Commit Graph

4591 Commits

Author SHA1 Message Date
Eric Chan
dc94613e6a fix(auth): allow bootstrap without password (#2048)
Integrated into release/v3.8.0
2026-05-08 17:34:51 -03:00
Paijo
56ccf4f8dd fix: clean up proxy page redundancy and fix 1proxy sync empty body error (#2052)
Integrated into release/v3.8.0
2026-05-08 17:34:47 -03:00
diegosouzapw
ad966b15f2 fix(core): restore Claude Code adaptive thinking defaults and resolve audio transcription CORS regression
- Restored default adaptive thinking injection for non-Haiku Claude Code models when explicit client headers are omitted.
- Updated Claude OAuth unit tests to accurately account for dynamic cliUserID property injection in mapped credentials.
- Fixed module resolution regression in audio transcription handler caused by missing getCorsOrigin utility.
2026-05-08 16:37:36 -03:00
Jan Leon
640ed6d2bc feat: add STREAM_READINESS_TIMEOUT_MS and integrate into chat handling 2026-05-08 19:28:40 +00:00
Jan Leon
43553646ed feat: add fallbackDelayMs to combo configuration and related settings 2026-05-08 19:21:34 +00:00
diegosouzapw
4331e129ab chore(release): v3.8.0 — optimize cache control preservation and align Antigravity provider 2026-05-08 16:19:04 -03:00
diegosouzapw
ef23e702af docs: update changelog for issue 1973 resolution 2026-05-08 15:58:04 -03:00
diegosouzapw
80d52d9a77 fix(db): preserve legacy SQLite database path on Windows to prevent data loss (#1973) 2026-05-08 15:58:04 -03:00
guanbear
fc84e5a34a Fix bare GPT-5.5 routing for Codex-only installations (#2054)
Integrated into release/v3.8.0
2026-05-08 15:57:52 -03:00
Paijo
962faa84e9 feat(chat): dynamic tool limit detection with proactive truncation (#2061)
Integrated into release/v3.8.0
2026-05-08 15:57:46 -03:00
ivan-mezentsev
afdebbc793 fix(sse): use Gemini schema for Antigravity Claude (#2063)
Integrated into release/v3.8.0
2026-05-08 15:57:41 -03:00
dependabot[bot]
9875b40420 deps: bump hono from 4.12.14 to 4.12.18 (#2065)
Integrated into release/v3.8.0
2026-05-08 15:57:37 -03:00
Jan Leon
23ec2f9fa8 feat: add service tier column to usage_history and update migration checks 2026-05-08 16:58:58 +00:00
Jan Leon
3662f90095 feat: enhance chat handling with cached settings and deduplicate quota fetches in reset-aware strategy 2026-05-08 16:57:25 +00:00
Jan Leon
1e80366b42 feat: add service tier breakdown component and handle missing docs directory 2026-05-08 16:47:39 +00:00
Jan Leon
9d3eb480a2 feat(usage): account for codex fast tier analytics 2026-05-08 11:16:14 +00:00
Jan Leon
1929b44235 feat: implement global Codex fast service tier functionality and related settings 2026-05-08 08:58:38 +00:00
ivan_yakimkin
f09c2d6b87 refactor: address PR review feedback 2026-05-08 11:53:46 +03:00
ivan_yakimkin
16febc0510 fix(antigravity): add duplex half for streaming bodies 2026-05-08 11:32:07 +03:00
ivan_yakimkin
cababfe58a fix(antigravity): align identity protocol and behavior with official AM 2026-05-08 11:20:32 +03:00
ivan_yakimkin
eeb836d62a fix(antigravity): don't inject default maxOutputTokens when client omits max_tokens
Real Antigravity client does not send maxOutputTokens when the user
hasn't specified it — the Cloud Code server decides the output limit.
OmniRoute was incorrectly injecting a capped default from model specs,
which caused thinking models to return empty content with low limits.
2026-05-08 11:05:26 +03:00
ivan_yakimkin
31da6a09a1 debug: add AG_REQUEST_HEADERS and AG_REQUEST_ENVELOPE debug logs
Dumps outgoing headers (with masked Authorization) and envelope
structure (fieldOrder, project, requestId, userAgent, requestType,
enabledCreditTypes, sessionId, generationConfig) at debug level
for production verification of identity overhaul.
2026-05-08 10:39:43 +03:00
Gi99lin
e7753698c9 ci: update build-fork workflow to build from main branch 2026-05-07 18:43:17 +03:00
ivan_yakimkin
f1af90e97e feat(antigravity): overhaul identity, fingerprinting & envelope format
- Add centralized antigravityIdentity service (sessionId, machineId, requestId)
- Switch User-Agent to Electron/Chrome desktop format
- Reorder upstream URLs: sandbox first, production last
- Add runtime headers: x-client-name, x-client-version, x-machine-id, x-vscode-sessionid, x-goog-user-project
- Add 403 retry without x-goog-user-project header
- Add generation defaults (topK=40, topP=1.0, maxOutputTokens guard)
- Strip cache_control from Claude requests recursively
- Enterprise/consumer routing via userAgent field (jetski vs antigravity)
- Update envelope field order and add enabledCreditTypes
- MITM proxy: support multiple target hosts
- Version: semver comparison with pickNewestVersion(), bump fallback to 4.1.33
- Update all affected tests
2026-05-07 18:14:55 +03:00
diegosouzapw
321f6070ac docs: update CHANGELOG.md for v3.8.0 (#2006, #2018, #2029) 2026-05-07 09:15:49 -03:00
diegosouzapw
57d37869c9 fix: add Google Gemini embeddings compatibility via OpenAI-compatible endpoint mapping (#2006) 2026-05-07 09:15:43 -03:00
diegosouzapw
0e844570dc fix: dynamically filter bare model auto-resolution by active provider connections to prevent dead-routing (#2029) 2026-05-07 09:15:37 -03:00
diegosouzapw
7330947ce2 fix: resolve model alias persistence double stringification preventing UI updates (#2018) 2026-05-07 09:15:32 -03:00
diegosouzapw
72d0e1ff1b chore: resolve merge conflicts in Dockerfile 2026-05-07 08:59:02 -03:00
diegosouzapw
61fb2ac36d chore: resolve merge conflicts in claude.ts 2026-05-07 08:57:30 -03:00
diegosouzapw
a430381434 chore: apply review suggestions and missing layers 2026-05-07 08:50:39 -03:00
rodrigogbbr-stack
4cd7ee1134 fix: allow Unicode letters in API key name validation (#1996)
Integrated into release/v3.8.0
2026-05-07 08:49:38 -03:00
Nathan Pham
40cc0d116a fix(docker): include OpenAPI spec in runtime image (#2007)
Integrated into release/v3.8.0
2026-05-07 08:49:29 -03:00
Alexander Averyanov
e9d96fa3ff Fix API key identity in usage analytics (#2008)
Integrated into release/v3.8.0
2026-05-07 08:49:23 -03:00
Paijo
7214efa86e fix: add fuzzy auto-combo routing for 'auto/*' model prefix (#2010)
Integrated into release/v3.8.0
2026-05-07 08:49:16 -03:00
Tentoxa
eb2579ec0a feat(sse): refresh Claude OAuth wire image to claude-cli/2.1.131 (#2011)
Integrated into release/v3.8.0
2026-05-07 08:49:12 -03:00
Sergey Morozov
d96f0c2fda fix(codex): expose native model ids in catalog (#2012)
Integrated into release/v3.8.0
2026-05-07 08:49:08 -03:00
xssdem
a13d2f9aff fix(chatgpt-web): plumb proxy through to native tls-client (#2022) (#2023)
Integrated into release/v3.8.0
2026-05-07 08:49:00 -03:00
ipanghu
312f2f3aeb Update claude md and update glm-cn max context to 200k (#2027)
Integrated into release/v3.8.0
2026-05-07 08:48:56 -03:00
Hernan Javier Ardila Sanchez
84955146d0 fix(catalog): auto-calculate combo context_length from target model limits (#2030)
Integrated into release/v3.8.0
2026-05-07 08:48:52 -03:00
wucm667
a7e00fbe4a docs(env): add GITLAB_DUO_OAUTH_CLIENT_ID to .env.example (#2031)
Integrated into release/v3.8.0
2026-05-07 08:48:48 -03:00
backryun
b4ba8379de chore: Remove Deprecated Models (#2033)
Integrated into release/v3.8.0
2026-05-07 08:48:43 -03:00
Automation
d1ff4a6905 chore(deps): resolve npm audit moderate vulnerability (hono) 2026-05-07 11:09:05 +02:00
Automation
3dc7542eca fix(catalog): auto-calculate combo context_length from target model limits
Fixes the root cause where OpenCode falls back to a ~4000 token limit
for combos because no context_length is exposed in /v1/models.

Previously combos only used context_length when set manually on the
combo record. Now, when unset, the catalog computes the effective
limit as the MINIMUM of its targets' individual token limits via
getTokenLimit()/parseModel(). Manual values still override.

Files changed:
- src/app/api/v1/models/catalog.ts  (+30 lines, auto-calc)
- tests/unit/models-catalog-route.test.ts  (+2 tests)

Tests pass: 25/25
2026-05-07 10:54:41 +02:00
Muhammad Tamir
c5dded8992 fix(mitm): prevent stub from loading at runtime via bypass module
Turbopack resolveAlias (@/mitm/manager → manager.stub.ts) was designed
for build-time safety but Next.js applies aliases to ALL imports —
including dynamic ones. This caused await import("@/mitm/manager") at
runtime to load the stub, which silently returned fake {running: true}
without spawning the MITM proxy. The UI showed "MITM proxy started"
but nothing was actually running.

Fix introduces a two-path design:
- @/mitm/manager        → stub (build-time, safe for Turbopack)
- @/mitm/manager.runtime → real manager (runtime, bypasses alias)

Route handlers now dynamic-import from manager.runtime, which
re-exports from ./manager and does NOT match the alias pattern.

Additional fixes:
- Make stub throw explicit errors at runtime so misconfiguration is
  immediately visible instead of silently faking success
- Add server.cjs to outputFileTracingIncludes (NFT trace) and Dockerfile
  COPY so the MITM server binary exists in standalone/Docker output
2026-05-07 10:36:11 +07:00
Jan Leon
aace2fcbd0 feat: enhance GLM quota handling and add new quota labels for Z.AI 2026-05-06 23:02:08 +00:00
Jan Leon
5c67df5508 Merge pull request #4 from JxnLexn/feat/reset-aware-routing
feat(combos): add reset-aware routing strategy
2026-05-06 23:59:42 +02:00
Jan Leon
e0613e6600 fix: address reset-aware follow-up feedback 2026-05-06 21:47:30 +00:00
Jan Leon
269186b9d1 fix: address reset-aware routing review feedback 2026-05-06 21:09:32 +00:00
Jan Leon
76326c6497 fix: generalize reset-aware quota routing 2026-05-06 20:34:43 +00:00