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 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 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.
The fix wave (4e1f545) put research + pdf in the prober's registry per
the owner ruling, but the doctrine never mentioned them. Owner chose
(2026-09-22) a brief grounded mention over schema-only discovery: the
paragraph extending 'read his actual material' now covers pdf (same
grounding for his PDF material, no copy-pasting) and research
(sparingly, only when pinning a fact would genuinely sharpen a probe
question — probing is measurement, not exploration, and a research
brief is never a reason to stall the questions).
Learner source files, on the teacher's own terms (nothing auto-injects):
- read tool (src/agent/tools/read.ts): pi-read port — path/offset/limit,
2000-line/50KB truncation with use-offset continuation notices, image
files (jpg/png/gif/webp/bmp) returned as native image content parts
(new LhToolImageResult escape hatch in lh-tool.ts). Always-on in both
the prober and teacher registries (user-decided 2026-09).
- pdf-reader sub-agent (JobKind 'pdf', toggleable, ack-and-steer): triage
via pdf_info (pdfjs text layer: per-page text/image/math-density),
targeted pdf_extract, regex pdf_search (hits count as consultation),
and pdf_render — pages painted by pdfjs onto a canvas shim in headless
Chrome (the pdfium viewer doesn't paint headless), screenshot fed back
image-in-the-loop (visual-maker idiom, providerSafePng applied). The
unread-finish gate bounces a zero-consultation brief once. Teacher gets
a text brief with page citations only; renders never leave the loop.
- MODELS.pdfReader = qwen/qwen3.8-flash (user override 2026-09-19: the
look-at-renders workload wants the vision-proven model; catalog listed
glm-5.3-flash as image-capable but qwen is the known-good daily driver).
- UI: PdfCompleteBadge + PdfBriefCard (steer-card, job-card), dispatch
card + activity-dock kind entries (type-forced, flagged for UI review).
- Prompts: 'Learner source files' section in teacher/30-jobs.md; read
line in prober/10-probe-doctrine.md. Doctrine rides tool descriptions
per the self-contained-tools principle.
Part 1 — tool availability (the settings seam, machinery generic):
- core/pending.ts: TOGGLEABLE_TOOLS (today: research, demo, visual —
the model-facing tool names), EnabledTools = the JSON-native seam
shape Partial<Record<string, boolean>> (absent key = enabled, so old
records behave exactly as today), filterEnabledTools shared helper.
quiz/ask_user_question are always-on FOR NOW (user-decided); the
filtering is generic so future toggleables (question-tool variants,
the read tool, …) need no factory change.
- createProberTools/createTeacherTools take enabled?: EnabledTools; the
composition root (chat-handler, Platform's lane this wave) passes the
resolved settings through. probe_done is re-added after the filter —
always-on by construction (it ends the phase; a prober that can never
conclude is a lockout).
- Prompts stay STATIC under toggles this wave (user-decided); standing
principle recorded: tools ship self-contained usage guidance in their
descriptions; system prompts reference only always-on tools.
Part 2 — phase-based question-writing principles (user-locked wording,
drafted with the user over three iterations):
- NEW teacher/21-question-principles.md (composes after 20-teaching):
answerable-by-reasoning-from-the-session (the fairness rule that
filters unanswerable questions without forbidding visible answers),
never-just-reciting-your-words-back, PREFER problems that apply the
knowledge (preference, not hard rule — honest recall is the fallback,
not the habit), catch-confusion-early-and-nameable (wrong options as
real misconceptions), answer-is-signal-not-verdict.
- prober/10-probe-doctrine.md: 'no rush' retired; quick-measurement
directive in — every question moves an edge (bracket, narrow, or
characterize); a bracketed strand is done.
Tests: TOGGLEABLE_TOOLS pin, prober/teacher filtering (absent = full,
false drops exactly that tool, probe_done survives), prompt pins (the
principles compose verbatim into the teacher prompt, the no-rush
framing is gone from the prober). 547/547, typecheck/lint/build green.
Diagnosis (2026-09-11 user testing, minimal-effort GLM): sessions stuck on
'plan' forever. Two causes: (1) the three-phase view read the stored tree's
currentNodeId, which nothing ever writes post author-once (2026-09-03) — a
structural dead seam; (2) the teacher stochastically left quiz.nodeId
untagged, and done-by-quiz-result semantics would have falsely completed
nodes anyway.
The redesign (docs/probe-teach-split.md) abolishes derived occupancy in
favor of explicit events:
- Two agents over one transcript: createProberAgent (quiz without a
nodeId field, ask, probe_done) and createTeacherAgent (full toolset,
plan_init onward). The chat-handler construction branch keys on a
probe_done part in the transcript. MODELS.prober added.
- probe_done: server-side seam tool — carries the learner assessment
(strands + free-form edge read), refuses while a question is open or
the probe is already concluded, and queues a handoff steer through the
generalized wake pipeline (steers now dedupe by id, not jobId; job
finalization only for job steers). The teacher auto-wakes and authors
the plan; the learner sees the assessment via the probe-done card.
- phases: probe ends at a concluded probe_done, plan ends at a
successful plan_init — strictly sequential, no skipping, no legacy
compatibility (data wiped at the pivot per doctrine).
- Plan map = position, not completion: derivePlanStatuses reads only
tagged quiz CALLS (state/outcome feed nothing); current = latest
tagged node with consecutive duplicates collapsed, visited = earlier
distinct stays (a revisit stays in both — current wins at render).
PlanTree is structure-only; currentNodeId/doneNodeIds and the dead
mutation helpers are gone. No fallback current.
- Prompts split per agent (prompts/prober/, prompts/teacher/ over the
trimmed shared base); graph-context injection removed entirely
(shelved, docs/probe-teach-split.md §5); knowledge-graph context no
longer reaches either agent.
- Plan blocks are full-only snapshots at plan_init (neighborhood
machinery retired; the persistent DAG window is the future UI wave);
usage capture unchanged.
Gates: tsc clean, 294/294 tests (phases/plan-tree/plan-blocks/question-
tools rewritten to the new semantics; probe-done + handoff-wake tests
added), lint, build. Live GLM smoke PASS: prober concluded with an honest
assessment, teacher auto-woke, authored a 10-node plan with the block
attached, then tagged checks on slope-instinct → secant derived current/
visited exactly as designed; grading honest both ways (driver off-by-one
proved a wrong answer grades false).
amosblomqvist