mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-06 07:12:12 +03:00
feat/plugin-browser-pool
470 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Diego Rodrigues de Sa e Souza
|
85b9c1754e |
feat: Xiaomi MiMo Token Plan provider + per-connection API protocol selector (#8861)
* feat(sse): add alternateFormats registry field and resolver
* feat(sse): honor per-connection targetFormat in getTargetFormat
Registry-driven format lookup now resolves an alternate protocol
declared for the provider when the connection's providerSpecificData
carries a matching targetFormat, falling back to the entry's default
format otherwise.
* feat(sse): resolve base URL from selected alternate format
resolveBaseUrl now falls back to the connection's selected alternate
protocol (providerSpecificData.targetFormat) before the provider's
default base URL, while a manual providerSpecificData.baseUrl override
still wins over both.
* feat(sse): apply alternate format auth header and extra headers
DefaultExecutor's registry authHeader lookup and BaseExecutor's shared
header preamble now both honor a connection's selected alternate
protocol: the alternate's authHeader wins over the registry default,
and its extra headers (e.g. Anthropic-Version) are merged in.
* refactor(sse): extract resolveAlternate helper into BaseExecutor
Centralizes the getRegistryEntry() + resolveAlternateFormat() pair
that resolveBaseUrl, buildHeadersPreamble, and DefaultExecutor's
authHeader lookup each duplicated, so a future call-site can't diverge
from the shared precedence. Also translates the PT-BR comments added
in the previous three commits to match the surrounding English. Pure
refactor — no behavior change.
* feat(sse): declare Anthropic-compatible variant for xiaomi-mimo
The provider publishes the same catalog over /anthropic/v1/messages on the same
host. Selecting it also required bypassing the per-provider URL normalizers in
DefaultExecutor.buildUrl(): normalizeXiaomiMimoChatUrl() appends /chat/completions
unconditionally, which mangled the alternate's already-complete endpoint into
.../anthropic/v1/messages/chat/completions.
* feat(sse): add xiaomi-mimo-token-plan provider with monthly quota
Token Plan is a separate product: tp- keys authenticate only on the regional
token-plan-sgp host and return 401 on api.xiaomimimo.com, where the existing
xiaomi-mimo provider points. Same pattern as qwen-cloud-token-plan.
Registers the monthly token allowance (no balance API upstream) and declares
the Anthropic-compatible variant on the token-plan host.
* feat(dashboard): add API protocol selector to connection modal
Providers that declare alternateFormats in the registry now expose an opt-in
protocol dropdown on the connection modal. The choice persists to
providerSpecificData.targetFormat as an explicit null when set back to the
default, since the PUT route merges { ...existing, ...incoming } and an omitted
key would keep the previous override.
* fix(i18n,quality): vi parity for the protocol selector + own-growth rebaselines
The three new provider keys landed only in en/pt-BR, so the vi parity test failed
(tests/unit/i18n-vi-completeness.test.ts asserts key parity AND no __MISSING__
markers — running i18n:sync-ui would have satisfied the first and broken the
second). Added translated values instead. Scoped to vi: it and pt-BR are the only
locales with a parity test.
Rebaselines are this PR's own growth: EditConnectionModal.tsx 1283->1316 (the
selector field) and open-sse/executors/base.ts 1540->1562 (alternate-format
resolution at the existing buildUrl/headers chokepoint).
Adds the changelog fragment.
---------
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
|
||
|
hppsc1215
|
85f1d78d11 |
fix(ghe-copilot): route OpenAI-native models via Responses API (#8835)
* fix(ghe-copilot): route OpenAI-native models via Responses API - Add targetFormat: 'openai-responses' to gpt-5.4-mini, gpt-5.3-codex, gpt-5-mini, mai-code-1-flash, and oswe-vscode-prime in ghe-copilot registry. - Register gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna with openai-responses targetFormat. - Update GheCopilotExecutor.buildUrl() to route openai-responses and codex models to <gheUrl>/responses while keeping Claude and Gemini on /chat/completions. - Add unit tests verifying targetFormat parity and buildUrl endpoint routing. * docs(changelog): add fragment for #8835 Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: Alex <sefias_methue@hotmail.de> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Tito Fauzan Putra
|
0809c73430 |
fix(providers): correct Codex GPT-5.6 context window (#8838)
* fix(providers): correct Codex GPT-5.6 context window (#7702) * docs(changelog): add fragment for #8838 Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> * test(providers): align the remaining GPT-5.6 context-window assertions Three suites assert the pinned GPT_5_6_CODEX_CAPABILITIES contract through the VS Code and provider-models routes, and still expected 372000. They only surface in a full run, so the focused loop on this PR stayed green while `npm run test:unit` failed with five `272000 !== 372000`. The two conservative-merge cases in provider-models-route-codex keep testing what they tested: live 999999 still exceeds the pinned value (pinned wins) and live 100000 is still below it (live wins). Only the pinned number and the comments naming it move. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Alan Vb
|
6a59c09460 |
feat(search): add Firecrawl search provider (#8814)
* feat(search): add Firecrawl search provider Introduce the Firecrawl search provider to handle `POST /v1/search` requests via Firecrawl /v2/search API (sources: web|news) * chore(changelog): add changelog on firecrawl search provider support * fix(search): satisfy file-size freeze and APIKEY count --------- Co-authored-by: allanvb <allanvb@users.noreply.github.com> |
||
|
Jonathan Bailey
|
052cab3d46 |
fix(providers): complete OpenCode Go effort alias exposure (#8610)
* fix(providers): complete OpenCode Go effort aliases * chore: number OpenCode Go changelog fragment |
||
|
Austin Liu
|
2247517697 |
fix(cloudflare-ai): sync missing free catalog models (fixes #8725) (#8763)
Adds @cf/qwen/qwen2.5-coder-32b-instruct, @cf/meta/llama-3.3-70b-instruct-fp8-fast, @cf/meta/llama-3.2-3b-instruct, @cf/qwen/qwq-32b, @cf/zai-org/glm-4.7-flash, @cf/moonshotai/kimi-k2.6, and @cf/google/gemma-4-26b-a4b-it to freeModelCatalog.data.ts to match the provider registry. |
||
|
Diego Rodrigues de Sa e Souza
|
7db3ba615b |
fix(sse): stop thrashing the provider prompt cache for caching-aware clients (#8705)
* fix(sse): stop thrashing the provider prompt cache for caching-aware clients - shouldPreserveCacheControl: preserve client cache_control markers for every combo strategy. The deterministic-strategy gate forced marker rewrites whose per-request breakpoint positions are not stable turn-over-turn, thrashing the upstream prompt cache (observed in production as ~200k cache_write tokens per turn on quota-share combos). Preserving is never worse: on a stable target the client's breakpoints advance deterministically; on a target switch both approaches miss equally. - prepareClaudeRequest: translator-path opt-in fallback — when preserve-mode has nothing to preserve (client sent no cache_control anywhere), apply the standard heuristic so requests never ship with zero cache breakpoints. The claude-code-compatible relay path keeps its no-supplement contract. - anthropic-beta: forward the client-negotiated context-1m-2025-08-07 through the allowlist merge so a /model <id>[1m] client keeps its long-context negotiation behind the proxy (never forced when the client did not send it). * fix(sse): surface cache tokens in non-streaming OpenAI usage + finalize pending on quota-share block - translateNonStreamingResponse (claude→openai): fold cache_read into prompt_tokens and expose prompt_tokens_details.cached_tokens / cache_creation_tokens, mirroring the streaming contract (#1426/#2215). Non-streaming OpenAI clients behind a cached Claude upstream previously saw prompt_tokens=<uncached remainder> (e.g. 23 for a ~9k request) with no cache visibility. - chatCore quota-share block: finalize the pending-request slot before returning the policy 429 — the path never reaches upstream and the orphaned pending lingered as a status-0 call-log row until the reaper swept it. Validated live on the staging box (repro: blocked key → orphan row; after: clean). --------- Co-authored-by: diegosouzapw <diegosouzapw24@gmail.com> |
||
|
backryun
|
0f874825cf |
Train 1D: merge via --admin on .113 validation
Squash merge from local merge-train (Hard Rule owner-approved). Tip 029cdf4215cf465f0e1716ac9f84a84692b1e881 validated on 192.168.0.113: 26631/26653 pass. |
||
|
AmirHossein Rezaei
|
553a0732b8 |
fix(sse): label HTTP 499 disconnects as client_disconnected (#8552)
* fix(sse): label HTTP 499 disconnects as client_disconnected Preserve caller-supplied error type/code in buildErrorBody so stream abort classification is not overwritten by the status-code table. * docs(security): document buildErrorBody classification arg --------- Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com> |
||
|
Hernan Javier Ardila Sanchez
|
3be0a5d290 |
fix: combo input-bound, Responses->Chat image strip, qwen-web toolCalling, empty-response exhaustion (#8476)
* test(tail): retire stale i18n __MISSING__ repro + fix qianfan website URL
Base-red slice 6, rebased onto the advanced release/v3.8.49 (
|
||
|
NOXX - Commiter
|
2d48bb6dca |
fix(hyperagent): default 1M context for fable/opus/sonnet (#8496)
* fix(hyperagent): default 1M context for fable/opus/sonnet
HyperAgent Claude-family models (fable, opus, sonnet) were falling through
getTokenLimit to the generic 128k default. Agentic tool-loop prompts with
large catalogs then failed with context_length_exceeded (~137k tokens).
- defaultContextLength + per-model contextLength = 1_000_000 on hyperagent registry
- DEFAULT_LIMITS.hyperagent / ha = 1M
- Resolve hyperagent/ha (and fable/opus wire ids) before models.dev DB fallback
Verified: getTokenLimit('hyperagent','fable-latest') === 1000000; context-manager tests 30/30.
* fix(sse): scope hyperagent 1M context fix to the registry, drop unscoped model-name match
The step-1b branch in resolveTokenLimit() matched fable/opus/sonnet model
name substrings for ANY provider, before the models.dev DB lookup. That
collided with anthropic/claude, kiro, windsurf and bluesminds registries,
which serve the same Claude model ids (e.g. claude-opus-4.7-max,
claude-sonnet-5) with their own accurate per-model contextLength — those
were being clobbered to 1M instead of their real (often 200k) limit.
The registry-level defaultContextLength added on the hyperagent provider
entry already fixes the reported bug (getTokenLimit('hyperagent', ...) ===
1_000_000) on its own, scoped correctly by provider. Remove the redundant,
unscoped substring branch and add regression coverage for every hyperagent
fallback model id plus the cross-provider collision.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
|
||
|
backryun
|
909642879f | feat: add Claude Opus 5 support (#8464) | ||
|
Prudhvi Vuda
|
88180d069a |
feat(providers): add missing opencode-go reasoning effort variants (#8441)
Register OpenCode Go registry effort aliases and EFFORT_TIERS rewrites so clients can select declared reasoning levels through OmniRoute. Closes #8353 |
||
|
Adrian Rogala
|
9a0e764459 |
feat(cli): replace ANTHROPIC_SMALL_FAST_MODEL with Fable default (#8343)
Claude Code retired ANTHROPIC_SMALL_FAST_MODEL; expose ANTHROPIC_DEFAULT_FABLE_MODEL from the claude registry instead. |
||
|
Prudhvi Vuda
|
af60f41e99 |
fix(providers): reconcile Kimi K3 vision when attachment contradicts modalities (#8250) (#8313)
* fix(providers): reconcile Kimi K3 vision when attachment contradicts modalities Synced models.dev rows for kimi-coding*/k3 can ship attachment=false while modalities_input still lists image/video. Prefer the modality signal (and normalize at sync + resolve) so supportsVision, attachment, and exposed modalities agree. Closes #8250 * fix(providers): keep Kimi K3 static fallback text-only (#8250) The Kimi K3 vision reconciliation added supportsVision=true directly to the kimi-coding registry entry for id "k3". That entry is the static/stable fallback catalog used when discovered capabilities are unavailable, and it must stay text-only per #4071 — the vision fix is already applied correctly on the discovered path via MODEL_SPECS["kimi-k3"] (aliases: ["k3"]) and modelCapabilities.ts::resolveVisionCapability. Restores the invariants guarded by tests/unit/kimi-k2.7-code-registration.test.ts ("Kimi Code k3 fallback leaves discovered capabilities unset") and tests/unit/catalog-updates-v3829-kimi-qwen.test.ts ("kmca stable fallback only carries documented static capabilities"). Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Diego Rodrigues de Sa e Souza
|
7202654f81 | fix(providers): classify per-model-quota 403 and DEGRADED 400 as model-unhealthy in checkFallbackError (#8247, #8248) (#8323) | ||
|
Ravi Tharuma
|
1684adcd63 |
fix(providers): adapt Kimi nonstream requests internally (#8302)
Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
backryun
|
869d08ff8b |
Add Alibaba-family media model support (#8266)
* Add Alibaba-family media models * chore(quality): rebaseline imageRegistry+cognitive for #8266 media own-growth --------- Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
backryun
|
2f65339378 |
fix(providers): limit Gemini CLI to legacy OAuth refresh (#8275)
#8232 correctly targeted OAuth auto-refresh for legacy stored Gemini CLI connections, but exceeded that compatibility goal by recreating a complete routable and UI-visible provider with an Antigravity model catalog. Preserve legacy refresh by mapping gemini-cli rows to the existing Gemini OAuth credentials. Remove the public provider registry, OAuth preset, model routing snapshot, and canonical-provider tests while keeping Gemini API and Antigravity unchanged. |
||
|
Álvaro Ángel Molina
|
81ade9e122 |
feat(providers): add Typhoon (Thailand) and Inception Mercury diffusion LLM (#8170)
* feat(providers): add Typhoon and Inception Mercury API-key providers Two OpenAI-compatible API-key providers, each verified against a live endpoint smoke test with a negative control before registration: an unknown route answers 404 while /v1/chat/completions answers 401, which rules out gateways that reply identically to every path. - typhoon (SCB 10X, Thailand): first Thai-first provider in the catalog. /v1/models answers 200 unauthenticated and serves exactly one chat model, typhoon-v2.5-30b-a3b-instruct (128K ctx). The docs also list typhoon-v2.1-12b-instruct, but the live endpoint no longer serves it, so it is deliberately not registered. The typhoon-ocr* and typhoon-asr* entries are OCR and speech models, not chat, and are omitted. - inception (Inception Labs): first diffusion LLM (dLLM) in the catalog. mercury-2 has a 128K context, 50K max output, and supports tools, json_mode and structured outputs. The mercury-coder models advertised on the vendor blog are no longer served by the live endpoint and are therefore not registered. Both expose a working /v1/models catalog, so they are added to NAMED_OPENAI_STYLE_PROVIDERS for discovery and key validation. Free-tier metadata is claimed only where it is documented and durable: Typhoon issues a free API key rate-limited to 5 req/s and 200 req/m, and Inception grants 10M tokens on signup with no card, so both are registered with hasFree: true. Provider count moves from 280 to 282; README/AGENTS/CLAUDE counters were stale at 278 and are resynced against docs/reference/PROVIDER_REFERENCE.md. * fix(8170): union frontier-labs Inception+Writer, regen ref+golden * fix(8170): close inception object + regen ref/golden --------- Co-authored-by: Álvaro Ángel Molina <alvaretto@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Álvaro Ángel Molina
|
7ca821aeee |
feat(providers): add Sarvam AI, Writer Palmyra and PLaMo API-key providers (#8161)
* feat(providers): add Sarvam AI, Writer Palmyra and PLaMo API-key providers Three OpenAI-compatible API-key providers, each verified against a live endpoint smoke test before registration: - sarvam (India): /v1/models answers 200 unauthenticated and lists sarvam-105b (128K ctx) and sarvam-30b (64K ctx). The older sarvam-m is discontinued upstream and is deliberately not registered. - writer (Palmyra): api.writer.com exposes the OpenAI alias /v1/chat/completions alongside its native /v1/chat — confirmed with a negative control, since an unknown route answers 404 'endpoint not available via API gateway' while /v1/chat/completions answers 401. Registers palmyra-x5 (1M ctx) and palmyra-x4 (128K ctx); the medical/financial/creative/vision variants are deprecated upstream and are omitted. - plamo (Preferred Networks, Japan): only plamo-3.0-prime (262K ctx) is registered. plamo-3.0-prime-beta is discontinued on 2026-07-31 and plamo-2.2-prime on 2026-09-30, so neither is worth wiring up. Free-tier metadata is claimed only where it is documented and durable: Sarvam ships a permanent signup credit, while PLaMo's 10M-token grant is a campaign that expires on 2026-07-31 and Writer documents no free tier, so both are registered with hasFree: false. * regen golden+ref --------- Co-authored-by: Álvaro Ángel Molina <alvaretto@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Álvaro Ángel Molina
|
6ba2260178 |
feat(providers): add CLOVA Studio, InternLM and Ant Ling API-key providers (#8077)
* feat(providers): add CLOVA Studio, InternLM and Ant Ling API-key providers Adds three OpenAI-compatible frontier-lab providers, closing regional gaps in the catalog (Korea had none; the Shanghai AI Lab and Ant Group families were both missing). - clova-studio: Naver HyperCLOVA X (HCX-007 reasoning, HCX-005 multimodal) on the current clovastudio.stream.ntruss.com host. The legacy clovastudio.apigw.ntruss.com endpoint is being deprecated and is not used. - internlm: Shanghai AI Lab Intern-S1 family (intern-s1-pro is a 1T MoE). Ships a free monthly quota, so it is flagged hasFree. - ant-ling: Ant Group / inclusionAI Ling-2.6-1T and Ring-2.6-1T. All three endpoints were smoke-tested: each returns HTTP 401 on <baseUrl>/models (endpoint live, awaiting auth) and resolves against public DNS. All three are registered for live model discovery, so their catalogs refresh from upstream. Known limitation: the ant-ling model ids are best-effort from public docs and are NOT verified against a live /v1/models response, which requires an API key. This is recorded in the registry comment and in the provider authHint so it is visible to operators rather than silently assumed. Its baseUrl is likewise not published in the public docs and was found by smoke test. Two AI SUTRA was evaluated for this batch and deliberately excluded: its documented endpoint api.two.ai does not resolve in public DNS (ENOTFOUND against 1.1.1.1 and 8.8.8.8, with www.two.ai resolving as control). The translate-path golden snapshot is regenerated; the change is additive only (209 -> 212 keys, exactly the three new providers, none removed or altered). * feat(providers): verify ant-ling against official docs, add Ling-2.6-flash and free tier The ant-ling entry was added with model ids marked best-effort because they could not be checked without an API key. Ant Ling's own documentation turns out to publish enough to verify them, so the uncertainty is now resolved: - The quickstart sample uses base_url "https://api.ant-ling.com/v1" with model "Ling-2.6-1T", confirming both the endpoint and the exact casing. - The pricing page bills exactly three models over the API, so Ling-2.6-flash was missing from the catalog and is added. - Each account gets 500,000 free tokens per day (resets 02:00 UTC+8, no rollover), so the provider is flagged hasFree with a freeNote. The Ming family (Ming-Flash-Omni, Ming-Light) is deliberately left out: it is documented as open-source / Ling Studio only and does not appear on the pricing page, so it is not served over this chat-completions API. That reasoning is recorded in the registry so it is not re-litigated later. The authHint no longer claims the ids are unverified, and now points at the API console (https://chat.ant-ling.com/open) where keys are actually created. Same correction applied to the en, pt-BR and vi message catalogs. * docs: sync provider counts to 283 and regenerate the provider reference --------- Co-authored-by: Álvaro Ángel Molina <alvaretto@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Sean Ford
|
71887ae529 |
fix: restore OAuth auto-refresh for gemini-cli connections (#8232)
* fix: restore OAuth auto-refresh for gemini-cli connections
gemini-cli OAuth connections had no PROVIDERS registry entry at all, so
the token-refresh health check permanently skipped them once the access
token expired, forcing a full re-authentication instead of using the
still-valid refresh token.
Two layered gaps, both required:
1. supportsTokenRefresh()'s explicit allow-set had "gemini" but not
"gemini-cli" (the id actually stored on these connections), and its
PROVIDERS[e].tokenUrl fallback also failed since...
2. ...open-sse/config/providers registry had zero entry for "gemini-cli"
at all: no clientId/clientSecret/tokenUrl/refreshUrl, so even the
generic refresh path had nothing to refresh with.
Adds a "gemini-cli" registry entry mirroring antigravity's Google
Cloud Code OAuth shape, reusing the same well-known public Gemini CLI
client credentials already embedded (and already used, unchanged, by
the Gemini Studio API-key provider's own oauth block) via
resolvePublicCred("gemini_id"/"gemini_alt"). Adds "gemini-cli" to the
explicit refresh allow-set, the Google-refresh dispatch case, and the
15-minute non-rotating-token proactive lead alongside antigravity/agy.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* fix: register gemini-cli in canonical provider list (provider-consistency gate)
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* fix(gemini-cli): use ANTIGRAVITY_RUNTIME_BASE_URLS (renamed by #8013 antigravity split)
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: seanford <seanford@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
|
||
|
backryun
|
18f1f667bf | fix(claude-web): align session transport and fallback (#8230) | ||
|
backryun
|
686375ba72 | fix(devin-cli): refresh shared model catalog (#8227) | ||
|
Markus Hartung
|
cc17b304ab |
fix(sse): Gemini TPM/RPD quota classification + combo cooldown-wait resilience (#8213)
* fix(sse): Gemini TPM classification, combo-cooldown-wait for auto/quota-share, and target-timeout floor
Gemini TPM/RPM 429s were misclassified as QUOTA_EXHAUSTED because
sanitizeErrorMessage() truncates to the first line, hiding Google's
metric name and retry hint on lines 2-3. Added a rawMessage field
(internal-only, never reaches the client) and classifyGeminiQuotaMetricFromText()
to classify from the untruncated text, reordered ahead of the generic
credits/daily-quota checks.
Widened comboCooldownWaitEnabled (wait out a short transient cooldown
instead of crystallizing a 429/503) from quota-share-only to also cover
auto-strategy combos, and raised the wait ceiling to 65s/130s-budget/90s-cap
to match Gemini's ~60s TPM/RPM windows.
The per-target timeout (DEFAULT_COMBO_TARGET_TIMEOUT_MS, 120s) was shorter
than the new 130s cooldown-wait budget, so a target could get cut off
mid-wait with a synthetic 524 instead of completing the retry. Added
resolveComboTargetTimeoutMsForCombo()/isComboCooldownWaitEligible() in
comboConfig.ts to raise the per-target floor to budgetMs+buffer only for
wait-eligible strategies (auto/quota-share), verified live: a 12-request
concurrent burst against a TPM-exhausted combo went from 2/12 succeeding
(10 x 524) to 12/12 succeeding with zero 503/524.
Also: liveGeminiShared.ts's sendAndValidate now fails fast on a 503
instead of retrying past it, and the health dashboard + request logger
surface TPM stats alongside RPM/RPD.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo-exhausted rejection logs now capture request body + attempted models
recordRejectedRequestUsage() (the fast path for combo requests that never
reach handleChatCore, e.g. all targets locked by resilience cooldown)
hardcoded provider: "-" and never passed a request body to saveCallLog(),
so /dashboard/logs entries for these failures were nearly useless for
debugging: no way to see the client's request or which models were tried.
- recordRejectedRequestUsage() now accepts requestBody and persists it
through the existing saveCallLog() artifact mechanism (same path
handleChatCore's own logging uses).
- Added summarizeComboAttemptedModels(), which reads the combo's own model
list (always available, unlike the response's combo-diagnostics headers —
a model-level resilience-lockout skip never touches the
exhaustedProviders/exhaustedConnections sets those headers are built
from) to populate a real "provider" value instead of "-".
- Wired both into the call site in src/sse/handlers/chat.ts.
NOTE: unrelated to the Gemini TPM/combo-cooldown-wait fix on this branch —
landed here per operator request, to be split into its own branch/PR.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* feat(sse): synthetic streaming keep-alive event + 5-minute Gemini cooldown-wait ceiling
Many clients enforce a first-SSE-byte timeout, which made it unsafe to wait
out a longer upstream rate-limit cooldown on a streaming request — the
client would abandon the connection before any bytes arrived. This landed
in two parts:
1. Synthetic startup "thinking" event (OpenAI chat/completions format):
the already-existing withEarlyStreamKeepalive wrapper (open-sse/utils/
earlyStreamKeepalive.ts, wired into /v1/chat/completions, /v1/messages,
/v1/responses since #2544) opens the SSE stream immediately once a
request runs past its threshold, but only ever sent empty/no-op
keepalive frames. Added a `startupFrame` option (defaults to
`keepaliveFrame` — zero behavior change unless a route opts in) so the
very first frame can carry real content instead. Wired
OPENAI_STARTUP_THINKING_FRAME (a reasoning_content delta: "OmniRoute:
got request, sending to provider") into /v1/chat/completions only —
Claude Messages and Responses API formats both require a preceding
envelope event (message_start / response.created) that a synthetic
pre-dispatch frame can't safely fabricate without risking a duplicate
envelope once the real stream arrives, so those two routes keep their
existing (safe, proven) keepalive frames unchanged.
2. Raised the "wait out a known cooldown, then retry" ceiling to 5 minutes
for both retry mechanisms, now that a client-side first-byte timeout is
no longer a risk on the (opted-in) route:
- comboCooldownWait (auto/quota-share combos, open-sse/services/combo.ts):
maxWaitMs hard clamp raised 90s -> 300s (src/lib/resilience/settings/
normalize.ts); defaults raised to maxWaitMs:90s/maxAttempts:5/
budgetMs:300s. comboConfig.ts's resolveComboTargetTimeoutMsForCombo
already derives the per-target timeout floor from budgetMs, so it
tracks the new ceiling with no further changes.
- waitForCooldown (direct, non-combo model requests, src/sse/handlers/
chat.ts): this mechanism had NO cumulative cap before — only a
per-wait cap (maxRetryWaitMs) and a retry count (maxRetries), so
maxRetries x maxRetryWaitMs could exceed 5 minutes with no ceiling.
Added a budgetMs field (mirrors comboCooldownWait) to
WaitForCooldownSettings/CooldownAwareRetrySettings, threaded a
requestRetryBudgetLeftMs tracker through chat.ts's requestAttemptLoop
(mirrors combo.ts's comboCooldownBudgetLeftMs), and made
getCooldownAwareRetryDecision refuse to wait once the cumulative
budget is exhausted even if the single wait is under maxRetryWaitMs.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): extend the synthetic keep-alive thinking event to /v1/responses
Live incident (OpenClaw, log id 1784407081908-cbc24f): a /v1/responses
request to gemini/gemma-4-31b-it took 56s to produce a first byte and the
client disconnected (499 request_signal_aborted) — the same client-first-byte-
timeout problem the previous commit fixed for /v1/chat/completions, but
/v1/responses only had the generic bare-comment keepalive (no content), so it
wasn't covered.
Added RESPONSES_STARTUP_THINKING_FRAME: a self-contained synthetic reasoning
item (response.output_item.added -> reasoning_summary_part.added ->
reasoning_summary_text.delta -> reasoning_summary_part.done), opened AND
closed within this one frame rather than left dangling — it never carries a
response_id, so it can't collide with the real upstream response's own
independent response.created lifecycle that follows. Mirrors the abbreviated
delta+part.done close pattern open-sse/utils/stream.ts's own
emitSyntheticResponsesReasoningSummary already uses for real mid-stream
reasoning content.
Wired into src/app/api/v1/responses/route.ts via the startupFrame option
added in the previous commit.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo cooldown-wait vars reset every setTry, crystallizing a bogus 503 instead of waiting
Live incident (log id 1784416706646-51): a request to the "default" combo
(strategy=auto, maxSetRetries=3) hit a real Gemini TPM 429 on both gemma-4
targets, correctly classified as a short 40s rate_limit lockout — then
crystallized a 503 "all upstream accounts are inactive" in 6.9s instead of
ever reaching the cooldown-aware wait.
Root cause: `lastError`/`earliestRetryAfter`/`lastStatus` were declared with
`let` INSIDE the `for (setTry...)` loop body, so they reset to null at the
start of every set-try. When both targets lock out on setTry 0, every
subsequent setTry (1..maxSetRetries) pre-skips both targets via the
isModelLocked check with no real dispatch — so on the FINAL setTry (the only
one whose values the post-loop decision reads, since it's gated behind
`if (setTry < maxSetRetries) continue`), lastStatus was null, hitting the
"!lastStatus" branch (ALL_ACCOUNTS_INACTIVE 503) and completely bypassing the
comboCooldownWaitEnabled / earliestRetryAfter wait logic — even though a
real 429 with a known ~40s retry-after WAS observed on setTry 0.
This bug predates today's Gemini TPM work (any combo with maxSetRetries > 0
whose targets all lock out on the first pass was affected) but was masked in
existing tests: the "auto strategy (2 models...)" regression test uses
maxSetRetries: 0, so it only ever runs ONE setTry iteration and never
exercises the reset-on-retry path. It also explains why the dedicated
12-concurrent-request burst test passed cleanly — with concurrent requests,
timing variance meant some request's FINAL setTry iteration still had a live
target to dispatch to, giving lastStatus/earliestRetryAfter fresh data. A
single isolated request has no such luck.
Fix: hoist lastError/earliestRetryAfter/lastStatus to just inside
dispatchWithCooldownRetry, before the setTry loop, so they persist across
set-tries (still reset fresh on each recursive dispatchWithCooldownRetry()
call after a wait, which is correct). recordedAttempts/fallbackCount/
exhaustedProviders etc. are intentionally left per-iteration (unrelated to
this bug).
New regression test in tests/unit/combo-quota-share-cooldown-wait.test.ts
reproduces the exact live scenario (2 targets, both lock out on setTry 0,
maxSetRetries: 3) — confirmed red (503) against the pre-fix code, green
(200, waits and retries) against the fix.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* test(sse): extend live Gemini workload to Responses API + add large-context TPM test
Two additions to the live Gemini test suite, both live-verified against the
dev instance:
1. sendAndValidate() (tests/integration/liveGeminiShared.ts) now accepts an
apiFormat: "chat" | "responses" parameter, building the Responses-API
request shape (input array, max_output_tokens) and parsing its SSE events
(response.output_text.delta / response.reasoning_summary_text.delta /
response.completed) via the new readResponsesSSEStream(). Wired into two
new tests in live-gemini-workload.test.ts ([30]/[31]), mirroring the
existing Chat Completions streaming coverage. Verified live: 24/25 + 5/5
payloads succeeded end-to-end through the new code path (the one failure
was a ~300s test-client fetch timeout unrelated to the Responses API code
itself — a separate, not-yet-addressed test-harness limitation).
2. genHugeContextMessage() builds a single message large enough (~4
chars/token estimate) to approach or exceed Gemini's free-tier TPM ceiling
(16000 input tokens/min for gemma-4) by itself. Every other prompt
generator in this file tops out around 1-2k tokens — nowhere near that
ceiling — so none of the existing workload tests ever exercised a REAL TPM
429, only RPM-style rate limiting. tests/integration/gemini-large-context-tpm.test.ts
sends two ~12-13k-token requests back-to-back (comfortably exceeding
16000/min together) to exercise the full path against production Gemini:
TPM classification, the comboCooldownWait retry, and the synthetic
keep-alive frame on a genuinely slow request.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): abandoned combo target dispatch now observes its own per-target timeout, fixing a permanent "pending" dashboard leak
Live incident (dashboard log id 1784418258231-14961a, reported as "an ongoing
request even though there's already a 200"): a combo target dispatch
abandoned by comboTargetTimeoutMs (open-sse/services/combo/targetTimeoutRunner.ts)
left a permanent phantom "pending" entry in the dashboard, even after the
overall combo request had already succeeded via a different retry.
Root cause: chatCore.ts's createStreamController — and everything downstream
that depends on it (withRateLimit's Promise.race against Bottleneck,
acquireAccountSemaphore) — only ever watches clientRawRequest.signal, which
is the ORIGINAL client's request signal (set once via buildClientRawRequest
and reused unchanged across every target dispatch in a combo). It has no
connection to targetTimeoutRunner.ts's OWN AbortController
(target.modelAbortSignal), which is what actually fires when
comboTargetTimeoutMs (300s) elapses. src/sse/handlers/chat.ts's
handleSingleModel bridge between combo.ts and handleSingleModelChat received
`target.modelAbortSignal` but silently dropped it — never forwarded it
anywhere. So when a target got abandoned (e.g. stuck inside a wedged
Bottleneck rate-limiter queue, see the WEDGED force-reset log line from the
same incident), its per-target timeout fired and let the COMBO move on and
retry successfully elsewhere — but the abandoned dispatch's own promise
chain never learned it had been superseded, so it hung forever waiting on a
signal that was never going to fire, and trackPendingRequest(false) (the
finalize call) never ran.
Fix: thread target.modelAbortSignal through as a new modelAbortSignal
runtimeOption, and merge it into clientRawRequest.signal (via the existing
mergeAbortSignals helper from open-sse/executors/base.ts) right before
dispatch, so an abandoned target's own promise chain now observes its abort
and can reach its cleanup path — new resolveDispatchClientRawRequest() makes
this mechanically testable in isolation.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo cooldown-wait state recording, rate-limit wedge recovery, OpenAI-format SSE error frames
Five related fixes surfaced by live incidents (dashboard log ids 1784457764961-73,
1784465227489-a2cbc0, 1784504040241-6f8b9a) while validating the Gemini TPM/cooldown-wait
work on this branch against real OpenClaw traffic:
- combo.ts: the model-lockout bail-out branches in dispatchWithCooldownRetry never
recorded lastStatus, so once every target in a set hit an existing lockout the final
check crystallized a bogus ALL_ACCOUNTS_INACTIVE 503 instead of reaching the
cooldown-wait decision, even with a real 429 + short retry-after observed.
- combo.ts/combo/types.ts: the "all credentials cooling down" pre-dispatch rejection
(buildModelCooldownBody) nests its retry hint as error.retry_after/reset_seconds, not
the top-level retryAfter every other 429 shape uses — combo's extraction only read the
latter, so earliestRetryAfter stayed null for this shape even after lastStatus was fixed.
- rateLimitManager.ts: the wedge-recovery watchdog used disconnect(), which releases the
heartbeat timer but never rejects jobs already QUEUED on that instance — orphaned
dispatches hung until the outer ~300s per-target timeout, well past real clients'
patience. Switched to stop({ dropWaitingJobs: true }), safe because the wedge condition
already requires RUNNING===0 && EXECUTING===0.
- earlyStreamKeepalive.ts: the in-band error frame emitted after committing to a 200 SSE
stream was hardcoded to Anthropic's `event: error` convention for every route, including
the OpenAI-format ones (/v1/chat/completions, /v1/responses) where that framing is
either invisible or malformed to a plain data-line parser. Added per-route
OPENAI_CHAT_ERROR_FRAME / OPENAI_RESPONSES_ERROR_FRAME and wired them in.
- chatCore.ts: persisted a synthetic clientResponse error body even when the client had
already disconnected (AbortError) before that body was ever computed — misleading the
dashboard into showing "what the client received" for a response that was never sent.
Also: RequestLoggerDetail.tsx — Provider/Client Event Stream panes lost their collapse
toggle when StreamSection replaced the collapsible PayloadSection (
|
||
|
Markus Hartung
|
6e1e5c9a45 |
fix(sse): tool-incapable provider handling (AI Horde + Responses content-collapse scoping) (#8212)
* fix(sse): collapse single-text-part Responses-API content to a plain string
Every /v1/responses request — even the simplest single-string input —
got 500'd by AI Horde's Aphrodite-backed facade. Root cause:
normalizeResponsesInputForChat() always wraps a plain string input as
`content: [{ type: "input_text", text: value }]` (a one-element array),
and openaiResponsesToOpenAIRequest() mapped that straight through to
`content: [{ type: "text", text: value }]` on the Chat Completions side
— an array. That's spec-valid (OpenAI's own API accepts both shapes),
but strict/naive OpenAI-compatible backends like AI Horde's only
implement the plain-string form and reject the array form outright.
A single-text-part array and a plain string are semantically
identical, so collapse is safe. Real multi-part messages (text+image,
text+file) are left untouched.
Regression test: tests/unit/openai-responses-single-text-content-string.test.ts
(RED before the fix — every collapsed-content assertion failed with an
object instead of a string; GREEN after).
Also adds a deeper AI Horde load-test suite (sequential/concurrent/
cross-model/sustained-throughput/new-capable-model-candidates) that
surfaced this bug via real live traffic after Behemoth-X-123B was
temporarily added to the "default" combo for evaluation.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): unsupportedParams provider-level fallback for aihorde's live-discovered models
Real OpenClaw traffic against the newly-added Behemoth-X-123B combo
target kept 500ing on every attempt even after the Responses-API
content-array fix landed. The pipeline artifact showed why: `tools`
was still present, unstripped, in the request actually sent to AI
Horde's Aphrodite backend.
Root cause: `unsupportedParams: ["tools", "tool_choice",
"parallel_tool_calls"]` was only declared on the 3 models statically
listed in the aihorde registry entry (Cydonia-24B, Skyfall-31B,
google/gemma-4-31b). AI Horde uses `passthroughModels: true` — its
live worker roster changes constantly — so Behemoth-X-123B, like every
other dynamically-discovered aihorde model, had no model-specific
unsupportedParams entry, and getUnsupportedParams() returned [] for
it. But "the workers run raw text-completion backends" (no tool
calling) is true of every model AI Horde serves, not just the 3
catalogued ones.
Adds a provider-level `unsupportedParams` fallback on RegistryEntry,
checked by getUnsupportedParams() after the per-model lookup misses.
Set on the aihorde entry so it covers its entire live-discovered
roster, present and future, without needing a static per-model catalog
entry for each one.
Regression test: tests/unit/aihorde-tools-unsupported-provider-fallback.test.ts
(RED before the fix — Behemoth-X and deepseek-v4-flash both returned
[] instead of the stripped param list; GREEN after, with a control
case confirming the fallback doesn't leak to unrelated providers).
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): flatten leftover tool-call history when stripping unsupported tools
Third bug in the same AI Horde/Behemoth-X saga: even after tools/
tool_choice were correctly stripped from the live request (previous
fix), real combo traffic still 500'd. The conversation history itself
carried a prior turn's role:"assistant" tool_calls and role:"tool"
result messages, left over from before the combo failed over from a
tool-capable model (Gemini) to a non-tool-capable one (AI Horde). Its
raw completion backend doesn't understand those message shapes at all,
independent of whether live `tools` is present — confirmed by
reproducing with a role:"tool" message and NO tools param at all.
flattenToolHistory() (open-sse/utils/flattenToolHistory.ts) already
existed for exactly this, fully unit-tested — it just had zero call
sites anywhere in the request pipeline. Extracts the unsupported-params
strip into a small testable module
(open-sse/handlers/chatCore/unsupportedParamsStrip.ts, following the
existing chatCore god-file decomposition pattern e.g.
executorClientHeaders.ts) that now also flattens tool-call history
whenever "tools" was among the stripped params.
Regression test: tests/unit/chatcore-unsupported-params-strip.test.ts
(RED before the fix — the flattening test failed with the raw
tool_calls array still present; GREEN after). All 434 existing
chatcore-*.test.ts tests still pass.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): gate tool-history flattening on unsupported, not on stripped-this-request
The previous commit's flattening only fired when "tools" was actually
present-and-stripped on THIS request. A second live reproduction
against AI Horde had no live `tools` param at all — only stale
tool_calls/tool-result messages inherited from before a combo
failover — and still 500'd, because that condition never triggered.
A model that can't do tool calling can't do it whether or not the
current request happens to carry a `tools` array. Gate on the
unsupported-params list itself (unsupported.includes("tools")) instead
of the subset that was actually present-and-deleted this time.
Regression test added to the same file (RED before — the no-live-tools
case left tool_calls/role:"tool" untouched; GREEN after). All 435
chatcore-*.test.ts still pass.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): skip tool-incapable combo targets, error clearly on direct requests
Two complementary fixes for a model that structurally can't do tool
calling at all (e.g. AI Horde's raw completion backends) rather than
silently degrading — following up on the earlier strip/flatten fix,
which stopped the crashes but let a tool-incapable target still get
selected and return a 200 that narrates a fake tool call in prose
instead of erroring or being skipped.
1. Root cause, combo routing: getResolvedModelCapabilities()'s
`supportsTools` resolution only checked per-model registry entries,
synced capabilities, and static specs — none of which exist for a
dynamically-discovered model (AI Horde's passthroughModels roster
changes as workers come and go). It fell through to
heuristicToolCalling(), which optimistically defaults to `true` for
any unrecognized model (TOOL_CALLING_UNSUPPORTED_PATTERNS is empty).
Added a provider-level fallback reusing the same unsupportedParams
signal the request-time strip already relies on. This makes the
EXISTING filterTargetsByRequestCompatibility (comboStructure.ts) —
which already correctly excludes non-tool-capable targets when a
request requires tools — actually work for these models; no combo.ts
changes were needed, it was only ever fed bad capability data.
2. Direct/pinned requests: filterTargetsByRequestCompatibility only
protects combo routing. A direct request naming an exact
tool-incapable model has no other target to fail over to — added
checkToolCallingRequiredButUnsupported (chatCore/toolCallingRequiredCheck.ts),
gated on isCombo: false, returning a clear 400 instead of a 200 that
silently can't do what was asked.
Regression tests (both RED before, GREEN after):
- tests/unit/model-capabilities-provider-unsupported-tools.test.ts
- tests/unit/chatcore-tool-calling-required-check.test.ts
All 463 chatcore-*/model-capabilities-*.test.ts and 31 combo
compatibility-filter tests still pass.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): correct handleChatCore return shape for the tool-calling-blocked error
handleChatCore's documented contract is `{ success, response, status,
error }`, not a raw Response — returning `new Response(...)` directly
(copied from a different early-return whose surrounding context turned
out not to share this function's top-level contract) produced "No
response is returned from route handler ... Expected a Response object
but received 'undefined'" and a bare 500 with an empty body, caught
immediately when verifying the previous commit live.
Uses createErrorResult() (already used by the adjacent
translation-failure branch a few lines up) instead of hand-building the
Response, matching the same pattern already established in this
function for early error returns.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): scope Responses single-text-content collapse to providers that need it
The single-text-part content array -> plain string collapse (added for AI
Horde's Aphrodite facade, which 500s on the array form) was applied
unconditionally to every provider, silently breaking the standard OpenAI
array-shaped content contract that other providers and existing tests
depend on. Added RegistryEntry.requiresPlainStringContent, gated the
collapse on it (true only for aihorde), and threaded modelInfo.provider
through responsesHandler -> responsesApiHelper -> the translator so the
real /v1/responses call site can identify the provider.
Co-Authored-By: Markus Hartung <markus.hartream@gmail.com>
---------
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
Co-authored-by: Markus Hartung <markus.hartream@gmail.com>
|
||
|
Roberto
|
4ecca379fc |
fix(providers): fix Azure AI Foundry multi-model discovery and per-deployment connection testing (#8174) (#8206)
Co-authored-by: not-knope <185121404+not-knope@users.noreply.github.com> |
||
|
backryun
|
f664af8f36 |
feat(github): refresh Copilot model catalog (#8226)
* feat(github): refresh Copilot model catalog * feat(github): refresh Copilot model catalog (gpt-5.6 family) Dropped the claude-opus-4.6 reinstatement (contradicts #7223/#2821 with no new evidence; risks a production 400 on /v1/messages). Kept the gpt-5.6-sol/terra/luna additions, which already exist on the Codex provider. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: backryun <backryun@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
backryun
|
ed8755a6d0 | feat(github-models): refresh catalog and compatibility (#8225) | ||
|
adevwithpurpose
|
2d4db0157e |
fix(providers): discover live AGY models (#8123)
Live AGY model discovery (isDiscoverableAgyModelId + filterUserCallableAntigravityModels) composing with the #8013 antigravity discovery rewrite. Reconstructed onto the current release tip (branch was ~977 commits behind); updated the test to the renamed version-cache API (seedAntigravityVersionCache -> seedAntigravityIde/CliVersionCache) after the fusion. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
backryun
|
888c872459 |
refactor(antigravity): align official clients and callable catalog (#8013)
* fix(antigravity): preserve protocol fidelity and fail closed * chore: add PR-numbered changelog fragment * test: split oversized Antigravity suites * refactor(antigravity): align official IDE and CLI identities * fix(antigravity): align catalog with callable models * test(antigravity): update 2 test files to renamed version-cache API (#8013 fix) Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: nguyenha935 <208228297+nguyenha935@users.noreply.github.com> Co-authored-by: backryun <backryun@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> Co-authored-by: nguyenha935 <nguyenha935@users.noreply.github.com> Co-authored-by: Probe Test <probe@example.com> |
||
|
Diego Rodrigues de Sa e Souza
|
e392a39047 | feat: native Fish Audio TTS provider on /v1/audio/speech (#8099) (#8164) | ||
|
Diego Rodrigues de Sa e Souza
|
c252c9d885 |
fix(providers): add missing poe registry baseUrl entry (#8082) (#8149)
* fix(providers): add missing poe registry baseUrl entry (#8082) The built-in poe provider (passthroughModels:true, NAMED_OPENAI_STYLE_PROVIDERS) had no open-sse/config/providers/ REGISTRY entry, so model discovery's getRegistryEntry("poe")?.baseUrl resolved to undefined and GET /api/providers/[id]/models always failed with {"error":"No base URL configured for provider"} even though credentials and inference worked fine (the validation/inference path already had a hardcoded https://api.poe.com/v1 fallback). Adds a real REGISTRY entry mirroring moonshot/byteplus, and points the audioMiscProviders.ts hardcoded fallback at the same POE_DEFAULT_BASE_URL constant so both paths agree going forward. * test: regenerate provider translate-path golden for poe (#8082) |
||
|
NOXX - Commiter
|
e86e5bcc51 |
feat(media): Adobe Firefly image + video generation provider (#8006)
* feat(media): Adobe Firefly image + video generation provider
Add unofficial adobe-firefly media provider with full OpenAI-compatible
image and video generation: Nano Banana / GPT Image families, Sora 2,
Veo 3.1 (standard/fast/reference), and Kling 3.0.
Supports browser session cookies (auto IMS token exchange) or direct
IMS access tokens, async submit-and-poll against Firefly 3P endpoints,
aspect-ratio and resolution controls, and multi-account web-session UX.
Chat completions are intentionally rejected (media-only surface).
Includes unit coverage for registry wiring, payload builders, auth
resolution, and mocked generate happy-paths.
* fix(adobe-firefly): clio auth, discovery fallback, credits balance
Root-cause 401 invalid token against live firefly.adobe.com captures:
generate/discovery use x-api-key + IMS client_id clio-playground-web
(not projectx_webapp). Align headers/origin, dual cookie to IMS exchange
(clio first, Express fallback), BKS poll rewrite for /jobs/result.
Models: parse POST /v2/models/discovery + static fallback catalog from
adobe/get_models.txt; expand image/video registries.
Limits: GET firefly.adobe.io/v1/credits/balance (SunbreakWebUI1) with
total/remaining + free/plan detail quotas. Clarify cookie vs JWT UX.
Unit tests: 27/27 pass.
* fix(adobe-firefly): reject guest tokens from page-only cookies
Live repro with firefly.adobe.com Cookie export: IMS check with
guest_allowed=true returns account_type=guest (no AdobeID). That token
fails generate (401 invalid token) and credits/balance (403
ErrMismatchOauthToken). guest_allowed=false needs adobelogin.com IMS
session cookies which are not present in a page-only Cookie paste.
- Detect/reject guest JWTs; clear error tells user to paste Bearer JWT
- Prefer user JWT from HAR/mixed paste; improve credential extraction
- Update web-cookie + credential UX to recommend Authorization Bearer
Unit tests 29/29.
* fix(adobe-firefly): production auth, Limits, and 408 load handling
Live validation against firefly.adobe.com + packaged VibeProxy:
Auth / credentials
- Prefer IMS user JWT (Bearer from firefly-3p); reject guest tokens from
page-only cookies with an actionable error
- Extract JWT from Bearer, access_token=, IMS sessionStorage tokenValue,
and mixed HAR pastes; prefer non-guest tokens
- Strip JWT from Cookie header (undici Headers.append crash on mixed paste)
- Keep sherlockToken → x-arp-session-id + sanitized Cookie for generate
Limits
- credits/balance → Record quotas (firefly_total / free / plan) so
providerLimits caches them (arrays were ignored)
- Allowlist adobe-firefly + firefly in USAGE_SUPPORTED + APIKEY limits
- Live: 10000 plan credits parsed end-to-end after refresh
Generate
- Browser-shaped gpt-image body (size auto, no extra top-level size)
- Exponential 408 "system under load" retries (8 attempts) with clear
client message that 408 is Adobe capacity, not invalid token
- Live: generate returns proper 408 under load; balance/models stay 200
Tests: adobe-firefly unit suite 33/33 pass.
* fix(adobe-firefly): match live capture headers; add gpt-image-2
- Do not send firefly.adobe.com Cookie to firefly-3p (wrong-origin; soft 408)
- Lift sherlockToken only into x-arp-session-id
- Poll headers match status_check.txt (Bearer + accept, no x-api-key)
- Catalog gpt-image-2 alias → upstream modelVersion "2" (GPT Image 2)
- Shorter 408 retry budget so clients fail fast with clear message
- Unit suite 34/34
* fix(adobe-firefly): always send x-arp-session-id on generate (fixes 408)
Root cause of Bearer JWT → HTTP 408 colligo "system under load":
submit only set x-arp-session-id when sherlockToken was present in a
cookie paste. JWT-only credentials never sent the header, and Adobe
soft-blocks those requests with instant 408 (x-colligo-timeout:0.0).
A/B against a real user IMS token:
- det nonce + synthetic ARP → 200
- random nonce + synthetic ARP → 200
- det nonce without ARP → 408
Match adobe2api / GPT2Image-Pro:
- buildAdobeSubmitNonce = sha256(user_id + prompt[:256])
- buildAdobeArpSessionId = base64({sid, ftr}) synthetic session
- buildAdobeSubmitHeaders always sets both headers
Live adobeFireflyGenerateImage end-to-end: submit + poll → S3 presigned URL.
* fix(adobe-firefly): drop literal cred fallbacks + type-clean tests
Addresses pre-merge review feedback on #8006:
- Removes the `|| "literal"` fallback after resolvePublicCred() in
adobeFireflyApiKey()/adobeFireflyExpressClientId()/adobeFireflyBalanceApiKey()
(open-sse/services/adobeFireflyClient.ts). resolvePublicCred() already
always returns the decoded embedded default, so the literal fallback
was dead code that reproduced the exact env-or-literal anti-pattern
docs/security/PUBLIC_CREDS.md documents as BAD (Hard Rule #11).
- Replaces the 11 `@typescript-eslint/no-explicit-any` casts in
tests/unit/adobe-firefly.test.ts with concrete types
(Record<string, unknown>, Headers, Error-narrowing on the
assert.rejects predicate), matching the pattern already used
elsewhere in this suite. `no-explicit-any` is a hard ESLint error
under tests/ in this repo.
- Freezes file-size baseline entries for the new
open-sse/services/adobeFireflyClient.ts (1958 LOC, new-file cap 800,
mirrors the qoderCli.ts precedent for a legitimately large new
provider client), open-sse/config/imageRegistry.ts (800->821, new
adobe-firefly registry entry) and the +3 LOC growth in
src/lib/usage/providerLimits.ts (1000->1003).
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
Co-authored-by: artickc <artickc@users.noreply.github.com>
|
||
|
NOXX - Commiter
|
1b010f6c40 |
feat(sse): add HyperAgent (hyperagent.com) unofficial web provider (#7994)
* feat(sse): add HyperAgent (hyperagent.com) unofficial web provider
Reverse-engineered from live SPA captures (hyperagent/*.txt):
Chat:
- Cookie session auth (full Cookie header)
- New thread via GET /threads/new (or POST /api/threads)
- POST /api/threads/{id}/chat with SPA feature flags + content
- SSE parse of text/session_start/session_end/done events
- Multi-turn sticky threadId + sessionId cache (history prefix + last assistant)
Models:
- Hardcoded catalog from SPA pricing map
- Pretty display names (Claude Fable 5) while wire modelId stays fable etc.
- /v1/models exposes pretty name; chat uses modelId
Limits:
- GET /api/settings/billing/usage → creditBlocks initialUsd/remainingUsd/usedUsd
- USD Credits quota for Limits page
Tests: 15/15 unit/executor-hyperagent
* fix(sse): HyperAgent execution mode + fable-latest wire model (no plan mode)
* fix(sse): document HyperAgent env vars + regenerate golden snapshot
Addresses pre-merge review feedback on #7994:
- Documents HYPERAGENT_USAGE_URL in .env.example and ENVIRONMENT.md
(OMNIROUTE_DATA_DIR was already documented via the sibling PromptQL
provider) so check-env-doc-sync.test.ts passes.
- Regenerates the provider-translate-path golden snapshot to include
the new hyperagent/ha registry entries.
- Swaps the local toNumber() helper in usage/hyperagent.ts for the
canonical @/shared/utils/numeric import (#7879 no-restricted-syntax
rule landed on the release branch after this PR was opened).
- Freezes file-size baseline entries for the new
open-sse/executors/hyperagent.ts (937 LOC, new-file cap 800) and the
+3 LOC growth in src/lib/usage/providerLimits.ts (1000->1003), both
irreducible to this PR's own provider-registration wiring.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
|
||
|
Ravi Tharuma
|
79ec594c1f |
fix(embeddings): support secure multimodal inputs (#7978)
* fix(embeddings): support secure multimodal inputs Closes #7956 * fix(embeddings): translate multimodal inputs and harden URL/base64 bounds Reject oversize base64 before format validation to avoid Zod stack overflows, translate canonical items to Jina modality-keyed and Gemini embedContent contracts, and fetch HTTPS media server-side with DNS pinning before provider submission. Closes #7956 * fix(embeddings): pin DNS only for embedding media fetches Default remote-image fetch keeps the previous globalThis.fetch path so image-generation tests and callers stay mockable. Multimodal embeddings still opt into undici DNS pinning for URL media. * fix(embeddings): close 2 SSRF/DoS gaps in secure multimodal input (#7978) Closes two gaps in the multimodal embedding input hardening from #7956: 1. `createPinnedFetch()` (the connection-pinning mechanism that closes the DNS-rebinding TOCTOU window, GHSA-cmhj-wh2f-9cgx) had zero test coverage anywhere in the repo. Writing that test surfaced a real regression: its custom `connect.lookup` only implemented the single-address callback form `(err, address, family)`. Node's autoSelectFamily/Happy Eyeballs (on by default since Node 18) calls `lookup` with `{ all: true }` and requires the array form `(err, addresses[])` — the mismatch threw `ERR_INVALID_IP_ADDRESS` on every real pinned fetch, silently breaking all URL-sourced multimodal embedding requests in production. Fixed by branching on `options.all`. 2. The documented "16 MiB decoded per request" cap was enforced by the Zod schema only for base64-sourced items; URL-sourced items were excluded, and all up-to-32 items were fetched concurrently via `Promise.all` — allowing ~256 MiB in memory at once (16x the documented bound). Fixed by resolving items sequentially with a running byte budget shared across base64 and fetched-URL sources, rejecting once the aggregate is exhausted instead of after over-fetching. Adds tests/unit/remote-image-fetch-pin-dns-connection.test.ts (real loopback-server pinning tests) and a new aggregate-cap test in tests/unit/embeddings-multimodal-7956.test.ts; both were verified to fail against the pre-fix code before the corresponding fix was applied. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Diego Rodrigues de Sa e Souza
|
0f342f41fe |
fix(providers): refresh duckduckgo-web catalog to current Duck.ai wire ids (#8000) (#8079)
duckduckgo-web returned 400 ERR_BAD_REQUEST on every request because the model
catalog advertised ids DuckDuckGo has retired from the free Duck.ai lineup
(gpt-4o-mini, gpt-5-mini, llama-4-scout, mistral-small-2501, o3-mini,
claude-3-5-haiku-20241022). duckchat/v1/chat validates `model` server-side and
rejects retired ids, and normalizeDuckDuckGoModel() defaulted to / passed through
gpt-4o-mini, so the retired id reached the wire verbatim.
Update all three id sources to the current free wire ids captured live from
duckchat/v1/models (2026-07-22): gpt-5.4-mini, gpt-5.4-nano, claude-haiku-4-5,
mistral-small-2603, tinfoil/gpt-oss-120b, tinfoil/gemma4-31b —
- executor: default gpt-4o-mini -> gpt-5.4-mini; legacy ids aliased to the
nearest current model via a lookup map; dropped the invalid gpt-5-mini
"minimal" reasoningEffort;
- freeModelCatalog.data.ts + providers/registry/duckduckgo-web: current ids.
Regression test duckduckgo-web-model-catalog-8000.test.ts asserts no retired id
ever reaches the wire and all three catalogs match the current set (RED on the
old default/passthrough + retired catalogs). Live 200 confirmation remains a
recommended VPS smoke per the plan-file.
|
||
|
Diego Rodrigues de Sa e Souza
|
91f4c35e9d | feat: copilot-m365-web tone-selected model variants (#7872) (#7997) | ||
|
Diego Rodrigues de Sa e Souza
|
159873719c |
feat(providers): add hailuo-web (MiniMax web) chat provider (#6673) (#7734)
Adds hailuo-web as a new free web-cookie chat provider targeting the
MiniMax consumer chat product at hailuo.ai (chat.minimax.io), distinct
from the existing paid API-key minimax/minimax-cn providers.
Ported from the g4f reference implementation
(g4f/Provider/needs_auth/mini_max/{HailuoAI,crypt}.py):
- MD5-chain request signing (generate_yy_header/get_body_to_yy)
- Custom event:/data: SSE parsing (send_result/message_result/close_chunk),
where message_result.content is a cumulative snapshot diffed into deltas
- Device-fingerprint query params, derived deterministically per-connection
from the token when the user hasn't captured the real browser values
New catalog entry, executor, registry entry, dispatch wiring, tests
(17 cases covering signing test vectors independently verified via
Python hashlib.md5, SSE parsing, streaming/non-streaming dispatch, and
401-terminal vs 429-transient error mapping), and a regenerated
provider-translate-path golden snapshot (purely additive diff).
|
||
|
Diego Rodrigues de Sa e Souza
|
287802cf86 |
fix: repair pre-existing red gates on the release/v3.8.49 tip (#8055)
* fix(dashboard): resolve Kimi banner casing collision + shrink frozen test file (release tip) - Rename src/app/(dashboard)/dashboard/kimiSponsorBanner.ts to kimiSponsorBannerGate.ts so it no longer differs from KimiSponsorBanner.tsx only by the first letter's case (breaks next build on case-insensitive filesystems). Updates the sole importer (KimiSponsorBanner.tsx) and the two tests that reference it. - Extract the 8 Kimi/Moonshot featured-ordering tests out of the frozen tests/unit/providers-page-utils.test.ts (grown 3 lines past its 1294 cap by #8039's rebrand-comment update) into a new sibling file tests/unit/providers-page-utils-kimi.test.ts. No assertions dropped; both files pass in full (24 + 8 = 32 tests). * fix(sse): register PromptQlExecutor in the executor registry (release tip) getExecutor("promptql") had no entry in open-sse/executors/index.ts, so it silently fell through to DefaultExecutor's provider fallback, which issues a raw fetch() and returns the bare upstream Response instead of the executor wrapper shape {response, url, headers, transformedBody}. The real PromptQlExecutor class (open-sse/executors/promptql.ts) already honors the contract correctly — it was just never wired into the registry. Fixes tests/unit/executor-web-cookie-sweep.test.ts "promptql executor returns wrapper shape". * fix(i18n): backfill 2220 missing pt-BR keys to restore en.json parity (release tip) pt-BR.json fell behind after #7935 restored +2220 keys into en.json and vi.json but left pt-BR.json unmodified. Translated all missing entries to Brazilian Portuguese, preserving ICU/interpolation placeholders and existing terminology, and merged them mirroring en.json's key order so the diff is additions-only (the small comma-only deletions are pure JSON reformatting from new sibling keys). * fix(providers): repair 4 pre-existing catalog/registry reds on release tip - providers-constants-split.test.ts: APIKEY_PROVIDERS grew 182->187 (PR #7887 added 5 free-tier providers: ainative/aion/sealion/routeway/nara). Verified no dup/loss (6-family partition sums exactly to 187) and updated the stale expected count + comment trail to match. - cline registry: added the missing minimax/minimax-m3 free OpenRouter entry (#3321) and fixed the neighbouring nemotron-3-ultra-550b-a55b entry, which carried a stray ":free" id suffix and an imprecise 1_000_000 contextLength instead of the 1_048_576 the test (and every sibling 1M-context entry in this catalog) expects. - promptqlModels.ts / registry/promptql/index.ts: PROMPTQL_FALLBACK_MODELS's minimax-m3 entry was missing supportsVision, and the registry mapping dropped it entirely (only id/name were passed through) — it was the sole minimax-m3 entry across the whole registry not flagged multimodal, despite every other provider (minimax, minimax-cn, ollama-cloud, trae, bazaarlink, clinepass, codebuddy-cn, opencode-zen/go, synthetic, huggingchat, lmarena) agreeing MiniMax-M3 supports vision. Added the field to the PromptQlModel type and threaded it through. - tests/snapshots/provider/translate-path.json: regenerated the golden via UPDATE_GOLDEN=1. Diffed old vs new — zero providers removed, 5 added (ainative/aion/nara/routeway/sealion, matching #7887), and the only changed entry (cline) reflects the already-merged #7914 ClinePass header protocol change (Cline/<version> User-Agent + X-Task-ID) that a prior narrow golden touch-up missed capturing. * fix(docs): repair docs-sync/env-sync/repo-contract gates (release tip) Six pre-existing reds on release/v3.8.49, all "repo drifted from its own documented contract": - check-docs-counts-sync: free-tier headline was stale (~1.4B/~2.0B) vs the live catalog (~1.53B steady / ~2.15B first month, 43 pools). Updated README.md and docs/reference/FREE_TIERS.md to the live numbers and added a v3.8.49 correction note explaining the pool-count delta (39->43, #7840). Also fixed a soft executors-count drift in ARCHITECTURE.md (84->86, 268->271 providers) while touching that line. - release-green-docs-drift-7253: docs/proxy-subscriptions.md referenced a fabricated migration filename (123_proxy_subscriptions.sql); the real file is 131_proxy_subscriptions.sql. Fixed all 3 occurrences. - check-env-doc-sync + issue-7793-env-doc-sync-repro: OMNIROUTE_DATA_DIR (DATA_DIR fallback alias read by open-sse/executors/promptql/threadSticky.ts) was undocumented. Added to .env.example and docs/reference/ENVIRONMENT.md. - check-db-rules: src/lib/db/proxySubscriptions.ts (#7299) is a db-internal split of proxies.ts (kept under the frozen file-size cap) whose one export is already re-exported via proxies.ts -> localDb.ts. Added it to INTENTIONALLY_INTERNAL with the same db-internal justification used for identical split modules (apiKeyColumnFallbacks, providerNodeSelect, webSessionDedup) rather than a redundant direct re-export from localDb.ts. - mcp-server-hollow-dist-deps: the sanity test expected better-sqlite3 among the MCP bundle's static top-level external imports. That's been stale since the pre-#7878 migration to a cascading SqliteAdapter driver factory (createRequire()-based lazy require, not a static import); better-sqlite3 already has its own native-asset copy guarantee in assembleStandalone.mjs, unrelated to this test's EXTRA_MODULE_ENTRIES concern. Updated the assertion to a still-genuinely-static external (zod) with a comment explaining the change. No production runtime behavior changed — docs, .env.example, and a checker allowlist/test-expectation only. * fix(dashboard): repair stale UI component-shape test assertions (release tip) Two pre-existing reds in the dashboard UI component-contract cluster were caused by test assertions that had gone stale after intentional, correct refactors — not by real defects in the components: - quota-pool-wizard-multi.test.ts: the step-3 preview assertion required the literal single-line substring "connectionIds.map((cid)". Prettier (100-char width, project config) legitimately breaks the connectionIds.map(...).filter(...) chain across lines because of the multi-line callback body, so the literal never matches. PoolWizard.tsx still builds previewByProvider correctly by mapping over connectionIds; updated the assertion to a regex that tolerates the line break. - v388-phase1-screen-fixes.test.ts: the shared Select placeholder-guard assertion required the literal "!children && placeholder". An earlier, intentional i18n commit changed the hardcoded "Select an option" default to a translated fallback (`placeholder ?? t("selectOption")`), which requires parens around the ?? expression for operator precedence. The guard behavior is unchanged (still gated on !children); updated the assertion to match the current, correct guard shape. Both fixes are read-only test-file changes; no production behavior changed. review-reviews-v3814-fixes.test.ts still has one pre-existing, unrelated red (LEDGER-4: minimax-m3 registry entries missing supportsVision) that requires editing the promptql provider registry/catalog — out of this cluster's scope, left untouched and reported separately. * fix(providers): reconcile cline catalog contradictions + deterministic golden (release tip) The first tip-green pass introduced 3 regressions caught by CI on sibling guard tests: - clinepass-provider + cline-catalog-models-3321 encoded OPPOSITE expectations of the same cline model list (minimax presence, nvidia :free suffix). Reference upstream (OpenRouter free lineup) confirms nvidia/nemotron-3-ultra-550b-a55b:free (with :free, 1M ctx) is correct, so restore that id and fix #3321's stale no-:free assertion; add minimax/minimax-m3 (the real #3321 gap) to clinepass-provider's list. - check-db-rules-classification froze INTENTIONALLY_INTERNAL at 35; proxySubscriptions was the intentional 36th entry — add it + bump the count. - provider-translate-path golden stored a LITERAL Cline/3.8.49: clineAuth resolves the version from APP_CONFIG.version (stable), but the golden sanitizer collapsed only process.env.npm_package_version (unset under `node`, set under `npm run`) — so the golden was shard-dependent. Resolve APP_VERSION from APP_CONFIG.version like clineAuth and regenerate; now Cline/<APP> normalizes identically in every shard. * fix(services): type execFile signal/killed in classifyError + ratchet dashboard baseline (release tip) Pre-existing base-red on the tip's Fast Quality Gates (dashboard-typecheck), missed in the first inventory: - src/lib/services/installers/utils.ts TS2339 — `err.signal` was read off a value typed as NodeJS.ErrnoException, which @types/node does not declare `signal`/`killed` on (those belong to execFile's ExecFileException). Widen classifyError's param to type both, and drop the now-redundant `(err as … { killed })` cast. - Ratchet config/quality/dashboard-typecheck-baseline.json down: 5 baselined errors were fixed by already-merged PRs but never ratcheted (OAuthModal TS2769 4→3 / TS2345 4→3, CliproxyModelMappingEditor TS2339, CompressionPreviewAccordion TS4104, MonacoEditor TS2307). Baseline now 254, matching live — gate exits 0. |
||
|
Navaneet Ramabadran
|
eab59d4048 |
fix(translators): normalize TitleCase tool names for non-Anthropic models (#7926)
* fix(translators): normalize TitleCase tool names for non-Anthropic models * fix(translator): parse XML <invoke> blocks in OpenAI→Claude response translator * fix(gemini-web): mark gemini-3.1-flash-lite as toolCalling: false * fix(gemini-web): mark all models as toolCalling: false, add to no-tools combo * fix(web-providers): mark all web-cookie models as toolCalling: false * fix(nvidia): disable tool calling on models that can't handle it * fix(lint): drop explicit any annotation on extractXmlInvokeBlocks state param Removes the no-explicit-any violation introduced alongside the TitleCase tool-name normalization work so the merged branch stays lint-clean (state stays implicitly typed like its sibling helpers in this file). Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
NOXX - Commiter
|
55549bfe5a |
feat(sse): add PromptQL playground provider (unofficial) (#7911)
* chore(ci): add .mergify.yml to main — Mergify only reads config from the default branch (#7168) * fix(ci): add the auto-enqueue pull_request_rule to the Mergify config (queue_conditions alone are eligibility-only) (#7179) * fix(ci): migrate Mergify auto-enqueue to merge_protections_settings.auto_merge_conditions (rules-based path is EOL 2026-07-16) (#7216) * fix(ci): drop Mergify batch settings (batching is a paid-tier feature; free plan queue is serial) (#7220) * fix(ci): merge queue tolerates the advisory dast-smoke failure (its GH-hosted build hang dequeued every attempt) (#7225) * test(ci): make the #6634 selfref guard hermetic — main's copy hard-fails every PR (#7341) main's copy of this test still does git I/O inside a unit test: const baseSrc = git(['show', 'origin/main:' + FILE]); Runners check out a shallow single ref, so origin/main does not resolve and the test dies with 'fatal: invalid object name origin/main'. Every PR into main fails Unit Tests (7/8) on it — today that is #7313, #7315, #7316, #7334, #7336 and #7337, six PRs red on a defect none of them introduced. #7313 has no other red at all. release/v3.8.49 already carries a fix ( |
||
|
FenjuFu
|
19cbe8ae14 |
fix(providers): route iflytek/sparkdesk to Spark's OpenAI-compatible host (#7942)
Both entries declare format: "openai" with authHeader: "bearer", but pointed at spark-api.xf-yun.com — Spark's WebSocket host, which authenticates with an HMAC-SHA256 signature over app_id/apiKey/apiSecret and rejects bearer tokens. The OpenAI-compatible HTTP API lives on spark-api-open.xf-yun.com/v1, so neither provider could complete a request as configured. sparkdesk also listed a "general" model; that is a WebSocket domain value and is not accepted by the HTTP endpoint, so it becomes "lite" (Spark Lite). The free-model catalog's sparkdesk row is updated to match, and a regression test locks both baseUrls, the removed "general" model id, and catalog/registry cross-reference. Reconstructed against release/v3.8.49 (folds in the same-PR follow-up "point sparkdesk free-catalog row at lite"). Signed-off-by: FenjuFu <92919259+FenjuFu@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
backryun
|
2d1801985c |
feat(cline): align ClinePass catalog and request protocol (#7914)
* feat(cline): align catalogs and official protocol * fix(models): clean imports after final connection removal * fix(quality): extract Cline/ClinePass auth-header wiring to shrink default.ts open-sse/executors/default.ts grew to 894 lines against the frozen 890-line cap after adding the ClinePass official-protocol import plus two Object.assign header-merge blocks. Extract the merge logic into a new applyClineAuthHeaders() helper in src/shared/utils/clineAuth.ts so the executor's case "clinepass" / case "cline" branches shrink to a single call each, dropping default.ts back to 875 lines. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Diego Rodrigues de Sa e Souza
|
11b5ce1f0e |
feat(providers): add 5 free-tier providers (ainative, aion, sealion, routeway, nara) (#7887)
Five OpenAI-compatible free-tier aggregators OmniRoute did not cover yet, added
as a registry entry plus a canonical provider each.
ainative api.ainative.studio/api/v1 — 84-model public catalog, passthrough
aion api.aionlabs.ai/v1 — 5 models, public catalog w/ pricing
sealion api.sea-lion.ai/v1 — AI Singapore, pinned models (10 RPM)
routeway api.routeway.ai/v1 — 236-model catalog; browser UA pinned
because Cloudflare 1010s non-browser UAs
nara router.bynara.id/v1 — shared 5M/day pool, pinned free models
All five /models endpoints were probed live 2026-07-20 (200 for the public ones;
sealion/nara 401 without a key, as expected) and every pinned model id was
confirmed to exist upstream.
Free-catalog honesty: ainative ("~10M tok/mo claimed"), aion (20k tok/day),
sealion (10 RPM) and routeway (200 RPD) have no verifiable monthly TOKEN quota,
so they are recurring-uncapped — real access, never summed into the headline.
Only nara publishes a token figure (5M tokens/day shared = 150M/month), recorded
as one deduped pool. Net: 484 -> 514 models, 1.376B -> 1.526B tokens, the +150M
coming solely from nara.
|
||
|
Paijo
|
3238df3204 |
perf: lazy provider init, P2C quota cache, structuredClone elimination, getSettings→getCachedSettings (batch 2) (#7893)
* perf: startup parallelization, stream TextEncoder lift, auth middleware bottlenecks
Startup (~100-300ms faster cold start):
- Parallelize 4 early imports via Promise.all() in registerNodejs()
- Parallelize 10 independent background services via Promise.allSettled()
- Each service has independent try/catch — no failure domino effect
Streaming pipeline (8 fewer TextEncoder GC allocations per SSE event):
- Lift new TextEncoder() from per-chunk inside buildClaudeStreamingResponse
to function scope alongside existing decoder singleton
Auth middleware bottlenecks (from PerfBottleneckAnalysis):
- Backoff decay loop: replace updateProviderConnection (full CRUD:
SELECT+encrypt+cache-invalidate+backup) with resetConnectionBackoff
(targeted UPDATE of backoff/error columns only)
- Dual .filter() for quota: replace two passes calling
isQuotaExhaustedForRequest per connection with a single for loop
partitioning into withQuota/exhaustedQuota
- Debug-log filter recomputation: capture connectionFilterStatus Map
during the filter pass; debug loop reads 6 string comparisons instead
of 6 function calls per connection
Supporting:
- Add resetConnectionBackoff to src/lib/db/providers.ts (patterned after
clearConnectionErrorIfUnchanged, no CAS check)
- Re-export resetConnectionBackoff from src/lib/localDb.ts
- Update integration-wiring.test.ts regex for parallelized dynamic import
* perf: P2C quota cache, lazy provider init, structuredClone elimination, getSettings→getCachedSettings
- **auth.ts: P2C quota re-evaluation cache** — quotaResults Map threaded
through selectPoolSubset → compareP2CConnections → getP2CConnectionScore.
Populated during filter + partition passes, eliminating redundant
evaluateQuotaLimitPolicy / isQuotaExhaustedForRequest calls when the
P2C comparator re-evaluates previously-scored connections.
- **constants.ts: lazy PROVIDERS via Proxy** — replaces eager
generateLegacyProviders() + loadProviderCredentials() at module load
with Proxy delegating to deferred init on first property access.
- **providerModels.ts: lazy PROVIDER_MODELS + PROVIDER_ID_TO_ALIAS** —
same Proxy pattern for both exports; generateModels()/generateAliasMap()
deferred until first read.
- **stream.ts: structuredClone → minimal object spread** — replaces
O(n) deep clone of SSE response chunks with targeted reconstruction
of only mutated fields (usage, delta.content, finish_reason).
- **progressTracker.ts: TextDecoder lift** — module-level decoder
instead of per-chunk new TextDecoder().
- **Route files: getSettings() → getCachedSettings()** — 13 API route
files converted from uncached per-request DB reads to TTL-cached
wrapper (5s default), eliminating redundant queries on every request.
- **settings.ts: re-export getCachedSettings** from readCache for
non-localDb consumers.
- **Remove settingsCache.ts** — dead file, no imports reference it.
TS compile: 0 errors. Auth tests: 225/225 pass. Services: 269/269 pass.
* perf: Phase 1 tangible wins — egressCache eviction, mmap_size PRAGMA, composite indexes, proxyFallback lazy import
- egressCache: lazy TTL eviction on getCachedEgressIp access (bounds memory
leak to distinct proxy URLs, typically <100)
- mmap_size: apply stored PRAGMA from key_value table (256MiB default) after
applyStoredDatabaseOptimizationSettings — setting was stored but never applied
- schemaColumns: add idx_uh_provider_model_timestamp (covers getModelLatencyStats)
and idx_pc_provider_auth_type (covers 6+ provider_connections queries)
- proxyFallback: convert static import to dynamic import() inside error handler
(defers 210ms module load from startup to first proxy-retry scenario)
* perf: add dedup expression index, unref() sweep timers
- Add COALESCE expression index idx_uh_dedup on usage_history
matching the exact dedup query pattern. Eliminates FULL TABLE
SCAN on every saveRequestUsage insert.
- Add composite idx_uh_provider_model_timestamp on usage_history.
- Add composite idx_pc_provider_auth_type on provider_connections.
- Add .unref() to setInterval in batchProcessor.ts (polling loop).
- Add .unref() to setInterval in runtimeHeartbeat.ts (heartbeat).
* perf: bump SQLite cache_size default from 16MB to 64MB
New installs now start with 64MB page cache (was 16MB). Existing
users' stored settings are unchanged. Reduces disk reads for the
typical ~250MB database by keeping ~25% of pages in memory.
Also resolved pre-existing merge conflict in webhooks.ts.
* docs: add Redis production config guide and proxy port clash investigation report
- docs/redis-production-config.md: comprehensive Redis tuning guide
covering client options, server config, Docker settings, scaling,
and monitoring for all three Redis workloads (rate limiting,
auth cache, quota store)
- docs/proxy-port-clash-report.md: investigation confirming proxy
subsystem has no port binding issues; real EADDRINUSE history
traced to process supervisor crash-loop restart race (#4425) and
live-dashboard port clash (#6324), both already fixed
* fix: address PR #7893 review — add Proxy traps, extract migrations to reduce providers.ts size
- Add set trap to PROVIDER_ID_TO_ALIAS Proxy (providerModels.ts)
- Add deleteProperty traps to all three lazy Proxies (PROVIDERS,
PROVIDER_MODELS, PROVIDER_ID_TO_ALIAS)
- Extract autoMigrateLegacyEncryptedConnections and getGheCopilotHosts
from providers.ts (1129→1036 lines, -93) into providers/migrations.ts
- Both functions re-exported via providers.ts for backward compat
File-size ratchet resolved: src/lib/db/providers.ts now 1036 lines.
* fix: resolve merge conflict markers in 3 route/test files
- model-combo-mappings/route.ts: kept upstream version (Zod pagination
via validateBody + isValidationFailure), restored missing return
statement for GET handler
- playground/presets/route.ts: kept stashed version details (satisfies
type-narrowing + inlined Response) — functionally identical
- error-sanitization.test.ts: matches upstream exactly (no diff)
Test verification: same 7 pre-existing failures confirmed on upstream
baseline (
|
||
|
backryun
|
0df0ff2ddb |
feat(grok-cli): align with official Grok Build client (#7358)
Rebuilt clean on release/v3.8.49 (branch forked from old main, ~drift). Resolved 2 real conflicts against the current tip: providerModelsConfig.ts keeps BOTH the tip's DashScope text-model helpers (#7882) and this PR's ProviderModelsHeaderContext type; OAuthModal.tsx takes this PR's DEVICE_CODE_PROVIDERS set (superset of the tip's hardcoded chain + grok-cli), dropping the now-dead qwen entry (#7866 removed qwen OAuth). Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
backryun
|
00677044be |
[Part 3/3] feat(qwen): add regional Alibaba and Qwen Cloud providers (#7882)
* feat(qwen): add Qwen3.8 Max Preview catalogs [Part 2/3] Rebuilt clean on release/v3.8.49 after Part 1 (#7866) squash-merged — applies only the Part-2 delta (Qwen Web / Qoder qwen3.8-max-preview registration + required-thinking allowlist + Qoder client rework) onto the current tip. No migration in this part (that was Part 1). Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> * feat(qwen): add regional Alibaba and Qwen Cloud providers [Part 3/3] Rebuilt clean on top of Part 2 (#7874) over the current release tip — applies only the Part-3 delta (alibaba Model Studio, Alibaba Token Plan, qwen-cloud, qwen-cloud-token-plan with region selector). No migration in this part. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
backryun
|
ccdbc89290 |
feat(qwen): add Qwen3.8 Max Preview catalogs [Part 2/3] (#7874)
Rebuilt clean on release/v3.8.49 after Part 1 (#7866) squash-merged — applies only the Part-2 delta (Qwen Web / Qoder qwen3.8-max-preview registration + required-thinking allowlist + Qoder client rework) onto the current tip. No migration in this part (that was Part 1). Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |