The model indicator on a stage page hovered to provider, model, and
reasoning effort only. Seeing what a stage actually spent meant leaving
for the Billing tab, which reports per node rather than per visit.
The stage list had no token data to show, so add a per-visit `billing`
block to `GET /runs/{id}/stages`. The Billing tab's pricing rule (a
provider-reported cost wins, otherwise the server catalog prices the
tokens) was private to `billing_rollup`; move it to
`StageProjection::billed_usage` and drive both call sites from it so the
two views cannot drift.
The popover's buckets use the Billing tab's labels verbatim. It stays
scoped to one visit, so a looped node's row on the Billing tab is the sum
of what each of its visits shows here.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The board cards showed wall-clock duration in the footer's bottom-right
corner. Replace it with the same SizeChip the list view and run detail
header use, so the cost signal is consistent across all three views.
The chip inherits the tooltip, which names the tier and adds the cost
once a run has terminal billing.
Add SizeChip tests pinning the tooltip label for each tier.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The Size column in the runs list rendered SizeChip without the billed
total, so its tooltip read "Size M" while the run detail header showed
"Size M · $12.34 billed".
The tooltip was also unreachable: the row title link paints a
`before:absolute before:inset-0` overlay across the whole row, which sat
above the chip and swallowed hover. Wrapping the chip in `relative z-10`
lifts it above that overlay, matching how the created-by and pull request
cells already handle interactive content.
Runs without terminal billing keep the plain "Size M" label, same as the
header.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
`active_time_ms` was only ever computed from terminal stage events, so a
stage still running contributed zero to the run rollup. A run parked in one
long agent stage reported 2m 8s of active time against 16m 53s of wall
clock — the two finished stages — while the running stage had been doing
continuous inference and tool work for over 14 minutes.
`live_run_timing` summed `filter_map(|stage| stage.timing)`, and
`stage.timing` is only written at finalization. Wall time ticked live off
`start_time`; active time did not tick at all.
Stage projections now accumulate brackets from the event log:
- Closing an inference bracket folds its span into `live_inference_ms`
instead of discarding it, including across retries, matching the
in-process stopwatch.
- Tool calls open a batch on the first outstanding call and close it when
the last one drains, so tools running concurrently within a turn count
once — the same span `execute_tool_calls` is bracketed by. Summing
per-call durations would over-count parallel tool use. Subagent tool
events are excluded; they run inside the root call's span already.
- `StageProjection::live_timing(now)` composes accumulators with any open
bracket, per handler: agent stages use the brackets, prompt and command
stages count elapsed time as inference and tool respectively, and
handlers that wait on a human, timer, condition, or child branches
report zero.
Active is clamped to wall per stage. A worker killed mid-turn leaves its
bracket open forever, and without the clamp it would tick up unbounded.
The clamp does not need to detect the dead worker: a stage cannot have been
active longer than it has existed. `watchdog.timeout` remains the authority
on whether a run is stuck. The clamp is deliberately not applied at run
level, where concurrent branches can legitimately sum past run wall time.
Timing is derived from events rather than emitted by the worker, so this
needs no event-schema change and applies to runs already stored.
`StageProjection.timing` keeps its terminal-only meaning, and the
authoritative breakdown still replaces the live estimate at terminal
events.
The billing endpoint had the same hole behind its `wall_only` fallback:
running stages reported zero inference/tool/active. Not visible in the
product, which renders only `wall_time_ms`, but wrong for any other
consumer of `GET /runs/{id}/billing`.
Parallel branch stages lose their breakdown permanently, even after
completion, because `parallel.branch.completed` carries only `duration_ms`.
That is a separate data-loss bug, tracked in #644.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A tab left open across a deploy keeps running the previous build's
JavaScript indefinitely. index.html is fetched only on a full page load,
all later navigation is client-side, and hashed bundles are served
`immutable`, so nothing reveals that the code is stale. This produced a
false-positive bug report where two correctly-deployed fixes appeared to
be missing.
Publishes a build id and offers a reload when the running document falls
behind. The toast never reloads on its own; the only automatic reload is
recovery from a chunk that no longer exists.
Build id derivation
-------------------
The obvious approach — hash the emitted asset filenames, which already
embed content hashes — does not work: Bun's minified identifier naming is
not deterministic. Building an unchanged tree twice produces byte-different
output roughly one run in three (same length, ~100k differing bytes, all of
it mangled names). Output hashes therefore move with no source change,
which would fire the toast on redeploys of identical code and train people
to ignore it.
The id is instead derived from the bundle's source inputs, so it changes if
and only if something we control changed. Verified stable across eight
consecutive builds while the entry hash flipped between both variants.
This non-determinism also means two builds of the same commit embed
different bytes into the server binary, which is worth addressing
separately for reproducible builds.
Detection
---------
SWR with `refreshInterval` + `revalidateOnFocus`, per the repo's React
effects policy. SWR does not poll while the document is hidden, so
background tabs stay quiet without extra gating. Unknown state on either
side — missing meta tag, failed fetch, 503 during a dev rebuild — never
produces a prompt.
Stylesheet hashing
------------------
Tailwind's output was stable-named and therefore served `no-cache`, letting
a tab revalidate into new CSS while running old JS. Tailwind purges unused
classes per build, so classes the old bundle still emits could silently
lose their styles. It is now content-hashed and moves with the build.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
agent.message already carries a `reasoning` property with the model's own
summary and its verbatim trace, and the generated client already types it.
The web app just never read it.
Read it onto the assistant turn and render it in the details panel, after
the message and before the metrics. A trace can run thousands of characters,
so leading with one would push the message the user clicked on below the
fold. Text over 280 characters collapses to a preview with a "Show all"
toggle, matching ChatUserCard's disclosure pattern.
Providers disclose one field or the other or both, so a trace with no
summary is labeled just "Reasoning" rather than "Reasoning trace" — that is
the common Anthropic thinking case, and the bare label reads better when
there is nothing to contrast it with. Both fields render as preformatted
text: reasoning is raw model output, not authored Markdown, and parsing it
would eat the line breaks that are part of what it says.
Adding the field to the assistant turn broke six existing toEqual fixtures
that assert whole turn objects; they now expect `reasoning: null`.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The prompt bubble is `w-fit max-w-[85%]`, so its width is measured
intrinsically and only then clamped. `items-start` left the inner content
wrapper intrinsically sized too, so it resolved against the available space
from before the clamp — the full column width — and kept that measurement
after the bubble shrank. The text laid out at 100% of the column while the
background painted at 85%, spilling out the right side.
Give the wrapper `w-full` so it fills the bubble's resolved width instead of
measuring itself. Short prompts still hug their content: a percentage-width
child contributes its content size during intrinsic sizing, so the bubble
measures the same and only the final wrap width changes. The expand button
keeps hugging its label as a separate flex child.
Also break long words in the collapsed preview. That is a separate overflow
path: the preview is raw prompt text under `whitespace-pre-wrap`, where an
unbreakable path or URL would spill even at the correct width.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A text-free agent message marks the boundary between two batches of tool
calls, so it stays in the turn stream to keep those batches as separate
"N tool calls" chips. But it rendered an empty prose div, which still took
a slot in the gap-4 column and doubled the vertical space between the chips
on either side of it.
Render nothing for those turns instead. The final assistant turn still
renders when it carries a token/duration footer, even with no text, so the
completed-stage metrics are unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Chat is the more useful first view for agent stages, so open there instead
of Thread. Only agent stages offer "chat" in availableTabs; every other
renderer already falls back to "primary", so this leaves Logs/Q&A/Decision
and the rest unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The "Model request · waiting on <model>" readout sat directly above the
Chat/Thread/Debug toolbar and appeared and disappeared as requests opened
and closed, shifting the toolbar underneath it.
Drops the StageInferenceIndicator component and everything that existed
only to feed it: the inference/runSettled prop threading through
RunStages, and StageActivity's watchdogTimedOut field. The watchdog.timeout
event now falls through to the same ignore path it always would have, since
it was never in STAGE_ACTIVITY_EVENT_TYPES.
The run-events invalidations for watchdog.timeout and agent.llm.* stay:
they still refresh stage events for the Debug tab and run state for the
insights sidebar.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
During a long LLM turn the durable event stream was silent: between
`agent.tool.completed` and the next `agent.message` nothing was emitted,
so "the model is generating" and "the worker is wedged" were
indistinguishable from the run store, SSE, or the UI.
The signal already existed. `AssistantTextStart` fired at exactly the
right point — after `build_request()`, after compaction, immediately
before the stream opens — then was classified as streaming noise and
thrown away. This promotes it rather than inventing a new one.
Two events, each asserting only what is provable when it is emitted:
- `agent.llm.started` carries the *requested* provider/model. No usage,
no cost, no context window: none of it exists yet, and failover can
re-target, so `agent.message` stays authoritative for what answered.
- `agent.llm.first_output` is edge-triggered on the first output of an
attempt and names what arrived. `ToolCall` is required, not optional:
a turn that opens with a tool call produces no text or reasoning
delta, so a latch keyed on those two would stay silent for exactly
the tool-heavy rounds where liveness matters most.
`agent.llm.retry` now also fires on the one previously invisible
mid-turn path — a stream that ends without a finish event, which
replays the turn and discards its output with nothing to show for it.
Its `attempt` field was already fed by two independent counters, so an
optional `phase` (open | consume) names which loop it counts.
`StageProjection.inference` projects the open bracket. `Some` means
"the event log contains an unclosed inference bracket", not "the model
is computing now" — a SIGKILLed worker leaves it open, which is the
truthful statement of what we know, and `watchdog.timeout` remains the
authority on actually-stuck.
The close is the subtle part. Terminal cancel and wall-clock timeout
tear the session down through `discard_session` without emitting a
message, error, or interrupt, so a session-lifecycle backstop is
required. It has to be `agent.session.ended`, not
`agent.session.deactivated`: deactivation is emitted by `lease.release()`
*before* the forwarder drains queued agent events, so a queued
`agent.llm.started` can arrive after it and re-open the bracket. But
`agent.session.ended` carries no stage identity, so the close takes
ordering from the event and identity from the projection, scanning for
brackets the ending session opened. A normal stage lookup there finds
no target and silently no-ops.
Presentation states what the log proves and nothing more: no progress
bar or ETA (no completion estimate exists), "reasoning" only when the
provider sent reasoning output, elapsed counted since the request
opened, and no live animation once the run is terminal.
Scope is session-backed agent stages. One-shot completions call
`client.complete` directly and never build a session; covering them
means moving the emit point into `fabro-llm`, filed as a follow-up.
`agent.output.start` was never persisted — it existed in a name map,
an `unreachable!` arm, and docs — so the rename carries no migration
risk. Corrects `events.md`, which documented it as a real emitted
event, and the v2 proposal, which mapped it to `message.part.started`
despite it firing before the request opens.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Empty-text `agent.message` events were discarded, erasing the boundaries
between batches of tool calls. Eight short shell calls issued across five
model responses collapsed into one `Bash x8` group whose DNA bar spanned
the model-response gaps between them, showing a misleading six-minute
duration. Filtering could recreate the same artificial adjacency.
- Always emit an assistant turn for `agent.message`, carrying
`tool_call_count` so a text-free response renders as
"Requested N tool calls" instead of a blank row.
- Derive grouping and DNA timing from the complete turn stream, then
apply kind/search filters as a pure visibility pass over display
items. Hiding a tool can no longer inflate an adjacent Agent bar, and
hiding an Agent can no longer merge the tool groups on either side.
- Give a tool group the wall-clock envelope of its children (earliest
start to latest end) rather than the sum of their durations or the
span to the last array element. Row, details header, DNA bar, and
tooltip all read the same values.
- Advance the DNA previous-activity cursor by the maximum observed end
so out-of-order or overlapping completions cannot move it backward.
Frontend only: no event, persistence, or API schema changes.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Adds a Chat tab to agent stage pages alongside Thread and Debug, styled
after the Ask Fabro sidebar: agent messages render as first-class chat
bubbles (the narration between tool batches is the content that matters),
the stage prompt is a collapsed user-side card, and each run of
consecutive tool calls collapses to a wrench-icon count chip. While the
stage is running, in-flight tool calls (agent.tool.started without a
completed event) show as a live spinner line with the tool name and input
preview — data the Thread view drops today.
Thread remains the default tab; Chat becomes the default only after
production testing.
Also fixes the demo dataset: detect-drift carries the agent-flavored
stage events (prompt, agent messages, tool calls) but was labeled a
command stage, so its Thread/Chat views were unreachable in demo mode.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Resolves conflicts with the shared-checkout parallel rewrite (#607) and the
cached-run/billing dedup (de60eb900):
- handler/parallel.rs: rebuilt on main's shared-checkout version. Branch
ordinals are still reserved inside the branch task right before
ParallelBranchStarted (with graph_visit/resumed_from_stage_id), and the
reserved StageScope is shared with post-await error paths via a OnceLock
slot instead of main's dispatch-time visit=1 scope, so completion events
are never emitted under a guessed ordinal.
- billing.rs: keep this branch's run_stage_from_projection (RunStage grew
graph_visit/resumed_from_stage_id and a typed id), adopt main's
state.cached_run() and drop the removed run_stage_from_stage_id import.
- run_projection.rs: adopt main's typed parallel_results
(Option<Vec<ParallelBranchResult>>).
- run_event/misc.rs: union of both sides' imports.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A node cancelled (or lost to a crash) mid-flight and then resumed now
starts a new stage execution with the next StageId ordinal (work@2)
instead of reusing and clearing the cancelled execution's projection.
The old execution stays immutable with its own events, session, output,
timing, billing, and termination state.
Engine:
- Add a run-scoped StageExecutionTracker on RunServices with per-node
high-water marks. Ordinals are reserved after the StageStart hook
passes on the first attempt (retries reuse the reservation), ensured
at the composite checkpoint pre-step for hook-skips, and reserved in
on_terminal_reached for terminal nodes' synthetic events.
- Keep three concepts distinct: graph visit (max_visits/checkpoints,
unchanged), stage execution ordinal (the @N in StageId), and handler
attempt. The tracker is not checkpointed; the append-only stage event
history is its durable source of truth.
- resume() seeds the allocator from the run projection and computes a
node -> StageId provenance map of executions observed after the
selected checkpoint, threaded through execute_persisted_run,
RunSession, and InitOptions.
Events and projections:
- stage.started, parallel.branch.started, and checkpoint.completed
carry optional graph_visit and resumed_from_stage_id; StageProjection
stores both. Old events deserialize with None and legacy duplicate
stage.started replays keep last-attempt behavior.
- The CheckpointCompleted reducer is envelope-first: diffs and
skipped-stage synthesis attach to the exact execution StageId, an
existing Retrying projection finalizes as Skipped without losing
identity, and historical node_outcomes no longer create or collide
with newer ordinals (node_visits remains a legacy fallback).
Handlers:
- Parallel fan-out reserves child ordinals through the shared tracker,
derives worktree pass{N} from the parent's execution ordinal, and
seeds branch contexts with explicit child stage scopes so branch
lifecycle and nested handler events agree.
- Artifact capture and manager-loop child logs follow the ordinal.
API and UI:
- RunStage documents visit as the execution ordinal and adds optional
graph_visit and resumed_from_stage_id; Rust and TypeScript clients
regenerated.
- The web sidebar lists both executions chronologically; resumed stages
show a "Resumed from" link in the stage detail header and hover
popover, with the graph visit surfaced when it diverges.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Extract emit_branch_completed() to replace three near-identical
ParallelBranchCompleted constructions; status now reads consistently
from outcome.status
- Add context_diff_public() so parallel.rs and manager_loop.rs share the
diff-minus-engine-internal-keys step; move context_diff tests next to
the function in context.rs
- Replace fan_in's dead BranchShape struct with the canonical
Vec<ParallelBranchResult> (from_value moves, so no payload cloning)
- Narrow parseParallelOverview to ParallelBranchSummary {id, status};
its only consumer renders just those fields
- Drop helpers.test.ts's duplicate envelope() fixture in favor of the
shared makeEventEnvelope
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Adds a disabled-by-default `fireworks` provider to the built-in catalog,
served through the existing openai_compatible adapter/codec. The curated
roster covers Kimi K2.7 Code (default), Kimi K2.6, DeepSeek V4 Pro/Flash,
GLM 5.2, MiniMax M2.7, Qwen 3.7 Plus, and GPT-OSS 120B/20B (small
default + probe), with serverless pricing including cached-input rates.
All api_ids were verified live against /chat/completions (Fireworks'
GET /v1/models only returns a featured subset), and serverless responses
were confirmed to report prompt_tokens_details.cached_tokens, so cache
billing works through the existing codec path.
FIREWORKS_API_KEY is registered as an optional vault secret; provider
login, vault storage, and diagnostics probing are catalog-driven and
need no code changes. Includes catalog/install tests, two live e2e
tests, an integrations docs page, and a provider logo for the web UI.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Adapted from poolside's official favicon mark: monochrome
fill="currentColor" at 24x24 to match the other provider logos, with the
brand's gradient-fade tail preserved via the original alpha mask.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Cumulative implement + simplify_fable diff recovered from the run's meta
branch (fabro/meta/01KY7YH7RYCJ1BDVTTP96ZA4HV, stage 006 diff.patch).
The run validated this tree clean: cargo nextest (7,007 passed), clippy,
fmt, TS client regen + typecheck, web tests (679 passed), docs check.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Extract the quadruplicated watchdog check-and-clear logic in
schedule_worker_cancel_escalation into ManagedRun methods
(escalation_still_current, clear_escalation_for)
- Derive strum::IntoStaticStr for WorkerRef instead of a hand-written
variant-to-string match in kind()
- Use the generated AgentControlState constant instead of the raw
"waiting_for_steer" literal in run-detail.tsx
- Replace optimisticCancellationRunId state with a boolean; the
component is keyed by run id, so the stored id could only ever be
this run's own
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Raises the LR graph zoom ceiling from 200% to 400%. TB is unchanged at
200%.
Zoom and pan are now tracked separately per direction instead of shared.
Switching LR to TB and back restores the viewport you left in each mode,
so a round trip no longer loses your position. Previously a single
shared zoom value was clamped down whenever you switched into TB, which
meant going LR to TB and back cost you your LR zoom.
`run-overview.tsx` holds two view states, remembered per run under
`<runId>-TB` and `<runId>-LR`. `clampZoom` and `zoomAtPoint` take a
`direction` argument and apply the matching ceiling, so the
clamp-on-direction-change effect is gone. 24 tests in
`graph-viewport.test.ts`.
Requirements:
docs/brainstorms/2026-07-21-graph-zoom-lr-increase-requirements.md
Plan: docs/plans/2026-07-21-graph-zoom-lr-increase-plan.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Fabro <noreply@fabro.sh>
## Problem
In the runs list view, avatars in the **By** column render as squished
ovals.
## Cause
The "By" column `<td>` is `w-8` (32px) with `px-3` padding (24px total),
leaving ~8px of content width. The glyph sits inside the Tooltip's
`inline-flex`, so its wrapper is a shrinkable flex item that collapses
to that 8px. Since Tailwind Preflight sets `img { max-width: 100% }`,
the 20px avatar's width shrinks to ~8px while `size-5` keeps its height
at 20px — producing the squished oval.
## Fix
Wrap the glyph in `inline-flex shrink-0` so it keeps its 20px intrinsic
width and the auto-layout column grows to fit instead of compressing the
image. This also covers the non-user principal icon glyphs
(agent/system/slack/webhook/worker).
Typecheck passes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Switching from a run's Overview tab to another tab and back reset the
graph zoom and position to the default. Now it holds.
## Why
The viewport (pan and zoom) lived in `RunOverview` component state.
Overview and Stages are sibling routes under `runs/:id`, so switching
tabs unmounts Overview and drops that state.
## Fix
`apps/fabro-web/app/routes/run-overview.tsx`: cache the viewport per run
outside the component so it survives the remount, and reset it when the
run id changes, since the route instance is reused when only the id
changes.
Added two tests: viewport restores on remount for the same run, and does
not carry across runs.
Does not persist across a full page reload (in-memory only).
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
## What
On **Runs → Overview**, the workflow graph now supports the standard
Figma/Excalidraw canvas interactions:
- **Two-finger scroll → pan**
- **⌘/Ctrl + scroll → zoom**, anchored under the cursor (mac trackpad
pinch works too — the browser delivers it as `ctrl+wheel`)
The graph already had drag-to-pan, stepped zoom (toolbar +/−), and
fit-to-window. This adds the missing wheel/trackpad input on top of that
existing transform state.
https://github.com/user-attachments/assets/15eac98b-2603-44c9-b438-7ee27034ccd7
## How
- **`app/lib/graph-viewport.ts`** (new) — pure, framework-free zoom
math: `zoomAtPoint` keeps the point under the cursor fixed while
scaling; `clampZoom` + zoom constants. Zoom becomes a continuous float
(was a discrete step index) so ⌘-scroll is smooth instead of jumping
between steps. Unit-tested (`graph-viewport.test.ts`), including the
cursor-anchor invariant.
- **`useElementEvent` in `hooks/effects.ts`** (new) — element-scoped,
non-passive listener, a sibling to the existing
`useWindowEvent`/`useDocumentEvent`. Non-passive is required so the
handler can `preventDefault()` the browser's own ⌘-zoom; a JSX `onWheel`
can't.
- **`routes/run-overview.tsx`** — coalesces zoom+pan into one `view`
state (atomic cursor-anchored updates), adds the wheel handler (plain
scroll → pan, ⌘/Ctrl → zoom), and `touch-none overscroll-contain` so a
horizontal swipe can't trigger browser back-nav.
- **`components/graph-toolbar.tsx`** — presentational continuous
interface; +/− buttons reuse `zoomAtPoint` (center-anchored). Deletes
the now-dead `graph-toolbar-constants.ts`.
## Testing
- `bun run typecheck` clean; `bun test` green (incl. 4 new viewport
tests).
- Verified live against a real 10-node run graph via Chrome DevTools:
two-finger pan tracks the scroll delta; ⌘+wheel zoom is cursor-anchored
(confirmed even with the cursor over a node); toolbar +/− step ×1.25 and
clamp/disable at 200%; fit-to-window sets a continuous scale; node
click/hover unaffected.
## Non-goals
- **Playground canvas** (`components/playground/canvas`) shares the same
hand-rolled pan/zoom pattern and also lacks wheel support — deliberately
out of scope; `graph-viewport.ts` is the seam to adopt it later.
- **No persistence** — zoom/pan stays ephemeral per visit, as it was
before.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
