WildDragonLLC/9router
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1081 commits 3 branches 0 tags 14 MiB
Commit graph

8 commits

Author SHA1 Message Date
seakleang.nhak
86131b9ca4 feat(codex): support GPT-5.6 Max and Ultra overrides 
Add "ultra" reasoning level for Codex GPT-5.6 Sol and Terra, and expose
Max for Luna (Luna falls back Ultra to Max since it is not supported
upstream). Scoped to cx/ routes only; Kiro and generic OpenAI routing
unchanged.
 2026-08-05 11:39:59 +07:00
decolua
a6a41dfb3c Merge remote-tracking branch 'upstream/master' 
# Conflicts:
#	.gitignore
#	open-sse/handlers/chatCore.js
 2026-07-16 11:59:46 +07:00
luoyide
ba508f2506 fix(thinking): send explicit thinking:{type:adaptive} alongside output_config.effort 2026-07-16 11:17:08 +07:00
DOMANHDUC
7610f28f42 fix(gemini-cli): raise output floor for thinking and add validated toolConfig (#2486) 
Gemini CLI requests with small max_tokens spend the whole output budget on
thoughts after reasoning_effort maps to thinkingConfig, returning blank
content or finish=length. Raise maxOutputTokens floors per thinking level/
budget (clamped to caps.maxOutput). Also emit toolConfig
functionCallingConfig.mode=VALIDATED for Gemini CLI tool requests to avoid
MALFORMED_FUNCTION_CALL.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-10 11:32:11 +07:00
whale
8c068a1f5c fix(kimi): normalize reasoning_effort to backend enum (#2427) 
Map auto→high, minimal→low, xhigh→max and whitelist low/medium/high/max
so Kimi/kimchi SGLang backends no longer receive invalid effort values.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-07 11:56:39 +07:00
ntdung6868
3a866fe18d fix(reasoning): preserve effort through Codex translations 
Carry Claude reasoning_effort/reasoning into OpenAI Chat, map into
OpenAI Responses reasoning.effort, and keep request-level effort
(incl. xhigh) across tool-result turns instead of collapsing to high.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-26 12:06:35 +07:00
Mink Nguyen
c4f80d30d8 fix provider thinking compatibility 
- claude: handle DeepSeek thinking blocks defensively, unsigned placeholder; fix kept-vs-seen thinking detection
- gemini: clamp unsupported max/xhigh thinking levels to high
- testUtils: probe Cloud Code Assist for gemini-cli/antigravity with 401 refresh retry
- tests: add translator regression coverage

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-26 10:12:48 +07:00
decolua
b282f05549 Refactor 2026-06-15 18:18:04 +07:00