The minimal implementation of the 2026-09-02 graph vision (docs/vision.md §1):
- contracts/graph.ts: every node is a TRUE proposition (statement is both
rendering label and identity key; required description; no kind, no name).
Edges are follows (derivable) / supports (grounds without entailing) with
message-granular provenance points {chatId, messageId}. Events reduce to
correct/miss/dont-know plus observation (understanding notes); no taught
events, no misconception kind.
- extraction.ts: extractor is TREE-BLIND (transcript only, no plan tree) and
free-form; auditor sees findings + the current graph, owns faithfulness and
identity (link-or-create verdict per proposition, recorded as linkTo);
transcriptView tags every line with its message id (provenance anchors).
- core/graph.ts merger: applies verdicts deterministically — linkTo appends
a link line (phrasings join aliases, provenance unions; reads merge by id),
absent creates; NO string matching anywhere. Quiz events rebuilt from tool
parts with attribution-only nodeId resolution; understanding notes become
observation events (obs:<sourceId>); mapping lines are the verdict audit
trail and make re-merges idempotent.
- deriveNodeStates: transitional — latest quiz event wins (known/missed/
dont-know, else candidate); taught unreachable until the state-model
ideation lands.
- graph-context.ts + 50-graph-context.md: follows chains, hotspot grouping,
state vocabulary updated for the new event kinds.
- graph-view.tsx: node label is the statement; detail shows statement +
description.
- tests: merger verdicts (link, no-string-match, cross-chat assertions),
tree-blind pipeline end-to-end, follows vocabulary in context tests.
276/276 green.
Records the 2026-09-02 graph philosophy decisions, replacing the
2026-08-22 live-emission construction model (second reversal — back to
post-hoc, now deliberately tree-blind):
- Node theory: every node is a TRUE proposition (no kind field);
statement (minimal, context-relative) + description (required) +
aliases (verbatim phrasings); contradictions coexist — the
surrounding subgraph is the context; misconceptions enter as true
corrections, wrongness lives in the event ledger.
- Edges: follows (derivable) | supports (grounds without entailing);
no scalars, no encoded strength — derived at read time.
- Provenance: message-granular (chat, message) points on nodes and
edges, deep-linkable.
- Construction: free-form extraction fully decoupled from the
session's formalism. Extractor sees ONLY the session transcript
(tree-blind, message ids); auditor sees extractor output + the
global graph (faithfulness net + identity judgment, link-or-create,
aliases as phrasings); merger stays deterministic append-only.
- Event ledger: quiz outcomes deterministic from tool parts; NO
taught events; extractor records per-proposition understanding
notes (named-word scale, no numbers) — treatment TBD.
- Understanding: inferred, never encoded; state model (session-
independent, computed from dependency depth/strength) is pending
ideation — current five-class derivation is transitional.
Also updates: §2 plan tree (session scaffolding only), graph-as-context
(follows-edge subtree, event-derived hotspots), home page (message
provenance, transitional states), roadmap item 5, open questions
#2/#3 resolved, amendments table (+6 rows).
Records the 2026-09-02 graph philosophy decisions, replacing the
2026-08-22 live-emission construction model (second reversal — back to
post-hoc, now deliberately tree-blind):
- Node theory: every node is a TRUE proposition (no kind field);
statement (minimal, context-relative) + description (required) +
aliases (verbatim phrasings); contradictions coexist — the
surrounding subgraph is the context; misconceptions enter as true
corrections, wrongness lives in the event ledger.
- Edges: follows (derivable) | supports (grounds without entailing);
no scalars, no encoded strength — derived at read time.
- Provenance: message-granular (chat, message) points on nodes and
edges, deep-linkable.
- Construction: free-form extraction fully decoupled from the
session's formalism. Extractor sees ONLY the session transcript
(tree-blind, message ids); auditor sees extractor output + the
global graph (faithfulness net + identity judgment, link-or-create,
aliases as phrasings); merger stays deterministic append-only.
- Event ledger: quiz outcomes deterministic from tool parts; NO
taught events; extractor records per-proposition understanding
notes (named-word scale, no numbers) — treatment TBD.
- Understanding: inferred, never encoded; state model (session-
independent, computed from dependency depth/strength) is pending
ideation — current five-class derivation is transitional.
Also updates: §2 plan tree (session scaffolding only), graph-as-context
(follows-edge subtree, event-derived hotspots), home page (message
provenance, transitional states), roadmap item 5, open questions
#2/#3 resolved, amendments table (+6 rows).
The §5 baseline had per-step lines, starts, drops, kept ratios, and
merge stats — but no durations (a background pipeline's cost profile
was invisible) and no failure line: a mid-pipeline throw left a
hanging 'pipeline start' in the server log with nothing recording
what failed or when. Now the extractor and auditor each log their
elapsed ms on completion, the merged line carries the pipeline total,
and runExtraction logs a failure line (with elapsed) before
rethrowing. Log shape only — no behavior, contract, or control-flow
change.
chat.tsx now uses createChatTransport(chatId): a send racing the wake
pipeline waits for the in-flight turn, merges onto the fresh server
record, and re-POSTs instead of surfacing the 409 banner. Also fixes the
transport's import to the core barrel (shell import law).
The optional "server-ahead heal" line in the jobs poller was considered
and skipped: the racing turn IS the wake turn, whose completion flips the
job to done within a poll tick or two — the existing settle-triggered
syncFromServer already heals the post-merge gap within ~1-2s. The extra
record fetch on every poll tick would double poll traffic for a path the
settle sync already covers.
The top-right overlay doubles as the state legend and the filter
surface: a search box (matches name or statement, case-insensitive)
plus one row per node state in reading order (taught, known, missed,
don't know, candidate) with its color dot, label, and total count.
Clicking a row toggles that state's visibility.
Filtering flows through sigma's official nodeReducer/edgeReducer
settings: hidden nodes drop out of rendering, hover, picking, AND
labels; edges drop when either endpoint is hidden; an open detail card
closes if its node is filtered out. Pure predicate (isNodeVisible) is
exported and covered by 7 tests; the reducers just consume its
verdict. Verified live: search 'Nietzsche' 5457->1687->5457 label px
(exact restore), known toggle drops 13 discs+labels and restores,
nonsense query shows the 'No matching nodes.' hint with zero labels,
counts 0/13/0/0/10 match the ledger.
The 409 fix is a merge-retry, not a bare retry: a 409 means the server
record is AHEAD (wake turn persisted the steer), and the write-ahead
persist makes the request body canonical — a naive re-POST would clobber
steer+wake messages and steerDelivered makes the loss permanent. The
transport waits for the racing turn (500ms poll, 30s cap), refetches the
record, appends the client's unsent messages by id, and re-POSTs. The
integration seam (one line in chat.tsx) follows in the next commit.
- components/chat-transport.ts (NEW): createChatTransport(chatId) — the
chat.tsx seam is now a one-line swap. Its fetch turns a 409 on POST
/api/chat (a learner send racing the wake pipeline's ~1s adoption window)
into: wait out the in-flight turn (poll turnInFlight, 30s cap), refetch
the record, MERGE the outgoing messages onto the fresh server list, re-POST.
A bare retry would clobber the steer + wake messages via the write-ahead
persist (steerDelivered makes that loss permanent) — merging is the whole
point. Unit-tested: pass-through, wait+merge+reorder, dedupe by id,
repeated-409 loop, bounded give-up.
- src/core/pending.ts: findPendingJobCall deleted (dead since wave 1 —
job tools resolve server-side with an ack, nothing pends client-side).
JOB_TOOLS kept (runner.ts still uses it). Header doc rewritten.
- src/server/jobs.ts: GRACE_MS 1500 → 750, with the evidence in the
comment: the race window is only the learner's answer→POST flight
(sendAutomaticallyWhen dispatches synchronously; ~10ms localhost,
<300ms realistic RTT — 750 is 2.5× worst case) and misses self-heal
via the pump's gate recheck, the 409 backoff ramp, and the new
transport merge-retry. POLL_MS=400 kept (sampling granularity only).
- tests/jobs.test.ts: prompt-size guard — every fragment ≤8k chars,
composed prompt ≤60k — the README-leak class (815 bytes ≈ 200 tokens
per teacher turn before wave 1's fix) can't silently recur.
Gates: typecheck, 279/279 tests, lint, build — all green.
Purely mechanical: src/core/contracts/{plan,graph,chat,jobs}.ts carry the
sections verbatim (graph = nodes + ledgers + extraction findings; jobs =
the async ack-and-steer protocol + tool results + demo bridge), and
contracts.ts becomes a re-exporting barrel so every existing import path
(@/src/core and ./contracts.ts) is unchanged.
Wave-2 lane ownership follows the split: the graph stream owns
contracts/graph.ts, the teacher stream owns contracts/jobs.ts — same-file
contract collisions between streams are structurally impossible now;
cross-domain schema changes go through master.
The right sidebar's mode (rail | list | graph) is now shared state: a
new useTreePanelMode() hook lets every sidebar section collapse and
expand together. With sub-agents running in rail mode the fleet shows a
quiet strip — bot icon (click expands the sidebar) + vertical 'N running'
count — mirroring the plan rail's node-count strip below it. The sidebar
now collapses all the way regardless of running jobs.
End-to-end verified through the real flow (dispatch part in the
transcript + running job record, the 1s jobs poll rendering the panel):
rail column exactly w-10 with both rails stacked and aligned (40px), the
fleet rail's expand click transitions to list mode and persists, fleet +
plan panels equal widths in list (256/256) and graph (384/384) modes,
9-node graph intact, console clean.
The sub-agents fleet panel was a w-64 fixed aside with no left edge —
aligned with the plan panel only by coincidence in list mode, floating
detached in rail (w-10) and graph (w-96) modes. It now stretches to the
sidebar column's current width and shares the panel's border-l, so the
sidebar is one continuous panel with SUB-AGENTS above PLAN (thin border-b
divider). Verified headlessly in list and graph mode: identical edges and
widths (256/256 and 384/384), perfect vertical stack (fleet 0..99.5, tree
99.5..800), no overlap, 9-node graph intact.
The rail-mode-while-jobs-run question (fleet cards would cram into w-10)
is logged as wave-2 UX design work for the UI stream.
The weave had nested the right sidebar inside the transcript column
(below the header), so the phase chip sat above the panel instead of left
of it and the panel was bounded by the scroller area. The column is now
a true sibling of the middle column under flex h-dvh, per the UI stream's
original design; TreePanel's aside gets flex-1 min-h-0 so it shares the
column with the fleet panel instead of overflowing it. The plan-graph
viewport (ResizeObserver-measured) now has real size, so the mermaid
view draws.
Headless-verified at 1280x800: panel spans 0..800 top-to-bottom in both
modes, chip right edge < panel left edge in both modes, graph SVG = 9
boxes + 8 beziers, console clean.
Node names word-wrapped as muted labels below nodes (global zoom gate),
constant-radius static glow in the node's own state color with
enter/leave crossfades, node-anchored detail card, and padded node
picking (+10px pickable radius via a picking-mode-only shader — the
maintainer-endorsed fix for sigma v3's half-resolution hitbox reads;
visible rendering pixel-identical).
chat.tsx woven by hand: UI's session-surface layout (transcript column +
right sidebar as full-height siblings, h-10 header with PhaseChip) wrapped
in sub-agents' JobsContext.Provider; the message map carries both the
steer ternary (steers bypass the Message wrapper — the model-facing glue
text never renders) and UI's PhaseDivider emission (steers are verified
phase-boundary no-ops). Right sidebar = sub-agents' fleet panel column
(SubAgentsPanel above TreePanel, xl-only) carried onto UI's skeleton.
contracts.ts auto-merged (ChatSummary.phase/pendingQuestion + ChatListItem,
additive above the async-protocol section).
Smoke-verified on the merged tree: steer renders bare as its artifact
badge with no learner bubble, no rendered glue text, and no spurious
phase divider at the steer boundary.
README mermaid + layout + protocol paragraph now describe the merged
protocol: server-executed job tools ack mid-turn, runners steer the
teacher later via the wake pipeline (server/jobs.ts), client adopts
wake turns via turnInFlight and renders steers as artifacts.
architecture.md turn-composition seam 3 rewritten; runner dependency
signature updated (deliver seam).
Server-executed job tools resolve mid-turn with an immediate ack; the
runner steers the teacher later via a server-side wake turn (per-chat
serialized queue on globalThis, turn-free + quiz-aware firing, 409
retry, idempotent per jobId, stale-job sweep). Live observability client:
central /api/jobs poll, dispatch cards, steer artifacts (research/visual/
demo renderers), sub-agents sidebar panel, wake-turn adoption via the
existing turnInFlight machinery. persistTurn fills empty message ids
(withMessageIds). prompt composition loads numeric-prefix fragments only
(README.md had been leaking into the system prompt).
composeInstructions loaded EVERY .md in src/agent/prompts — including
README.md, the directory's human documentation, which rode into the
system prompt as its own section (visible in OpenRouter logs, old POC
paths and all).
The loader now enforces the documented convention: only numeric-prefix
fragments (\d+-*.md) compose. README.md stays in the directory as docs
and can never reach the model again. README's rule text updated to
match; composeInstructions exported for tests; regression test asserts
the README never leaks and every numeric fragment composes verbatim.
Figures now always fill the card's width (h-auto keeps the aspect
ratio): narrower svgs scale up instead of leaving a white strip on the
right when they carry their own background color; oversized ones still
shrink to fit. bg-white stays as a neutral backing for svgs without
their own background.
Fixes the hover flicker the maintainers' way (jacomyal/sigma.js#1493):
sigma v3 picks nodes by reading a single pixel from a picking
framebuffer rendered at HALF the CSS resolution, and has no setting
for hit padding. Small nodes get tiny, ragged hit edges, and our glow
halo (9px beyond the disc) was NOT pickable — moving the cursor from
the disc onto its own halo de-hovered it, an oscillation loop.
NodeCircleProgram subclass (registered via nodeProgramClasses)
replaces only VERTEX_SHADER_SOURCE: a verbatim copy of sigma 3.0.3's
circle vertex shader that adds PICKING_PAD_PX (10) of radius under
#ifdef PICKING_MODE alone. The visible pass never takes that branch,
so rendering is pixel-identical (verified headless); the pickable
disc is disc + 10px, covering the whole hover halo, so the halo is
now hoverable and small candidate nodes are comfortable to hit.
sigma/rendering is imported dynamically (its ESM build touches
WebGL globals at module scope; SSR-safe like the sigma import).
This replaces the reverted prototype-patch approach (f12480e).
sigma v4 ships this officially as the nodePickingPadding setting —
noted for a future upgrade.
The persistTurn id hygiene (2d7b004) only covers NEW writes — records
persisted before it still carry messages with empty SDK ids, and two of
those in one transcript re-trigger the duplicate-React-key error.
- data/chats: backfilled all empty ids (6 messages across 5 records,
msg_<ts>_<hex> scheme matching withMessageIds).
- chat.tsx: key={m.id || `m-${mi}`} on both message branches — even an
unmigrated legacy record can never collide keys again.
NOTE for master at merge: the master tree's data/ needs the same
one-time backfill (any chat saved before the withMessageIds commit).
Three refinements from live testing:
- Steer messages no longer sit inside the user Message container (the
bubble background + right alignment it gave artifact cards). chat.tsx
renders SubagentSteerCard directly in the transcript column — full
width, centered, same register as the teacher's artifacts.
- Research steers render a quiet "Research complete · N sources" badge
(the dispatch-settled idiom), not the full brief: briefs are long, the
wake turn weaves them into the lesson anyway, and the full text stays
persisted in the artifact part — a "view full research" affordance
can be added later without any protocol change. Failures keep the
failure card (the brief explains what went wrong).
- The sub-agents' verification notes (visual/demo builder notes) are
model-facing glue and no longer render on success; failure notes
remain the error explanation.
SSR-verified against a synthetic record: badge + SVG bare in the
transcript (no is-user wrapper), notes/brief confined to the RSC
payload. 229/229, typecheck, lint, build green.
The persisted mode (lh:tree-panel-mode) was read inside TreePanel — a
per-page component that remounts on every session navigation. First
paint rendered the SSR-safe "list" default, then the mount effect
applied the stored mode: with the animated frame, opening a session
visibly opened the panel and then closed it. The mode now lives in a
root-layout provider (the SidebarProvider pattern) and survives
navigations untouched — the panel mounts already in the right mode.
The default stays "list" so SSR and first client render agree; the
stored preference applies once, on provider mount.
Root cause: sigma's getNodeAtPosition reads the picking framebuffer,
which is rendered at HALF the device resolution
(pickingDownSizingRatio = 2 * pixelRatio). Small nodes' hit circles
are a couple of device pixels across in that buffer with ragged,
quantized edges — near a node boundary, tiny cursor movements flip
the hover state on/off, and each flip makes sigma clear the hover
layer immediately. That state churn is the flicker; it survived every
animation change because it was never in the animation.
Mitigations:
- patchNodePicking() replaces Sigma.prototype.getNodeAtPosition with
a smooth distance test (rendered radius + HIT_PAD_PX = 6px) built on
public renderer APIs only (getGraph, getNodeDisplayData,
framedGraphToViewport, scaleSize). No ragged edges, and small
candidate nodes get roughly double the hoverable area.
- Leave-debounce (90ms): when hover drops, hold repainting the
captured hover paint at the current fade (sigma would otherwise
clear the layer the instant hoveredNode flips to null), and only
fade out if the cursor hasn't bounced back within the window. A
re-enter cancels the fade, so boundary oscillation never visibly
dims anything.
- The three panel modes were three separate fixed-width asides, so a
mode switch jumped the whole transcript column width in one frame:
scrollbar flash, overshoot, re-correct. Now ONE aside animates its
width exactly like the left sidebar (reusing the sidebar-motion
hook, so it inherits the provider's mount-gated transition), with
a FIXED-width inner layer clipped by overflow-hidden — content
never reflows mid-transition.
- The chat header was auto-height: the sidebar toggle (a size-9 icon
button) renders only while the sidebar is closed, so opening it
collapsed the row and slid the title + phase chip up. The header is
now a constant h-10.
The instant muted->bright color swap felt abrupt next to the fading
halo. The hover name is again drawn at partial alpha over the muted
resting label, using the SAME transition factor as the halo — text
and glow fade in/out in sync. Because every enter/leave interpolates
from the current fade value, rapid hover toggles at a node's hit
boundary glide instead of snapping (the flicker-damping fix).
The pi-style ack protocol (previous commit) left the client describing the
old world: artifact cards read the ack string as a result ("could not be
displayed"), the only job poller rendered on input-available parts that no
longer exist (so wake turns landed invisibly until re-navigation), steers
rendered as learner bubbles with no SVG anywhere, and server-persisted
assistant messages carried empty SDK ids (duplicate React keys).
- persistTurn (turn-service): fill empty message ids at the canonical write
— server-only messages (last turn's, wake turns') now key uniquely;
client-authored ids untouched.
- chat.tsx: ONE central /api/jobs poll (fast while jobs run, slow discovery
cadence, off for job-less sessions) drives every job surface, re-syncs
once when a job settles (the record already holds the steer + wake
response at flip time), and adopts server-side wake turns via the same
turnInFlight machinery as returning mid-turn. Steers branch to the
artifact card — never a bubble. Composer no longer gates on jobs.
- /api/jobs now reports turnInFlight alongside the job list.
- dispatch-card: the tool-call box — live activity by toolCallId while
running, quiet "delivered"/"failed" one-liner after; the ack is visible
observability, the artifact lives in the steer.
- steer-card: renders the delivered artifact by kind (research brief /
sanitized SVG / sandboxed demo iframe) from the data-subagent-artifact
part; result renderers extracted and exported from the artifact cards.
- sub-agents-panel: right-sidebar section above the plan tree listing
running sub-agents (kind, elapsed, live activity) — vanishes when idle.
- tests: dispatch/steer/panel render tests re-target the new protocol;
persistTurn id-hygiene suite. 229/229 green, build green.
Out-of-lane touches for master review: chat.tsx + components/** (cleared
this wave), app/api/jobs/route.ts, src/server/turn-service.ts, contracts
protocol doc §2. Live-verified on :3003 (full loop, SSR DOM checked).
- The halo no longer grows during the fade: radius is constant at
size + 9px; only its opacity fades in/out over ~180ms.
- The hover name is drawn opaque in the bright color instead of
cross-fading over the muted resting label. Partial-alpha text
oscillated whenever hover toggles rapidly at a small node's hit
boundary (sigma fires enterNode/leaveNode on every state change) —
an un-animated color can't flicker.
- The glow no longer pulses: it's a static halo (9px beyond the disc,
0.45 alpha at the edge fading outward) in the node's state color.
- Hover enter/leave now cross-fades over ~180ms instead of appearing
instantly: entering schedules sigma renders so drawHover repaints at
the interpolated fade; leaving draws through a repainter captured on
the last hover paint (sigma stops calling drawHover once unhovered).
The text cross-fades too — the brighter hover name is drawn at
partial alpha over the muted resting label on the layer beneath.
- The halo starts flush at the node disc edge (was size+1, leaving a
dark gap ring that read as a gray border between node and glow).
- Both fade directions cancel each other and stop on completion, so
there is no continuous loop — idle CPU stays near zero.
Gate 1 found the teacher staying silent after a research brief landed.
The SDK only evaluates sendAutomaticallyWhen inside addToolOutput — an
external setMessages (our syncFromServer) updates the UI but never
triggers the continuation. Fix: syncFromServer checks
lastAssistantMessageIsCompleteWithToolCalls and calls sendMessage()
(itself a valid continuation trigger); plus a mount-continuation effect
for the reload case (job fulfilled while no client was open).
- src/core/math-delims.ts: pure preprocessing for the \(...\)/\[...\] math
contract — balanced delimiters rewrite to the two-dollar forms remark-math
parses ($ is never math). Skips code fences/spans, escaped delimiters, and
leaves unbalanced (mid-stream) delimiters untouched. Display math renders
as a block: mid-paragraph gets blank-line padding; indented (list items)
degrades to inline so list continuations don't half-parse.
- message.tsx: transform in the render path (children-memoized); math plugin
now singleDollarTextMath: false — the currency hazard dies structurally.
remark-breaks via the cjk remarkPluginsAfter slot (the bare remarkPlugins
prop would replace the [remark-gfm, codeMeta] defaults).
- mermaid: dark theme + sans font via Streamdown's mermaid prop; dark-styled
error fallback (components/mermaid-error.tsx) with error, source in
<details>, and retry.
- globals.css (appended): @source for streamdown dist — its internal UI
chrome (code blocks, mermaid containers, tables) was entirely unstyled
because Tailwind v4 never scans node_modules; --color-sidebar → card; wide
mermaid SVGs capped to the column; .katex-display scrolls.
- tests/render-markdown.test.tsx: 26 tests (transform unit + render). The
math describe block in render-cards.test.tsx is updated to the new
contract ($...$ now renders as literal text — pinned).
- src/store/jobs.ts: per-job JSON store in data/jobs (create/get/update/list,
dedup by toolCallId)
- src/agent/tools/jobs.ts: research tool — client-side (no execute), turn ends
at the call; input per contracts ResearchToolInput
- src/agent/tools/web.ts: server-side web_search (Google CSE) + web_fetch
(Readability/Turndown/linkedom, Jina fallback) — errors return as strings,
never thrown into the agent loop. Deps: @mozilla/readability, linkedom,
turndown (+@types/turndown dev)
- src/agent/subagents/researcher.ts: isolated ToolLoopAgent (web tools only,
12-step cap), researcher prompt ported from pi
- src/agent/subagents/runner.ts: spawnPendingJobs hook + runResearchJob —
fire-and-forget, activity line per tool call, fulfills the part in the
LATEST chat record (output-available) before flipping job status; failure
still fulfills the part so the teacher learns the outcome
- src/server/chat-handler.ts: onFinish spawn hook after saveMessages
- app/api/jobs/route.ts: GET ?chatId= polling endpoint
- components/artifacts/job-card.tsx + registry entry: polling activity card
(2s) → syncFromServer on finish; research-brief card (markdown + sources)
- src/agent/prompts/20-jobs.md: research doctrine for the teacher
- tests/jobs.test.ts: store CRUD, spawn hook via scripted mock teacher,
runner completion/failure with fake model + stubbed fetch
- src/core/plan-tree.ts: pure tree ops (createTree/addNode/updateNode/removeNode/
addEdge/removeEdge/setCurrent/markDone), DAG invariants (unique ids, existing
endpoints, no self-loops/duplicates/cycles), cascade remove, version bumps on
state changes only (true no-ops for idempotent setCurrent/markDone).
- src/agent/tools/plan.ts: plan_init (refuses re-init), plan_add_node (optional
parents → requires edges), plan_update_node, plan_remove_node, plan_add_edge,
plan_remove_edge, plan_set_current, plan_mark_done. Execute = getChat → op →
saveTree → PlanToolResult with the full updated tree; PlanTreeError and missing
chats become {ok:false, error, tree}.
- src/agent/prompts/10-plan-tree.md: tree-authoring doctrine (when: post-probe;
grain: one reasoning step per node; discipline: set_current on start,
mark_done on demonstrated mastery; freedom: mid-session restructure).
- tests/plan-tree.test.ts: every validation error path, version semantics,
cascade remove, no-mutation, tool round-trips against the real chat store.
- Every session starts with the learner's knowledge graph as base
context (precision probing); selection problem noted: pedagogical
relevance != semantic closeness (structural neighborhood, diagnostic
hotspots, frontier strip); strategies to tune on data.
- Sub-agent architecture: async background workers with live activity
indicators; demo-builder TESTS code headlessly; visual-maker verifies
by looking (port of vault svg-maker); mermaid needs no sub-agent;
researcher tool for fact verification (port of pi web-search/web-fetch
+ interactive-subagents researcher prompt).
- Not-a-chat presentation principle marked LOW PRIORITY per user.
Margin model flaws (user feedback): fragment placement needs unreliable
routing; scattering kills the receipt moment and chronology; session
value is in the moment, revision is rare, HTML export deprioritized.
Evolved model: one chronological spine; learner blocks are intact typed
'interjection' cards; teacher replies as woven Q&A interludes
(quote-then-answer); anchoring is a link overlay (backlinks), margins
demoted to a computed view. Chat-ness dies by type asymmetry, not
relocation.
Asymmetry of artifact: the teacher writes the document (whiteboard), the
learner writes in the margins (voice/floor). Bubbles die; the unit is the
block; chronology yields to tree structure; Q&A becomes document
furniture; the composer becomes a response field. Presentation-layer
change only — the interaction model stays conversational.
Captures 2026-08-22 decisions: hybrid live-emission + consolidation graph
construction (reversing the vault doc's teacher-untouched rule), one
substrate merged across sessions, structured plan-tree tools (mermaid
demoted to ad-hoc), probe/teach phase separation with collapsed teach
checks, right-panel tree view, LaTeX delimiter switch plan, and a
dependency-ordered roadmap.
Clicking the collapsed bar set expanded=true and started a smooth
scrollToBottom — but the scroll position was still legitimately inside
the collapse zone (that's why the bar was showing), so the hysteresis
listener re-collapsed the dock on the very next scroll event, then
re-opened it when the scroll arrived: open → snap shut → reopen.
The machine had no notion of intent. Now the bar click sets an
expandIntent flag that suppresses the collapse branch; it clears when
the scrollToBottom promise settles (completion or interruption) or after
a 2s safety net, so a user yanking the scroll away mid-reveal collapses
the dock again instead of wedging it open.
Verified live: click = exactly one transition (bar→open at ~26ms, stays
open, lands at d=1); collapse still healthy afterward; mid-reveal
interrupt re-collapses within ~300ms.
- Chat now remounts per session (key={chat.id}): fresh StickToBottom,
fresh DockOverlay (no cross-session morph from the previous shell
height), fresh useChat.
- Conversation initial="instant" (was "smooth"): the mount scroll to
bottom is a jump, not a slide.
- DockOverlay skips the pending-question scroll/expand effect for the
session's INITIAL pending question (dock starts expanded; the initial
scroll positions us) — previously it fired a second smooth
scrollToBottom right after the library's initial scroll (the visible
'pause, then the quiz pops and pushes everything up').
- The dock-variant fade/rise no longer plays for the session's opening
variant; reserved for mid-session transitions.
Verified live: client-side switch settles at d=1px from the bottom within
one frame of content swap, dock open from the first frame, both
directions (quiz session, plain session).
- Oscillation fix: collapsing the dock frees ~Δpx of flow height; within
Δ of the bottom the browser clamps scrollTop to the new max, landing
the learner AT the bottom, which re-expanded the dock → loop. Now a
hysteresis state machine on the scroller's scroll events: collapse only
when distance-from-bottom > Δ+64 (strictly clamp-proof), expand only
within 16px of the bottom. ~370px dead band; exactly one transition per
direction verified live. Heights measured live per question.
- Reaching the bottom re-expands the dock AND scrolls to reveal it fully
(previously it grew over the content and left you short of the bottom).
- Streaming follow fixed: ConversationContent had h-full, so the observed
content box never grew and use-stick-to-bottom's ResizeObserver never
fired — no auto-scroll during streaming. min-h-full restores growth.
Verified: distance-from-bottom ≤70px transient during a 25s stream,
settles at 1px.
- Animation: the blob's shell morphs height (WAAPI, 180ms) on every
variant change — chat ↔ question ↔ collapsed bar — plus a quick
fade/rise (160ms) on the swapped content. Gotcha pinned in code: never
measure the shell while a morph is in flight (getBoundingClientRect
reads the ANIMATED value and corrupts the next morph's start height);
cancel running morphs before measuring, refresh settled height only
when no morph is running.
- Gradient-over-scrollbar fixed structurally: the dock is no longer an
absolute overlay on the conversation root — it's sticky bottom-0 INSIDE
the scroller (in flow). The transcript scrolls fully clear of the dock,
the fade never touches the scrollbar lane, and the pb-hack clearances
are gone.
- New question while at the bottom scrolls to reveal the dock; scrolled
up → collapsed bar, no yank.
- Thin dark native scrollbar app-wide (8px webkit + scrollbar-width:thin,
dark thumb, transparent track). Note: use-stick-to-bottom sets
scrollbar-gutter: stable both-edges on its scroller — the lane is
outside the content flow by design.
- 'Writing a question…' transcript shimmer while a tool call streams its
input (same slot as 'Thinking…'). Protocol pinned by a test asserting
tool-input-start precedes tool-input-available; scripted mock now
streams tool input as deltas like real providers do. (OpenRouter/
Anthropic often delivers the whole input in ONE delta — then the dock
appears instantly and no indicator is needed or shown.)
Verified live: grow 54→349px and shrink 349→54px fire with correct
from/to; collapse/expand intact; gradient stops before the gutter;
Thinking… observed in-page; 58/58 tests.
- A pending quiz/ask now REPLACES the chat composer: one persistent
rounded-2xl shell in the transcript overlay swaps contents (composer ↔
question ↔ collapsed bar), never remounting — the structure a future
grow-morph animation needs.
- Unified bottom row inside the question: the note field (select modes),
the answer field (text-mode asks), or the Other text — one field, one
'Submit answer' button, Enter submits.
- Collapse on scroll: uses useStickToBottomContext — scroll up and the
dock folds to a slim bar (kind chip + LaTeX-flattened question teaser +
'tap to answer'); click scrolls to bottom and re-expands. The expanded
form stays mounted-hidden so a half-made selection survives.
- Pending/streaming tool parts no longer render inline; answered parts
land in the transcript as graded cards on submit. Question generation
shows a shimmer in the shell.
- Composer back to pure chat (no mode machinery); quiz-card.tsx and the
pendingText/registerSubmit bridge deleted; render tests re-pointed at
the dock (wrapped in StickToBottom).
Verified live: docked quiz submit (note+selection), ask-text Enter
submit, collapse/expand with selection survival, bar teaser text.
Sidebar (replaces the modal drawer):
- Inline, toggleable, no backdrop/focus theft — can stay open while working
- Open state persists across pages (provider in root layout) and reloads
(localStorage; starts closed server-side to avoid hydration mismatch,
stored value applied post-mount; default open on first run)
- Hamburger in page headers only when closed; close button in sidebar header
Floating composer blob (per reference screenshot):
- Floats over the transcript (absolute overlay), persists at bottom while
scrolling, content fades behind it (gradient mask); pb-44 scroll clearance
- Concentric corner radii: blob rounded-2xl(16px) − p-1.5(6px) = send
rounded-[10px] = 25% of the 40px button; CornerDownLeft icon per reference
- Stop moved from header into the blob (busy → square icon)
- prompt-input.tsx + 7 orphan ui files pruned (attachments/command palette
unused); hand-rolled Composer is ~100 lines and render-tested
Pending-question morph (one text field on screen, never two):
- Quiz/ask-select pending → blob becomes the note field (send hidden, hint
line above); card's internal note input removed; Submit consumes it
- Ask free-text pending → blob becomes the answer field; its send submits
via the card's registered submit api (ref bridge); Enter works
- Chat owns the single text state; card clears it on submit
- canSend for answer mode mirrors the card predicate directly — reading the
ref during render lagged one commit (found in browser testing)
Widths: one shared column (max-w-3xl + px-4) for transcript, cards, and
composer — all three measured pixel-identical (left 416, width 736).
Assistant Message max-w-full/MessageContent w-full (was max-w-[95%]/w-fit —
the 'cards are a bit shorter' bug).
User messages render plain text again — no math pipeline on learner-authored
text (currency hazard accepted for the model only, guarded by the prompt).
Tests: 58 pass (5 new composer pins; card tests updated to controlled
props). Verified live: note flow, answer flow, sidebar persistence, float,
fade, zero console errors — plus the live model spontaneously honoring the
$ currency escape contract in a continuation.
Layout:
- Home = knowledge-graph placeholder (main view) with new-session input
docked below; session list moved out of home into a hamburger drawer
- SessionDrawer: slide-over session navigation (backdrop/ESC close, active
highlight, fetches /api/chats on open) on both home and chat headers
- Chat header loses the back button — the drawer is the navigation
Math (inline $ was silently not rendering):
- @streamdown/math defaults singleDollarTextMath:false — now
createMathPlugin({ singleDollarTextMath: true }) in message + reasoning
- katex.min.css imported in layout (streamdown does not inject plugin
styles; display math only looked right via browser MathML fallback)
- QuizCard/AnsweredCard route question/options/explanation through
MessageResponse; user chat bubbles render markdown+math too
- Currency hazard: micromark-extension-math@3.1 lacks pandoc's
closing-digit rule, so bare '$5 and $10' parses as math — defense is at
the source: system prompt now instructs escaped \$5 / 'USD' for money
Hydration fix (React #418):
- QuizCard shuffled options with Math.random() — server/client orders
diverged. shuffleOptions now takes an injectable RNG; QuizCard passes
seededRandom(toolCallId) (mulberry32/FNV-1a in question-core). Same
question → same stable order across reloads; still varies per question.
Tests: 53 pass (5 new math-rendering pins incl. fenced-vs-one-line $$
behavior and the escaped-currency contract). tsc + next build clean.
Verified live in browser: inline/display math in text + cards, drawer
open/navigate/active-highlight/ESC, no console errors, no font 404s.
The teaching agent no longer runs on pi. Stack:
- ToolLoopAgent (ai@7) + OpenRouter (OPENROUTER_API_KEY), model via LH_MODEL,
default anthropic/claude-sonnet-4.5 with reasoning tokens
- quiz/ask_user_question = client-side tools (no server execute): the call
lands as a typed tool part in input-available state; the card grades via
src/core/question-core.ts; addToolOutput sends the verdict; the teacher's
reaction continues the same assistant message
- resume-mid-quiz is free: the pending tool part persists in the transcript
- persistence: one JSON per chat (data/chats/), full UIMessage transcripts,
saved onFinish (also on abort)
- UI: AI Elements (owned copy-paste components, pruned to the five in use)
+ button-based QuizCard/AnsweredCard (ask answers never graded)
- pi fully removed: TUI, extensions, Fastify+WS server, bridge, custom
protocol all deleted (recoverable from git history)
- tests: question-core units carry over; chat-flow integration drives
handleChatRequest with MockLanguageModelV4 (48 tests, zero tokens);
render smoke tests guard the cards (renderToStaticMarkup)
Carried over unchanged: teacher system prompt, question-core, schema/
ledger/derive/extract pipeline, data model.
- Markdown.tsx never passed text as children to ReactMarkdown (valid JSX,
compiled clean, rendered nothing) — the 'thinking shows, text doesn't' bug
- toolResult entries (quiz/ask dispatch instructions for the LLM) leaked
into the transcript as visible text; now never rendered
- render smoke tests (renderToStaticMarkup, no DOM): pin markdown content,
KaTeX, button-based quiz options, ask answers not graded, toolResult and
[Quiz answer] hiding — negative-tested against the actual bugs
- React default import in all .tsx: tsx test runner uses classic JSX
transform (ignores tsconfig jsx option), Vite uses automatic runtime;
explicit import works under both
- katex css moved to main.tsx (tests can't import css)
- verified live in browser: all assistant messages render, ask card has no
grading marks, pending quiz re-arms on resume
Root causes of the v1 browser bugs (all fixed + covered by deterministic tests):
- duplicated messages: per-socket snapshot + global broadcast marking raced;
replaced with a single append-only entry log (exactly-once per socket,
structurally) — covered by tests/server.test.ts
- delayed/missing echo of own messages: optimistic append with sending/failed
status, reconciled by text when the real entry arrives
- no thinking shown: thinking deltas streamed live (kind: thinking) and
persisted in assistant entries so they survive reloads
- ask answers graded as wrong: AnsweredCard no longer applies quiz grading to
ask answers (no ✓/✗, no verdict)
- broken option selection: native radio/checkbox inputs fighting React state
replaced with button-based options (single source of truth, one-click select)
- no URLs: History API routing — / home, /s/<file> per session (deep links,
refresh, back button); session view resumes its file on mount
- lost connection = dead UI: exponential-backoff reconnect with full resync
- stick-to-bottom transcript with jump-to-latest pill
Server: startServer() with injectable runtime factory (scripted model in
tests); createSession returns file for routing; scripted model gained thinking
turns. 51 deterministic tests green.
amosblomqvist