feat: extraction coverage — message-granular ledger + token-batched runs (d132373 vision)

THE MESSAGE IS THE UNIT OF COVERAGE (vision-extraction-coverage.md): a
per-chat append-only ledger (coverage.jsonl) records which messages the
pipeline has extracted, by content fingerprint over exactly what the
extraction view sees (one shared line builder — core/coverage.ts); the
uncovered remainder is DERIVED at read time, never dual-tracked. A quiz
answer merging into the asking message re-opens only that message;
plan-block data-part attach never re-opens anything.

- The trigger (turn-service) replaces every-3-quiz-answers with
  uncovered-tokens >= EXTRACTION.chunkTokens (4096) — quiz-less sessions
  extract too, content size is the honest signal.
- runExtraction is now chunked: token-budgeted batches of the oldest
  uncovered consecutive messages (a tool call + result never split), each
  merged batch checkpointing its messages' coverage atomically — an abort
  or error loses at most the in-flight batch; merged batches stay covered.
- Observation refs are batch-tagged (obs:<batchTag>:<sourceId>): re-runs
  of the same batch dedupe; a re-opened message's fresh understanding
  lands as a new event. Fixes the old obs:p1 position-collision.
- New API: GET /api/graph/coverage (exact per-session derived coverage +
  running flags, most-uncovered first) and POST /api/graph/coverage/extract
  (manual run for one session, 409 while in flight).
- Graph view chrome: the coverage button opens a panel with every
  session's covered/uncovered tokens and a per-session Extract button —
  the manual answer to aborted runs, errors, and dormant tails. Renders
  even when the graph is empty: an empty graph with uncovered sessions is
  exactly when it matters. Polls only while open.
- Notes imports keep the whole-file checkpoint path (coverage undefined).
- Tests: pure-core coverage suite (11), chunked-pipeline suite (3:
  multi-batch + no-op, abort-keeps-earlier-batches + remainder re-run,
  re-open alone + data-part invisibility), panel render suite (5);
  pendingQuizAnswers and its tests deleted as dead code. 486/486.

Live-smoked on real GLM: manual extract of "teach me modal realism" ran
one batch, wrote 4 coverage entries, panel flipped to "1.3k covered ·
complete" with the button disabled, graph refetched (nodes 11), usage
persisted with real stats.

config.ts

@@ -62,7 +62,16 @@ export type ModelRole = keyof typeof MODELS;
  * (server/turn-service.ts) so it can be swapped without touching the
  * pipeline.
  */
-export const EXTRACTION = { everyNQuizAnswers: 3 } as const;
+/**
+ * The extraction trigger (vision-extraction-coverage.md, 2026-09-15): a run
+ * fires when a chat's UNCOVERED transcript tokens reach the chunk budget.
+ * Runs are token-budgeted batches of the oldest uncovered messages — this
+ * knob is the transcript share of the extractor's context (it also carries
+ * the whole graph + instructions), so it bounds both cost and chunk size.
+ * Replaces the old every-3-quiz-answers trigger, which never fired for
+ * quiz-less sessions.
+ */
+export const EXTRACTION = { chunkTokens: 4096 } as const;
 
 /**
  * The LIVE graph store (src/store/graph.ts) — owned by the app's extraction
@@ -74,6 +83,10 @@ export const LEDGER_FILES = {
 	events: path.join(PATHS.graph, "events.jsonl"),
 	mappings: path.join(PATHS.graph, "mappings.jsonl"),
 	sessions: path.join(PATHS.graph, "sessions.jsonl"),
+	/** Per-message extraction coverage (contracts/graph.ts CoverageEntry;
+	 *  the checkpoint's replacement for chat extractions — notes keep
+	 *  sessions.jsonl, whole-file as they are). */
+	coverage: path.join(PATHS.graph, "coverage.jsonl"),
 	/** LLM-named community records (contracts/graph.ts ClusterLabeling). */
 	clusterLabels: path.join(PATHS.graph, "cluster-labels.jsonl"),
 } as const;