quantmodel — Define StrategySpec schema + LLM extraction prompt from AS blog posts

Objective

Define StrategySpec schema + LLM extraction prompt from AS blog posts.

Notes: Shipped research/strategy_spec (schema.json + validate + LLM prompt). Hand specs: findings/specs/{haa-balanced,baa-balanced,baa-aggressive}.json. CLI validate/prompt/tickers. Tests: 22 passed. Findings: strategy-spec.md

Approach

Reuses existing report research/findings/strategy-spec.md — tables/metrics preserved verbatim via source_report pointer. Body below summarizes grounded evidence from that report and adjacent artifacts.

Files / code / data changed

No commit SHA confidently associated with t10 in sampled log [reconstructed — uncertain].
Source report: research/findings/strategy-spec.md
Task-history entry: research/findings/task-history.json#t10

Results

Key table from source report (preserved):

Path	Role
`research/strategy_spec/schema.json`	JSON Schema (draft 2020-12) documentation
`research/strategy_spec/validate.py`	Stdlib validator + ticker union helper
`research/strategy_spec/prompt.py`	System prompt + `build_extraction_messages`
`research/strategy_spec/__main__.py`	CLI: validate / prompt / tickers / schema
`research/findings/specs/haa-balanced.json`	Hand-extracted HAA Balanced
`research/findings/specs/baa-balanced.json`	Hand-extracted BAA Balanced
`research/findings/specs/baa-aggressive.json`	Hand-extracted BAA Aggressive

Conclusions and metrics are in research/findings/strategy-spec.md; see detail page for preserved tables/metrics.

Conclusions

[reconstructed — uncertain] Outcome inferred from status done and task note.

Problems / follow-ups

See source report or PR discussion for follow-ups. No unsupported follow-ups fabricated.