- 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history on the current clock; flags historical references without a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.
- Introduced a comprehensive document detailing the interaction interface design for the intelligent information collection robot.
- Updated version history with new features, including the addition of the clientMode parameter and its impact on output formatting.
- Enhanced clarity in the API request and response structures, including examples for better understanding of the interaction flow.
- Replaced direct FastGPT client usage with a backend-neutral chat interface, allowing for improved flexibility and maintainability.
- Introduced a new `ChatBackend` protocol and implemented `FastGPTBackend` to handle chat operations.
- Updated the chat endpoint to utilize the new backend structure, enhancing the handling of chat requests and responses.
- Added comprehensive tests to ensure compatibility and functionality of the new backend integration.
- Updated ANALYSIS_AUTH_TOKEN and APP_ID in the .env file for enhanced security and configuration.
- Added a comprehensive migration plan document for transitioning the LangGraph backend, detailing the background, scope, goals, and architectural decisions for the project.
Eric Wang