Owner-approved brief (orchestrator): the canvas stops drawing implication
nodes as first-class nodes and starts drawing them as what they are — the
point where co-premise lines converge.
- deriveView (core/graph.ts): single-premise chains collapse to ONE direct
premise->conclusion arrow — no imp node minted (a chain is always N-in/
1-out; one premise is the degenerate case). Multi-premise chains keep
the imp node + fan. Dangling guard unchanged.
- physics (core/layout.ts createGraphSimulation): per-link rest length —
a link touching an arg_-prefixed endpoint gets HALF the base link
distance, default or user-tuned alike; everything else about imp-node
physics citizenship unchanged.
- canvas (components/graph-canvas.ts): imp nodes are PURE GEOMETRY —
invisible (no disc, no label) and unpickable (excluded from pickAt's
hit-test projection). Edges INTO an imp node: headless, shaft runs to
its CENTER (toRadius 0, no head triangle). Edges OUT: shaft starts at
the center (fromRadius 0), arrowhead lands on the conclusion's disc
edge. Single-premise direct arrows render as today's plain arrows.
- comment repairs (same commit): the two stale double-shaft claims
(CanvasEdge doc + the draw-pass block) rewritten to the truth — plain
single shafts; bundles are headless converging lines + one arrowed
out-edge; no double-shaft glyph exists anywhere.
- tests (+9): deriveView pins (single-premise collapse, multi-premise
fan, shared-conclusion distinctness, dangling drop); imp-link half-
distance settle pins; arrowGeometry zero-radius laws + isImpNodeId
pin; graph.test.ts's snapshot invariant now counts only MULTI-premise
live chains (its fixture's single-premise chains mint zero imp nodes);
layout settle fixture updated for the collapse.
The owner's live test surfaced it: after importing notes, the chains view
listed implication nodes as bogus singleton "chains" — and each carried
the same arg_ id as the real stored chain, tripping React's duplicate-key
error (chain-table.tsx:372).
Root cause: graph-view passed snapshot.nodes — the derived canvas view
(propositions + implication nodes) — into ChainTableOverlay, whose
chainsForSelection turns every unchained node into a singleton chain.
An implication node is never a chain member (members are proposition
ids), so every imp node minted a bogus singleton with a colliding id;
its row was even selectable, leaking arg_ ids into practice input.
Fix (owner-approved shape): GraphSnapshot gains `propositions` — the
stored-truth node list riding beside `chains` for exactly this class of
consumer. The chain table now receives snapshot.propositions; the canvas
keeps snapshot.nodes (imp nodes are meant to be drawn). Practice pipeline
unaffected (it already read getGraph, which is propositions-only).
Test: the snapshot split pinned as an invariant in graph.test.ts — image
= truth + one imp node per fully-live stored chain; truth never carries
an arg_ id.
- architecture.md section 6 rewritten: stored truth = propositions + chains
(chains.jsonl); deriveView as the lossy image (implication nodes +
untyped arrows, rebuilt per read); the bijection framing (independent
arguments for one conclusion stay distinct — the corruption the edge
store invited); new deletion-semantics paragraph (proposition death
cascades to every referencing chain; arg_ death = one argument);
supports retirement stated plainly; auditor's propositions-only scope;
clusters stated as birth-session partition truth (no Louvain claim)
- section 7 practice chain model: stored-chains inclusion law replaces
follows-edge grouping; chainsToGraph bijection claim deleted
- README: graph clauses (stored chains, derived view, chain dedupe),
practice clause, ledger inventory, and two long-stale line-5 claims
(ledger events, semantic top-K) corrected
- contracts/graph.ts GraphSnapshot comment: Louvain claim replaced with
birth-session truth; extraction.ts comments no longer narrate the
dead expandFindings/chainsToEdges seam
Owner rulings 2026-09-30: reasoning chains are the stored truth; the graph
canvas renders a lossy derived image. No migration, no backcompat — old
graph data was wiped.
- contracts: GraphChain (arg_-minted id, premises, conclusion) replaces
typed edges; GraphEdge survives only as the untyped derived arrow;
GraphSnapshot carries stored chains; supports edges retired entirely
- store: chains.jsonl ledger (edges.jsonl purged at load alongside legacy
events.jsonl); readChains/appendChain seam; merge dedupes by
(sorted premises, conclusion), re-assertions append under the same arg_ id
- core: deriveView mints implication nodes (name ⟹, statement via
formatChainLine) plus premise→imp→conclusion arrows; clusters stay
proposition-only (birthSessionPartition); chainsForSelection now groups
STORED chains (chain rides iff every member selected) — independent
arguments for one conclusion never union; chainsToGraph/chainsToEdges die
- extraction: extractor submits chains natively (expandFindings deleted);
auditor receives propositions only; supports fan-out gone
- deletion: full death of a proposition kills every referencing chain;
arg_-prefixed node deletes kill that chain; chainsRemoved stats
- UI: every arrow renders the ⟹ double shaft; supports toggle + thickness
slider and detail-card edge sections deleted (card keeps name +
proposition); chain table + practice pipeline read stored chains
- tests: 1188 green across the new seams
Owner 2026-09-30: the confirm dialog's pre-flight impact read had to
go — what full death takes is obvious, the per-open fetch flickered,
and richer facts would only confuse as deletion semantics evolve
(rewiring is on the table). The screen is now: Delete node? / Delete
N nodes?, the names in the mono block, one permanence line, Cancel /
Delete. No loading state, no gone state (a 404 mid-run lands in the
honest failure line), no sessions join — the joins prop died too.
The dead path is deleted end to end: GET /api/graph/nodes/[id],
graphNodeImpact (server), nodeDeletionImpact (core) and their tests.
WORDING: node/node(s) is THE UI word for graph objects, standardized
across every surface's copy (owner, same ruling): the dialog titles,
the chain table's counts/search/summary/delete aria-labels, the
practice dialog's cluster counts, selection line, and empty-cluster
hint. Internal identifiers (selection.propositions) unchanged.
Rewritten dialog pins (tests/delete-node-dialog.test.tsx): minimal
contract — no facts/loading/fetch copy, singular/plural titles, the
cap, 409 dock phrasing, busy states, no 'proposition' left in the
dialog.
- core formatChainLine: names + arrow one-liner, singleton marker, pure
- graph-view Chains button (chrome row, empty-graph hidden) opens the
overlay: fuzzy search (names/aliases/statements), collapsible chain →
member → statement rows, birth-session + created columns, no
understanding-levels column
- pinned Selected section derives the agents' actual input live
(chainsForSelection over the selection; premise without its
conclusion shows as the singleton it becomes)
- Generate opens the creation dialog in CUSTOM mode: selection summary
+ dated default title, posts {nodeIds, params, note}; cluster mode
untouched on /practice
- live-verified on the owner's dev server: 219 chains, derived preview,
search-never-filters-Selected, dialog handoff (selection pass-through
bug caught + fixed en route), Esc/backdrop dismiss, zero writes
- practice UI files re-normalized to tabs (my earlier prettier runs had
drifted them to the 2-space default; whitespace-only)
17 render/unit pins added; gates: tsc 0, 1174/1174, lint 0, build 0
- dialog: optional 'Anything else?' textarea (typing-only, 2000-char mirror)
- API: body gains note? — trimmed, whitespace-only omitted, hard 400 over 2000
- pipeline: note persisted on the set and threaded to both agent stages
- agents: THE LEARNER'S NOTE prompt block (present only when set) + the
weighed-never-owed stance pinned in both doctrines
- fix en route: doubled THE PARAMETERS heading in both prompts since slice 3
(renderParams owns the heading; the literal blocks removed)
Rulings: each problem generation is its own visible dock job (the
extraction per-chunk pattern), and practice shares extraction's
semaphore — one process-wide 3-permit pool for ALL background LLM
jobs; total background LLM concurrency bounded at 3.
A. SHARED POOL: new src/agent/subagents/bg-llm-semaphore.ts —
globalThis __lhLlmSlots, PERMIT_COUNT 3 (the ruling), the
fresh-take/handed-off-permit deadlock discipline preserved for
BOTH callers. extraction.ts's withExtractSlot is now a thin
wrapper (job-row signal → withBgLlmSlot); __lhExtractSlots and
__lhPracticeSlots both die. The partitioner now acquires a permit
too (it's a background LLM job — it didn't before).
B. REGISTRY ROWS: the aggregate setId:generation / setId:grading rows
are replaced by setId:partition (phase partitioning, label
'Partitioning — title'), setId:gen:problemId (queued→generating,
'Problem i/N — title'), setId:grade:problemId (queued→grading,
'Grading i/N — title'). Each row carries its OWN abort controller
and its OWN usage (one PracticeStepLog per row — the aggregate
partitioner/generator/grader folding dies). Row key = feed id =
abort key (the dock dup-key law).
C. ABORT SEMANTICS: abortPracticeRow(key) routes by shape — gen row:
THAT problem only (error 'Aborted', siblings continue, set settles
ready with one errored problem); partition row: the whole run;
grade row: that grade drops (answer kept, re-submittable).
abortPractice(setId) composes from row aborts + the synchronous
persisted marks (a set-abort's verdict stands before the settles
re-read it — the settle step keeps an existing error status).
/api/activity/abort kind practice now takes the ROW key (charset
admits ':').
D. FEED + DOCK: ActivityPractice/FeedPractice carry per-row identity
(id = row key, problemIndex/problemTotal); dock blobs render per
row, labels carry the i/N; the aggregate row is gone.
E. Boot sweep unchanged at set grain; the live-row check is now a
key-prefix scan (any live row of the set protects it). The
updatedAt heartbeat covers the new row scheme as-is.
Tests (20 in the pipeline suite): per-problem row shape/uniqueness/
i-N labels (partition row frozen behind a gated partitioner; per-row
usage ISOLATION pin — b's log never shows on c's row); abort-one-gen
(sibling completes, set ready with one errored problem); partition-
row abort; queued grade-row abort (dead-ticket path: answer kept,
re-submittable, sibling lands); shared-pool identity + contention
(practice queues behind extraction-style holders); registry/dock
feed mapping. Test isolation hardened: unique per-store set ids,
afterEach registry/lock/pool reset (a timed-out test can no longer
poison the rest).
architecture.md: jobs-pattern paragraph rewritten (per-problem rows,
shared pool, abort routing).
1149/1149, tsc 0, lint 0, build 0.
Prior state: zero formatting guidance anywhere in the agent module —
models wrote prose-only by default.
GENERATOR_DOCTRINE Part III gains the FORMATTING bullet (after the
THE PARAMETERS bullet, before PREVIOUS PROBLEMS): statement, solution,
and rubric render as full Markdown — math always LaTeX (inline $…$,
display $$…$$), code/pseudocode/formal systems in fenced blocks with
a language tag, identifiers inline as `code`, tables for parallel
structure, lists for enumerations; prose-only renderings of
mathematical or structured content are a defect.
GRADER_INSTRUCTIONS gains the feedback-formatting paragraph (before
the OUTPUT section): full Markdown, LaTeX math, fenced code, lists/
tables where they carry structure — teach the boundary in properly
formatted prose, not plain text.
PARTITIONER gets nothing (machine-shaped output).
Tests: substring pins on the exported doctrine constants — the exact
FORMATTING sentence + ordering (after presentation, before previous
problems), the exact grader paragraph + before-OUTPUT ordering.
Architecture.md §7 one clause (the formatting doctrine in the
generator's prompt inventory).
1144/1144, tsc 0, lint 0, build 0.
Owner report: created a set, 'Interrupted (server restarted)' showed
on list + set views, generation proceeded and overwrote it. The
sweep's 'generating + no registry row' test had a false-positive
mode: it ran at EVERY pipeline instantiation, and an instance could
evaluate against a registry whose fresh row it couldn't observe.
Three guards, per ruling:
1. HEARTBEAT: ProblemSet.updatedAt? (contract + doc) — bumped on
every store write; createSet stamps it = createdAt; saveSet
re-stamps (validator tolerates absence for legacy rows).
2. ONCE PER PROCESS: the sweep guards on globalThis
.__lhPracticeSweepDone — no instance re-evaluates after the
process's first sweep.
3. GRACE WINDOW: only sets whose heartbeat (updatedAt ?? createdAt)
is older than 120s are stamped. A live run saves at every phase/
problem transition, so it is structurally unreachable; a true
orphan is minutes stale at next boot. One [practice <id>] log
line per stamped set (the extraction/jobs console.error idiom).
Tests: stale orphan stamped; FRESH generating set untouched (grace);
once-guard (second factory instantiation never re-sweeps); live-row
protection re-armed via resetSweep() test seam; store pins for
updatedAt birth-stamp + re-stamp + legacy tolerance. Architecture.md
sweep sentence updated (once-per-process + grace semantics).
1142/1142, tsc 0, lint 0, build 0.
Contracts: LadderRung 0-4, CueDistance 0-2, Presentation theory|
application; PracticeParams carries the three named levels. Doc
comments hold the three definition tables verbatim (rung names +
definitions from the ladder doctrine; cue levels; presentation
levels).
Core: LADDER_RUNGS/CUE_LEVELS/PRESENTATIONS tables in src/core/
practice.ts (definitions verbatim) — ONE source spoken by the agents'
prompts, the dialog's stepped controls, and the exam header; core
barrel re-exports practice.ts (pure domain, browser-safe).
Agents: Part I's ladder intro now 'five rungs, numbered; the request
arrives as a rung' with bullets numbered 0-4 (definitions untouched);
Part III's parameters block replaced with the named-level doctrine
(rung = exact class, no continuum; cue counts lesson examples AND
previous problems' situations; presentation dresses, never changes);
partitioner's RESPECT THE PARAMETERS replaced (low rungs = many small
assignments, high = larger; far cue makes confusables-together MORE
important; presentation does not shape the partition). renderParams
outputs the exact named-level block. Anchor/0..1 language swept dead.
Service + store: strict union validation — floats between levels,
out-of-range, wrong strings, legacy dial shapes all 400 at the API
and fail isProblemSet (legacy sets skipped from lists; no migration —
data/practice is disposable scratch, owner wipes before testing).
UI: dialog = 5-detent ladder slider + 3-detent cue slider (each shows
the level NAME + one-line definition) + Theory|Application segmented
toggle; defaults rung 2 / cue 1 / theory; Create posts the new shape.
Exam header gains the levels line ('Direct exercise · Adjacent
context · Theory').
Tests: renderParams exact-block pin; strict-validation pins (new
tests/practice-service.test.ts — bad unions 400, legacy shape 400);
store pins (legacy floats + 2.5 rung fail); render pins (detents +
names + definitions, defaults, detent-swap, toggle active segment,
levels line); every params fixture moved off floats. 1138/1138, tsc
0, lint 0, build 0.
Docs: architecture.md — discretization paragraph (compact tables,
named-level invocation, defaults, one-table source), UI mentions;
README axes sentence.
Owner escalation on deviation 1: practice availability must not
inherit a visual-rendering threshold. graphClusters() now runs
birthSessionPartition(snap.nodes) directly (same size-desc/id-asc
ordering) instead of reading the snapshot's MIN_CLUSTER_SIZE-filtered
clusters array — MIN_CLUSTER_SIZE stays a hull-drawing rule only.
Label join mirrors the snapshot's (chat title / notes path, null when
the naming record is gone). Contract doc + architecture.md sentence
corrected to match; empty-picker copy reworded ('once a session births
its first proposition' — no 3+ mechanics). Render pins: new empty line
+ a 1- and 2-proposition group listing pin. 1130/1130, tsc 0, lint 0,
build 0.
Owner ruling: 'problem sets always take in nodes — graph objects' —
practice is graph-domain, not chat-domain. No session-created sets.
API: POST /api/practice/sets takes {nodeIds, params, title?} ONLY —
the chatId branch, UnknownChatError, and the any-provenance filter are
deleted; the selector is nodeIds (readNodes filtered to the selection,
unknown ids drop, empty live intersection → 400 empty_selection);
title optional from the UI (the picker's cluster label), dated default
stays. chatStore leaves the pipeline deps entirely (labels resolve
store-side in the clusters service).
GET /api/graph/clusters (new): the birth-session groups the graph view
renders — graphSnapshot's clusters verbatim (same ordering, same
MIN_CLUSTER_SIZE presentation filter), mapped to {key, kind
chat|notes, label (null when the naming record is gone — honest,
never guessed), nodeIds, nodeCount}; corrupt/empty graph → empty
list. GraphClusterGroup contract in core/contracts/graph.ts (client-
safe — the dialog imports it).
practice-dialog: session picker → cluster picker (rows show label +
proposition count, notes clusters marked); Create posts the cluster's
nodeIds + label as title + params. 400 empty-selection copy reworded
for the vanished-nodes edge ('Nothing practicable is left in that
cluster — the graph changed.'); 503 deep link unchanged. Preselected
mode gone — the dialog is the only creation entry for now (the graph-
view cluster entry comes later with free-form selection).
Sidebar: session right-click 'Practice this session's propositions'
removed (item + state + dialog wiring); the /practice nav row stays.
Tests: pipeline — chatId/any-provenance tests die, nodeIds selection
pins added (unknown-id filtering, dated-default title, title hint
rides, empty/vanished → EmptySelectionError); render — cluster picker
pins (label+count rows, notes kind, unlabeled cluster muted, empty
graph line), preselected pins removed; 16 render + 13 pipeline.
Docs: architecture.md §7 API+UI paragraph rewritten (graph-domain
ruling, /api/graph/clusters, cluster picker as the only entry, no
404-unknown-chat); README creation-flow line updated.
1130/1130, tsc 0, lint 0, build 0.
src/agent/subagents/practice.ts: createPracticeAgents(deps) with the
ExtractionModels mirror (per-stage engine overrides + engineFor +
providerKeyMissing + refuseIfStagesUnready, all three roles strong-tier).
Generator doctrine = the owner's problem-engineering framework verbatim
(minus Sources) + Part III wiring section per the green-lit amendments
(FULL SET input with minimal-use doctrine; degradation never in
meta-commentary). Partitioner: true-partition doctrine, validate via
chainCoverage + exactly-once + unknown-ids, error-back retries through
runSubmitAgent's new validate hook (ToolInputError → error tool result).
Generator: echo law (chains set === target). Grader: verdict union +
nonempty feedback (schema-enforced). renderChains/renderPropositions/
renderParams/renderPreviousProblems. BACKGROUND_MODEL_ROLES extended with
the practice trio (settings override symmetry). runSubmitAgent gains the
validate seam (null = accept). 16-test faux-engine suite incl. retry
paths, refusal gates, neverSubmitted.
runSubmitAgent moved verbatim from extraction.ts to src/agent/subagents/
submit-agent.ts (exported; extraction imports it — zero behavior change,
extraction suites green untouched). New optional prepareArguments seam:
extraction wires its healStringifiedArrays heal; default is identity
pass-through. ModelRole += partitioner | problemGenerator | grader;
ROLE_SLOT pins all three to strong (quality-critical trio, plan default).
Note: BACKGROUND_MODEL_ROLES (per-role settings overrides) deliberately
NOT extended — settings-surface decision, flagged for the planning
session.
Costs were rendering '—' for tonight's extraction runs. Root cause: the
pi family bump (df1328e, 0.85.1 -> 0.87.1) added deepseek-v4.1-flash to
the shipped catalogs, but scripts/sync-pricing.ts was never re-run after
it — src/core/prices.ts was still the 2026-09-25 generation. The design
itself is sound and matches the owner's expectation: nothing stores
dollars; records keep tokens + model string; callCost infers at read
time from PRICES[model]. So the re-sync retroactively re-prices every
run the moment the entry lands.
- npx tsx scripts/sync-pricing.ts: 1495 keys (+314/-173 lines);
openrouter:deepseek/deepseek-v4.1-flash = 0.15/0.6/0.003 (matches the
catalog the picker serves)
- glm-5.3-flash price drift (0.075/0.25 -> 0.15/0.5, cacheRead 0.015 ->
0.05): four pinned-cost tests re-derived (usage, cost-summary via
callCost, activity-dock, stats-bar)
- prices.ts header: dropped the false bare-slug-legacy claim (the table
has zero bare keys; sync emits provider-qualified only) and noted the
forgetting-the-sync failure mode
Observed live: the auditor looped find for a very long time, never touching
list_sessions/list_propositions. Root cause was the prompt: its only
procedure text was 'For each proposition, search the graph (its key words,
its synonyms, its phrasings)' — a per-proposition find loop with no
starting point, no sense of the space's extent, and no termination rule.
And find returned id+name+statement with no session pointer, so results
never composed with the listing tools (owner diagnosis, 2026-09-29).
- AUDITOR_INSTRUCTIONS now prescribes the process: (1) list_sessions ONCE —
the graph is small and finite, this shows its entire extent; (2) read
plausibly-related sessions with list_propositions (full text) — every
realistic candidate seen in a few calls; (3) find as the targeted sweep;
(4) SUBMIT once related sessions are read — never re-search seen ground
- find hits now carry 'born in: <session id>' — results point at sessions
the auditor can read whole (legacy no-provenance nodes name none)
- identity doctrine untouched: equivalence bias, linkTo mechanics,
verdicts-only deliverable
Diagnosis on tonight's data (4 sources, 173 nodes, 216 edges): supports is
62-83% of edges, topology is hub-and-spoke (34/94 libertarianism nodes are
degree-1 leaves), hub edges read as essay-flow not logic, 33-41% of nodes
are degree<=1 across sources. The old doctrines asked for exactly this:
'every distinct proposition' + 'lonely nodes = failed extraction' +
'COMPLETENESS... omitting is the main way extraction fails'.
Owner rulings, prompt-only (data model untouched, both prompts):
- strict reasoning bar: a proposition earns its node by being a premise,
step, or conclusion of an argument the source actually makes; isolated
facts, name-drops, asides, trivia, example enumerations are dropped
- supports tightened: ONLY explicit grounding acts in the text, rare
exception, genuinely argumentative relations are almost always follows
- completeness inverted: precision over recall, WHEN IN DOUBT OMIT,
never connect merely-related propositions
- MUST-connect clause dropped; corrections of misconceptions stay in
(argumentative by nature)
Identity doctrines untouched (established-terminology names, MERGE YOUR
OWN OUTPUT, aliases) — zero near-duplicate statements proves they work.
A LINEAR 0–1 multiplier of Edge width (default 0.5, dead-center at step
0.1 — 11 stops like the ladder rows but ratio-valued), grayed out by the
supports-edges toggle (the Dilation dependency pattern). Renderer splits
supports shafts into their own Path2D and strokes a second pass at
edgeWidth × supportsWidth; arrowheads stay full-geometry in the one shared
path (owner pick: shaft only). A true 0-width stroke is undefined on
canvas — the 0 end floors to a 0.5px on-screen hairline; hiding remains
the toggle's job. Sanitizer: real numbers clamp to [0,1], everything else
resets to 0.5; clamps pinned in render-settings.test.
Off hides supports edges from the canvas: the renderer skips them when
building the shaft/head paths (draw-only — the physics sim still feels
them and detail cards still list them; settings never shift the graph).
Server-persisted with the rest (render-settings.json); sanitizer takes
real booleans only, anything else (missing key, legacy file) loads ON —
today's look. Toggle row styled as the Background-colors row; sanitiser
pinned in render-settings.test.
The persisted (chatId, sourceId)→node table was a shared namespace across
independent chunk/batch jobs: each chunk's extractor mints local ids fresh
(p1..pN), so later chunks collided with earlier ones — propositions silently
skipped as 'already resolved' (coverage checkpointed anyway: permanent silent
loss) and edges resolved onto the wrong nodes (the 'everything links to
everything' mush). Owner ruling 2026-09-29: mergeFindings resolves THIS job's
ids in memory, nothing persists between jobs; cross-job identity is the
auditor's linkTo verdicts alone.
- contracts: NodeMapping dies; NotesSource.contentFp — sha256 of the text at
the last run, the re-import guard (unchanged re-import = TRUE no-op, no
model calls, no usage; changed text re-runs; legacy unstamped sources
re-run once)
- merger: job-local resolution map, in-submit duplicate ids skip once,
edges resolve extractor-local ids only
- ports/store: appendMapping/readMappings, LEDGER_FILES.mappings,
rewriteLedgers.mappings gone (stale data/graph/mappings.jsonl just stops
being read)
- session-clusters: birthSessionOf is provenance-only — the legacy
mapping-line fallback for provenance-empty notes nodes dies
- deletion: no mapping rows to strip; stats lose mappingsRemoved
- replay-layout batches nodes by first provenance point
- graph.test pins the new independence semantics (re-merge re-creates;
duplicate ids within one submit resolve once); extraction tests pin
per-chunk merges + the fingerprint guard
Hypothesis under test by the owner: coherent extractions turn to mush
after merging because the auditor minted too many bridging edges of its
own — inference, not identity, and out of the auditor's scope. The graph
now connects across sources solely through identified equivalences;
relations between propositions come from the extractor alone.
- auditSchema drops 'edges' (submit_review = links only); the submit-seam
required-field doctrine reworded per tool
- AUDITOR_INSTRUCTIONS: the BRIDGING EDGES section dies; deliverable is
the identity verdicts only
- AuditVerdicts drops edges; ExtractedEdge endpoints are extractor-local
ids only; mergeFindings stops consuming verdict edges and its resolve()
drops the raw-node-id branch (dead — the extractor never sees graph ids)
- extractor untouched: submit_findings keeps propositions + follows/
supports edges, required as before
- tests: 17 submit fixtures + 9 typed verdict literals slimmed to links
- docs: architecture.md division-of-trust + pipeline diagram updated
The live import surfaced it: a multi-chunk notes source renders N feed
rows, and the dock keyed every one by run.chatId (the SOURCE id) —
React's duplicate-key error. The activity feed also dropped run.part
entirely, so all chunk rows showed identical titles.
- ActivityExtraction/FeedExtraction gain a unique row id (source id, or
'src#i' for chunk jobs) and part; the feed title carries the '· i/N'
suffix like the graph status route
- toBlobs keys extraction blobs by the row id; chatId stays the SOURCE
id (identity for links)
- abort sends the SOURCE id for extractions — aborting any chunk row
kills the source's whole fan-out (the new source-wide abort), and the
abort route's id charset rejects '#' anyway
- new pin: one source, two chunk rows → two blobs, distinct ids, same
chatId; dock fixtures updated
Every notes chunk and chat coverage batch is its own job — registry row,
usage record, failure domain. Extracts fan out process-wide behind a
3-permit extract semaphore on globalThis (new 'queued' phase); audits and
merges stay serialized behind the existing FIFO gate ('waiting'), so each
auditor explores the graph after every earlier job's merge.
- ExtractionPhase gains 'queued'; RunningExtraction gains part {i,n};
the feed shows one row per job with a '· i/N' suffix (status route)
- abortExtraction is source-wide: every job of a fan-out dies together;
merged jobs keep their coverage checkpoints
- failure isolation at the fan-out (Promise.allSettled + aggregation):
a failed chunk no longer kills its siblings — the run returns what
actually merged; job-level aborts log, pre-fan-out errors still throw
- usage ledgers: one record per job (source-keyed), failed jobs bill
their partial spend
- runJob/aggregateJobs helpers; setPhase/recordStep/extract/audit/
notesExtract key the registry by jobKey (src#i) — notesExtract's
signal lookup was the one real bug the new tests caught (source-id
lookup meant fan-out aborts never reached the model call)
- semaphore is handoff-correct (fresh takes increment; handed-off
permits don't double-count — an inflated counter deadlocks at 3)
- tests: isolation pins rewritten (stage failure now resolves zeros),
single-flight/registry tails updated, per-job usage counts, and a new
describe pinning the fan-out: 3 extracting + 5 queued, parts 1..8,
source-wide abort, per-job usage on failure, extract peak == 3,
audit peak == 1
- docs/architecture.md: serialized-audit paragraph rewritten for
per-chunk jobs; two-front-doors wording aligned
The reported bug (2026-09-28): every chat ran glm-5.3-flash regardless of
any pick, while composer and settings UIs agreed with each other and lied
about the run. Root cause: a fossil default-settings record (settings.json
chat section, frozen pre-slots-wave) was stamped verbatim into every new
chat at birth by the new-session flow, and resolveConversationSpec prefers
the per-chat record over the strong slot forever.
Owner redesign — models are per session, always; the strong slot is the
new-session default:
- POST /api/chats stamps the newborn verbatim from the strong slot
(model + thinking level); no client settings PUT on create anymore
- the composer control is dual-bound: in-session it reads/writes the
session's own record (GET /api/chats/:id, PUT .../settings); on the
draft surfaces it binds the strong slot (picking there = changing the
default)
- thinking levels follow the identical mechanics (confirmed by owner)
- the zombie default-settings system dies whole: useDefaultSettings,
/api/settings/defaults, src/store/default-settings.ts, the chat
section of UserSettings (sanitizer strips fossil copies), the legacy
default-settings.json fold, and DEFAULT_SETTINGS_FILE
- catalogDefaultsFor collapses to the strong slot alone
- thinking display for a legacy unstamped session resolves exactly like
the engine (session ?? strong ?? model ladder)
Tests: new chat-birth-stamp suite pins the stamp, the unconfigured boot,
the unset level, and the copy-not-live-view regression; defaults pins
rewritten strong-only; legacy-migration suite deleted.
Owner ruling 2026-09-28: the auditor has no control over the
extractor's output and never alters it, so re-emitting the full
findings per submit was pure payload cost — the retry collapse the
schema slim attacked, halved again. submit_review is now links
(local proposition id -> existing graph node; EQUIVALENCE BIAS
carried in the linkTo description) + bridging edges ONLY; the
merger joins extractor findings + verdicts.
mergeFindings(chatId, findings, verdicts, ...) — propositions come
from findings verbatim, links join by id, edges emit extractor's
then auditor's through one dedup-preserving emitter. The old echo
form hid an accidental drop channel: an auditor that omitted a
proposition from its echo silently dropped it from the merge.
Verdicts-only removes it structurally — extractor output always
fully merges (tests updated to full-merge expectations).
AuditResult/AuditedProposition -> IdentityLink/AuditVerdicts;
audit() logs links/bridges; batch view renders anchorless like
transcriptView; auditor prompt rewritten to the verdicts-only
deliverable; architecture.md division-of-trust updated.
OpenRouter log diagnosis (owner, 2026-09-28): extraction time was
dominated by tool-validation retries. The failing call had the whole
propositions array emitted as ONE JSON-STRING ('propositions.0: must
be object'), a truncated placeholder artifact inside it, and
word-salad statements late in the array — payload-size collapse.
Field audit: 'evidence' was never persisted anywhere and its
faithfulness-checking consumer died with the fully-trusted ruling;
'messages' fed messageId granularity that NOTHING downstream reads,
and the model sent [] anyway (chat-level provenance in practice).
'aliases' stays (optional now): the auditor's find tool globs them.
Schema: propositions = {id, name, statement, aliases?}; edges =
{from, to, type}. Prompts lose the evidence/messages doctrine and
[id]-anchor guidance, gain a compact faithfulness line;
transcriptView renders anchorless. The auditor echo instruction
drops the evidence/messages mention, so its payload halves too.
Heal: healStringifiedArrays on the submit tool's prepareArguments
(pi-agent-core's sanctioned pre-TypeBox shim) parses a stringified
propositions/edges back into arrays — the LaTeX-restore doctrine:
heal weak-model wire behavior at the seam. Test drives the real
agent-loop seam with a stringified submit.
Extraction may run in parallel across sources (extractors are
source-local and graph-blind), but the auditor explores the LIVE
graph through its tools and stamps identity verdicts against what
it finds — two concurrent audits would each link into a graph the
other is about to change, the structural mint of duplicate nodes.
withAuditLock: a FIFO promise-chain mutex on globalThis (the same
module-instance idiom as the run registries — a module-level lock
would be per-route-instance and useless in dev). The check runs
before any LLM is invoked or the graph read; the lock spans audit
through merge inclusive (the merge is the graph mutation) and is
reacquired per batch, so interleaved multi-batch runs each audit
against the latest graph instead of starving each other. Applied at
both front doors — chat batches and notes imports.
New 'waiting' phase (extracting → waiting → auditing → merging):
visible in the status feed so a queued run never looks stalled in
extracting. Abort-aware on both sides of the queue: a run aborted
while waiting leaves without auditing (its chain link still
releases — successors never hang); a run aborted mid-audit releases
in finally.
Tests pin: a second run queues at the gate and its auditor is
invoked only after the first run's merge is in the ledgers (the
post-merge-graph invariant itself); a run aborted while waiting
never audits, checkpoints nothing, and leaves a healthy chain for a
third run. Gates: typecheck, 1061/1061, lint, build.
Owner's first live test of the relinked pipeline surfaced three issues,
diagnosed against the ledgers:
1. Detail-card edge labels were backwards (UI only — data and canvas
arrows were correct). Semantics pinned 2026-09-28: an edge A→B
means A implies B (follows) or A supports B (supports). Outgoing
edges now list under 'What follows from this' / 'What this
supports', incoming under 'Follows from' / 'Supported by'.
Verified against the ledger: Invariance --supports--> Twin
paradox / Relativity of simultaneity; Argumentation ethics
--follows--> Homesteading — arrows correct, only the words were
swapped. docs/architecture.md wording fixed to match.
2. Session-local terminology leaked into node names ('Criterion C',
'Action axiom (F1)'). Both extractor prompts gain a naming
doctrine: names use established, discipline-canonical terminology
(glossary-headword test); never source-local bookkeeping (letters,
numbering, positional labels); local shorthand goes to aliases.
3. Near-duplicate propositions and lonely nodes (~40% of fresh-run
nodes edge-less; 'Argumentation ethics' vs 'A priori of
argumentation' duplicated despite the auditor having linked that
phrase once). Root cause is upstream of the auditor: the extractor
had no self-merge or edge-completeness duty. Both prompts gain:
MERGE YOUR OWN OUTPUT (same claim at different precision = one
proposition, phrasings to aliases; nothing downstream dedupes) and
edge COMPLETENESS (a proposition that arose as evidence for,
consequence of, or prerequisite of another must carry the edge —
a graph of lonely nodes is a failed extraction).
Owner rulings on the open question: keep two edge types (no
'relates to' junk drawer); re-measure loneliness after these fixes.
Gates: typecheck, 1059/1059, lint, build.
The graph becomes raw reasoning chains only. Quiz outcomes and
understanding observations are no longer formalized; assessment
moves to the future practice module.
Events ledger removed end-to-end: LedgerEvent/LedgerEventKind/
UnderstandingLevel/ExtractionAttribution/AuditResult.dropped and
snapshot nodeObservations deleted from contracts; quizEvent builder
and the events step of mergeFindings gone; appendEvent/readEvents
dropped from the port and store; LEDGER_FILES loses events.jsonl
with a one-time purge of a stale file next to the nodes ledger;
graph-deletion and the delete dialog lose event purge + quiz-answer
impact counts; GraphSessionProposition becomes a pure birth list.
Whole-session markdown source view: new core/session-markdown.ts is
the shared formatting engine (id-anchored speaker blocks, quiz/
recall/question blocks, tool one-liners) — the extractor's prompt
view and the future user-facing export render from one engine.
Coverage fingerprints deliberately stay on the old line format
(content-hash semantics; re-formatting never re-opens covered
history). The whole session goes to the extractor — no phase cut.
Auditor refocused as the identity linker: never sees the source;
explores the graph via new auditor-specific tools in
agent/tools/graph.ts (find — glob over name/statement/aliases;
list_sessions; list_propositions with full statement text; no
timestamps) instead of an injected full-graph dump; equivalence
bias — paraphrases merge, only genuinely distinct propositions stay
apart; no drop channel, the extractor is fully trusted; may draw
bridging edges (typed follows/supports) between existing nodes and
the batch, resolved by the merger with chat-scoped message-less
provenance. Agentic loop, maxTurns 16.
UI: the node detail card gains an edges section above the sessions
list (follows-from / supported-by / what-follows / what-it-supports,
rendered only when present, click-to-select neighbors); the
understanding-note chips are gone.
Prober list_propositions reworded to what a session covered —
names only, no levels. docs/architecture.md + README updated to
the as-built pipeline. Gates: typecheck, 1059/1059, lint, build.
Two follow-up rulings on the explain tool:
1. No 'I don't know' row — not needed in free recall. If he doesn't
know, he says so in his own words; his text is the only answer
channel. Dock: text mode is rowless again (the composer IS the
surface); doctrine and the shared prompt chunk updated; the format
branch and card revert to quiz-only dontKnow.
2. explanation + correctAnswer collapse into ONE field — the separate
explanation was quiz remnant (MC needs the why outside its options;
a free-text commitment carries its own reasoning). Schema is now
{question, correctAnswer, details?}; the reveal shows the single
committed answer; no explanation snapshots anywhere on the explain
path.
1047/1047 tests, typecheck/lint/build green.
Sycophancy mitigation as a structural commitment: the model writes its
full correctAnswer (plus explanation, in that order) BEFORE the learner
sees the question; the commitment rides the persisted call args, is
revealed on submit, and grades his free text in the model's next reply —
the client never grades free recall.
- tools.explain setting (segmented 'Quizzing — Multiple choice | Free
recall' in Agent settings' Tools group): free arms explain and drops
quiz for BOTH agents (prober variant carries no nodeId, same pattern
as the probe quiz); mechanics keys never pass filterEnabledTools —
quiz stays unwritable (the 2026-09-19 wedge ruling stands)
- doctrine lives pi-natively in the tool descriptions (owner ruling —
no conditional system-prompt chunks): explain carries the commitment
rule; the MC option-building craft moved out of the prompt into the
quiz description; shared/20-question-tools.md slims to the
quiz-agnostic core
- display seams: parseExplainInput (LaTeX-debris restoration included),
dock text-mode with an 'I don't know' row (kbd row 0), AnsweredCard
reveal (The answer / Why, no verdict chips), [Explain answer] format
- phases/plan seams recognize both quizzing tools' nodeId tags; explain
answers deliberately feed no ledger evidence (no client grading to
key on — a future ruling can parse the model's grade)
1049/1049 tests, typecheck/lint/build green.
The owner's capture-vs-composition check confirmed the wire sends exactly
what composes (byte-identical save the nodeId paragraph ebfe058 had since
changed). This wave removes the implementation meta that leaked into the
prompts and reorders so the method carries weight:
- base: owner's new opener verbatim (install understanding; the
understanding definition — which absorbs the old 'Understanding is
structure' paragraph); Voice moved in from shared/10 (deleted); the
philosophy keeps edge-dependence + logistics ('standard learning'
dropped per owner); intro's two-agents/fragments sentence gone.
- teacher/05-method opens with the owner's methodology bridge ('No other
teaching methods come close') — paragraph 3 of the opener, placed here
so the shared base never points the prober at methodology it doesn't
carry.
- deleted: teacher/60-probing-in-brief (self-evident from shared history;
its mid-lesson mini-probe move salvaged into 20-teaching as one
sentence), the 'Session shape — the durable artifact' section
(extraction-pipeline meta), the fragments-meta lines in shared/20 and
05-method, 'the transcript's seam' phrasing, prober's 'the teacher
that takes over' / 'the handoff is automatic'.
- composition reorder (listSourceSegments): base -> the agent's own
fragments -> shared/ appendix. Teacher method now starts at 12% in
(was 62%); prober doctrine at 34%. shared/20 opens with the owner's
decision rule (quiz only for known-correct-answer, ask for everything
else).
- HANDOFF_TEXT: the owner's user-message version — first-person, paces
the planning (unconditional truths, motivated derivations), ends at
plan_init + accept-or-changes.
Teacher 31.4k -> 28.7k chars; prober 10.0k -> 9.6k. Gates: typecheck 0,
1018/1018, lint clean, build green. (Suite runs 16s; the earlier 10-min
timeout was stale node_modules after master's df1328e 0.87.1 sync —
npm install fixed it.)
The probe intro was redundant with 60-probing-in-brief.md (and its
no-probe fallback described a state the code can't produce — the teacher
only exists post-probe). 'How the map tracks itself' folded into one
tagging paragraph; grain and rewriting compressed; the live-map context
kept to one sentence. The discovery-chain thinking block stays verbatim,
and the stress-test stays. Presenting: ask him to confirm the plan
before teaching begins — medium unprescribed (owner ruling 2026-09-27;
dock-question confirmation leaves the teach divider floated next to the
planning divider when no text reply splits the group — accepted as
cosmetic).
The inferred teach seam sat as a ternary branch in the messages.map
chain (alongside the no-bubble marker branches), so the ENTIRE first
teaching group — thinking, prose, the tagged quiz call — rendered AS
the divider and vanished below it (the Lacan session, 2026-09-27).
The marker branches replace contentless scaffolding; the teach group is
a real message. The divider now prepends inside the group's Fragment.
Also tightens 10-planning.md: the presenting turn asks NOTHING — no
quiz, no ask_user_question, no 'shall we begin?' (the teacher was
substituting a confirmation question for the dead verdict buttons).
The Accept/Decline verdict gate is gone (owner ruling 2026-09-26):
presenting the plan ends the teacher's turn; the learner's next message
is a natural reply. Teaching begins at the first quiz call tagged with a
nodeId (probe quizzes carry none) — both folds (view phaseAt3, native
phaseAt3Lh) advance on the call itself, and the teach divider renders
before that whole assistant block. No backwards compat: verdict markers,
the verdict input event, optimistic appends, composer buttons, and
projection all deleted; prompts and docs rewritten to the natural flow.
Three owner rulings from the gradient-descent session
(chat_muhskq6p_e8c3600b — 7 failed quiz calls, answers leaked in
option descriptions, planning divider floating at the transcript top):
1. RETRYING LINES (general): any tool call that errors back to the
agent (validation failure, malformed args — the retry loop) renders
one quiet "Retrying…" SystemLine instead of silence. Question tools
previously rendered null, so a flailing quiz loop read as a stall.
Aborts are terminal ("Operation aborted") and stay silent. Verified
live: exactly 7 lines render at the 7 failure sites of the session.
2. QUIZ OPTION DESCRIPTIONS: NUKED. The model used them to telegraph
correctness in every quiz of the session ("that moves uphill — it
climbs f instead of descending it") — answerable by elimination.
The field is gone from BOTH quiz schemas (probe + teach); ask keeps
it (ungraded — nothing to leak). The dock additionally suppresses
descriptions for quiz kind, so pre-fix records stop leaking too.
Verified live: the session's pending quiz renders bare labels.
Plus the diagnosed failure-mode fixes: GLM sometimes emits `options`
as a JSON-encoded string (6 of 7 failures). prepareArguments hooks
on all three question tools coerce it BEFORE pi's validation (the
call lands instead of bouncing); the client coerces again in
normalizeOptions (pi persists raw call args). Schema descriptions
hardened ("REQUIRED ... never a JSON-encoded string").
3. DIVIDERS AT THE MARKERS: the probe-handoff SystemLine
("Preparing your plan…") IS NOW the Planning divider; the accepted
verdict IS NOW the Teaching divider ("✓ Plan accepted" line gone) —
one signal per seam, not two. The fold-based divider block is
DELETED: Wave D grouping merged the whole probe into one giant
assistant group, so the inclusive-fold comparison floated the
divider to the transcript top (reproduced against the real record:
6 view messages, phase flipped at the giant group). The markers
render in the right spot by record construction. A DECLINED verdict
is not a seam — it keeps the "↻ Plan revision requested" line.
Verified live: plan divider after the probe concluded, teach
divider after the plan presentation, nothing at the top.
Tests: 1004/1004 — string-coercion pins (normalizeOptions + the
prepareArguments hooks on all three tools, identity fast path),
quiz-schema-has-no-description pin (ask keeps it).
TWO owner-reported bugs from the live red-circle session
(chat_muhpyoll_27305e23), both investigated to root cause first:
1. THINKING BLOCKS UNDER THE MESSAGE. GLM emits trailing reasoning
tokens, so the persisted content lands [text, thinking] (4 of the 6
thinking-bearing messages from [21] on in that session) - and the
view canon presented arrival order verbatim, rendering the reasoning
UNDER its own message. Fix: projectView stable-partitions each
assistant message - reasoning parts first (their own order kept),
then text/tool parts. Owner ruling 2026-09-26: the reasoning belongs
above, always. Covers live partials and settled records alike (one
projection canon). NOT addressed (owner ruling): the plan_tools
"missing" claim in the same session - wire-verified 11 tools incl.
plan_init; GLM confabulation, no mitigation wanted.
2. DOCK CARDS LINGERING AFTER DELIVERY. /api/activity lists jobs with
status "running", and the status flipped only in settleSteers at the
DELIVERING TURN'S onFinish - so a subagent whose card was already
visible in the transcript (marker injected mid-run) stayed in the
background dock until the teacher finished teaching. Fix: flip the
job at the moment the result reaches the learner - noteSteerVisible
(jobs.ts) called from BOTH visibility seams: the marker's message_end
wire event (live steer injection, ui-stream) and the write-ahead
persist (the wake's input appends, chat-handler). finalizeJob is
idempotent; settleSteers/runner-200 re-run it as a no-op, and the
registry's delivery promise still settles exactly as before.
Tests: 1001/1001 - view-canon hoist pin (trailing [text, think, call]
projects reasoning-first; think-first unchanged), noteSteerVisible unit
pin (flip at the seam, idempotent, handoff no-op), and the mid-run
steering e2e now holds the turn open past the injection and pins the
job flipping done at the marker's message_end WHILE the turn still
streams. Live-verified read-only on the owner's server: the original
session reloads with every reasoning trigger above its message.
amosblomqvist