Extraction-UX data layer: the chunk budget becomes a graph setting; the chat view gets a per-session coverage read

Owner-locked extraction-UX redesign (dispatch 2026-09-24), part 1 (data
layer; the UI chunk follows).

THRESHOLD -> SETTING
- config.ts's EXTRACTION.chunkTokens dies; the default moves into
  FACTORY_SETTINGS.graph.extractionChunkTokens (4096, the old constant's
  value). GraphSettings gains the optional field, Required at resolution
  via the standard ?? FACTORY pattern — pre-redesign records resolve the
  default cleanly.
- FLOOR 500 (the implementer's call, documented on the field): every run
  pays the graph-carrying prompt overhead out of the write channel's
  money — a smaller budget fires penny-batches that cost more per
  extracted token than the content is worth. The sanitizer CLAMPS up
  (bd68486 clamp-never-reject discipline: fractions floor, junk drops);
  the settings PUT REJECTS below-floor with the rationale in the message.
  No ceiling: a large budget just delays extraction — the user's stated
  cost/thoroughness tradeoff, not a misconfiguration to police.
- The trigger (turn-service.triggerExtraction) takes the budget as a
  parameter — chat-handler passes effective.graph.extractionChunkTokens,
  the fresh per-turn read, same as every other gate.
- The pipeline's BATCH side threads through the same number:
  ExtractionPipelineDeps gains an OPTIONAL getChunkTokens getter with the
  factory default (Teacher's 24 test fixtures stay untouched; the two
  call-site lines inside extraction.ts are the only cross-band edits,
  flagged). chat-handler + backfill/import-notes wire the live
  effectiveSettings — trigger and batches share one budget, always.

PER-SESSION COVERAGE READ
- sessionCoverage(chatId) (server/chats.ts): the chat view's ring-meter
  block — totalMessages/coveredCount/uncoveredCount/coveredTokens/
  uncoveredTokens (the same coverageOf derivation /api/graph/coverage
  serves, scoped to one chat), running (chat-kind extraction registered
  for this id), and lastFoldedAt (the chat's newest coverage row's fold
  — a cheap single pass; null before any fold). GET /api/chats/[id]
  carries it as coverage: {...}; unknown chat -> null (the route 404s
  first).
- /api/graph/coverage (the all-sessions list) compiles untouched — the
  per-session read is a scoping of it, not a supersession; the UI's
  sidebar/ring chunk decides which surface it consumes.

Tests: factory/sanitizer pins (clamp-up, fraction-floor, junk-drop),
resolution pins (absent -> 4096, stored 2000 wins), settings-body pins
(valid/absent/fraction/below-floor 400/junk 400), sessionCoverage pins
(derived split, newest-fold scoping, cross-session isolation, running via
the registry, null on unknown chat). 893/893.
This commit is contained in:
amosblomqvist
2026-09-24 15:12:24 +03:00
parent b9397fa783
commit 2e9fd01c0c
16 changed files with 275 additions and 41 deletions
+70 -1
View File
@@ -21,6 +21,7 @@ import type { UIMessage } from "ai";
import type { AuditResult, NamingRunUsage } from "../src/core/contracts.ts";
import type { QuestionAnswerData } from "../src/core/question-core.ts";
import { getGraph, graphSnapshot, mergeFindings, type GraphDeps } from "../src/core/graph.ts";
import { coverageSlots } from "../src/core/coverage.ts";
import { graphStore } from "../src/store/graph.ts";
import { chatStore } from "../src/store/chats.ts";
import { LEDGER_FILES, PATHS, SOURCES_FILE } from "../config.ts";
@@ -618,7 +619,7 @@ describe("graph ledger store", () => {
// ─── session deletion (wave 6 — the first destructive ledger operation) ─────
import { deleteChatTraces, type ChatDeletionStats } from "../src/core/graph-deletion.ts";
import { deleteChatSession } from "../src/server/chats.ts";
import { deleteChatSession, sessionCoverage } from "../src/server/chats.ts";
import { beginTurn, endTurn } from "../src/server/turn-liveness.ts";
import { jobStore } from "../src/store/jobs.ts";
import {
@@ -989,3 +990,71 @@ describe("single-node deletion (deleteNodeTraces + deleteGraphNode, node interlu
assert.deepEqual(deleteGraphNode("n_orch"), { ok: false, status: 404, code: "not_found", error: "No such node" });
});
});
describe("session coverage read (extraction-UX redesign, 2026-09-24)", () => {
it("one session's block: derived uncovered, the newest fold, honest nulls", () => {
// Empty coverage: everything uncovered, no fold yet, not running.
const chat = fixtureChat("coverage read", [
user("cov_u1", "tell me about coverage reads"),
user("cov_u2", "and about per-session blocks"),
user("cov_u3", "a third distinct message"),
]);
const empty = sessionCoverage(chat.id)!;
assert.ok(empty);
assert.equal(empty.totalMessages, 3);
assert.equal(empty.coveredCount, 0);
assert.equal(empty.uncoveredCount, 3);
assert.equal(empty.coveredTokens, 0);
assert.ok(empty.uncoveredTokens > 0);
assert.equal(empty.running, false);
assert.equal(empty.lastFoldedAt, null, "no fold yet");
// Fold the first two messages: the read derives the split + the
// newest fold timestamp from the ledger rows.
const slots = coverageSlots(chatStore.getChat(chat.id)!.messages as UIMessage[]);
graphStore.appendCoverage({ chatId: chat.id, fp: slots[0]!.fp, tokens: slots[0]!.tokens, foldedAt: "2026-09-24T10:00:00.000Z" });
graphStore.appendCoverage({ chatId: chat.id, fp: slots[1]!.fp, tokens: slots[1]!.tokens, foldedAt: "2026-09-24T11:30:00.000Z" });
// Another session's row must not leak into this read.
graphStore.appendCoverage({ chatId: "chat_other", fp: slots[2]!.fp, tokens: slots[2]!.tokens, foldedAt: "2026-09-24T23:00:00.000Z" });
const cov = sessionCoverage(chat.id)!;
assert.equal(cov.totalMessages, 3);
assert.equal(cov.coveredCount, 2);
assert.equal(cov.uncoveredCount, 1);
assert.equal(cov.coveredTokens, slots[0]!.tokens + slots[1]!.tokens);
assert.equal(cov.uncoveredTokens, slots[2]!.tokens);
assert.equal(cov.lastFoldedAt, "2026-09-24T11:30:00.000Z", "the NEWEST fold, and scoped to this session's rows");
});
it("running: true only for THIS session's chat-kind run (the registry pin)", () => {
const chat = fixtureChat("coverage running", [user("cov_r1", "running pin")]);
const g = globalThis as { __lhExtractionRuns?: unknown };
const realRuns = g.__lhExtractionRuns;
try {
g.__lhExtractionRuns = {
running: new Map([
// a notes run for the same id is NOT this session's chat run
["src_notes", { chatId: "src_notes", kind: "notes", phase: "extracting", startedAt: 1, usage: {}, controller: new AbortController() }],
["other_chat", { chatId: "other_chat", kind: "chat", phase: "auditing", startedAt: 2, usage: {}, controller: new AbortController() }],
]),
inFlight: new Set(),
lastStartedAt: 0,
};
assert.equal(sessionCoverage(chat.id)!.running, false, "no chat-kind run for this id");
g.__lhExtractionRuns = {
running: new Map([
[chat.id, { chatId: chat.id, kind: "chat", phase: "extracting", startedAt: 3, usage: {}, controller: new AbortController() }],
]),
inFlight: new Set(),
lastStartedAt: 0,
};
assert.equal(sessionCoverage(chat.id)!.running, true);
} finally {
g.__lhExtractionRuns = realRuns;
}
});
it("unknown chat → null (the caller owns the 404)", () => {
assert.equal(sessionCoverage("chat_never_was"), null);
});
});