spawn PATH so npm-shebang tools like codex resolve under a minimal launcher PATH (#8036)
--- a/changelog.d/fixes/8041-forwarded-response-header-budget.md
+++ b/changelog.d/fixes/8041-forwarded-response-header-budget.md
@@ -1 +0,0 @@
- **fix(sse):** Bound forwarded upstream response headers so large provider metadata cannot turn successful streaming requests into reverse-proxy errors ([#8041](https://github.com/diegosouzapw/OmniRoute/pull/8041)) — thanks @insoln
--- a/changelog.d/fixes/8045-windows-wal-checkpoint.md
+++ b/changelog.d/fixes/8045-windows-wal-checkpoint.md
@@ -1 +0,0 @@
- fix(db): register SIGHUP handler and stop force-killing the server on win32 stop paths so storage.sqlite's WAL gets checkpointed on shutdown (#8045)
--- a/changelog.d/fixes/8046-codex-oauth-lan-ip.md
+++ b/changelog.d/fixes/8046-codex-oauth-lan-ip.md
@@ -1 +0,0 @@
- fix(oauth): warn instead of silently opening an unreachable localhost:1455 redirect for Codex/xAI/Grok CLI OAuth when the dashboard is reached from a LAN IP (#8046)
--- a/changelog.d/fixes/8052-codex-ws-compression.md
+++ b/changelog.d/fixes/8052-codex-ws-compression.md
@@ -1,2 +0,0 @@
- **fix(sse):** run the prompt-compression pipeline per turn in the Codex Responses WebSocket bridge instead of skipping it entirely — a reused WebSocket connection now re-runs `prepare()` (auth/policy/memory/reasoning-routing/compression) for every logical `response.create` turn, not just the first (#8052)
-
--- a/changelog.d/fixes/8059-oauth-refresh-connection-dedup.md
+++ b/changelog.d/fixes/8059-oauth-refresh-connection-dedup.md
@@ -1 +0,0 @@
- **fix(oauth):** Refreshing the token on an email-less OAuth connection (e.g. GitHub Copilot, whose identity lives under `providerSpecificData`) no longer creates a duplicate connection. `persistOAuthConnection` gated its whole dedup behind `if (tokenData.email)`, so the explicit `connectionId` passed on refresh was discarded and a new connection was created every time; the connectionId is now honored regardless of email, and email dedup only applies when a non-empty email is present. ([#8059](https://github.com/diegosouzapw/OmniRoute/issues/8059))
--- a/changelog.d/fixes/8065-quota-cache-globalthis.md
+++ b/changelog.d/fixes/8065-quota-cache-globalthis.md
@@ -1 +0,0 @@
- fix(routing): anchor quota routing cache on globalThis so cross-chunk reads/writes stay consistent (#8065)
--- a/changelog.d/fixes/8082-poe-baseurl.md
+++ b/changelog.d/fixes/8082-poe-baseurl.md
@@ -1 +0,0 @@
- **fix(providers):** add the missing `poe` REGISTRY entry so built-in Poe model discovery resolves a base URL instead of failing with "No base URL configured for provider" ([#8082](https://github.com/diegosouzapw/OmniRoute/issues/8082))
--- a/changelog.d/fixes/8083-responses-input-items-status.md
+++ b/changelog.d/fixes/8083-responses-input-items-status.md
@@ -1 +0,0 @@
- fix(translator): set `status: "completed"` on translated OpenAI Responses `input` items so strict Responses-compatible upstreams stop rejecting them with 400 MissingParameter input.status (#8083)
--- a/changelog.d/fixes/8085-images-anon-fallback.md
+++ b/changelog.d/fixes/8085-images-anon-fallback.md
@@ -1 +0,0 @@
- fix(sse): give keyless Pollinations image requests the same anonymous fingerprint-pool fallback the chat path already uses, instead of a real upstream 401 (#8085)
--- a/changelog.d/fixes/8089-responses-system-image.md
+++ b/changelog.d/fixes/8089-responses-system-image.md
@@ -1 +0,0 @@
- fix(sse): stop Codex/Responses sanitizer from turning system/developer image_url parts into invalid output_text (#8089)
--- a/changelog.d/fixes/8091-supervisor-spawn-err.md
+++ b/changelog.d/fixes/8091-supervisor-spawn-err.md
@@ -1 +0,0 @@
- fix(cli): surface the real spawn error (err.code/path/syscall/message) in the process supervisor instead of silently swallowing it on a child spawn failure (#8091)
--- a/changelog.d/fixes/8098-antigravity-protocol-fidelity.md
+++ b/changelog.d/fixes/8098-antigravity-protocol-fidelity.md
@@ -1 +0,0 @@
- **fix(antigravity):** preserve request/tool fidelity, make credits modes explicit, and separate runtime endpoints from discovery/bootstrap ([#8098](https://github.com/diegosouzapw/OmniRoute/pull/8098)) — thanks @nguyenha935
--- a/changelog.d/fixes/8107-resilience-cooldown-clamp.md
+++ b/changelog.d/fixes/8107-resilience-cooldown-clamp.md
@@ -1 +0,0 @@
- fix(dashboard): clamp provider-cooldown min/max ms to their field bounds before Save so an out-of-range typed value can never reach the resilience settings API (#8107)
--- a/changelog.d/fixes/8134-github-t5-fallback-filter.md
+++ b/changelog.d/fixes/8134-github-t5-fallback-filter.md
@@ -1 +0,0 @@
- fix(providers): filter unsupported family-fallback candidates against the provider catalog (#8134)
--- a/changelog.d/fixes/8136-antigravity-400-lockout.md
+++ b/changelog.d/fixes/8136-antigravity-400-lockout.md
@@ -1 +0,0 @@
- fix(providers): classify HTTP 400 model-unavailable as MODEL_NOT_FOUND so Antigravity Pro fallback locks out the deprecated model
--- a/changelog.d/fixes/8169-lite-word-boundary-truncation.md
+++ b/changelog.d/fixes/8169-lite-word-boundary-truncation.md
@@ -1 +0,0 @@
- fix(backend): word-boundary-safe tool-result truncation in lite compression mode (#8169)
--- a/changelog.d/fixes/8189-classifier-compat-auto-narrow.md
+++ b/changelog.d/fixes/8189-classifier-compat-auto-narrow.md
@@ -1 +0,0 @@
- fix(api): narrow claudeClassifierCompat auto trigger so stop_sequences alone no longer short-circuits (#8189)
--- a/changelog.d/fixes/8200-perplexity-web-401-cooldown.md
+++ b/changelog.d/fixes/8200-perplexity-web-401-cooldown.md
@@ -1 +0,0 @@
- fix(providers): carve cookie-auth providers out of terminal 401 'expired' classification so one 401 cooldowns instead of killing the connection
--- a/changelog.d/fixes/8231-gemini-civic-integrity-default.md
+++ b/changelog.d/fixes/8231-gemini-civic-integrity-default.md
@@ -1 +0,0 @@
- fix(gemini): drop HARM_CATEGORY_CIVIC_INTEGRITY from the default Gemini safety settings (#8231)
--- a/changelog.d/fixes/8233-codex-dashboard-regressions.md
+++ b/changelog.d/fixes/8233-codex-dashboard-regressions.md
@@ -1 +0,0 @@
- **fix(dashboard):** Normalize Codex client URLs, restore the analytics input-bar color, resolve OAuth modal TypeScript regressions, synchronize the documented compression-engine count, and sanitize Muse Spark fetch errors ([#8233](https://github.com/diegosouzapw/OmniRoute/pull/8233)) — thanks @nguyenha935
--- a/changelog.d/fixes/8247-8248-accountfallback-model-unhealthy.md
+++ b/changelog.d/fixes/8247-8248-accountfallback-model-unhealthy.md
@@ -1 +0,0 @@
- fix(providers): classify per-model-quota 403 and DEGRADED 400 as model-unhealthy in checkFallbackError (#8247, #8248)
--- a/changelog.d/fixes/8250-kimi-k3-vision-capability.md
+++ b/changelog.d/fixes/8250-kimi-k3-vision-capability.md
@@ -1 +0,0 @@
- **fix(providers):** reconcile Kimi K3 vision metadata when synced `attachment=false` contradicts image/video `modalities_input`, so `supportsVision`, `attachment`, and exposed modalities agree ([#8250](https://github.com/diegosouzapw/OmniRoute/issues/8250)) — thanks @Prudhvivuda
--- a/changelog.d/fixes/8284-provider-docs-link.md
+++ b/changelog.d/fixes/8284-provider-docs-link.md
@@ -1 +0,0 @@
- **fix(providers):** the Providers page Learn more button now opens the maintained GitHub documentation instead of the retired `docs.omniroute.io` page ([#8284](https://github.com/diegosouzapw/OmniRoute/pull/8284)) - thanks @KaynXu
--- a/changelog.d/fixes/8295-namespace-leaf-collision.md
+++ b/changelog.d/fixes/8295-namespace-leaf-collision.md
@@ -1 +0,0 @@
- fix(api): fold namespace into the flattened Chat tool name so cross-namespace leaves do not collide
--- a/changelog.d/fixes/8298-focused-8177-runtime-fixes.md
+++ b/changelog.d/fixes/8298-focused-8177-runtime-fixes.md
@@ -1 +0,0 @@
- **fix(runtime):** sanitize Muse Spark fetch failures before logging and resolve the sql.js WASM asset without the unexported package metadata subpath ([#8298](https://github.com/diegosouzapw/OmniRoute/pull/8298)) — thanks @backryun
--- a/changelog.d/fixes/8310-combo-responses-payload.md
+++ b/changelog.d/fixes/8310-combo-responses-payload.md
@@ -1 +0,0 @@
- **fix(sse):** Combo middleware preserves OpenAI Responses request bodies and maps combo system overrides to `instructions`, preventing Responses-native fallbacks from receiving an unsupported `messages` parameter. ([#8310](https://github.com/diegosouzapw/OmniRoute/pull/8310)) — thanks @ridho9
--- a/changelog.d/fixes/8326-compatible-id-regex.md
+++ b/changelog.d/fixes/8326-compatible-id-regex.md
@@ -1 +0,0 @@
- fix(api): accept the current compatible-provider connection id scheme in the models test route (#8326)
--- a/changelog.d/fixes/8327-models-owned-by-prefix.md
+++ b/changelog.d/fixes/8327-models-owned-by-prefix.md
@@ -1 +0,0 @@
- fix(api): stop leaking the internal provider UUID in /v1/models and honor the configured prefix (#8327)
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
diegosouzapw	12b957a2df	feat(dashboard): Conductor panel — fleet live view, task detail and cancel over /api/conductor proxy	2026-07-22 20:55:19 -03:00
diegosouzapw	5d3c988715	feat(dashboard): /api/conductor proxy routes (fleet, task detail, cancel) behind management auth	2026-07-22 20:44:03 -03:00
diegosouzapw	af97f7fc31	feat(dashboard): server-side hub proxy for the Conductor panel (whitelisted shapes, fail-open)	2026-07-22 20:41:46 -03:00
diegosouzapw	4d6c855258	feat(a2a): agent card announces Conductor fleet skills	2026-07-22 08:36:51 -03:00
diegosouzapw	7b951761fc	feat(a2a): fleet skills derived from the Conductor hub for the agent card	2026-07-22 08:35:16 -03:00
diegosouzapw	b97318d73b	docs(reference): document CONDUCTOR_HUB_URL/TOKEN in ENVIRONMENT.md (env-doc-sync gate)	2026-07-22 01:06:22 -03:00
diegosouzapw	a75295f359	fix(a2a): conductor bridge parses the hub's real SSE wire format (id/type in frame, data={ts,payload})	2026-07-22 00:25:35 -03:00
diegosouzapw	00e15af622	feat(a2a): start conductor bridge at boot behind CONDUCTOR_HUB_URL	2026-07-22 00:23:28 -03:00
diegosouzapw	5eb10e896d	feat(a2a): conductor bridge connection loop with persisted cursor and backoff	2026-07-22 00:21:10 -03:00
diegosouzapw	33baf62b58	feat(a2a): incremental SSE parser for conductor bridge	2026-07-22 00:21:10 -03:00
diegosouzapw	d42a58141b	feat(a2a): conductor bridge core — event mapping with canceled->cancelled	2026-07-22 00:20:29 -03:00
				`@@ -1 +0,0 @@`
				- feat(oauth): Add a one-click browser (PKCE) login for Grok Build (`grok-cli`) ALONGSIDE the existing device-code flow — reusing the same `auth.x.ai` authorize/token endpoints and public client id as the sibling `xai-oauth` provider on its own loopback port — while keeping the pre-existing device-code method and the paste-token/`auth.json` import flow both available; the connect modal lets the user pick "Device Code", "Browser Login", or "JWT Token" ([#7013](https://github.com/diegosouzapw/OmniRoute/issues/7013))
				`@@ -1 +0,0 @@`
				`- feat(providers): copilot-m365-web tone-selected model variants (#7872)`
				`@@ -1 +0,0 @@`
				- feat(shared): Add canonical numeric coercion helpers (`toNumber`, `toNumberOrNull`, `toNumberArray`) in `src/shared/utils/numeric.ts` with table-driven tests and a lint rule barring new local `toNumber` definitions, then migrate the report/analytics tier (usage analytics route, provider metrics route, usage stats, usage history helpers, call-log formatting, cost-analysis A2A skill) off their local duplicates ([#7879](https://github.com/diegosouzapw/OmniRoute/issues/7879))
				`@@ -1 +0,0 @@`
				- feat(mcp): add a narrow `mcp:connect` API-key scope for the `/api/mcp/` LOCAL_ONLY carve-out (separate from `manage`/`admin`) and populate `authInfo.scopes` from the caller's real per-key scopes over HTTP/SSE so `scopeEnforcement.ts` prefers per-key scopes over the `OMNIROUTE_MCP_SCOPES` env fallback when enforcement is enabled (#7895).
				`@@ -1 +0,0 @@`
				`- feat(dashboard): provider tab account search (id/tag/name/email substring, cross-page) + mirrored top pagination bar + pagination for the tagged/grouped connections view (#7937)`
				`@@ -1 +0,0 @@`
				`- feat(sse): classify grok-web Cloudflare anti-bot blocks + gated browser-backed cf_clearance path (#8019)`
				`@@ -1 +0,0 @@`
				- Teach the model the CCR retrieve protocol (marker → `omniroute_ccr_retrieve`, verbatim 24-char hash, `dedup:ref` look-back) on the first marker, gated on MCP-tool capability (#8033)
				`@@ -1 +0,0 @@`
				- Add a per-model/endpoint compression exclusion filter: name model ids or `provider/model` patterns (`*` wildcard) that must never be compressed, checked before any engine runs so the request passes through byte-identical; configurable from a new Dashboard → Compression → Exclusions tab (#8034)
				`@@ -1 +0,0 @@`
				- feat(i18n): zh-CN terminology glossary + consistency gate + 提供商→提供者 normalization — one-shot pass across `src/i18n/messages/zh-CN.json` (679 substitutions) and `bin/cli/locales/zh-CN.json` (54) mirroring #8024's zh-TW pass, a new versioned glossary (`scripts/i18n/glossary/zh-CN.json`) and protected-terms list (`scripts/i18n/glossary/protected-terms.json`), a pure-function consistency check (`scripts/i18n/check-glossary-consistency.mjs`, `npm run i18n:check-glossary`) wired into CI as `i18n-glossary-zhcn`, and zh-CN added to the visual-QA harness default locales (#8038).