Workflow reconciliation (see previous commit) showed the 20261022
state variable really stores person identity under driver{i}ID /
driver{i}Phonenumber (x2), while the API get_info group keys
(sfzmhm{i}/sjhm{i}) have zero references in any workflow version -
the legacy group read always returned empty for workflow-produced data.
- registry: +4 keys (driver1/2ID, driver1/2Phonenumber) in
human1/human2 groups, SENSITIVE, documented as synonymous with
sfzmhm{i}/sjhm{i}; 24 -> 28 specs
- driver{i}License deliberately NOT registered: the sandbox reads
state.hphm{i} and only renames the output for confirmation prompts -
it is not a state key, set_info rejects it as unknown (workflow
never consumes it)
- intentional diff documented: acdhuman1/2 group output now includes
the driver keys (legacy FastGPT output did not) - fixes the legacy
'workflow person data unreadable by group' gap; synonym merging
(driver1ID vs sfzmhm1) deferred pending caller confirmation
- tests: registry size 28, driver keys present with sensitive level,
License alias excluded
Verified: 230 unit tests
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)
- 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
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.
- 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 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.
- 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.
- Updated documentation and API endpoint to include a new state code '0005' for handling cases where photo recognition fails consecutively, directing to human assistance.
- Ensured consistency between documentation and code for improved clarity in state management.
- Revised the formUpdate section to clarify the conditions under which structured updates are pushed.
- Added specific examples for accident vehicle count and cause of the incident to enhance understanding.
- Adjusted text_delta examples for improved clarity in response handling.
Eric Wang