TurnRuntime now publishes every turn's events (durable ones tagged with
their 1-based file offset, deltas without) to an injected TurnEventHub,
regardless of who started the turn. Main forwards durable events to all
windows on one turns:events channel; the renderer's new useTurn(turnId)
hook joins live turns gap/duplicate-free via the offset protocol. The
sub-agent card drops its 1s polling for push updates, and the nine
per-channel window fan-out loops collapse into one broadcastToWindows.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Capability guidance now co-locates with the tools that skills own:
- Register the previously orphaned slack skill in the catalog (excluded
when Slack isn't connected, like composio-integration) and shrink the
prompt's Slack block to a routing line + followed-channels hint — the
agent-slack command patterns already live in the skill body.
- Compress the per-capability routing directives (meeting-prep,
create-presentations, doc-collab, app-navigation, background-task,
apps, browser-control, notify-user) to when-to-load signals; the
how-to detail loads with each skill.
- Slim the knowledge-graph access examples to the essential patterns.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Skills now own their tools. The copilot attaches only a small hardcoded
base set (~16 tools instead of all ~42); loading a skill via loadSkill
attaches its declared tools as native tool definitions from the very
next model step, and they stay attached for the rest of the session.
- tools_extended: new durable turn event (the one sanctioned exception
to per-turn tool immutability — explicit, replayable, never silent).
Reducer tracks extensions per model-call index; effectiveTools()
composes base + extensions for both the live loop and inspect.
- Runtime: sync tool results may carry metadata.toolAdditions; dedupe
and the durable append run atomically on the serialized commit chain
(safe under concurrent sync tools). Crash recovery rebuilds the
extended toolset from the log.
- Skills declare tools (SkillDefinition.tools; SKILL.md tools:/
allowed-tools frontmatter); catalog entries list them; loadSkill
returns them via a reserved $toolAdditions key the registry lifts
into result metadata. builtin-tools skill = escape hatch, derived as
"every non-base builtin" at module init.
- Sessions derive composition.activeSkills from the previous turn's
request + its tools_extended events; the resolver attaches active
skills' tools on top of the base set (stable order, so snapshot
inheritance keeps working).
- Legacy code-mode path keeps working on the base set (which includes
code_agent_run/launch-code-task) and strips $toolAdditions.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The collapsed card read just "Sub-agent:" — zero information, and the
expanded view showed the task twice (the task chip plus the child
transcript's opening user message, which IS the task).
The title is now "<Humanized name>: <task>" ("London weather: Find the
current weather…"), truncated by the header with the full text on
hover; "Agent" when the model gave no name. The redundant task chip is
gone — the child transcript's first message carries the task.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The spawn-agent tool shipped with mechanics but no judgment layer —
the only guidance was the tool description. This adds the ambient
decision heuristics and closes a child-profile hole.
- Copilot system prompt gains a "Sub-Agents (parallel & heavy work)"
section (same strong/anti signal structure as Background Tasks):
the organizing principle is context hygiene — a sub-agent's reads
and fetches never enter the main conversation, only its distilled
answer. Research-shaped requests (catch-me-up, dig-into, meeting
prep) now route through sub-agents by default, with copilot as
synthesizer. Anti-signals: single quick lookups, journeys-as-answer,
anything needing mid-task user input, driving shared surfaces.
- Background-task agent gets a matching (shorter) note — children
have their own model-call budgets, so a bg-task covers more ground
per run by fanning out.
- The inline default child profile now also excludes app-navigation
and browser-control: both drive shared visible surfaces (the UI the
user is watching; the single embedded browser pane), which headless
or parallel children would corrupt, not just clutter. Still
available via explicit tools selection.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
First real-world use showed the model calling spawn-agent with
{name, tools, task} and no instructions — a complete spec by any
reasonable reading — and burning a correction round-trip on the
"exactly one of agent_id or instructions" rejection (both children
then succeeded on retry).
Requiring instructions bought nothing: the task is the spec. Omitting
both agent_id and instructions now spawns a general-purpose worker
with a default headless prompt; only supplying BOTH remains an error.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Adds the agent-as-tool capability deferred in turn-runtime-design §29.2:
a `spawn-agent` builtin that runs a sub-agent in its own standalone
headless turn and returns its final answer to the parent. Multiple
spawn calls in one assistant batch run concurrently (previous commit).
- RequestedAgent is now a union: by-id (unchanged shape) | inline
{name, instructions, model?, tools?}. Inline definitions persist
verbatim in turn_created and resolve to the same immutable snapshot.
- Agent resolution splits by variant: DispatchingAgentResolver narrows
the union once; InlineAgentResolver materializes inline specs
(builtin catalog validation, headless default profile when tools are
omitted); RealAgentResolver keeps the by-id path byte-identical. The
builtin→ToolDescriptor conversion is extracted to a shared helper.
- The spawn handler (RealToolRegistry branch → runSpawnedAgent) runs
the child via HeadlessAgentRunner on the parent's model by default,
clamps the model-call budget at 20, cascades the parent's abort
signal, and records {kind:"subagent", childTurnId} as durable tool
progress — the only parent→child link; no parentTurnId is added to
the schema. Task-level failures return as conversational isError
results, never terminal.
- Depth is capped at 1: both resolvers strip spawn-agent from children
(inline always; by-id via the new subagent composition flag) and the
handler refuses child-shaped parents outright.
- Renderer: spawn-agent calls render as a SubAgentBlock — a collapsed
status card that expands to the child's live transcript
(CompactConversation over sessions:getTurn, polled at 1s while
running; standalone child turns don't reach the session bus).
- The BuiltinTools entry gives copilot (and other catalog-attached
agents) the tool automatically; its execute is the degraded legacy
path only, since the turn runtime intercepts builtin:spawn-agent.
Schema note: RequestedAgent widened under schemaVersion 1 (pre-release)
— requires wiping ~/.rowboat/storage.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Sync tools in one assistant batch now run via Promise.all instead of
sequentially — a tool pending on I/O no longer blocks its siblings.
Three coordinated changes keep the event-sourced runtime sound:
- executeAllowedTools is two-phase: invocation events are appended
serially in source order (durable before any side effect, deterministic
log prefix), then all sync executions run concurrently, each appending
progress/results as they land. Per-call error and cancel semantics are
unchanged (moved to executeSyncTool).
- append() commits through an internal queue: persist → reduce → stream
runs to completion per batch, so file order, in-memory order, and
stream order stay identical even while executions overlap. A failed
commit rejects only its caller; the chain survives for siblings.
- Abort-registry state is scoped per tool call (turnId:toolCallId) via a
wrapper, fixing two latent races: createForRun destroying a running
sibling's tracked processes, and cleanup tearing down the turn-wide
force-kill scope when the first tool finished.
Wire ordering is untouched: model requests already reference tool
results by the assistant message's source order, pinned by a new test.
No concurrency cap and no per-tool serialization by design; tools that
share state must tolerate racing (file edits already reject stale
writes via their search/replace precondition).
Spec §4.5/§10.5 updated. New runtime tests cover overlap (deadlock
unless concurrent), progress interleaving, sibling failure isolation,
mid-batch cancellation, and crash recovery with multiple open
invocations.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Expand the curated toolkit whitelist from 26 to 67 entries, adding
well-known services that support Composio-managed OAuth2 (the only
auth scheme the app's connect flow supports): Zoom, Discord, ClickUp,
monday.com, Confluence, GitLab, Bitbucket, Supabase, Sentry, PagerDuty,
Stripe, Square, QuickBooks, Mailchimp, Google Ads/Analytics/Search
Console, Figma, Canva, YouTube, Instagram, Facebook, Box, SharePoint,
and more. Adds three new categories: design, marketing, finance.
Also fix two entries that were never connectable: 'microsoft_outlook'
and 'onedrive' do not exist in Composio's catalog (the API returns 404,
so initiateConnection always failed). The real slugs are 'outlook' and
'one_drive'.
Excluded per curation policy: Composio's own utility toolkits
(composio_search, codeinterpreter, browser_tool), no-auth toolkits
(Hacker News, OpenWeatherMap), API-key-only toolkits the app cannot
connect (Firecrawl, Tavily, Exa, PostHog, etc.), and niche/low-quality
entries.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Adds a Caffeinate switch (Settings → Mobile channels) that uses
Electron's powerSaveBlocker ('prevent-app-suspension', equivalent to
caffeinate -i) to stop the machine from idle-sleeping so the
WhatsApp/Telegram bridge stays connected. While active, an amber
coffee icon in the titlebar shows the state and can be clicked to
turn it off; a power:caffeinateChanged push keeps the titlebar
indicator and the settings switch in sync.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Anthropic caching is opt-in, and nothing sent breakpoints: observed
sessions show 0% cache hits on Claude models (~1.27M of 1.36M sampled
input tokens billed at full rate) vs ~82% implicit hits on Gemini. Two
ephemeral breakpoints fix that: the system prompt (whose cache prefix
also covers the tool schemas — both immutable per turn by construction)
and the last message (Anthropic's incremental-conversation pattern).
Conservative simulation on the sampled traffic floors the saving at 44%
with no cross-turn reuse; realistic reuse lands 70-85%.
Applied in the model registry bridge just before streamText, gated by
provider flavor or model id (covers direct Anthropic, OpenRouter, and
the gateways — the installed OpenRouter provider reads the same
providerOptions.anthropic key). Transport-only: nothing is persisted,
message content is untouched, and non-Anthropic requests pass through
byte-identical. Verify with cachedInputTokens on model_call_completed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The resolver helper's inline policy type predated middlePaneContent and
no longer satisfied ElisionPolicy; use the exported type. Coerce message
content to string where the preview assertions call string methods.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- catalog is ranked by GitHub star count (per-repo lookup with a 10-min
cache; unauthenticated works, the publish token is used when present)
- star button on each catalog card stars/unstars the app's repo as the
signed-in user (public_repo scope covers it), optimistic with revert
and a sign-in hint when signed out
- the info panel now offers Delete for local apps (apps:delete already
existed and cleans up app-owned agents; only installed apps had a
removal button before)
The original suite covered the tool-result path well but left holes:
loadElisionPolicy had no tests at all (now: missing file, full config,
partial merge, unparseable JSON, and the all-or-nothing malformed-key
behavior — via an injectable config path so tests stay off the real
WorkDir), images/note policies had no idempotency or determinism tests
(the properties prefix caching depends on), the note floor boundary was
unpinned, resolveAgent delegation was unverified, and nothing exercised
a multi-turn reference chain or the per-resolve hot config reload.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Elision reads config/context.json at compose time, so the composed
payload is no longer a pure function of the durable log — inspecting an
old turn after a config edit can show different prefix bytes than were
transmitted. Document the exception against §8.3 and make the inspect
CLI print the policy in effect so divergence is visible instead of
silent. The gold fix (recording the applied policy on the turn) is
noted for when exact-bytes replay becomes a hard requirement.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
TurnRepoContextResolver was still freely constructible, so a future
call site could silently lose elision. The factory now accepts an
injectable policy loader (also keeps tests off the machine's real
context.json), the raw class carries a do-not-construct note, and
factory-level tests pin both the decorator wiring and the default
policy behavior.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Real session data shows ~5k-char skill bodies are the most common
oversized historic result; the 10k default replayed them on every model
call for the life of the session. With the head preview in place the
model retains enough scent to re-load on demand, so the aggressive
default is the right trade. Still tunable via config/context.json.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A bare placeholder tells the model only the tool name and size; the
first 400 characters tell it what the output actually was (a skill
guide reads very differently from a fetched page), which is what it
needs to judge whether re-running the tool is worth it. The preview is
capped at the threshold so small thresholds still shrink content, and
the transform stays a pure per-message function (byte-stable prefixes).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Every user message sent while a note is open carries a full snapshot of
that note in userMessageContext, so a long chat over one open note
resends N full copies on every model call. The elision decorator now
rewrites prior-turn user messages to keep the pane kind and path but
replace note content above a small floor with a placeholder pointing at
the still-readable file. The current message's snapshot is untouched,
so "summarize this" keeps working; the system prompt already tells the
model later middle-pane context overrides earlier. Config:
elideHistoricMiddlePaneContent, default on.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Video-mode webcam and screen-share frames matter for the response they
were captured for; afterwards the assistant's own text carries the
takeaway and fresh frames arrive with every new call message, yet each
message's frames (~10k tokens) were resent on every subsequent model
call. The elision decorator now strips image parts from prior-turn user
messages, leaving a text part recording how many frames of each kind
were dropped. The current turn's just-captured frames are always sent
verbatim, and the policy generalizes the existing config
(elideHistoricImages, default on).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Tool results from prior turns (skill loads, file reads, HTTP fetches)
dominate resent context and are rarely needed verbatim. A decorator over
the context resolver now replaces prior-turn tool results above a size
threshold with a short placeholder telling the model to re-run the tool
if it needs the output. The current turn's in-flight results are always
sent verbatim, the durable log is untouched, and elision is a pure
per-message function so resolved prefixes stay byte-stable for provider
prefix caching.
Policy lives in config/context.json (elideHistoricToolResults, default
on; elideHistoricToolResultsThresholdChars, default 10000). The inspect
CLI composes through the same decorated resolver so debug output still
matches transmitted bytes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Show a generic animated Working status whenever an active turn can be stopped, and reserve the Thinking shimmer for model reasoning_start/reasoning_end windows.
Keep human-wait state separate so permission and ask-human controls remain interactive, and add renderer state and component coverage for the new behavior.
Removes the placeholder comment added in #684 to trigger the
path-filtered 'test' check; doubles as the trigger for this PR.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Adds a harmless comment under apps/x/ so the path-filtered required
'test' check runs on this otherwise README-only PR.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Cards for apps already installed from the catalog show a green
Installed badge (matched via the install record's registry name) that
opens the app, instead of a second Install button.
Two races around the post-install prompt:
- AppsView kept a stale selectedFolder after the open app was
uninstalled; on reinstall the 4s apps:list poll matched it again and
instantly swapped in the app frame, unmounting the catalog and the
enable-agents dialog mid-choice. Clear the selection when its app
disappears from the list.
- Bundled agents materialized on the NEXT apps:list poll, not at
install — so the dialog's bg-task:get/patch hit a task that didn't
exist yet if the user acted within ~4s. Install handlers now call
syncAppAgents synchronously.
The enable dialog now lists the user's available models (models:list),
preselecting the host-pinned default from materialization. Turning the
agents on patches the chosen model/provider onto the task along with
active — so installers can route a bundled agent to a specific model
at the moment they opt in, without digging into bg-tasks.
Bundled agents can't ship a model override (the author's providers are
not the installer's), so materialized tasks ran on the bg-task category
default — gemini flash lite — which reliably mangles large app-set-data
payloads (invalid JSON string → contract rejection → the installed app
never gets data; observed with pr-dashboard's refresh agent).
Materialization now resolves getDefaultModelAndProvider() on the host
and pins that on the new task — the installer's machine picks the
strong model, the package still pins nothing. Existing tasks keep
their user-set model (update path unchanged).
Bundled agents install disabled (§8.3), but nothing told the installer
they exist — the app opened empty with the refresher buried in
bg-tasks. After an install that materialized agents, offer to turn
them on: 'Turn on & run now' activates each task and fires a first run
so the app opens with data; 'Not now' keeps them off.
The detail panel's Publish update button opened the same dialog as
first publish, which hardcoded apps:publish — so updating an already
published app always failed with name_taken from the registry check.
The dialog now takes a published flag: it runs apps:publishUpdate with
a version-bump picker (patch/minor/major), shows a simple progress
state (the update path emits no step events), and links the new
release on success.
The skill treated mirroring the bg-task into agents/<slug>.yaml as
optional ('if the app should ship the agent'), so the copilot built
agent-backed apps (e.g. pr-dashboard) with the refresher as a loose
personal bg-task only. Publishing such an app ships a dead UI: data/
is user state and never packaged, and installers get no agent.
Bundling is now a required step with the failure mode spelled out.
langium imports vscode-jsonrpc/lib/common/events.js without declaring the
dependency, which fails to resolve under pnpm's strict layout and broke the
renderer's production (vite) build during forge packaging.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
GitHub rate-limits the device-code token endpoint: a poll arriving even
slightly under the flow interval returns slow_down and permanently raises
the required interval. The renderer polled on a fixed 5s timer (exactly
the limit), so one jittery request tripped slow_down and every poll after
it was 'too fast' — GitHub answered slow_down forever and the dialog sat
on 'Waiting for authorization' even after the user approved.
Core now tracks lastTokenPollAt and skips the request until the flow's
current interval (base +1s margin) has elapsed, so slow_down bumps take
effect and the flow recovers. The renderer timer is just a heartbeat (2s).
- start the apps server before createWindow instead of after the full
service-init chain: the Apps view was reachable ~10s before port 3210
was listening, so every app iframe opened to connection-refused
- retry EADDRINUSE binds (quick relaunch races left the server disabled
for the whole session with no retry)
- app frame: auto-retry the iframe instead of a dead manual Retry, and
surface when the apps server itself is down (new apps:serverStatus)
- log render-process-gone/child-process-gone reasons; renderer helper
crashes were previously invisible in packaged builds
- toolbar (local apps): 'Publish' button; turns into a green 'Published'
badge-check once published (click opens the detail panel)
- detail Source section: clickable repo + release links for published apps
Re-reading refs/heads/main immediately after the bootstrap commit can 409 on
a stale replica (GitHub eventual consistency) — the Contents API response
already carries the commit sha, so use it directly.
Resumed publishes skipped already-done steps without emitting progress, so
the dialog showed stale spinners for steps that finished in a prior attempt.
