Commit Graph

1620 Commits

Author SHA1 Message Date
Luis Pater
913f4a9c5f test: fix executor tests after helpers refactor 2026-04-02 11:12:30 +08:00
Luis Pater
25d1c18a3f fix: scope experimental cch signing to billing header 2026-04-02 11:03:11 +08:00
Luis Pater
d09dd4d0b2 Merge commit '15c2f274ea690c9a7c9db22f9f454af869db5375' into dev 2026-04-02 10:59:54 +08:00
Michael
8435c3d7be feat(tui): show time in usage details 2026-04-02 10:35:13 +08:00
Luis Pater
b05f575e9b Merge pull request #2444 from 0oAstro/fix/codex-nonstream-finish-reason-tool-calls
fix(codex): set finish_reason to "tool_calls" in non-streaming response when tool calls are present
2026-04-02 10:01:25 +08:00
Aikins Laryea
f5e9f01811 test(amp): update tests to expect thinking blocks to pass through during streaming 2026-04-01 20:35:23 +00:00
Aikins Laryea
ff7dbb5867 test(amp): update tests to expect thinking blocks to pass through during streaming 2026-04-01 20:21:39 +00:00
Aikins Laryea
e34b2b4f1d fix(gemini): clean tool schemas and eager_input_streaming
delegate schema sanitization to util.CleanJSONSchemaForGemini and drop the top-level eager_input_streaming key to prevent validation errors when sending claude tools to the gemini api
2026-04-01 19:49:38 +00:00
edlsh
15c2f274ea fix: preserve cloak config defaults when mode omitted 2026-04-01 13:20:11 -04:00
edlsh
37249339ac feat: add opt-in experimental Claude cch signing 2026-04-01 13:03:17 -04:00
Luis Pater
105a21548f fix(codex): centralize session management with global store and add tests for executor session lifecycle 2026-04-01 13:17:10 +08:00
Luis Pater
ca11b236a7 refactor(runtime, openai): simplify header management and remove redundant websocket logging logic 2026-04-01 11:57:31 +08:00
Luis Pater
330e12d3c2 fix(codex): conditionally set Session_id header for Mac OS user agents and clean up redundant logic 2026-04-01 11:11:45 +08:00
Luis Pater
b468ca79c3 Merge branch 'dev' of github.com:router-for-me/CLIProxyAPI into dev 2026-04-01 03:09:03 +08:00
Luis Pater
d2c7e4e96a refactor(runtime): move executor utilities to helps package and update references 2026-04-01 03:08:20 +08:00
Luis Pater
1c7003ff68 Merge pull request #2452 from Lucaszmv/fix-qwen-cli-v0.13.2
fix(qwen): update CLI simulation to v0.13.2 and adjust header casing
2026-04-01 02:44:27 +08:00
Lucaszmv
1b44364e78 fix(qwen): update CLI simulation to v0.13.2 2026-03-31 15:19:07 -03:00
0oAstro
ec77f4a4f5 fix(codex): set finish_reason to tool_calls in non-streaming response when tool calls are present 2026-03-31 14:12:15 +05:30
Luis Pater
51fd58d74f fix(codex): use normalizeCodexInstructions to set default instructions 2026-03-31 12:16:57 +08:00
Luis Pater
faae9c2f7c Merge pull request #2422 from MonsterQiu/fix/codex-compact-instructions
fix(codex): add default instructions for /responses/compact
2026-03-31 12:14:20 +08:00
Luis Pater
bc3a6e4646 Merge pull request #2434 from MonsterQiu/fix/codex-responses-null-instructions
fix(codex): normalize null instructions for /responses requests
2026-03-31 12:01:21 +08:00
Luis Pater
16231947e7 Merge pull request #2426 from xixiwenxuanhe/feature/antigravity-credits
feat(antigravity): add AI credits quota fallback
2026-03-31 10:51:40 +08:00
MonsterQiu
39b9a38fbc fix(codex): normalize null instructions across responses paths 2026-03-31 10:32:39 +08:00
MonsterQiu
bd855abec9 fix(codex): normalize null instructions for responses requests 2026-03-31 10:29:02 +08:00
xixiwenxuanhe
a0bf33eca6 fix(antigravity): preserve fallback and honor config gate 2026-03-31 00:14:05 +08:00
xixiwenxuanhe
88dd9c715d feat(antigravity): add AI credits quota fallback 2026-03-30 23:58:12 +08:00
MonsterQiu
d3b94c9241 fix(codex): normalize null instructions for compact requests 2026-03-30 22:58:05 +08:00
MonsterQiu
d11936f292 fix(codex): add default instructions for /responses/compact 2026-03-30 22:44:46 +08:00
CharTyr
279cbbbb8a fix(amp): don't suppress thinking blocks in streaming mode
Reverts the streaming thinking suppression introduced in b15453c.
rewriteStreamEvent should only inject signatures and rewrite model
names — suppressing thinking blocks in streaming mode breaks SSE
index alignment and causes the Amp TUI to render empty responses
on the second message onward (especially with model-mapped
non-Claude providers like GPT-5.4).

Non-streaming responses still suppress thinking when tool_use is
present via rewriteModelInResponse.
2026-03-30 20:09:32 +08:00
sususu98
25feceb783 fix(antigravity): reorder model parts to prevent tool_use↔tool_result pairing breakage
When a Claude assistant message contains [text, tool_use, text], the
Antigravity API internally splits the model message at functionCall
boundaries, creating an extra assistant turn between tool_use and the
following tool_result. Claude then rejects with:

  tool_use ids were found without tool_result blocks immediately after

Fix: extend the existing 2-way part reordering (thinking-first) to a
3-way partition: thinking → regular → functionCall. This ensures
functionCall parts are always last, so Antigravity's split cannot
insert an extra assistant turn before the user's tool_result.

Fixes #989
2026-03-30 15:09:33 +08:00
CharTyr
b15453c369 fix(amp): address PR review - stream thinking suppression, SSE detection, test init
- Call suppressAmpThinking in rewriteStreamEvent for streaming path
- Handle nil return from suppressAmpThinking to skip suppressed events
- Narrow looksLikeSSEChunk to line-prefix detection (HasPrefix vs Contains)
- Initialize suppressedContentBlock map in test
2026-03-30 00:42:04 -04:00
CharTyr
04ba8c8bc3 feat(amp): sanitize signatures and handle stream suppression for Amp compatibility 2026-03-29 22:23:18 -04:00
Luis Pater
13aa5b3375 Revert "fix(codex): restore prompt cache continuity for Codex requests" 2026-03-29 22:18:14 +08:00
Luis Pater
1587ff5e74 Merge pull request #2389 from router-for-me/claude
fix(claude): add default max_tokens for models
2026-03-29 13:03:20 +08:00
hkfires
f033d3a6df fix(claude): enhance ensureModelMaxTokens to use registered max_completion_tokens and fallback to default 2026-03-29 13:00:43 +08:00
hkfires
145e0e0b5d fix(claude): add default max_tokens for models 2026-03-29 12:46:00 +08:00
Ravi Tharuma
5fc2bd393e fix: retain codex thinking signature until item done 2026-03-28 14:41:25 +01:00
Luis Pater
55271403fb Merge pull request #2374 from VooDisss/codex-cache-clean
fix(codex): restore prompt cache continuity for Codex requests
2026-03-28 21:16:51 +08:00
Ravi Tharuma
66eb12294a fix: clear stale thinking signature when no block is open 2026-03-28 14:08:31 +01:00
Ravi Tharuma
73b22ec29b fix: omit empty signature field from thinking blocks
Emit signature only when non-empty in both streaming content_block_start
and non-streaming thinking blocks. Avoids turning 'missing signature'
into 'empty/invalid signature' which Claude clients may reject.
2026-03-28 14:08:31 +01:00
Ravi Tharuma
c31ae2f3b5 fix: retain previously captured thinking signature on new summary part 2026-03-28 14:08:31 +01:00
Ravi Tharuma
76b53d6b5b fix: finalize pending thinking block before next summary part 2026-03-28 14:08:31 +01:00
Ravi Tharuma
a34dfed378 fix: preserve Claude thinking signatures in Codex translator 2026-03-28 14:08:31 +01:00
Luis Pater
b9b127a7ea Merge pull request #2347 from edlsh/fix/codex-strip-stream-options
fix(codex): strip stream_options from Responses API requests
2026-03-28 21:03:01 +08:00
Luis Pater
2741e7b7b3 Merge pull request #2346 from pjpjq/codex/fix-codex-capacity-retry
fix(codex): Treat Codex capacity errors as retryable
2026-03-28 21:00:50 +08:00
Luis Pater
779e6c2d2f Merge pull request #2231 from 7RPH/fix/responses-stream-multi-tool-calls
fix: preserve separate streamed tool calls in Responses API
2026-03-28 20:53:19 +08:00
Luis Pater
10b824fcac fix(security): validate auth file names to prevent unsafe input 2026-03-28 04:48:23 +08:00
VooDisss
e5d3541b5a refactor(codex): remove stale affinity cleanup leftovers
Drop the last affinity-related executor artifacts so the PR stays focused on the minimal Codex continuity fix set: stable prompt cache identity, stable session_id, and the executor-only behavior that was validated to restore cache reads.
2026-03-27 20:40:26 +02:00
VooDisss
79755e76ea refactor(pr): remove forbidden translator changes
Drop the chat-completions translator edits from this PR so the branch complies with the repository policy that forbids pull-request changes under internal/translator. The remaining PR stays focused on the executor-level Codex continuity fix that was validated to restore cache reuse.
2026-03-27 19:34:13 +02:00
VooDisss
26eca8b6ba fix(codex): preserve continuity and safe affinity fallback
Restore Claude continuity after the continuity refactor, keep auth-affinity keys out of upstream Codex session identifiers, and only persist affinity after successful execution so retries can still rotate to healthy credentials when the first auth fails.
2026-03-27 18:27:33 +02:00