Plugin reply shape, preferences UI, cited-record status, and the lesson kind #166
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: bvandeusen/FabledScribe#166
Reference in New Issue
Block a user
Seven commits. The reason for merging NOW is the plugin: the marketplace checkout tracks
main, so the two plugin files ondevcannot reach a session until this lands. Everything else here was already testable on:dev.What this unblocks
plugin/skills/reporting-back/SKILL.mdand the manifest (2026.09.18.0436→2026.09.18.1606). The version moves, so the executing-cache refresh (#2209) actually fires rather than silently keeping the old copy.After merging, a
/pluginrefresh or a fresh session picks it up. Nothing else is required.What rides along
#4154 — a record you merely CITE carries its status.
next_stepon every milestone summary (one flat query per batch, not per milestone — #2384's fan-out), and a task's status in the injected line's kind marker. This is the gap that let #4014 be reported as milestone 409's open step when it had been done for four days.#3895 — preferences are writable, and their drift is visible.
GET /rules/drift, a restore route carved out for preferences only, the preference chip, andPreferenceDriftPane. Milestone 323 refused one-click restore for rules because a binding instruction should not be revertible in one click; the carve-out turns on that reasoning being about the operator's own decision, where a preference's rewrite is the agent's. Nothing is erased — the restore goes throughupdate_ruleand snapshots.#3729 / #3730 — the lesson kind, steps 2 and 3 of milestone 385. Half-built on purpose, and inert on arrival:
create_lessonexists yet (step 4), and the MCPcreate_notetool hardcodesnote_type="note", so no agent surface can write one;include_global_kindsis wired only to the explicit MCP search, which returns nothing because the corpus holds no lessons;KnowledgeView.vue(step 7, #3734) stays unreachable until a lesson can exist.Merging before step 4 rather than after is deliberate for exactly that reason.
No migration in this batch —
note_typecarries no CHECK constraint, so rule 36 has nothing to expand.Verification
CI 7023 green on
1361ed7, all six jobs including the integration lane against real Postgres. Runs 7016 and 7005 went red first and are fixed in 7017 and 7006; both were guards working as intended.🤖 Generated with Claude Code
https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy
Milestone 409 step 6 measured the scaffold on live sessions and found its two halves disagreeing: adherence passed and the read test failed. Completion replies carried every section the table asks for and were still hard to read. The cause was in the skill, not in compliance with it. It said to pick a kind of reply "then fill its sections... keep them even when one is short", which is an instruction to complete a form, and nothing anywhere set a ceiling. A faithful reply and an unreadable one were the same reply. Four changes to the discipline around the scaffold. The categories and their sections are untouched. - Sections are what to consider including, not a form to complete. A section answering a standing question ("does anything need me?") is always answered, even with "nothing"; a section that explains earns its place only when it changes what the operator does. Otherwise it belongs in the record's log, where it is available and not in the way. - Write the shortest reply that carries the answer, with named exceptions so this cannot be read as "always be terse". - "Needs you" takes BOTH tests: theirs to decide, AND work is waiting on it. A question answerable by reading something or taking an available measurement is work not yet done, not a request — settle it, say which way you went, and leave them free to overrule. - A decision already made gets acted on. Re-arguing a settled question reads as contradicting yourself rather than as being careful, and costs the operator the decision twice. "Before sending" gains a second pass for what can go, since the existing check asks what is MISSING, which a bloated reply passes. Guards in tests/test_reply_discipline.py, three topics registered for ownership. Every guard was falsified against the pre-change text before committing (rule 167): all five fail on it and pass on the fix, and the sixth deliberately passes both since it guards the scaffold against collateral damage. No absence checks — the skill legitimately discusses filling in order to warn against it, so asserting "fill" is absent would false-alarm on the corrected text (snippet #3352). Instance-agnostic per rule 115: the added text carries no record ids, no software-specific terms and no verbatim quotes. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuylessonkind, and one join for every trigger title (#3729)Milestone 385 step 3 — the step where the kind either works or is cosmetic. THE DOCUMENT, and why there is no `lesson_document()` beside `rule_document()` in embeddings. The step expected one. The difference is where the sharp shape LIVES. A rule keeps its trigger in a column and its title is a plain name, so `{title} — {trigger}` has to be synthesised at embed time and exists nowhere else. A snippet — the only sharp record in the corpus by #2485's measurement, 0.153 top-to-second against 0.010–0.023 — gets there the other way: its STORED title is already the join and its stored body already opens with the trigger, so the ordinary `title\nbody` join IS the sharp document. Step 1 chose the snippet route and step 2 built it, so `lessons.lesson_document` composes what is STORED and the generic chunker does the rest. The consequence the step asked about: `chunk_document` is untouched, so CHUNKER_VERSION does not move and NOTHING re-embeds. The step's "Re-embed" section describes a change this design does not make. THE NARRATIVE stays in the body, departing from the step's instruction to keep it out. `rule_document` excludes `why` because long dated narrative made sixteen dev-logs land on the centroid of "development" — but that finding predates chunking (#280). A body over budget is now split, and every chunk is prefixed with the title, which for a lesson carries the trigger. The story occupies its own vectors instead of averaging itself into the trigger's, and each of those is still anchored to when the lesson applies. A guard asserts exactly that. Holding the story out would cost the reader the only part that explains the insight, to buy a sharpness the chunker already provides. GLOBAL IN THE SEARCH is the real new code: `GLOBAL_NOTE_TYPES` and `include_global_kinds` on `semantic_search_notes`, widening the PROJECT filter alone. Off by default, because two callers depend on that filter holding — the near-duplicate gate compares a record only against its own project on purpose, and a globally visible kind there would let a lesson block an unrelated note's create on a project its author never touched. It composes with `note_type` rather than overriding it, so narrowing to snippets does not quietly acquire lessons, and it changes nothing about the ACL: `notes_visibility_clause` still gates every row. Wired into the explicit MCP search only — the operator asked, and there is no budget to spend. The unasked-for injection arms are step 5's subject (#3732) and the legibility of a lesson appearing on a foreign project is step 7's (#3734), so neither is turned on here. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy