1660 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
bvandeusen	c08655914f	Merge pull request 'Soft links: a lesson and a rule arriving together are proposed as a link (milestone 440 step 3, #4637)' (#190) from dev into main	2026-10-01 14:59:30 -04:00
bvandeusenandClaude Opus 5.5	dbbab859ce	feat(lessons): soft links — a lesson and a rule arriving together in distinct situations are proposed as a link (milestone 440 step 3, #4637) ... When one hook response puts a lesson and a rule in front of the reader, the pair is recorded as evidence on a SUGGESTED lesson_rule_links row; once the pair has arrived together in PROPOSE_SITUATIONS (3) distinct situations, the next co-arrival carries one line asking the reader to judge it with judge_lesson_link. Nothing about surfacing changes: a suggested link carries no rule anywhere (that is #4633, confirmed links only). - lesson_rules: co_surfaced (fail-open; only pairs the reader could confirm — a lesson they may write, a rule they own; judged pairs gather nothing; one proposal per response; PROPOSE_COOLDOWN 6h between asks), plus the pure counting rules: situation_key, add_evidence, proposal_due, evidence_summary. A situation is the prompt on /retrieve (word tokens, sorted and de-duplicated, so trivial rewordings count once) and the FILE on /prior-art (every edit to one file is one situation). - rules_for_lessons shows a suggested link's evidence counts. - plugin_context: build_autoinject_hint returns lesson_ids, build_prompt_rule_hint returns shown_rule_ids, build_write_path_hint records its own pair; routes/plugin /retrieve records the prompt pair. Shown lines, repeats included: relevance makes a co-arrival, not the session ledger. - Evidence lives in the existing evidence column — no migration, and backup already carries it. - Tests: counting rules (unit), the recorder against Postgres (bar, repeat, judged pairs, ownership, cooldown, evidence kept on confirm); conftest stubs co_surfaced for unit tests. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 14:30:58 -04:00
bvandeusen	6ba40c9e10	Merge pull request 'Lessons point at rules (milestone 440 steps 1–2) + the away-from-home usage readout' (#189) from dev into main	2026-10-01 13:48:01 -04:00
bvandeusenandClaude Opus 5.5	95be2512ab	fix(lessons): build the rule-candidate query with trigger_title (#4631) ... CI run 707 failed test_the_trigger_separator_is_spelled_in_exactly_one_place: rule_candidates joined the lesson's claim and trigger with an inline " — ", a second spelling of embeddings.TRIGGER_SEP (#3207). It now calls trigger_title — the same join a rule's own document title is built with, which was the point of the query shape in the first place. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 13:34:08 -04:00
bvandeusenandClaude Opus 5.5	f7d8dc2e55	feat(lessons): judged when written — a new lesson is offered its rules, and "no rule fits" is an answer (milestone 440 step 2, #4631) ... "Which rule is this lesson an instance of?" now has three recorded answers: a rule named (a confirmed link, #4630), no rule fits (new), or unjudged. - Model + migration 0112: lesson_no_rule (lesson_id PK, CASCADE from the note; why; judged_at). A table rather than a key in notes.data, because that mirror is re-composed from the body on every edit and would erase it. - Service (lesson_rules): set_no_rule rejects any confirmed link with the reason; a confirmation (set_lesson_rules or judge_link) deletes the answer; require_one_answer refuses both answers in one call before any write; judgments_for_lessons + attach_lesson_rules add rule_judgment (and no_rule) to every lesson payload; list_unjudged lists the open ones; rule_candidates searches rules with the lesson's claim + trigger at the explicit-search bar, None when the search could not run. - MCP: create_lesson/update_lesson take no_rule; an unanswered create returns rule_candidates, rule_judgment and a rule_hint; list_lessons(unjudged=true). - REST: the same on POST/PATCH /api/lessons and GET ?unjudged=1; create returns rule_candidates. - Backup v19: a lesson_no_rule section, export (full and per-user) and import. - Guidance: create_lesson docstring, writing-records.md in using-scribe (owner, pinned in test_guidance_ownership), create_rule docstring on linking the lessons a new rule governs. Plugin version minted. - Tests: door units, integration for the three states, the rejection reason, scoping, cascade; backup registries. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 13:25:27 -04:00
bvandeusenandClaude Opus 5.5	c8393975c3	fix(mcp): classify judge_lesson_link as a write tool (#4630) ... The tool-classification guard (test_mcp_auth) failed CI run 705: the new judge_lesson_link tool sat in no set, so a read key would have been silently denied it. It changes a link's state, so it belongs in _WRITE_TOOLS. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 12:44:06 -04:00
bvandeusenandClaude Opus 5.5	41e4fbaba1	feat(lessons): a lesson names the rule it is an instance of — lesson_rule_links (milestone 440 step 1, #4630) ... The link between a lesson (one concrete situation) and the rule that governs it, with the operator's soft-then-hard design built into its state: suggested while evidence accumulates, confirmed or rejected once judged. Only confirmed will carry a rule in retrieval (#4633); rejected is kept so the pair is never proposed again. - models/lesson_rule_link.py + migration 0111: one row per (lesson, rule), CASCADE on both ends, indexed both ways, CHECK on state (rule 36), evidence JSONB and judged_at. - services/lesson_rules.py: require_rules (validated before any write, so a bad id leaves nothing half-linked), set_lesson_rules (set-semantics; a dropped rule becomes rejected, not forgotten), judge_link, and the two reads. ACL: write on the lesson (share-aware), ownership of the rule; a reader sees only rules they own. Decorations are fail-open (#4286). - MCP: create_lesson / update_lesson take rule_ids; get/create/update return `rules`; new judge_lesson_link tool. REST: the same on /api/lessons plus PUT /api/lessons/<id>/rules/<rule_id>. Rules: rule_detail carries `lessons`. - Backup v18: export (full and user-scoped, both ends in scope), builder, importer; both column guards register the table. - Tests: integration (states, set-semantics, judge, ACL all-or-nothing, cascade both ways, CHECK, one row per pair); unit (door wiring, judge registered, migration/model state agreement, backup skip and unjudged stays unjudged). conftest stubs the decorations for unit tests. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 12:38:02 -04:00
bvandeusenandClaude Opus 5.5	2e4c2d9493	feat(usage): count what happened away from a record's own project — the readout #3735 needs ... Milestone 385 step 8 (#3735 "a lesson is recalled on a project it was not written on") is defined by opened-on-another-project. The reader's project has been recorded on every usage event since 0c8e109, but nothing compared it with the record's own, so the criterion was still unreadable. - note_usage.usage_for_notes: a second aggregate in the same session joins notes and counts surfaced_away_count / pulled_away_count. Counted only where both projects are known and differ; ranked surfacings only (#2477). The first aggregate is untouched, so events on deleted notes still count. - empty_usage carries both keys zero-filled; every door that attaches usage (list_lessons, get_lesson, snippets, knowledge) gets them through attach_usage. - UsageBadge tooltip says "On other projects: surfaced N×, opened M×" when it happened, and nothing when it did not. - Tests: the mocked split test feeds both aggregates; a unit test for the away counters; a real-Postgres test that home, unreported and ambient events are all left out. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 10:47:03 -04:00
bvandeusen	d7641e57a8	Merge pull request 'Shapes are judged when they are written (milestone 439 steps 1–6) + #4608 fixes' (#188) from dev into main	2026-10-01 08:55:10 -04:00
bvandeusenandClaude Opus 5.5	582a5a4f48	feat(shapes): the practice is written where it is read, and the coverage line measures the slip (milestone 439 step 6) ... - reusing-code: "Before the turn ends — say what you built" — the four verdicts, the one classify_shapes(repo=…) call, and the component file as a shape. Description names the end-of-turn moment. - shape-accounting: the writer judges; audits are the check that it held. The write path SUGGESTS (no more hook instances); component file rows and whole-file canon described; scoped covers Svelte too. - _INSTRUCTIONS reuse line: "before the turn ends, say what you built (create_snippet the reusable, classify_shapes the rest)" — 1570/1600. - Coverage line: "written-shape check (7d): N turns checked, M asked, K left unjudged", from the Stop hook's recorded outcomes; silent until the question has been put. - test_guidance_ownership pins the new topic on reusing-code. - prior-art hook header no longer says it stamps instance rows. Plugin version minted. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 08:46:58 -04:00
bvandeusenandClaude Opus 5.5	8b1567cf2c	feat(shapes): a component file is a candidate shape in its own right (milestone 439 step 5) ... A single-file component defines `.card`, `.title` and a `Props`, never anything named after itself — so the ledger could not hold "StatusChip is canon" and could not say a new card was built where one already existed. - coverage.is_file_unit: a file that RENDERS (its markup names classes, or it opens a <script>/<template>/<style> block) and defines nothing named after its stem gets one `file` row. Structural, not a framework list: Svelte and Vue components qualify, a TSX component already has its function's row, a module is accounted for by its definitions. Emitting every file would have put every module of every project in the todo at once. - No body fingerprint on file rows, so an edit never re-asks a judgment. - `file` is its own form and family; derive grouping skips it (`index`, `+page` repeat by convention). Divergence buckets it on its own, so a new component where a component canon dominates is a fair question. - mark_canonicals: a snippet recorded at a path with no symbol makes that file row canonical; it still covers no definition inside. - The write hooks apply the same test before noting a new file for the end-of-turn question. Plugin version minted. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 08:45:14 -04:00
bvandeusenandClaude Opus 5.5	4cf1c6f042	feat(shapes): the write-path hook suggests and no longer stamps (milestone 439 step 4) ... The hook used to land its evidence as `instance` rows, classified_by=hook — a permanent verdict nobody read, and the source of the weak stamps that poisoned two ledgers (#4608). Now the agent that wrote the code judges it at the end of the turn, and the hook's evidence is what it is shown. - shape_ledger.suggest_write_path_instances (was stamp_write_path_instances): same evidence and form gate, but it writes a PROPOSAL — proposed_snippet_id, basis "reference" (named) or "semantic" (resembles), score — and never a status. A judged row is left alone; a new shape gets an unclassified provisional row so the suggestion reaches the end-of-turn question as "looks like #N". By-name uses edges stay: a fact, not a verdict. - The prior-art line says "looks like #N … when you judge this turn's shapes, say whether it is", and the result key is `suggested`. - write_time_divergence takes `suggested`; _RESEMBLE_MIN re-documented as the suggestion bar and the weak-stamp line. - reusing-code skill no longer says the pull stamps an instance. - Tests moved to the new contract, plus a guard that nothing the hook does writes classified_by="hook". Plugin version minted. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 08:42:10 -04:00
bvandeusenandClaude Opus 5.5	f1fbdf746a	feat(shapes): the agent judges what it wrote, at the end of the turn (milestone 439 steps 1-3) ... Recording used to be decided by machinery — the only "record it" prompt fired when a same-named copy already existed (#2664), so a first instance of a reusable piece was never asked about, and judgment arrived only through audits. Now the question is asked where the knowledge is: the end of the turn that wrote the code, of the agent that wrote it. - Write hooks keep `<sid>.written.ids` (path, kind, name) for every definition a write names; a new file adds a `file` line for its stem — a candidate in any language without a framework rule (scribe_written_append). - Stop hook scribe_shape_check.sh sends the ledger to GET /api/plugin/shape-check and blocks once, in the server's words, when anything is unjudged. Same discipline as the report check: never twice, never without a recorded check, another hook's loop left alone; the ledger is kept when the instance cannot be reached. - shape_ledger.unjudged_shapes: no row, unclassified, scoped and hook stamps are unjudged; an agent/audit/import verdict is not. A snippet recorded at the shape answers for it until the refresh stamps it canonical. - services/shape_check owns the reason text and records every outcome in app_logs (passed / blocked / judged_after_block / left_after_block). - classify_shapes(repo=…) judges a shape the ledger has not synced yet via a provisional row under a bound repo; the sync confirms it, or vanishes and revives it with the verdict intact. An unbound repo is refused. Plugin version minted. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-01 08:39:36 -04:00
bvandeusenandClaude Opus 5.5	eb5cc6d3a7	fix(shapes): weak stamps elect no canon; the arrival line names the review; Svelte scopes by default (#4608) ... Librarian and Stash had 132 and 488 write-path stamps written at 0.68-0.72, before the 0.80 floor (#4204). Nothing re-judged them, and dominant_canon counted them, so a YAML CI snippet (#3410) "dominated" Librarian's web directory and every write there was told it diverged from it — 1408 flags on one project, 902 on the other, all skimmed past. - is_weak_stamp: one predicate for "hook-stamped below today's floor". dominant_canon and canon_form skip such rows; stamps_to_review lists them by the same predicate. No stored row changes — they stay for judgment. - flag_divergence withdraws a standing flag whose canon no longer dominates its directory. A flag is a mechanical prompt, not a judgment. - The coverage line ends "N weak stamps · M incoherent canons to judge — stamps_to_review" when either is nonzero, so a project's own session sees the queue on arrival. The shape-accounting skill says what to do with it. - scoped_definitions handles .svelte: every <style> is component-scoped unless <style global> or :global(...); instance-script syms are scoped, module-script ones stay ordinary. Plugin version minted for the skill change. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-30 23:27:07 -04:00
bvandeusenandClaude Opus 5.5	3270fe90c1	refactor(settings): one bounded_float for every numeric bar read from settings ... The shape ledger's divergence readout flagged _gate_setting (#4385). Reading it turned up a family with no canon: floor_for, get_duplicate_threshold, get_plan_match_threshold and _gate_setting each parsed a stored string, fell back to the default (never 0) and clamped into [lo, 1]. - services/settings.bounded_float(raw, default, lo=0, hi=1) is the pure parse, fallback and clamp. Each caller keeps its own get_setting read, so tests patching get_setting per module still take effect, and _gate_setting still fails open on an unreadable setting. - SettingsView.saveKbInject: eleven inline Math.min/Math.max clamps and the local gateAt become one asBar(v, d, lo = 0), mirroring the server. No behaviour change. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 12:30:58 -04:00
bvandeusen	33c0f2c95d	Merge pull request 'Server instructions orient the workflow; using-scribe splits into reference files (#4389, #4398)' (#187) from dev into main	2026-09-24 11:30:02 -04:00
bvandeusenandClaude Opus 5.5	d5dad587f1	refactor(skills): using-scribe keeps the every-turn practices; moment-specific depth moves to reference files (#4398) ... 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>	2026-09-24 09:58:41 -04:00
bvandeusenandClaude Opus 5.5	4fb53b844d	refactor(mcp): _INSTRUCTIONS orients the workflow, not a rulebook (#4389) ... 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>	2026-09-24 07:50:34 -04:00
bvandeusen	779efb2e74	Merge pull request 'dev → main: MCP SDK v2 port, create-gate thresholds in Settings' (#186) from dev into main	2026-09-24 07:31:51 -04:00
bvandeusenandClaude Opus 5.5	c26b7f248e	feat(mcp): port the server to MCP Python SDK v2 (FastMCP → MCPServer) (#2196) ... - server.py: `mcp.server.mcpserver.MCPServer`; StrictArgsFastMCP becomes StrictArgsMCPServer, whose call_tool takes and forwards v2's `context` and raises ToolError (the SDK logs anything else as an unexpected crash; the message reaches the caller either way). - stateless_http and transport_security moved from the constructor to `streamable_http_app(...)` in mount_mcp, with their reasons. - Per-request user identity is unchanged: the contextvar set around the ASGI call reaches the handler on both v2 paths (legacy stateless spawns from the request task; the 2026-07-28 modern path opens its task group inside the request). - pyproject: mcp[cli]>=2.2, no ceiling (installs are --locked). uv.lock regenerated with --upgrade-package mcp in the ci-python image: only mcp and its own dependencies moved (106 → 110 packages). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 07:21:27 -04:00
bvandeusenandClaude Opus 5.5	4502f0a1ae	feat(dedup): the create gate's similarity bars are settings (#4385, rule 25) ... gate_bars(user_id, note_type) resolves the block bar and, for notes and tasks, the overlap floor from kb_gate_* settings, with the old constants as defaults. Fail-open on an unreadable value; a block bar clamps at 0.80 and the overlap floor at 0.70 and never above the bar. Five fields in Settings beside the duplicate-report floors. CLAIM_LEASE stays a constant, with the reason written at it: a per-user lease would make one shared task live to one reader and dead to another. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 07:11:10 -04:00
bvandeusen	f385d9075b	Merge pull request 'dev → main: task claims (milestone 381), embedding model stamp, dedup copy band, sweep-shared.css' (#185) from dev into main	2026-09-24 06:57:12 -04:00
bvandeusenandClaude Opus 5.5	baf22179ef	refactor(frontend): the sweep pane's column wrapper joins sweep-shared.css (#3207) ... .sweep was the one rule still written identically in both sweep panes. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 06:53:11 -04:00
bvandeusenandClaude Opus 5.5	c787957ddf	fix(frontend): load sweep-shared.css once from main.ts — a shared <style src> breaks vite build (#3207) ... plugin-vue throws "Cannot read properties of undefined (reading 'scoped')" when several SFCs share one src stylesheet. vue-tsc passed, so only the image job caught it; :dev has not rebuilt since 22b7a92. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 06:50:59 -04:00
bvandeusenandClaude Opus 5.5	4a93c8b262	fix(task-logs): a collaborator who may write a task may log on it (rule 78) ... create_log filtered on Note.user_id == user_id, a bare owner check, so a collaborator with write access to a shared task was told it did not exist — and, since a log now stamps the claim, could never be seen working it. It now asks can_write_note. Editing and deleting a log still require its author, which is authorship rather than access. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 06:48:01 -04:00
bvandeusenandClaude Opus 5.5	22b7a928da	refactor(frontend): derive the sweep-row visual language into sweep-shared.css (#3207) ... The note sweep, rule sweep, preference drift and rule history panes each restated the same row recipe in a scoped block. It now lives once in assets/sweep-shared.css under `sweep-` names (unprefixed globals would leak into the unrelated scoped .row-title/.lede/.age/.actions elsewhere), imported unscoped beside each pane's own scoped remainder. Moved only what was shared: RuleHistoryPanel takes .sweep-state and keeps its button row head; PreferenceDrift keeps its tiny-type footnote and overrides the action row's layout. Lede and state now use the body-sm token instead of 0.85rem/0.9rem (13px vs 13.6/14.4px) — one value, from the design system. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 06:45:43 -04:00
bvandeusenandClaude Opus 5.5	952e56ee75	feat(tasks): the hand-off — SessionEnd releases a session's claims; the practice is written down (milestone 381 step 4) ... Release is the mechanical half: scribe_session_end.sh sends the ending session's id to /api/plugin/release-session, which releases the claims it held. A tidy-up, not the guarantee (no SessionEnd on a crash; the lease covers that), and skipped on /clear so SessionStart(clear) can still hand the claimed work back. Saying what happened is the half only the model can do. It is stated as a practice where it is read: the using-scribe skill owns it ("Hand off before this session's context stops existing", pinned in test_guidance_ownership), the static context points at it for the wrap-up moment, and add_task_log's docstring says a log claims the task. _INSTRUCTIONS is untouched. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 06:43:14 -04:00
bvandeusenandClaude Opus 5.5	e46eea3b52	feat(tasks): SessionStart reads the claim — a compaction gets its work back (milestone 381 step 3) ... The claim now pays rent to the session that set it. The SessionStart hook sends the host's `source` and the session id; the server renders a claim section by source (task_claims.render_claims): - compact / clear: the work this session had claimed, each with its two latest log entries, so a compacted session resumes from the record rather than from a count of open tasks. - startup / clear: other sessions' live claims (may still be running) and in-progress tasks whose claim went quiet (abandoned mid-task). - fork: the same, framed as "two sessions may now hold this". - resume, or no source sent: nothing. The task sidebar shows a live claim as "Being worked" and a dead one on open work as "Went quiet", so the operator sees a session die mid-task. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-24 06:41:19 -04:00
bvandeusenandClaude Opus 5.5	a585fe0be0	fix(backup): a task claim does not travel in a backup (milestone 381) ... Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 19:11:48 -04:00
bvandeusenandClaude Opus 5.5	b06b3a1d8a	feat(tasks): a task can say a session is working it — the claim (milestone 381 step 2) ... status is durable and nothing clears it, so in_progress cannot also mean "someone is on this now". The claim is that second meaning, stored as who and when so it dies on read rather than needing to be cleared. - notes.claimed_by / claimed_at / claim_touched_at / claim_session (0110). - The server stamps it on the write that is the work: reaching in_progress (update or create, via apply_status_transition) and a work log on an open task. done/cancelled/todo release it. Live while touched within CLAIM_LEASE (2h); dead on read past it, with no sweep. - The plugin's PostToolUse hook on update_task/add_task_log binds the harness's session_id (GET /api/plugin/claim-session). It binds only to a live claim the caller holds; it cannot create one. - to_dict carries `claim`. Plugin version minted. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 19:10:06 -04:00
bvandeusenandClaude Opus 5.5	b8f543f45a	fix(tasks): a create that names a status is stamped like an update to it (#3683) ... build_note (create_note and create_records) set the status and nothing it implies, so create_task(status="in_progress") wrote a started task with no started_at, and done/cancelled had no completed_at or next recurrence. The transition is now one function, apply_status_transition, called by both paths; tests pin the invariant for every status. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 19:04:27 -04:00
bvandeusenandClaude Opus 5.5	f4e9cd429b	feat(embeddings): every vector records the model whose space it lives in (#4132) ... The four embedding tables stamped chunker_version but not the model, and vector(384) is a width, not an identity: a same-width model swap would write a second geometry beside the first with no error. - embedding_model on note/rule/milestone/system embeddings (0109; existing rows stamped with the only model any install has ever run). - Every write stamps EMBEDDING_MODEL; every backfill's "current" test is is_current_stamp(), both halves of calibration_stamp(). - migrate_floor refuses while any row its surface searches is off the live model, before sampling: re-embed, then migrate. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 19:02:30 -04:00
bvandeusenandClaude Opus 5.5	11b286d786	test(dedup): a note is gated at its copy band, not the general floor (#4306) ... Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 19:00:03 -04:00
bvandeusenandClaude Opus 5.5	fc1c463641	feat(dedup): a note or task blocks only as a copy; a close match is surfaced for judgement (#4306) ... Measured on the live corpus, the 74 note pairs at or above the old 0.90 bar were almost all distinct siblings — consecutive dev-logs, sub-notes of one design, research parts — and the one clear copy sat at 0.997. The block refused the next dev-log and taught force=true, as #4134 found for rules. - The semantic arm blocks notes and tasks only at >= 0.98. The title block stays; processes keep 0.90 (not measured). - 0.87 to 0.98 comes back as `overlaps` on the create reply, from the same per-chunk searches, with a note that leaves the call to the session: fold in and delete if it is the same record, keep both if a sibling. - create_note, create_task, create_records and start_planning's steps all carry it; a batch names the record each overlap belongs to. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 18:53:22 -04:00
bvandeusen	eb6912c722	Merge pull request 'Snippets gain notes; when_to_use is the situation it is ranked on (#4378)' (#184) from dev into main	2026-09-23 18:00:35 -04:00
bvandeusenandClaude Opus 5.5	4ae18a9dd9	feat(snippets): a snippet has notes; when_to_use is the situation it is ranked on (#4378) ... A snippet had no field for prose, so what a session learned about one went into when_to_use — the trigger joined onto every chunk it is embedded as. A sweep found write-ups of up to 3 KB there, headings and all. - notes: stored after the code under `## Notes`, parsed back from the body, carried by every path that rebuilds it (update, merge, un-merge). A snippet with no notes composes the body it always did. - create/update_snippet (MCP) take notes and return trigger_advice when when_to_use is long, headed or multi-paragraph. Advice, not a refusal. - Tool docs, the reusing-code skill and the editor hint describe the trigger as the situation and point the explanation at notes. - Editor gains a Notes field; the detail view renders it as markdown. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 17:27:22 -04:00
bvandeusen	14734ebe46	Merge pull request 'dev → main: auto-inject reads the conversation, startup names its failure, menu lines carry metadata, titles are names' (#183) from dev into main	2026-09-23 16:57:42 -04:00
bvandeusenandClaude Opus 5.5	66e21a6c60	refactor(notes): a snippet's and lesson's stored title is its name; the trigger joins it only in the embedded document (milestone 427) ... The title was `subject — trigger` because the stored title WAS the embedded one, and the join is what makes these kinds rank on the situation they apply to (#2485). Every surface that shows a title then showed the trigger too -- menus, lists and search rows ran to kilobytes. - embeddings.document_title(title, note_type, data, body) joins the trigger from `data` (body fallback) at embed time. Idempotent: an un-migrated composed title comes out the same, never doubled. The embed path, the startup backfill and the dedup gate's semantic signal all use it, so the embedded text -- and every vector -- is unchanged. - Writers store the subject: snippet create/update (service, REST, MCP) and lesson_document. Both compose_title helpers are removed. - Readers: dedup takes `data`; the menus strip the embedded title from a passage; list rows project `when_to_use`, which SnippetListView reads. - 0108 rewrites existing rows on an exact `' — ' || <own trigger>` suffix with raw SQL, leaving updated_at alone so the backfill does not re-embed the corpus for identical vectors. Downgrade recomposes. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 16:48:28 -04:00
bvandeusenandClaude Opus 5.5	bb632c4196	feat(retrieval): a menu line is a name, its kind and System, and the whole passage that matched (#4364) ... Injected lines rendered a snippet's or lesson's title, which carries its whole trigger by construction (the embedding shape) and ran past 1,500 characters -- again on every `seen` repeat. The passage under a line was cut to 200 chars from the middle, keeping its head (the title again) and losing where the match was. Now, on both the prompt menu and the write-path prior-art menu: - the line shows the record's NAME (snippet data.name / lesson subject), with its kind and System (`[issue (done) · Plugin & hooks]`); - the passage is the whole matched chunk, title prefix stripped, on one line so the blockquote holds; a title-only match hands over the trigger; - a `seen` record is a one-line pointer to what is already in context. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 16:29:48 -04:00
bvandeusenandClaude Opus 5.5	20227ebb5d	fix(plugin): recent-context cap counts text, and an empty transcript is not a failure (#4364) ... The trailing newline became a space before the 600-char cut, so the cap kept 599 characters of text; and under pipefail a grep that matched no reply made the helper exit 1. Trim before cutting; return 0 explicitly. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 16:08:01 -04:00
bvandeusenandClaude Opus 5.5	eb00554976	fix(plugin): a SessionStart that loads no project says why, and names the first move (#4366) ... The context fetch folded a timeout, an HTTP error and a refused key into one sentence that ended "enter_project() as needed" -- read as optional, so a session could start with no recent milestones or open tasks and no way to know what prior work existed. The fetch now names the cause and the elapsed time, retries once (6s) only where a retry can change the answer, and the fallback states enter_project as the first step, with the marker's project id when there is one. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 16:07:33 -04:00
bvandeusenandClaude Opus 5.5	574b27ae74	feat(plugin): auto-inject retrieves on the conversation, not the typed words alone (#4364) ... The prompt hook sent only the operator's message, so a mid-session follow-up ("yes do that") named nothing a note, lesson or rule could match. The hook now reads the tail of the last assistant reply from the transcript and sends it as `ctx`; the notes and rule arms append it to a short prompt (<= 280 chars), prompt first, capped at 600 chars. No model tokens: it is embedding input, and the injected menu's budget is unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-09-23 16:05:21 -04:00
bvandeusen	bf2871ffb4	Merge pull request 'Shape ledger: a semantic miss is not evidence; floors sized for the reader (#4208, #4306)' (#182) from dev into main	2026-09-22 09:50:33 -04:00
bvandeusenandClaude Opus 5	a01deeb851	fix(shapes): the signature basis admits the band true instances score in (#4306) ... Measured over 459 judged instance rows against every same-family canon: true instances score 1.0 or ~0.795 (a model whose mixin list differs from the canon's), and 0.8 cut the second band entirely. The proposal is read before it is confirmed, so the floor admits it: 0.75 takes every measured true row, at 35 wrong-canon pairings instead of 14. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy	2026-09-22 08:44:58 -04:00
bvandeusenandClaude Opus 5	312dc9f6f7	fix(shapes): the semantic arm proposes at the write-path floor, not a private 0.8 (#4208) ... 0.8 was sized for proposals nobody reads; every semantic proposal is read by a judge before it is confirmed. Measured, it proposed 0 of 150 while judged instances of a canon score 0.68-0.71 - the write-path hint's own floor asks the same question of the same documents at 0.68. The arm now uses that floor, scans 8 hits instead of 3 (a true instance ranked 4th behind snippets of other language families), and the proposer version bumps to 5 so rows examined under the old floor are read again. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy	2026-09-22 08:33:01 -04:00
bvandeusenandClaude Opus 5	a875a1b2ee	fix(shapes): a semantic miss is not evidence — the divergence check stops reading it (#4208) ... Measured live: true instances of the service-unit canon score 0.68-0.71 against it at best, helpers 0.66-0.75 against unrelated snippets, and nothing reaches the 0.8 floor. The "conclusive miss" fired for nearly every body and silenced real divergences exactly as it silenced helpers. The stored miss basis, its flag withdrawal and the report plumbing are removed; the floor stays at 0.8 and the new-shapes-first ordering stays. False prompts are answered by judgment (exempt with a reason). Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy	2026-09-22 08:27:15 -04:00
bvandeusen	3530ed5e87	Merge pull request 'dev → main: the meaning check reads new shapes first, and its miss withdraws an early flag (#4208)' (#181) from dev into main	2026-09-22 08:14:50 -04:00
bvandeusenandClaude Opus 5	e2197ac799	fix(tests): assert the withdrawn flag on its row, not on a count the skew margin inflates (#4208) ... Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy	2026-09-22 08:09:52 -04:00
bvandeusenandClaude Opus 5	19438cc894	fix(shapes): the capped meaning pass reads new shapes first, and its miss withdraws an early flag (#4208) ... Measured on the first live refresh after 91cde6c deployed: the version bump queued 1,533 rows for the semantic arm, the cap read 150 of them in row order, and all six shapes new since the previous refresh - the only rows flag_divergence acts on, and the highest ids - were flagged before the arm reached them. The gate silenced nothing because it never got to look, and since a flag persists until judged, a later conclusive miss could not take it back. - propose_for_repo sorts the semantic todo by _semantic_priority: unclassified before scoped, newest first. - flag_divergence withdraws a standing flag when the row now carries a conclusive miss; that evidence alone withdraws one. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy	2026-09-22 08:05:49 -04:00
bvandeusen	cc791de0e5	Merge pull request 'dev → main: rule overlap check, design-guidance write arm, usage chip seam, divergence meaning gate' (#180) from dev into main	2026-09-22 07:48:53 -04:00