33c0f2c95d3402fbe3d572b92c96e505f4faf586
3
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
d5dad587f1 |
refactor(skills): using-scribe keeps the every-turn practices; moment-specific depth moves to reference files (#4398)
CI & Build / Python lint (push) Successful in 4s
CI & Build / Plugin hooks (push) Successful in 12s
CI & Build / TypeScript typecheck (push) Successful in 55s
CI & Build / integration (push) Successful in 1m8s
CI & Build / Python tests (push) Successful in 1m44s
CI & Build / Build & push image (push) Successful in 21s
Anthropic's skill guidance: keep SKILL.md under 500 lines, split into reference files linked one level deep as it nears that. using-scribe was 478 and every new practice lands there. - SKILL.md 478 -> 317 lines. It keeps orientation, one copy, the reflexes, scope, the judge section, UI and the process-skill index, plus a "Read these when the moment comes" list naming each file with its moment. - projects.md: binding a non-git directory (.scribe) and project inception. - writing-records.md: where a new rule goes, lesson growth, and notes that carry their own check (reflex 10 keeps a pointer). - missed-retrieval.md: the record-before-dial route, verbatim. - Text moved, not rewritten, except for the seams and one cross-reference. Tests: - tests.helpers.skill_text reads SKILL.md plus its reference files. The ownership registry, the miss-route and the verification tests use it, so a topic stays owned by its skill whichever file holds it. - The force test scans every skill .md on its own, since each file is read on its own. - New test_skill_structure: SKILL.md <= 350 lines, every reference file is linked from SKILL.md, none links another, and one over 100 lines opens with Contents. Each guard is shown to fail. The plugin version is minted. That also clears 4fb53b8's red Plugin hooks lane, which failed only because PACKAGING.md changed without a mint. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
|
4fb53b844d |
refactor(mcp): _INSTRUCTIONS orients the workflow, not a rulebook (#4389)
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Failing after 12s
CI & Build / TypeScript typecheck (push) Successful in 53s
CI & Build / integration (push) Successful in 54s
CI & Build / Python tests (push) Successful in 1m35s
CI & Build / Build & push image (push) Successful in 23s
Spike #4389 read the spec, Claude's docs and a dozen servers: the field is for how the tools fit together, and the field runs ~600-1,600 characters. Ours sat at the 2,048 cap as a keyword index that also carried stance. - JUDGE, REPORT and MISSED leave the index. They fire mid-work, not at session start; using-scribe and reporting-back state them in full, and `placement`/`report_back` cue reporting in-band. No skill text changes. - The rest is rewritten as plain practices (1,503 chars) and keeps every session-start marker the ownership registry pins. - INSTRUCTIONS_BUDGET 2000 -> 1600; the three index markers are dropped from the registry; the miss-route index test now checks that the index keeps what_might_apply and stays off the route. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
|
104c1d6f37 |
feat(plugin): a recognized retrieval miss has a route, and the record comes first (#4133)
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 9s
CI & Build / integration (push) Successful in 50s
CI & Build / TypeScript typecheck (push) Successful in 55s
CI & Build / Python tests (push) Successful in 1m34s
CI & Build / Build & push image (push) Successful in 43s
The tuning loop shipped in steps 4 and 6 and logged zero events in its lifetime. `tune_retrieval`, `retrieval_telemetry` and `retrieval_surfaces` appeared on no instruction surface at all — not the skills, not the hooks, not the MCP instructions — so the decision that "the model should be the thing handling it 9 times out of 10" could not begin to happen. What was missing was not an auditor but a route. `using-scribe` now carries it, ordered: read the refused records, fix the trigger, and only then consider the dial. The order is the content. A rule's `when_to_apply` IS the text its score is computed against, so a miss is evidence about that text first; rewording one trigger changes one rule's reach, while moving a floor changes what every record on the surface does and cannot tell a badly-worded trigger from a genuinely distant one. Measured, and the reason the order is asserted rather than suggested: rule 1 scored 0.6515 and ranked 5th for the moment it governed, behind three rules that restrained the same act. Every percentile said "lower the floor"; at 0.60 the arm delivered those three restraints and still not rule 1. Rewriting the trigger to lead with the symptom put it 1st at 0.7130. Also: the create path gets a precondition. A new record is itself a retrieval-affecting act, so before writing one, what_might_apply asks what already covers that moment — fifty candidates and no bar, because a bar is what lets the existing record hide. `_INSTRUCTIONS` gets one index line, not the route: 1,986 of 2,000 characters, since Claude Code cuts the rest mid-word (#2562). Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy |