- Config.llm_profiles: LLM_PROVIDERS declares names, each group defined by
LLM_<NAME>_BASE_URL/_API_KEY/_MODEL (required) and optional _TIMEOUT_SECONDS/
_MAX_RETRIES/_TEMPERATURE/_EXTRA_BODY; JSON-dict form of LLM_PROVIDERS also
supported. LLM_PROVIDER selects the active group at runtime; empty/fake =
offline scripted model
- removed fixed openai/kimi groups (AGENT_LLM_PROVIDER, KIMI_LLM_*)
- validate(): incomplete groups and unknown LLM_PROVIDER fail fast with
the configured-name list
- OpenAILLMService: http client trust_env from LLM_HTTP_TRUST_ENV (default
False - local gateways must bypass the Windows system proxy)
- build_llm_service(provider): explicit name or LLM_PROVIDER default
- .env/.env.example: deepseek + kimi groups side by side, switch by
LLM_PROVIDER=kimi (thinking off via EXTRA_BODY reasoning_effort=none)
- eval probe scripts updated to the new config interface
Verified: 172 unit tests; live calls succeed on both providers
(deepseek 28s, kimi 6.6s, both emitting valid <state> prefixes)
- 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
- 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history on the current clock; flags historical references without a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)
- Updated prompts to enhance clarity and consistency in user interactions, particularly focusing on safety prioritization and accurate information collection.
- Introduced new YAML evaluation cases to test various user input scenarios, ensuring robust handling of short, ambiguous, or irrelevant responses.
- Enhanced guidelines for transitioning to human assistance, emphasizing strict conditions for triggering state changes based on user responses.
- Updated the evaluation runner to support live dialogue printing and transcript saving in both Markdown and JSON formats.
- Introduced new data classes for managing transcripts and their components, improving structure and readability.
- Modified existing YAML case files to align with the new direct client mode and updated stage codes.
- Added new test cases for the direct client mode, ensuring comprehensive coverage of user interactions.
Eric Wang