feat(ai): add _run_survey() and submit_survey tool (#5) #43

Closed

archeious wants to merge 0 commits from feat/issue-5-run-survey into main

archeious commented

2026-04-07 03:50:06 +00:00

Owner

Closes #5

Adds the survey pass with submit_survey tool, wired into _run_investigation before the dir loop. Output logged, not yet consumed (that is #6). Includes Band-Aid prompt warning about classifier bias pending #42.

Closes #5 Adds the survey pass with submit_survey tool, wired into _run_investigation before the dir loop. Output logged, not yet consumed (that is #6). Includes Band-Aid prompt warning about classifier bias pending #42.

archeious added 1 commit 2026-04-07 03:50:07 +00:00

feat(ai): add _run_survey() and submit_survey tool (#5 ) fecb24d6e1

Adds the reconnaissance survey pass: a fast, ≤3-turn LLM call that
characterizes the target before any directory investigation begins.
The survey receives the file-type distribution (from the base scan),
a top-2-level tree preview, and the list of available dir-loop tools,
and returns description / approach / relevant_tools / skip_tools /
domain_notes / confidence via a single submit_survey tool call.

Wired into _run_investigation() before the directory loop. Output is
logged but not yet consumed — that wiring is #6. Survey failure is
non-fatal: if the call errors or runs out of turns, the investigation
proceeds without survey context.

Also adds a Band-Aid to _SURVEY_SYSTEM_PROMPT warning the LLM that
the file-type histogram is biased toward source code (the underlying
classifier has no concept of mail, notebooks, ledgers, etc.) and to
trust the tree preview when they conflict. The proper fix is #42.