feat(skill-memory): per-skill cross-session recall + historian auto-extraction

[iceteaSA]

Summary

Adds skill-memory — per-skill "motor memory" that gives a skill cross-session recall of its own hard-won lessons (gotchas, discoveries, fixes, workflow steps). When a skill's SKILL.md declares skill-memory: { enabled: true }, accumulated notes for that skill surface automatically in a <skill-memory> block appended to the skill tool's result on every load — and, with the historian extension, the historian writes those notes automatically during compaction (no agent action required).

It's fully opt-in per skill and cache-safe by construction: the block rides the tool-result tail (conversation), never the cached system/m[0] prefix, so it can't bust the prompt cache.

How it works

• Transparent recall — three-hook augmentation: tool.definition advertises an intent param; tool.execute.before stashes the intent (bounded TTL); the after-hook parses the skill's Base directory, reads its SKILL.md frontmatter, and formats the recall block. Lands in the tool RESULT (cache-safe).
• Write paths — ctx_skill_note (agent-authored) and the historian (auto-extracted). Both dedup on a normalized hash.
• Intent-scoped ranking — a recall cascade: model-matched embeddings → cosine blend over intent_embedding + delta_embedding (relevance/recency/hit weights tunable per skill via ranking_* frontmatter); FTS5 fallback over a content-linked skill_memory_fts vtable; flat recency×hit fallback.
• Historian auto-extraction — the historian sees TC: skill(<name>) markers in its chunk and emits a <skill_observations> block; both the OpenCode and Pi runners promote those post-commit as global notes (project_identity='*', source_type='historian'), recallable from any project.

Review units (4 commits)

The branch is organized into four coherent, reviewable phases:

1. P1 — transparent per-skill recall: skill_memory table migration, the three-hook augmentation, flat recall + storage, ctx_skill_note/ctx_skill_recall tools, opt-in distill-skill-memory dreamer task, TUI/ctx-status stats, docs.
2. P2 — embeddings + intent-scoped recall: delta_embedding + recall_count columns + skill_memory_fts FTS5 vtable; embed-on-write; the cosine/FTS recall cascade; a programmatic (no-LLM) reembed pre-step.
3. P3a — historian-extraction foundation: the TC: skill(<name>) marker keystone; origin_project + source_type columns; global-tier notes unified under project_identity='*' (collision-merge); partitionKey routing.
4. P3b — historian auto-extraction pipeline: prompt emits <skill_observations>, parser, validated-result threading, both runners promote via the shared promoteSkillObservations helper, plus an initializeDatabase self-heal net (re-creates skill_memory + ensureColumn so an upgraded DB recovers even if a migration row is lost).

Schema / migrations

Three migrations (numbered after the current master ceiling): skill_memory table, then delta_embedding/recall_count/FTS, then origin_project/source_type/* unification. LATEST_SUPPORTED_VERSION bumped in lockstep (the schema-version-fence test enforces it). Migration bodies are ensureColumn/IF NOT EXISTS idempotent.

Testing

Full plugin + Pi suites pass (one unrelated pre-existing full-suite ordering flake in tui-config.test.ts that passes in isolation), tsc clean both packages, lint clean, build produces all bundles. Dedicated coverage for the migrations (coexistence + fence), recall rungs, the tools, FTS triggers/backfill, the '*' collision-merge, and the historian promotion path on both runners. Verified working live: the historian auto-extraction writes genuine source_type='historian' notes, embeddings populate, and the read-side recall_count increments on surfacing.

Notes for reviewers

• Migration version numbers are placeholders relative to this fork's base — happy to renumber to whatever slots are free at merge time.
• The four commits are independently meaningful; if you'd prefer this as stacked PRs (P1 / P2 / historian), I can split it.

---

^{Need help on this PR? Tag /codesmith with what you need. Autofix is disabled.}

---

Summary by cubic

Adds per-skill cross-session memory with opt-in via SKILL.md and a cache-safe <skill-memory> block appended to skill tool results. Also adds intent-scoped recall with embeddings, historian auto-extraction to global notes, and a fix to prevent opencode 1.17 from breaking plugin load.

• New Features

  • Per-skill recall: ctx_skill_note writes notes; ctx_skill_recall fetches without reloading. The skill tool advertises an optional intent; a before-hook stashes it and an after-hook formats recall into the tool RESULT (cache-safe).
  • Intent-scoped ranking: cosine blend over intent_embedding + delta_embedding with FTS5 fallback; flat recency×hit fallback; read-side recall_count. Programmatic re-embed backfills stale vectors; opt-in dreamer task distill-skill-memory runs a read-only health pass.
  • Historian pipeline: prompt emits <skill_observations>, parser extracts them, and both runners promote them as global '*' notes (source_type='historian') when not discarded. TC: skill(<name>) markers anchor extraction.
  • Schema/migrations: add skill_memory table + FTS vtable, delta_embedding/recall_count, origin_project/source_type, and unify global notes under '*'. LATEST_SUPPORTED_VERSION set to 44 with init-time self-heal.
  • UX: Status/TUI show per-project skill-memory totals and pinned counts. Config/docs include opt-in distill-skill-memory.

• Bug Fixes

  • Move buildHiddenAgentConfig to a non-entry module so only the default export remains; stops opencode 1.17 from invoking it as a plugin factory and breaking hook/tool registration.

^{Written for commit 952e736. Summary will update on new commits.}