Reconciled the field registry against workflow/20261022 (synced with
main@c7ca781) and historical versions 20250419-20261021:
- form six keys match the workflow form variable (bNJkeXot) and the
更新表单 whitelist semantics exactly
- acd business keys originate from the 20250419 extraction schema
(dropped by the workflow since 20251015, kept as the API contract)
- person group keys (xm1/sfzmwh1/sjwh1/csbw1...) exist in no workflow
version - they are the API server's own contract
- the form<->business key mapping is migration-new semantics bridging
both sides, fixed by bidirectional tests
Finding: workflow 20261022 state uses driver1ID/driver1License/
driver1Phonenumber naming, which never matched the API get_info group
keys - existing behavior read empty; recorded in the audit backlog to
confirm which naming live callers actually use
- fields_registry: FORM_TO_BUSINESS_KEY bidirectional mapping between
the graph's six form keys (has_injury...) and the acd business keys
(ywrysw...); bjrjs/ywmtc have no form source (set_info only);
business_patch_from_form maps graph diffs to whitelisted business keys
and filters internal/unknown keys
- app_service: chat injection now maps repository business keys back to
form keys; both complete() and stream() write back field diffs
(FormUpdate events captured in stream, closing the skeleton gap);
form keys never leak into the business repository
- docs/assignment6-compat.md: mapping table documented, stream write-back
backlog item resolved
- tests: mapping coverage, write-back mapping end-to-end, reverse
mapping injection (bjrjs/ywmtc excluded), stream FormUpdate write-back
Verified: 205 unit tests
- fields_registry: 24 business keys in acd/human1/human2 groups with
value_type, writable and SensitiveLevel metadata; strict bool/int
parsing (no bool('0') trap); INTERNAL_FIELD_KEYS protection list
- repository: SessionRepository protocol + InMemorySessionRepository
(idempotent delete; PostgreSQL swap-in is assignment 7)
- AccidentAppService: chat/set_info/get_info/delete_session share one
business state - chat injects latest repository fields into the graph
and writes back validated field diffs; set/get/delete make zero LLM
calls and zero helper conversations (includeInputInfo accepted but
unused); unknown get keys keep the '' JSON-empty-string contract,
unknown set keys are rejected by whitelist
- ChatInput.injected_fields neutral contract extension; LangGraphBackend
merges injected fields into graph input (set_info visible next chat)
- endpoints: thin layer - langgraph mode routes business state through
the app service (fastgpt mode keeps the legacy path); delete cleans
repository + graph checkpoint, idempotent
- tests: registry completeness (sfzmwh/sjwh/csbw included), app service
combos with LLM-call spy, HTTP acceptance flow (set -> get -> chat ->
groups -> delete -> no leak, idempotent re-delete)
- docs/assignment6-compat.md: behavior diff list vs FastGPT status quo
and the audit backlog (arbitrary set_info key usage, stream formUpdate
write-back, sensitive-field display boundary)
Verified: 200 unit tests (172 existing + 28 new)
- 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)
- merge main (fb9271e): collection prompt restructured (state-bound-to-action,
gatekeeper principle); fill_missing eval cases relaxed to semantic regexes
- prompts/collection.md regenerated; byte-identity test updated and passing
- rerun golden evals: collection_skip 11/12, time_confirmation 1/2
(inter-run variance; only single_no_inferred_count fails consistently -
model routes without asking vehicle count after time confirmation)
- plan: assignment status table, five landed architecture decisions
(propose-validate, context_schema DI, verbatim alignment, no LangGraph
Server/SDK with rationale, 2004 semantics), real-model eval results
(collection 12/12; photo_skip 0/4 and no_false 2/8 share the '对'
routing pattern), three open questions with next actions, code map
- 2004 task rewritten as plate-confirm with both paths whitelisted
- graduation requirement reworded: illegal transitions never committed
- README: current status section pointing to plan appendix
- prompts/collection.md: versioned collection system prompt extracted
from workflow node yQaBxfrWjbRr with source/version/porting notes
- llm.py: LLMService protocol; FakeLLMService (scripted, records
calls); OpenAILLMService (async, wait_for timeout with cancellation,
retry only on timeout/429/connection, errors normalized)
- collect.py: run_collect reference impl - one LLM call produces
state prefix + body, controlled repair (max 1 retry) for missing
prefix or illegal stage proposal, whitelist guard, CollectReplyError
without raw model content; dialogue history + confirmed fields
injected into prompt so the model skips known info (作业4-5)
- fields.py / clock.py: three-state field candidates (unknown/
candidate/confirmed), per-type validation (count not inferred from
description, future time rejected), injectable Clock
- graph.py: welcome node - first message returns fixed 1001 greeting
without LLM (mirrors workflow is_first_message -> Assigned Reply#3),
route empty stage to welcome
- endpoints/delete_session: backend switch - langgraph clears graph
checkpoint, fastgpt path unchanged
- config: AGENT_LLM_PROVIDER fake|openai with validation
- untrack .env (secrets), move template to root .env.example
Verified:
- pytest 103 passed; smoke turns 1/2/1
- Real LLM e2e: POST /chat multi-turn context works
- Golden eval collection_skip_known_info: 12/12 cases pass
- Golden eval no_false: 8/10 cases pass; 4 confirm/photo cases fail
at final step - model routes on short reply '对' (prompt-adherence
gap, photo/confirm stages are assignment 5 scope); recorded in
evals/results/20261020-144856
Known limits: field extraction from model reply not wired (stub);
photo/confirm nodes still scaffold; clarify counting is approximate.
Architecture (mirrors workflow/20261016 chatNode structure):
- events.py: client markers parsed to typed ClientEvent (sources
verified against workflow JSON); plain text like '拍好了' is not an event
- transitions.py: LEGAL_TRANSITIONS whitelist drafted from chatNode
prompts and Condition edges (16 entries, each with source_ref);
is_legal_transition rejects unlisted/terminal-violating moves
- graph.py: multi-node graph (collect/single_photo/dual_photo/...
matching workflow chatNodes), route_by_stage conditional edges,
_fake_llm_propose simulates LLM stage-code proposals (assignment 4
replaces with real LLM); code only keeps context bookkeeping
(no_reply_count) and validation
- state.py: expanded domain fields (pending_question, accident/
person fields, clarify/no-reply counts, turn_patch, state_version)
Key finding: 单车拍照#6/双车拍照#7 are browser_addon branches ending
at 0000, so 2005/2015 allow both 300x (direct) and 0000.
Verified: pytest 87 passed (24 transition/event tests newly green).
Known limit: stage proposals come from a fake LLM; per-stage scripts
and real LLM integration are assignments 4-5.
- src/backends/langgraph.py: LangGraphBackend implements ChatBackend;
complete() runs one graph turn per session (thread_id=sessionId) and
returns state-prefixed content; stream() emits the full state prefix
before body fragments (full-answer slicing, not yet real incremental
output - assignment 8)
- src/core/config.py: AGENT_BACKEND=fastgpt|langgraph, langgraph mode
no longer requires FastGPT credentials at startup
- src/core/fastgpt_client.py: lifespan builds the backend by switch
- test/backends/test_langgraph_backend.py: adapter acceptance tests
Verified:
- pytest: 48 passed
- AGENT_BACKEND=langgraph uvicorn: POST /chat -> 1002;
browser_addon -> browser_addon.1002; SSE = stage_code, text_delta,
single done
Known limit: stream slices a complete answer; no formUpdate deltas yet
(assignment 6).
- Introduced a comprehensive JSON configuration for a new workflow that includes user guidance, input handling, and AI chat integration.
- The workflow features nodes for system configuration, workflow start, and accident information collection, enhancing user interaction and data collection capabilities.
- Implemented various input types and configurations to support dynamic user interactions and improve overall workflow efficiency.
- Introduced a comprehensive prompt file detailing the role and operational guidelines for a traffic accident reporting AI.
- Established strict output formatting rules to ensure clarity in user interactions, including state management and response protocols.
- Emphasized safety prioritization and robust handling of user inputs, particularly regarding the assessment of potential injuries and the transition to human assistance.
- Changed the module name for form extraction to "更新表单" for clarity.
- Enhanced the extraction process to accommodate various output formats from nodes, ensuring compatibility with different structures.
- Improved handling of empty or invalid form updates, returning an empty object when necessary to maintain robustness.
- 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.
- Introduced new section for user inputs that confirm system availability, detailing specific phrases that indicate active engagement.
- Clarified response protocol for such inputs, ensuring the system maintains its current state and provides brief confirmations.
- Enhanced overall user experience by addressing common interaction scenarios in the accident reporting process.
- 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.
- Introduced a normalization function for client mode to default to "direct" when input is empty or None.
- Updated the clientMode field to use a new type with BeforeValidator for improved validation.
- Added a test to ensure empty client mode inputs correctly default to "direct".
- Introduced two new prompt files for traffic accident reporting, detailing the interaction protocol and state management for both single and dual vehicle scenarios.
- Established strict output formatting rules to ensure clarity and consistency in user interactions, including handling of user responses.
- Enhanced guidelines for safety prioritization and accurate information collection during the accident reporting process.
- Revised state codes to enhance clarity in user interactions, replacing previous codes with new ones indicating successful verification and transition to human assistance.
- Adjusted output messages to reflect the updated state management, ensuring a smoother user experience during the information confirmation phase.
- Improved guidelines for handling user responses, emphasizing accurate information collection and efficient transition to human support.
- Introduced a detailed prompt file for dual vehicle accident photo capture and verification, outlining the interaction protocol and state management.
- Established strict output formatting rules to ensure clarity and consistency in user interactions.
- Included comprehensive guidelines for handling various user responses, prioritizing accurate information collection during dual vehicle accident reporting.
- Introduced a detailed prompt file for a traffic accident reporting AI, outlining the interaction protocol and state management.
- Established strict output formatting rules to ensure clarity and consistency in user interactions.
- Included comprehensive guidelines for handling various user responses, prioritizing safety and accurate information collection during accident reporting.
- Introduced a comprehensive prompt file for a traffic accident reporting AI, detailing the interaction protocol and state management.
- Established strict output formatting rules to ensure clarity and consistency in user interactions.
- Included guidelines for handling various user responses, emphasizing safety and accurate information collection during accident reporting.
Eric Wang