yf176 commited on
Commit
2df5565
·
1 Parent(s): 2fd6704

docs: record typed trend verification

Browse files
Files changed (1) hide show
  1. docs/V8.0_IMPLEMENTATION_PLAN.md +7 -0
docs/V8.0_IMPLEMENTATION_PLAN.md CHANGED
@@ -238,6 +238,12 @@ and an explicit missing-input case. Keep existing reasoning duties intact.
238
  coordinator integration and baseline delta comparison are verified.
239
  - [ ] M03 TrendAnalyst: perform LLM technical interpretation from valid typed
240
  prices/indicators and publish cited trend records with explicit data gaps.
 
 
 
 
 
 
241
  - [ ] M04 SentimentAnalyst: perform LLM sentiment interpretation for GENERAL
242
  scope; distinguish unscored or thin news from genuinely neutral evidence.
243
  - [ ] M05 MarketEventWatcher: organize DataFetcher evidence and compare prior
@@ -391,3 +397,4 @@ actual migrated runtime or live verification.
391
  | R03b | `487287b` | `tests/test_dependency_executor.py` plus routing, run-record, and complete typed-contract regressions: each ready batch captures completed dependency records before scheduling; sibling runners cannot mutate another activation's snapshot; legacy controlled runners remain compatible; capture failure is attributed to the agent and blocks only its dependents. | Passed; 272 tests, 1 Windows symlink test skipped | The coordinator does not yet provide `PublishedInputResolver` or concrete input construction to this hook. Product runtime integration remains R03/R02/M01-M19. |
392
  | M01a | `70f220c`, `e1c1f66` | `tests/test_market_data_normalizer.py`, `tests/test_datafetcher_typed.py`, existing Finnhub tests, artifact publication/input resolution, and the full typed-contract regression set: the existing primary/fallback fetch returns without legacy writes for V8; actual OHLCV source is retained; invalid/missing values remain excluded, null, or explicitly unavailable; typed inputs, per-ticker JSON/Markdown, and the manifest publish through the ACL. | Passed; 284 tests, 1 Windows symlink test skipped | Controlled providers only; no live credentials or calls. The legacy handler remains active and the coordinator does not yet invoke `execute_typed`, so M01 and product readiness remain open. |
393
  | M02a | `50689bc` | `tests/test_options_typed.py`, options contracts, existing options-flow behavior, artifact publication/input resolution, and the expanded typed regression set: the existing bounded provider publishes sampled contracts, known-only totals, exact volume/OI/IV candidate criteria, unsupported provider capabilities, immutable JSON/Markdown, and explicit unavailable evidence for returned or raised provider failures. | Passed; 227 tests, 1 Windows symlink test skipped | Controlled provider only; no live provider call. Candidate heuristics remain non-directional and `unusual_flows` stays empty because the current provider lacks trade-side, sweep/block, opening/closing, premium, and validated-classifier evidence. Baseline comparison and coordinator activation remain M02/runtime work. |
 
 
238
  coordinator integration and baseline delta comparison are verified.
239
  - [ ] M03 TrendAnalyst: perform LLM technical interpretation from valid typed
240
  prices/indicators and publish cited trend records with explicit data gaps.
241
+ - [x] M03a Add typed execution to the existing TrendAnalyst class. Use the
242
+ registered structured LLM prompt and payload, verify citations against frozen
243
+ current and baseline inputs, preserve source quality issues, compare approved
244
+ prior trend context in delta mode, and publish explicit unavailable analysis
245
+ without calling the LLM when no valid OHLCV evidence exists. Keep M03 open
246
+ until coordinator, cost/trace, and live configured-LLM integration are verified.
247
  - [ ] M04 SentimentAnalyst: perform LLM sentiment interpretation for GENERAL
248
  scope; distinguish unscored or thin news from genuinely neutral evidence.
249
  - [ ] M05 MarketEventWatcher: organize DataFetcher evidence and compare prior
 
397
  | R03b | `487287b` | `tests/test_dependency_executor.py` plus routing, run-record, and complete typed-contract regressions: each ready batch captures completed dependency records before scheduling; sibling runners cannot mutate another activation's snapshot; legacy controlled runners remain compatible; capture failure is attributed to the agent and blocks only its dependents. | Passed; 272 tests, 1 Windows symlink test skipped | The coordinator does not yet provide `PublishedInputResolver` or concrete input construction to this hook. Product runtime integration remains R03/R02/M01-M19. |
398
  | M01a | `70f220c`, `e1c1f66` | `tests/test_market_data_normalizer.py`, `tests/test_datafetcher_typed.py`, existing Finnhub tests, artifact publication/input resolution, and the full typed-contract regression set: the existing primary/fallback fetch returns without legacy writes for V8; actual OHLCV source is retained; invalid/missing values remain excluded, null, or explicitly unavailable; typed inputs, per-ticker JSON/Markdown, and the manifest publish through the ACL. | Passed; 284 tests, 1 Windows symlink test skipped | Controlled providers only; no live credentials or calls. The legacy handler remains active and the coordinator does not yet invoke `execute_typed`, so M01 and product readiness remain open. |
399
  | M02a | `50689bc` | `tests/test_options_typed.py`, options contracts, existing options-flow behavior, artifact publication/input resolution, and the expanded typed regression set: the existing bounded provider publishes sampled contracts, known-only totals, exact volume/OI/IV candidate criteria, unsupported provider capabilities, immutable JSON/Markdown, and explicit unavailable evidence for returned or raised provider failures. | Passed; 227 tests, 1 Windows symlink test skipped | Controlled provider only; no live provider call. Candidate heuristics remain non-directional and `unusual_flows` stays empty because the current provider lacks trade-side, sweep/block, opening/closing, premium, and validated-classifier evidence. Baseline comparison and coordinator activation remain M02/runtime work. |
400
+ | M03a | `e84d1e1`, `2fd6704` | `tests/test_evidence_verifier.py`, `tests/test_trend_typed.py`, the real structured-completion boundary with a controlled text response, analysis contracts, I/O bindings, providers, publication, scheduling, and the applicable typed regression set: current and baseline citations must resolve to frozen artifact identities and real JSON pointers/record IDs; the existing TrendAnalyst performs schema-valid LLM analysis, records usage when state is supplied, publishes immutable JSON/Markdown, compares prior trend context, and emits explicit unavailable evidence without LLM inference when OHLCV is absent. | Passed; 264 tests, 1 Windows symlink test skipped | No live LLM request or coordinator activation. The repository-wide suite cannot collect because unchanged legacy academic files contain syntax errors and optional `mcp`, `sentence_transformers`, and `bibtexparser` dependencies are absent. Cost/trace coordination and product-path execution remain M03/R02/R03/R06 work. |