zoushiyang/page-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
973 Commits 1 Branch 0 Tags
e7b93efda0d9f70b7ec245151f76ac77d11eded3
Commit Graph

41 Commits

Author SHA1 Message Date
Simon
90270fb76c fix(ts): InvokeErrorType separate confusing value/type space 2026-04-28 15:57:51 +08:00
Simon
dc41969503 feat(models): support gpt-5.4 and refresh recommendations 2026-04-27 21:40:19 +08:00
Simon
15f3af406c fix(llms): remove tool_choice for deepseek models 2026-04-27 20:32:53 +08:00
zzy-life
a7cc935453 feat(llms): add transformRequestBody hook and improve prompt assembly (#480) 
* feat(llms): add transformRequestBody hook and refine prompt handling

* docs(website): document transformRequestBody usage

* refactor(extension): keep function-valued config handling consistent in useAgent

* feat: simplify `transformRequestBody`

---------

Co-authored-by: Simon <10131203+gaomeng1900@users.noreply.github.com>
 2026-04-27 19:46:46 +08:00
Simon
66a85c0dd3 feat: option to disable named tool choice 2026-03-20 17:40:16 +08:00
Simon
fe82b11285 feat: AK optional 2026-03-19 19:50:05 +08:00
octo-patch
8ad4d19232 feat: add MiniMax model support with temperature clamping 
Add MiniMax (M2.5 / M2.5-highspeed) as a tested model provider:

- Add model-specific patch in utils.ts: clamp temperature to (0, 1]
  since MiniMax API rejects temperature=0, and remove unsupported
  parallel_tool_calls parameter
- Add MiniMax to the tested models list on the Models documentation page
- Add MiniMax configuration example alongside existing providers
 2026-03-15 23:42:30 +00:00
tsubasakong
eec601e6b2 fix(llms): avoid reasoning_effort for GPT-5.4 chat tools 2026-03-08 16:37:32 -07:00
Simon
53db2069ce feat: zod support v3/4 2026-03-05 19:13:18 +08:00
Simon
0dacbda9da chore: improve logging 2026-03-05 16:54:41 +08:00
Simon
68d68182e2 feat(website): drop hash-based router 2026-02-27 19:46:44 +08:00
Simon
b4377ed152 chore: remove unused env.d.ts file 2026-02-25 17:19:09 +08:00
Simon
b7be29d792 feat(core): enhance tollcall validation with better error reporting 2026-02-25 17:17:35 +08:00
Simon
22fe448d95 refactor: unify zod imports 2026-02-25 16:18:56 +08:00
Simon
49bdc70c78 chore: improve error logging 2026-02-25 16:13:39 +08:00
Simon
8cb57befb3 feat(model): disable thinking for Qwen model patch 2026-02-23 17:30:35 +08:00
Simon
dffcb53db9 feat!: Refine lifecycle hooks; fix abortSignal 
- add `stop` method. agent can be reused after stopped
- agent can not be reused after disposed
- extension DO NOT exposes `dispose` anymore. only `stop`.
- update panel for new `stop` method
- fix MultiPageAgent dispose event
- better handling abortSignal
 2026-02-13 17:57:12 +08:00
Simon
1fcf931685 feat(core): add a observe phase in a step; improve abortSignal 2026-02-10 22:20:42 +08:00
Simon
6f0ff1fd33 refactor: zod tree-shaking; better error handling in agent steps 2026-02-09 17:49:10 +08:00
Simon
8ea8ce9acd fix(llms): gpt-5-mini temperature 2026-02-06 17:19:06 +08:00
Simon
f6394a04b1 feat(core): add rawRequest in history for debug 2026-01-28 14:30:04 +08:00
Simon
dad837e173 fix: don't retry or show AbortError; remove reason from dispose; don't clean history in dispose 2026-01-22 20:19:51 +08:00
Simon
22516dec74 feat: unify InvokeError; add rawResponse to historical ErrorEvent 2026-01-20 20:16:34 +08:00
Simon
1ede1d9911 feat!: redo Panel; decouple Panel from Agent 
BREAKING CHANGES: Agent and Panel API Changes
 2026-01-17 23:14:26 +08:00
Simon
4f6249a252 feat!: require user to provide LLM api. do not fallback to demo LLM 
BREAKING CHANGE: LLM API will be required for agent constructor
 2026-01-14 18:49:23 +08:00
Simon
2f2bdb4697 fix: update Qwen patch condition for model name 2026-01-13 15:07:01 +08:00
Simon
3fa7c8b85a feat: improve qwen3 compatibility (#106) 
* feat: improve qwen3 compatibility

* fix: qwen

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2026-01-13 15:04:03 +08:00
Simon
35d1fd1166 chore: better erroring 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2026-01-13 14:16:51 +08:00
Simon
526cb4dbb3 chore: rename OpenAIClient; clean up old notes 2026-01-13 13:58:21 +08:00
Simon
6dc56c57c6 chore: rm legacy llm client 2026-01-13 13:56:30 +08:00
Simon
a3263fdd3a chore: rename OpenAICompatibleClient 2026-01-13 13:51:09 +08:00
Simon
14974c0257 feat!: mv brain from llms to agent; redo toolCall auto fixer 2026-01-13 13:49:19 +08:00
Simon
bfa6a5347e fix: rm maxTokens from api 2026-01-10 23:27:08 +08:00
Simon
66be1e56e3 fix: tool description lost 2025-12-24 19:28:59 +08:00
Simon
0fd4eaf9af chore: log network error for better debug 2025-12-24 19:06:35 +08:00
Simon
49af3a9c58 fix: illegal custom fetch 2025-12-24 19:00:43 +08:00
Simon
59fcfaa503 feat: add customFetch config 2025-12-24 16:42:31 +08:00
Simon
17befe4bab refactor: unify LLM configuration types 2025-12-23 17:37:09 +08:00
Simon
35db15460e feat: improve perf on newer models 2025-12-22 19:10:13 +08:00
Simon
635416f964 feat: implement @page-agent/llms 2025-12-22 16:29:19 +08:00
Simon
7c2d000e29 feat: create llms package and mv files 2025-12-22 16:12:34 +08:00