3 Commits

Include renames

Author	SHA1	Message	Date
Eric Wang	e72d9c9bc0	feat(agent): align with workflow@20261022 - turn_context messages and prompt tails ... - merge main (b0ff2e0..c7ca781): workflow/20261022 moves dynamic context out of fixed prompts - collection/extraction prompts carry no inline vars; reference time and current form travel in the user message <turn_context> block; photo/confirm data kept at prompt tails - prompts: all 8 files regenerated from 20261022 (byte-identity tests point at the new export) - collect: user message = <turn_context>(本轮参考时间) + <user_input>; extraction message adds 当前表单; single trusted clock per turn threads through reply/extraction/repair - photo: raw input only (20261022 photo nodes use system_text, no wrapper) - workflow fake llm: unwraps <user_input> before event parsing - fields: accident_time normalized to extraction format (YYYY年M月D日H点m分, strip zero padding) - fixes form assertion mismatch with padded output - evals/run.py: trust_env=False - bypass Windows system proxy (registry proxy at 192.168.0.4:7897 was intercepting localhost and returning 503) - verified: 172 unit tests; ALL golden suites pass on real model (46/46): collection_skip 12/12, photo_skip 4/4, no_false 2/2, button_guidance 12/12, non_motor_vehicle 14/14, time_confirmation 2/2	2026-10-22 12:28:24 +08:00
Eric Wang	9e28f69b3c	feat(agent): trusted time evidence and collection prompt optimization ... - time_context.py: server-side observation clocks for relative-time evidence (anti client-forgery); resolves X分钟前/小时前 against the observation timestamp of the turn that produced them, never re-basing history on the current clock; flags historical references without a reliable baseline - state: dialogue_timestamps keyed by dialogue message index, persisted with checkpoint; welcome seeds index 0 - collect: single clock per turn shared by reply/extraction/repair; time_evidence injected into runtime context; reply_validator hook rejects time claims lacking evidence (one shared repair budget); model still interprets facts and chooses actions - prompts: collection prompt restructured (shorter, state-bound-to-action table, gatekeeper principle, time source rules); extraction prompt aligned; workflow@20261021 json updated to match - evals: prompt_probes / prompt_compare / time_boundary probe scripts (supplementary checks, original cases untouched) - docs: collection-prompt-optimization.md (method + baselines), time-boundary-fix.md (problem, design, verification) - gitignore: editor artifact dirs (.agents/.claude/.vscode, skills-lock) Verified: 171 unit tests pass (16 new time-context tests)	2026-10-22 09:41:32 +08:00
Eric Wang	74db6be385	feat(agent): form pipeline + collection prompt workflow@20261021 ... - merge main: workflow/20261021 (collection prompt adds step-5 mandatory time readback-confirm before routing; non-motor/0003 branch rework; accident_cause unified schema), updated eval suites (photo_skip/ button_guidance rewritten, no_false trimmed to asr, new non_motor_vehicle + time_confirmation with form/reply assertions), runner gains form/formMatches/replyMatches expectations - prompts/collection.md regenerated from 20261021; extraction prompt archived (contentExtract description, 6-key whitelist) - collect: extraction call per turn (extraction.md + current time/form injected), merge follows 更新表单 semantics (meaningful values only, number/string equality, diff -> turn_patch); accident_fields now uses external form keys - backend: form_update flows to ChatResult and SSE formUpdate event (stream emits prefix, FormUpdate, body) - fields: FORM_FIELDS whitelist with strict type validation - verified: 155 unit tests; golden evals on real model - photo_skip 4/4, no_false 2/2, photo_button_guidance 12/12, non_motor_vehicle 14/14, collection_skip 10/12, time_confirmation 1/2; remaining 3 failures are model sequence/literal-template adherence, recorded in plan appendix	2026-10-21 17:10:33 +08:00