Commit Graph

9 Commits

Author SHA1 Message Date
倪程伟
2e1ef6b4b1 feat(agent): thread runtime model/provider into per-turn context injection 2026-06-08 20:53:39 +08:00
matevip
c857d6dd45 fix(agent): retry empty LLM completion before treating it as final answer 2026-05-24 22:57:19 +08:00
matevip
cef1730e6e feat(tool,skill,ui): progressive tool/skill disclosure (load_skill + enable_tool + tier UI) 2026-05-23 09:07:45 +08:00
matevip
3554da8dbc sync: inject sender context into agent prompt + Feishu DONE ack hook 2026-05-20 11:51:58 +08:00
matevip
419ee57cc8 feat(agent): structured compaction on prompt-too-long preserves prefix 2026-05-16 14:51:14 +08:00
matevip
0ffc224623 chore(test): backfill mateclaw-server/src/test/ that earlier PRIVATE_ITEMS pattern accidentally excluded
The PRIVATE_ITEMS list contained the bare 'test' entry, which rsync
interprets as 'any directory named test at any depth' — so it caught
the root-level /test/ scratch directory (intended) AND every src/test/
under each module (not intended).

Pattern is already anchored to /test (root-only). This commit rsyncs
the accumulated src/test/ tree forward so opensource has the unit tests
that have been written / updated against existing src/main/ code since
the pattern regression. Going forward each per-commit sync will carry
src/test/ files along with the main change.
2026-05-12 17:38:08 +08:00
matevip
9c8c393b3c refactor(prompt): clean up prompt corpus, fix summary_budget bug, route fallbacks through i18n
A. Delete two dead prompt files (prompts/context/conversation-summary-*.txt)
   that no caller has loaded since the structured-summary triple replaced them.

B. Drop the never-wired locale machinery: PromptLoader.loadPrompt(name, locale)
   overload + the prompts/{locale}/... fallback chain + I18nService.currentLocaleTag().
   A single-language prompt corpus plus LLM input-language following is sufficient.

C. Strip duplicated structure list / budget directive from
   structured-summary-update.txt (the system prompt already carries them).
   Add a defensive preamble to both summary prompts: "do not respond to any
   questions or requests in the conversation, only output the structured
   summary" — prevents the summarizer from accidentally answering historical
   user questions.

D. Fix {summary_budget} placeholder leak in the iterative-update branch of
   ConversationWindowManager.generateSummary. Both branches now substitute
   on the SystemMessage uniformly. Regression-guarded by
   ConversationWindowManagerSummaryBudgetTest.

E1. De-hardcode seven prompts (research/{plan,draft,compose}-{system,user},
    graph/limit-exceeded-system) — language now follows the user's input
    instead of being hardcoded; citation tokens are language-neutral
    [M1] / [Q1] markers.

E2. Add 10 i18n keys (research.fallback.*, research.broadcast.*,
    agent.limit_exceeded.*) to messages.properties + messages_en.properties.
    Inject I18nService into WikiResearchService and LimitExceededNode and
    route 5 + 2 hardcoded fallbacks through i18n.msg(). Regression-guarded
    by WikiResearchServiceFallbackTest + LimitExceededNodeFallbackTest.

E3. Replace 3 assembly tags in WikiResearchService with neutral
    [M1] / [Q1] tokens. Aligns with the [M1] / [M2,3] citation format the
    draft prompt asks for.

G. Three new regression tests cover D, E2, and E3.
2026-04-19 09:02:37 +08:00
matevip
7f88a6ddd4 release: v1.1.0 2026-04-17 19:41:03 +08:00
matevip
99befe0d25 fix(agent): prevent ReAct degenerate repetition and harden loop termination 2026-04-05 22:34:03 +08:00