docs(plan): note classifier rebuild (#42) in Phase 2

The filetype classifier is biased toward source code and would mislead
the survey pass on non-code targets (mail, notebooks, ledgers). #5
ships with a prompt-level Band-Aid; #42 captures the real fix and is
sequenced after the survey pass is observable end-to-end and before
Phase 3 depends on survey output.
This commit is contained in:
Jeff Smith 2026-04-06 21:47:49 -06:00
parent 2afef76a67
commit 05fcaac755

View file

@ -535,6 +535,11 @@ without 9 phases of rework.
- `_SURVEY_SYSTEM_PROMPT` in `prompts.py` - `_SURVEY_SYSTEM_PROMPT` in `prompts.py`
- Wire into `_run_investigation()` before dir loops - Wire into `_run_investigation()` before dir loops
- Survey output injected into dir loop system prompt - Survey output injected into dir loop system prompt
- **Rebuild filetype classifier (#42)** to remove source-code bias —
lands after the survey pass is observable end-to-end (#4#7) and
before Phase 3 starts depending on survey output for real decisions.
Until then, the survey prompt carries a Band-Aid warning that the
histogram is biased toward source code.
### Phase 3 — Investigation planning ### Phase 3 — Investigation planning
- Planning pass after survey, before dir loops - Planning pass after survey, before dir loops