Closes the gap where recurring_error suggestions showed generic 'Investigate'
instead of the curated recommendation. Added a covers[] field to SolutionPattern
(lowercase substrings a pattern's recommendation also applies to) + Catalog.find_for
(exact key first, then covers match against signal key+locus). Retro now resolves
recommendations through find_for. Tagged the read-before-edit pattern with
covers=['file has not been read','modified since read','file_not_read'] (v1.0.1).
Live: file-not-read suggestions across all repos now inherit 'Read the file before
Edit/Write'. 6 new tests; suite 158/158.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Replaced the placeholder 'TODO: capture the recommended resolution' in the five
auto-approved patterns with grounded problem descriptions + concrete resolutions
drawn from the friction assessment: budget_overrun (read narrowly / checkpoint),
infra_overhead (batch hub writes / orient once), schema_thrash (front-load tool
schemas), tool_thrash (batch shell + larger edits), clean_pass (tests gate done).
Each versioned 1.0.0 -> 1.0.1 with the stub archived to <id>.history.jsonl.
Proposals regenerate with real content (0 TODO). Suite 139/139.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Acts on the #1 friction finding. T01: added a data-cited Read-before-Edit /
re-read-on-stale reflex to AGENTS.md (top error: 'File has not been read yet',
12/27 sessions). T02: captured it as a curated SolutionPattern
(sp-problem-file_not_read-edit, approved/distribution_ready) with real
resolutions + per-flavor hints, so Distribute proposes it across repos/flavors —
closing assess->curate->distribute on a real pattern. Suite 126/126.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Re-ran ingest->detect with the quality filter + infra signals over real local
sessions (72 captured -> 27 real). Purged the false-positive 'abandoned' catalog
entry and re-curated; catalog now carries tool_thrash/schema_thrash/infra_overhead
patterns. docs/ASSESSMENT-infra-friction.md ranks the friction: ~17.6% of real
tool activity is hub/task/schema plumbing (State Hub 10.3%, one session 231 calls;
ToolSearch in 81% of sessions). Validates the CLI/MCP-skill hypothesis as top-2;
recommends a State Hub skill (front-load schemas + batched writes) + bulk hub ops.
Workplan finished; suite 88/88.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
