FabledScribe

Raised by the operator: are we limiting what comes back by character count,
and how do we verify the pertinent part is the part displayed?

We were not. mcp/tools/search.py sent (note.body or "")[:240] — a head cut,
with no marker that anything had been removed, so a 240-character preview of
a 4000-character record was indistinguishable from a complete short one.

The opening is the wrong span. The match is semantic and per chunk, and
semantic_search_notes collapses to best-chunk-per-note — its own comment at
the collapse says "the first appearance of a note is its best chunk". So the
system identified the passage that earned the hit and then discarded it:
select(Note, distance) kept no chunk column. A record could rank first on its
sixth paragraph, be previewed by its first, and be judged irrelevant on a
span the search had already scored lower. That biases against long records,
and it is self-concealing — the caller who does not open it never learns the
preview was misleading.

  - embeddings: chunk_index/chunk_text ride along in the select, and the
    collapse records the winner in report["best_chunk"]. Carried in `report`,
    NOT by widening the return tuple: ten callers unpack (score, note) at
    ~18 sites and nothing would catch the misses (lesson #4207). `report` is
    the side-channel this function already uses for best_available_score.
  - search(): excerpt / excerpt_is / body_length, and read_full when there is
    more. A caller that cannot tell a matched passage from a document opening
    cannot judge whether to look deeper, which is the only decision the field
    supports.

elide() moves to services/text.py so both callers share one copy, and it
keeps BOTH ends with a stated gap — it is the fallback for when nothing
identifies a better span than "all of it", not the goal.

Also fixes a guard that produced a false failure on the previous commit:
test_pull_telemetry checked `"project_id: int = 0" in body.split("\n")[0]`,
which sees only the first line, so wrapping get_task's signature over four
lines made it report a function that does take the project as one that does
not. Parsed with ast now, and proven to still reject an absent or
wrongly-typed parameter rather than being appeased by reflowing the code.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy

2026-09-21 08:50:16 -04:00

__init__.py

feat(lessons): a lesson can be written, and it keeps every incident that taught it (#3731 )

2026-09-18 18:19:28 -04:00

design_systems.py

feat(mcp): enter_project becomes a small primer: goal, recent work, open work, vocabulary (#4045 )

2026-09-14 22:04:38 -04:00

lessons.py

feat(lessons): the kind whose whole question is "is this trigger right" was the one kind that could not see its own counts (#4196 )

2026-09-21 02:33:33 -04:00

milestones.py

fix(tasks): add_task_log wrote to a surface no agent could read back (#4241 )