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.
Owner correction (2026-09-26, later): a real lesson is ONE continuous
teach->quiz->teach run - there are no run-would-stop moments mid-lesson,
and the run ends that DO exist are quiz stopper exits where delivery
must not fire. Subagent results must land BETWEEN messages INSIDE the
run, never splitting a toolCall from its toolResult.
Vehicle 1 now hands markers to agent.steer() - pi's STEERING queue:
the loop drains it at TURN BOUNDARIES (after a completed assistant
message AND its tool results - the bonded pair survives injection) and
again at RUN START (a continuation drains before its first LLM call),
then CONTINUES the run with the marker in context.
steeringMode "all" replaces followUpMode.
registerLiveAgent moved BEFORE runPiTurn and now hands pending markers
itself: the start poll drains the queue SYNCHRONOUSLY inside the
runPiTurn call, so a later registration would miss it. A marker
stranded by a quiz-terminated run therefore rides the ANSWER run's
first LLM call - the native replacement for the old continuation
coalescing.
Settlement reconciliation, the idle wake, probe-handoff exclusion,
and the registry-as-truth design are UNCHANGED; stranding is now
exactly the stopper-exit case.
Tests: jobs 45/45 (fakeAgent.steer; new pin - registration steers
pending markers into the new run, parked wake never fires); chat-flow
24/24 (new e2e through the real composition - a gated mid-run turn, a
marker delivered while the turn streams, record shape
[call, result, MARKER, response] with the marker adjacent to the
completed unit, the model SEES the marker in its next prompt, zero
wakes); full suite 999/999, tsc/lint/build green.
Live smoke (PORT=3004): research dispatched in the probe turn parked
behind the dangling quiz; on the quiz answer the marker injected at
the answer run's START poll - record [answer result, marker, teacher
response], job flipped done/delivered at settlement, brief card
rendered with its sources toggle.
Plan doc: docs/PI-NATIVE-MIGRATION-PLAN.md gains the pivot section.
Deferred (owner list): thinking blocks rendering after messages;
vanishing tool-call output tokens.
Delivery now rides pi's OWN follow-up queue when a run is live, and a
carry-everything idle wake otherwise. One registry, two vehicles;
claimSteers and continuation coalescing are deleted (owner rulings,
2026-09-26: follow-ups only; one queue; the wake is the only appender).
THE LIVE RUN (vehicle 1): the chat-handler registers the streaming
turn's agent (registerLiveAgent, next to registerTurn); the pump hands
every eligible queued marker to agent.followUp() - pi polls that queue
when the run would otherwise stop, injects the markers
(message_start/message_end on the live wire), and CONTINUES the same
run. followUpMode "all" joins every handed marker in one continuation
turn. The question stopper runs before the follow-up poll, so an open
quiz is never overridden - a handed marker strands at settlement and
waits (today's pacing). probe-handoffs never take this path (the
handoff must START the teacher's run - a record-level branch).
SETTLEMENT RECONCILIATION: settleSteers(chatId, persisted) at onFinish
(after unregisterLiveAgent) resolves+flips entries the run delivered
and returns stranded ones to pending - the registry stays the truth;
the dead agent's queued copy is abandoned. This is what makes the
handoff safe: pi owns no retry for a stranded follow-up.
THE IDLE WAKE (vehicle 2): waitForIdle (unchanged gates) then ONE turn
carrying EVERY pending marker as its input appends - dequeue-at-fire
(the Wave B regression lesson: the wake run's own follow-up poll must
never see its own cargo; a 409 pushes the cargo back and retries).
CLIENT: applyWireEvent now upserts non-assistant messages by id, so
in-run injected markers render live instead of dropping until settle.
Tests: jobs 44/44 (live handoff, settlement stranding, handoff-waits,
one-wake-carries-all); chat-flow 23/23 (the double-append pin drives
the real pump through the new input); session-core 28/28 (custom-role
wire appends). Full suite 997/997, tsc/lint/build green.
Live smoke (PORT=3004): research job delivered mid-probe - parked
behind the dangling questions exactly per semantics, landed once on
the open gates, teacher folded the brief in and re-dispatched; the
second (good) result rendered the full 10-source brief card and the
lesson continued from it. No duplicate ids anywhere in the record.
Known gap flagged to owner (NOT from this change): the server accepts
malformed answer events via raw API (answers without the answers[]
shape) and AnsweredCard then crashes the page render - surfaced by the
smoke's scripted answers, repaired by hand in the scratch record.
A pump-fired wake turn carries its steer in the input appends, but the
pump only shifts its queue entry AFTER the turn registers - so the
handler's claimSteers popped that very steer too. The record-side
steerDelivered filter checks the PRE-write-ahead snapshot and cannot
see the carried copy: the marker persisted twice with the same
steer_<jobId> id, two view messages shared one React key, and the
client crashed on delivery (live: steer_job_muhlokbf_84e9373c).
This exact bug was known and fixed 2026-09-18 (the old claimSteers
received the incoming body messages and finalized-without-appending
anything the request already carried). Wave B's turn-root rewrite kept
only the record-side filter and lost the carried-side half.
The fix restores the carried filter: a steer whose id the input already
carries is claimed-and-finalized but never appended a second time.
Regression pin in chat-flow.test.ts drives the REAL pump end to end
(deliverJobResult with a real job record -> waitForIdle -> scripted
wake turn) and asserts exactly one copy + the wake response. Two test
lessons baked into comments: chatIdOf resolves a job steer's chat
through the JOB STORE (a synthetic jobId with no record silently
no-ops the pump), and deliverJobResult resolves at CLAIM time, not at
turn completion (the record assertion waits for the wake response).
The live-corrupted record (chat_muhlcltz) was deduped by hand.
Live-driven via the owner's dev server (browser tools), reproduced on
/chat/new: send fires, optimistic appends, POST never happens, and the
page shows the frozen empty state. Three compounding defects:
1. session-core: default fetch stored UNBOUND — the browser's native
fetch requires this === Window, so every call threw 'Illegal
invocation' and the POST /api/chat never fired. Node's undici has no
receiver discipline, which is why 994/994 tests passed while the app
was dead. Now defaulted through a receiver-preserving wrapper; pinned
by a strict-this regression test (the browser's semantics simulated.
2. session.ts: state memo keyed on [model, forceRender] — the reducer
dispatch is STABLE by contract, so the memo computed once per mount:
no optimistic bubble, no stream events, no error banner. The view was
frozen at first render. Rekeyed on a version counter bumped by the
model's onChange.
3. view.ts: turn_end carries the clean 'Question posed' placeholder as
a toolResult message (details: null) — applyResult flipped the quiz
part to output-available with a null output and AnsweredCard crashed
on answer.dismissed (killed the whole page render). Fork 2 now holds
on the message-attachment path too: clean question results with null
details are ignored; the AnsweredCard renders only the learner's real
answer. Regression pin extended in session-core.test.ts.
Verified live end to end: new session → text send → probe questions in
the dock → ask answer → graded ✓ quiz card with explanation → reload
renders the full transcript from the native record with the pending
question intact.
EOF
)
Server: ui-stream.ts is verbatim pi AgentEvent passthrough (SSE data
lines + [DONE]); only app-level events are the loop-level error and
turn-settled terminal; onError carries raw provider text (owner ruling).
Client: useChat + the AI-SDK transport replaced by components/session-core.ts
(SessionModel: 409 identity-retry, optimistic c_ appends, absorbed()
adoption, needsContinuation, shared consume for POST + reattach) and the
session.ts hook; the golden-master grouping canon moved client-side into
core/view.ts (projectView); scanners read the native record (phaseAt3Lh,
danglingQuestionOf, graph toolParts, plan-blocks, runner, extraction).
Coverage: the native message is the unit (fork 3) with the call+result
inseparability bond rule; view-line-less messages (markers, error
results) are invisible to coverage and never checkpointed.
Deletes: chat-transport, projection, ui-message, their tests (ported to
tests/session-core.test.ts), and the ai + @ai-sdk/react dependencies —
the Vercel SDK is fully out of the tree. Wire pins in chat-flow rewritten
onto the AgentEvent dialect (eventsOf parser).
Gates: tsc clean, 994/994 tests, eslint clean, build green; live smoke
on PORT=3004 (verbatim wire → native record).
The chat record is now pi-native agent history (LhMessage[]), the AI SDK's
UIMessage transcript contract is gone from the server, and every client turn
arrives as ONE explicit input event.
Core (new):
- src/core/native-messages.ts — the LhMessage taxonomy (user/assistant/
toolResult + lhMarker customs: verdict, probe-handoff, subagent-steer,
subagent-abort, plan-block), constructors, and toLlmMessages — the single
model-facing seam (convertToLlm): strips ids, flattens markers to user
text, drops UI-only plan-blocks, synthesizes INTERRUPTED results for
dangling aborted calls, never throws.
- src/core/projection.ts — projectNative: the one-way native → UIMessage
projection (consecutive assistant+toolResult runs group into one
assistant view message; toolResults attach backward by toolCallId;
markers project to data parts; plan-blocks splice after the last
successful plan_init). Every existing consumer reads through it.
- src/core/input-events.ts — the ChatInput union (text/answer/verdict/
continue), parseChatInput validation, and inputAppends (answer targets
the dangling question call or 400s; verdict = optional note user
message + native verdict marker).
Server:
- chat-handler.ts — the turn root takes {chatId, input}; write-ahead
persists input appends + claimed steers before the turn; claimSteers
coalesces the whole queue with the handler's steerDelivered filter as
the dedupe seam; teacher-vs-prober branch on hasProbeDone.
- turn-service.ts — persistTurn stamps ids, drops clean question
placeholder toolResults (the record ends at the unanswered call),
emits plan-block markers idempotently (plan-blocks.ts rewrite), and
persists abort partials.
- ui-stream.ts — PiTurnSpec takes the native base; the wire dialect is
unchanged. jobs.ts steers are native markers (steer_<jobId> dedup ids);
waitForIdle reads danglingQuestionOf. teacher-agent.ts wires
convertToLlm: toLlmMessages. record-adapter.ts DELETED wholesale.
- GET /api/chats/[id] serves messages: projectNative(record.messages).
Client:
- chat-transport.ts — the 409 retry is IDENTITY (re-POST the same event
body after the turn settles — the event was never persisted
pre-acceptance; the merge logic is gone). The transport consumes the
stashed input event via prepareSendMessagesRequest and throws loudly on
a missing stash.
- chat.tsx — every send call site stashes exactly one ChatInput event
(text, answer, verdict, continue) before invoking the SDK send.
Tests: full native migration (chat-flow rewritten to input events and
native record pins; jobs/extraction/demos/graph/usage/plan-blocks/
probe-done/reattach-transport converted; record-adapter.test.ts deleted;
chat-transport tests pin the identity retry). 982/982, typecheck, lint,
build all green.
- src/agent/lh-tool.ts deleted: the zod-wrapped LhTool + toPiTool bridge
(z.toJSONSchema per call, clientQuestion flag, hand-rolled result mapping)
is gone. Tools are pi-agent-core native AgentTools now.
- New src/agent/tool-execute.ts owns what the wrapper added: the abort guard
(runWithAbortGuard: run signal + 30s per-call timeout + 250ms grace,
'Operation aborted' / timeout wording preserved), ToolInputError (the
retryable '- problem at path' format), result mapping (string verbatim /
object JSON / image parts, details rides the record's tool part output),
and questionResult() — placeholder + terminate:true (owner Option A:
belt of terminate + slim makeQuestionStopper with the clean-question
rule; maxTurns deleted from the teaching turn entirely per owner).
- All 11 tool files + tools.ts registries converted to TypeBox parameters
(typebox@1.3.7, pinned to pi-agent-core's copy). zod refinements
(quizInputProblems, askOptionProblems, live-nodeId) moved from schemas
into execute — the model sees the same retryable error shape.
- question-core + contracts/probe TypeBox-authored (single source shared
with the UI); tool-parts parse seam runs the boundary's full chain
(Convert → Check → Clean → refinement), fixing the live-smoke lockout:
pi's boundary Value.Converts correctAnswer: 17 → '17' but the record
keeps raw args, so a parse without Convert rejected a posed quiz
(invisible pending question, turn ended). Pinned with the real smoke
emission shape.
- Subagents converted: demo-builder/researcher AgentTool-native,
visual-maker/pdf-reader declaration-only pi-ai Tools with local execute
fns, extraction submit schemas re-authored in TypeBox (owner option 2:
zod defaults → Type.Optional + fill at the submit seam).
- Accepted delta, flagged: TypeBox-native schemas skip pi's JSON-Schema
primitive coercion fast path... (boundary still Value.Converts), and
prober-quiz unknown keys ride through (Value.Clean strips at display).
- Tests: 988 passing (was 967 at the recon baseline); tool-abort and
read-tool rewritten against the native seams; question-core/question-
tools/tool-parts/demos/web-search/graph-tools/plan-tree/probe-done/
tool-toggles converted to Value.Check/execute pins.
Live smoke (PORT=3004, real model): native ls turn streams end-to-end; a
real quiz pose (first attempt missing correctAnswer → tool-input-error →
model retry → posed) terminates the turn cleanly and persists pending.
baseAgentOptions (teacher-agent.ts) and runSubagent (subagents/pi-run.ts)
passed getApiKey: () => openRouterApiKey(). pi-agent-core resolves
(config.getApiKey ? await config.getApiKey(provider) : undefined) || config.apiKey
(agent-loop.js:191) — a provided hook OVERRIDES pi-ai's native per-provider
env resolution, and this one ignored its provider arg: every non-OpenRouter
provider was sent the OpenRouter key and 401'd (owner repro: openai and
anthropic direct). Deletion restores the architecture's stated intent —
the keys seam reflects file-saved keys into env and pi-ai reads them per
request. openRouterApiKey() export kept (now consumer-less; visual-maker/
pdf-reader read process.env.OPENROUTER_API_KEY directly for their own
OpenRouter-specific fetch paths — correct, untouched).
Pinned by tests/api-key-hook.test.ts: built teacher + prober expose NO
getApiKey hook. Gates: typecheck 0, 987/987, lint clean, build green.
The prober was planning perfect 7-question batches instead of probing. Three
surfaces now say the same thing — one question, adapt, next question:
- prober/10 rewritten to ~2.6k (from 5.6k): serial discipline leads (ask,
wait, choose the next question from the answer); 'How your questions
arrive' deleted (owner: does nothing); 'You cannot get there by thinking'
deleted (owner: didn't reduce thinking); 'never plan a batch' and the
first-message-length line dropped per owner — no overcorrection, no
strong-instruction inflation. Binary search compressed to four moves.
- tool descriptions: the async-era fossil 'Ask exactly one question per
tool call; after calling, end your turn and wait' — which permitted
multi-call batches — swapped for 'ONE question per turn: ... his answer
determines the next' in all four places (prober quiz + ask descriptions,
teacher quiz description, both zod question-field describes).
- shared/40-formatting: markdown/LaTeX coverage now explicitly names quiz
questions, options, and explanations ('in prose and in quiz questions
alike') — the prober wasn't using LaTeX in questions.
Prober composed prompt ~13.2k -> ~10.0k chars. Pins preserved verbatim
('measurement should be efficient', 'the read tool can inspect it directly').
Gates: typecheck 0, 986/986, lint clean, build green.
The probe→teach handoff wake read as a dispatch order ("Author the session's
plan map now") and the teacher skipped the deliberation the planning fragment
asks for. The wake now paces it: take your time, read the assessment and the
probing transcript, reason out the optimal way to teach this person this
thing — floors, ceilings, misconceptions, the minimal tree so every step
lands as obviously true — and only then call plan_init. Machinery honest:
plan_init is still the first tool, the plan map still the first artifact, and
the tail now says to wait for his verdict (which is what presenting actually
does — the old "then begin teaching" tail skipped the verdict seam).
Owner ruling 2026-09-25. runPiTurn executes a turn decoupled from any HTTP
response: an unbounded memory-only event log (finite by construction; the
30-min liveness TTL bounds the pathological case) plus a subscriber set.
The POST /api/chat stream and the new GET /api/chats/[id]/stream are both
subscribers — identical SSE dialect; late subscribers get FULL replay
(starting at the start chunk) then live until finish + [DONE]. A view
cancelling (reload, navigate) now detaches ONLY — never aborts the turn.
The remote kill is the abort channel: POST /api/activity/abort gains
kind: "turn" (id = chatId; not_running 409 like jobs); handle.abort sets
sawAbort + agent.abort(), every subscriber closes cleanly, the partial
persists through the usual settle (onFinish runs once, then endTurn,
then unregisterTurn LAST so a view that finds nothing finds the record
current). No running turn on reattach: the cheap terminal — one
{"type":"turn-settled"} event + [DONE] (settledTurnResponse).
The live smoke caught what the unit suite had masked: the agent_end
close() had been left behind in the restructure — ReferenceError every
turn, steered into the error path; fixed and pinned (clean turns must
never emit an error chunk; finishReason stop present).
Root cause (interlude, owner 2026-09-25): keyboard-shortcuts dispatches
registry actions on the lh:kbd-<action> convention, but the sidebar's
listener sat on the pre-convention name "lh:toggle-sidebar" — a name
nothing ever dispatches, so ⌘B silently did nothing while its tooltip
and cheat-sheet row kept claiming the binding. A sweep of every lh:
listener confirmed the sidebar was the lone stray (chat-renamed and
graph-revision are deliberate non-kbd events).
Fix, structural: kbdEventForAction(action) exported from
src/core/keyboard.ts — the ONE spelling — and both sides compose
through it (dispatcher's default branch, sidebar's toggle listener);
keyboard-shortcuts re-exports the helper so the contract pin can assert
no second spelling exists. The mismatch is now impossible by
construction.
Thinking pill: label trimmed to "Thinking" with its real shortcut via
the registry-composition path — "Thinking (⇧⇥)" (cycle-thinking,
rebind-live like every Hint suffix).
Pins (tests/keyboard-toggle-sidebar.test.ts): the full chain — mod+b →
actionForBinding → toggle-sidebar → kbdEventForAction →
lh:kbd-toggle-sidebar; formatBinding("shift+tab") → ⇧⇥; the
dispatcher-imports-the-same-helper contract.
Live-verified on :3001: ⌘B visually toggles on home, /chat/[id], and
/chat/new (sidebar 0↔288px, hamburger slot 0↔36); with the rebind
lh:keymap {"toggle-sidebar":"mod+j"}: ⌘J toggles and ⌘B is inert
(rebind-live); thinking pill renders "Thinking (⇧⇥)"; keymap restored,
sidebar left open.
Owner-diagnosed: the turn gate checked only model coordinates, so a
pinned slot whose provider key was deleted passed the gate and died
mid-stream masked to 'An error occurred.' The key is now gated where
the model is — by what would RUN (env-first keyValue truth, so an
env-shadowed key passes).
- core/settings.ts: the provider_key_missing envelope family (code,
provider, slots, human line naming the provider from AUTH_PROVIDER_KEYS
labels) + ProviderKeyMissingError + isProviderKeyRefusal matcher.
- chat-handler turn gate: refuses 503 before beginTurn when the resolved
conversation's provider key is gone (slots: [strong]).
- Job runner: same check via an injected dep (agent layer cannot read
the key store) — a keyless engine refuses the spawn through the
existing failure-shape convention, no phantom run.
- Extraction pipeline: refuseIfStagesUnready refuses BEFORE any batch
(first offender: extractor before auditor); the trigger skips info-
level, /api/graph/import surfaces the 503 envelope per file.
- Tests: 8 new pins (turn gate both ways, runner refusal, pipeline
first-offender + pass-through, envelope factory, matcher); the three
turn-driving suites seed OPENROUTER_API_KEY like any real setup.
- Doc fix: stale EXTRACTION.chunkTokens comment in the manual-extract
route (left over from eed4b4e).
Known residual (pre-existing, flagged for master): the manual extract
route logs BOTH config refusals as console.error (fire-and-forget path);
the coverage ledger keeps everything uncovered either way.
Off UI's d651f93 flag (displayCostTotals already isolates the display to
extraction + audit; the naming stage row and naming runs were filtered
out client-side). This culls the server side of the same ruling.
THE STANDING RULING, REVERSED BY ITS OWN PREMISE: NamingRunUsage /
readNamingRuns / appendNamingUsage were kept at the wave-7 namer kill
ONLY because cost-summary's HISTORICAL naming stage read them. With the
fold culled, that premise dies — so the whole ledger read path goes too,
following the wave-7 embeddings precedent chain: consumer-less ledger
seams are deleted, and the on-disk naming-runs.jsonl stays INERT (real
trees keep their historical spend bytes; they are simply not displayed
anywhere — the same treatment as historical stages.embedding spend).
- core/cost-summary.ts: two channels in (chat + notes front doors), two
stages out; RecentRun.kind collapses to "extraction" (labels field
gone); CostSummaryInput.naming gone; totalDollars = extraction + audit.
- ports/store/contracts/config: appendNamingUsage + readNamingRuns ports,
store impls + guards, the NamingRunUsage interface, and
LEDGER_FILES.namingRuns die. graphRevision no longer counts the file
(a smaller revision value is harmless — reads never compare).
- components/graph-view.tsx (mechanical, flagged): the defensive
.filter(run.kind !== "naming") guards a kind that no longer exists.
- Tests: cost-summary's both-channels fold pins; the naming fixtures and
the appendNamingUsage store pin die with the seams.
Extraction-UX close-out interlude (master dispatch 2026-09-24, off UI's
ff1ec7a confirmation): nothing client-side consumes GET /api/graph/coverage
— the sidebar block and the chat-bar ring both read GET /api/chats/[id]'s
coverage block. The dead route (app/api/graph/coverage/route.ts) is
deleted; the manual-extract front door (POST /api/graph/coverage/extract)
stays by design.
No server helper was orphaned — the route was composition-only over
shared seams (chatStore, extractionStatuses, stores, coverageOf). The
sessionCoverage doc + the chats/[id] route comment now point at the
per-session block as THE coverage surface.
Pin (tests/coverage.test.ts): the route file's absence (prompt-overrides'
structural-pin precedent) + the Extract POST's survival — a merge cannot
resurrect the dead surface silently.
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.
Owner ruling (2026-09-23, amendment to 04e336d): no hardcoded fallback
exists anywhere. contextWindow(record, limits) resolves the denominator
ONLY from the live index (provider:id -> contextWindow straight from
pi's catalog); a model missing from it (historical session, package
update, failed fetch) reads limit null and the meter renders
usage-only — the honest-render precedent, never a fake window.
- src/core/prices.ts: the 1354-entry CONTEXT_LIMITS table (65KB) and its
generation apparatus deleted; the fold returns limit: number | null.
PRICES untouched (regen verified byte-identical via the reworked
sync-pricing script).
- scripts/sync-pricing.ts: generates PRICES only; contextWindow leaves
the priced map, the guard, and the template.
- The dock meter's owner-selected treatment: the activity feed carries
the limit server-side. catalogContextLimits() (server/model-catalog.ts)
builds the index over the same keyed providers the picker federates;
activityFeed() joins it onto every running job (ActivityJob.contextLimit,
null when the model is missing — the dock reads it off the feed, no
client-side table, no regression while the UI's catalog-join chunk lands).
- components/activity-dock.tsx: toBlobs reads job.contextLimit (import
of CONTEXT_LIMITS gone); stats-bar renders usage-only on null limit
(mechanical interim — UI stream's join chunk follows).
- tests: usage.test.ts pins the no-fallback contract (index hit / absent
/ empty / missing-model -> null); activity-feed.test.ts pins the
server join (catalog model -> 1048576, unknown -> null, no-usage ->
null); render pins updated to the interim usage-only render.
The owner's context-meter audit (2026-09-23), three fixes in the pure
contextWindow() fold (core/prices.ts):
- NUMERATOR: cache tokens count. Provider "input" excludes
cacheRead/cacheWrite, so input+output read wildly low on cache-heavy
sessions (40k shown vs ~190k real). The fold is now pi's own
totalTokens semantics: input + output + cacheRead + cacheWrite. The
fields were already persisted in every CallUsage (chat-handler's
capture seam); non-caching providers are unchanged.
- DENOMINATOR: the live catalog wins. contextWindow() accepts an
optional live-limits index (provider:id -> contextWindow — the shape
the client already holds from GET /api/models, where toModelDto
projects pi's Model.contextWindow); CONTEXT_LIMITS, the generated
duplicate, is demoted to fallback for models the live catalog doesn't
carry. The UI's stats-bar join passes its catalog index; the call is
unchanged when omitted.
- RIDE-ALONG (honesty guard): a zeroed/aborted last step falls back to
the previous step's footprint — an abort artifact is not a reading.
All-zero runs return null (no meter, never a bogus tiny number).
Tests pin all three: the cache-inclusive fold (and the plain no-cache
fold unchanged), live-index-beats-table + table fallback + unknown-to-
both null, and the zeroed-step fallback (previous step wins; all-zero
is null).
885/885 tests, typecheck/lint/build green.
Flag routed from the UI stream's rename-shuffle fix (a9339b3): the
positions ledger was the one remaining plain writeFileSync among the
rewritable ledgers — a torn write (crash mid-write) could replace it
with a half-written file, and readPositionMap parses a failure to {}
(honest empty, but the resting layout would be silently lost). The
tmp+rename pattern from rewriteLedgers, ~4 lines up the file: write a
uniquely-named temp, rename over the ledger — a crash leaves either the
old ledger intact or the new one complete, plus an orphan .tmp-*.
879/879 tests, typecheck/lint/build green; live-verified via the node
deletion's positions prune (no temp residue, valid JSON).
The remedy for undeletable nodes (preserve-graph orphans from session
deletion; notes-import nodes with no chat behind them): DELETE
/api/graph/nodes/[id], full-death semantics — the user pointing at the
node IS the intent; references from other sessions do NOT preserve it.
- core/graph-deletion.ts deleteNodeTraces: the node's every line, every
edge touching it, every quiz/observation event naming it, its mapping
lines, and its resting position — one synchronous atomic rewriteLedgers
call; only the ledgers that changed rewrite (mtimes stay honest). Blast
radius is exactly the rows naming the node id; notes source records stay
(deleting a proposition is not deleting the file). Derived data
self-heals on read: the birth cluster shrinks below MIN_CLUSTER_SIZE and
stops rendering.
- nodeDeletionImpact (GET /api/graph/nodes/[id]): the confirm dialog's
pre-flight facts — edge count, quiz/observation history, referencing
sessions. The snapshot's edges + nodeSessions cover part of this, but
the raw event history was nowhere on the client — hence the read.
- Guards (server/graph.ts deleteGraphNode), decided + documented: NO
turn/jobs gates (they never write graph ledgers; the orchestration is
synchronous end to end, nothing interleaves). THE EXTRACTION GATE: 409
while ANY pipeline run is registered — a mid-flight run holds
pre-deletion findings and could re-reference the dying node. The run is
never aborted (its spend belongs to another session — outside this
deletion's blast radius; the UI retries once the dock drains. A run
started after the deletion is legitimate re-learning: fresh ledgers,
fresh node id, and mergeFindings' existingIds guard ignores linkTo ids
that no longer exist — no dangling edges, no resurrection.
Live-verified on dev data: impact read, full-death stats, honest 404 on
repeat, and the file cluster fell 3→2 and unrendered itself.
859/859 tests, typecheck/lint/build green.
EOF
)
Part 1 — the ledger + remnants interlude (master-dispatched, owner ruling
2026-09-23: nothing configures the graph beyond chat models):
- The embedding ledger surface is gone: readEmbeddings/writeEmbeddings
ports, the EmbeddingsLedger contract, EMBEDDINGS_FILE (config, store
impls, graphRevision source list), and graph-deletion's vector-pruning
step. On-disk data files stay untouched (inert history).
- The extraction embedder seam dies wholesale: ExtractionPipelineDeps
drops the embedder dep (chat-handler + backfill/import-notes stubs go
with it), the 'embedding' phase leaves ExtractionPhase, the usage
capture/persist helpers die, and stages.embedding leaves
ExtractionRunUsage (historical records keep their shape — reads are
lenient). Extraction is two stages again, like the local-embedder era.
- Consumer-less remnants: latestQuizOutcomes + QUIZ_EVENT_KINDS,
clusterContentId, matchClusterLabelings + Community + ClusterLabeling,
the readClusterLabels/appendClusterLabel port seams + store impls +
LEDGER_FILES.clusterLabels. NamingRunUsage/readNamingRuns STAY
(standing ruling — the cost pill renders historical naming spend);
clusterHue + MIN_CLUSTER_SIZE stay (live).
- The 'labeler' role dies: BACKGROUND_MODEL_ROLES, ROLE_SLOT, ModelRole,
the catalog pin projections, and the UI roster strings. RolePins keys
shrink with the union.
The notes birth fallback (owner-approved 2026-09-23, surfaced by the
interlude's live smoke: production notes imports create provenance-EMPTY
nodes (importNotes passes messages: null — the file's anchor is the
mapping line), so the provenance-only birth rule left every imported
file unclustered and invisible to the prober's session list, against the
locked file-birth ruling. A provenance-empty node now births under its
FIRST mapping line's chatId (ledger order); only notes-born nodes ever
hit the fallback (chat nodes always carry provenance; a re-encountered
node's link-append re-opens the provenance rule). Deletion-safe: mapping
lines of deleted chats are stripped alongside their provenance.
Live-verified on port 3004: a fresh notes import clusters under its
src_ id with the file path as the label, end to end with no embedder.
845/845 tests, typecheck/lint/build green.
EOF
)
The owner's zero-configuration ruling (2026-09-23): nothing configures
the graph beyond chat models. The prior-knowledge injection — its budget
dial, its runner, its marker part, its dock/dispatch entries — is
removed across all bands; the prober now reads the learner's persistent
knowledge map on demand through two gated tools instead:
- list_sessions: every birth session, names + kinds + counts + dates
(graphSessionIndex, Platform's core seam)
- list_propositions(session): what was born there + the session's own
latest understanding level + that evaluation's date
(graphSessionPropositions) — names/levels/dating ONLY, no statement
text (owner ruling: the map's organization is the prober's business,
its prose is not)
Registered via createProberTools when chat-handler passes graphStore
(the graphToolsEnabled gate decided server-side, per-turn fresh); the
prober doctrine gains the map-review nudge at session start.
Also: runner's JobKind special-casing collapses (KIND_ROLE/KIND_RUNNERS
are plain records again), semantic-clusters.ts dies with its test, the
embedder dep's doc tells the wave-7 stub story, and ports.ts's
readClusterLabels/readNamingRuns surface stays untouched for Platform's
ledger-port interlude.
848/848 tests, typecheck/lint/build green.
amosblomqvist