Fixes#11803.
**Problem**
`tool_search` builds a tool's search text from its parameter schema but
never followed `$ref`. MCP servers (Pydantic, FastMCP) often put nested
models in `$defs`:
```json
{ "properties": { "options": { "$ref": "#/$defs/options" } },
"$defs": { "options": { "properties": { "mode": { "description": "reconciliation" } } } } }
```
Search text was `Inspect records options`, so
`tool_search("reconciliation")` found nothing. Durable's copy of
`tool_search` had the same gap. The codemode `resolves to` summary had
the same blind spot for output schemas: a field behind a `$ref` showed
as `structuredContent?` with no field names.
**Fix**
- pi-codemode exports its existing local JSON Pointer resolver as
`resolveSchemaRef(ref, root)`. A malformed percent escape now resolves
to nothing instead of throwing `URIError` (this also affected
`schemaToType()`).
- coding-agent and Durable `schemaText()` follow local `$ref`s. Each
referenced subschema is read once, so recursive and shared definitions
neither loop nor inflate BM25 term counts. Unreferenced `$defs` and
remote refs stay out.
- coding-agent `describeFields()`/`describeUnionFields()` resolve `$ref`
chains against the output schema root.
**Tests**
- `packages/codemode/test/declarations.test.ts`: escaped, remote,
missing, malformed refs.
- `packages/coding-agent/test/tool-search.test.ts`: refs, escaped
segments, recursion and shared definitions, unused definitions.
- `packages/coding-agent/test/suite/agent-session-codemode.test.ts`:
summary through root, field, const, and union refs.
- `packages/durable/test/tool-search.test.ts`: end-to-end load via a
ref'd description; unused definition does not match.
`npm run check` passes.
SqliteStorage.commit(batches) reads the check state of all batches up front,
checks each batch in memory against what the earlier ones left (same
prefix-stop refusals, no savepoints), and writes the accepted batches per
table: small rows as one JSON array parameter (json_each), rows with much
text bound column by column within 100 parameters. A group commit over a
remote SQLite takes a few round trips instead of about eight per batch;
local groups are faster too. Randomized differential test against
MemoryStorage, raw-table and statement-count guards.
pi-schema: opt-in coercion, compile(schema, { coerce: true }) with coerce() and
parse(), the superset of TypeBox's Value.Convert rules and pi-ai's old coercion;
unresolvedRefs option; url and json-pointer-uri-fragment formats.
pi-ai: Tool takes any JSON Schema; validation through pi-schema; Type, Static
and TSchema are no longer exported (breaking). pi-agent-core and pi-durable:
tools on pi-schema, no TypeBox dependency. Coding agent: extensions keep Type,
Static, TSchema and StringEnum through an extension view of pi-ai; built-in
tools stay on TypeBox.
After every commit that changed a task, the scheduler re-checked every
conversation with a kept context range (every conversation read in the last
contextRetentionMs) by walking its subtree, scanned them again for the next
expiry, and wake() scanned every live task. CPU per run grew linearly with the
number of conversations.
Now a commit re-checks only the conversations above tasks that became live or
ended (collected before the sweep; a chain load that resolves an unknown for a
live unloaded task falls back to a full check), idle context ranges expire
from an index ordered by idleSince (re-sorted when the clock goes back; zero
retention drops all idle ranges; reconcile passes still expire for hosts that
decline timers), and wake() takes the earliest sleep from the sleeping tasks
and scans live tasks only while nothing runs.
One Session, one-tool runs, no storage latency: 2048 conversations 100 -> 805
runs/s, 4096: 46 -> 772; local SQLite at 2048: 88 -> 459; CPU per run flat at
about 1.6 ms.
This PR uses unicode-aware segmentation and normalization to handle tool
search for multilingual text.
Fixes#10816
---------
Co-authored-by: Petr Houška <houskape@gmail.com>
Ports the coding agent's tool ranking fixes for #11331 (#11440, #11625)
to durable, which keeps its own copy of the ranker in `src/search.ts`.
Problem: durable's `rankDocuments()` was still the coding agent's ranker
from before both fixes. `thread_read` with `limit: 1` returned
`queue_read`, and a tool name among other words (`peekaboo app`) lost to
tools that only mention the words in their descriptions.
Change:
- `src/search.ts`: same scoring as the coding agent's `Bm25Ranker`, plus
coverage first: a tool matching more of the query's terms (in any field)
ranks above one matching fewer, whatever the scores. Without it, name
weighting regressed `screenshot window` (1 to 2, `window` beat `image`)
and `describe app` (1 to 2, `app` beat `see`). The name is a separate
field (3x IDF per term, above any number of description mentions), a
tool whose whole local name is in the query gets a bonus worth one more
match of every query term, a query that is exactly a tool's name ranks
it first, and namespace text is a separate 0.5x field that is not
length-normalized.
- `tool_search`: the search text no longer repeats the name; the ranker
reads it from `name`.
- `searchTools()`: same, and the namespace text now includes the
namespace instructions, as in the coding agent.
- `test/search.test.ts`: the coding agent's ranker cases.
Remaining difference from the coding agent: durable's `tool_search` has
no namespaces (they are a code mode option), and `searchTools()` ranks
on the tool sample from the start data (description plus TypeScript
declaration) rather than description plus schema text.
`searchTools()` results are journaled, so replaying a script started
before this change returns the old results; no `CODEMODE_MODULE_VERSION`
bump.
## Before/after
`searchTools()` ranking on a made-up set of 16 MCP tools from 5 servers.
Each tool is searched with its description; each server is a code mode
namespace (prefix `mcp__<server>__`) with the description and
instructions below. Rank of the wanted tool among all matches, with the
top result when it is another tool.
| Server | Description | Instructions | Tools: description |
|---|---|---|---|
| `github` | GitHub repositories, issues, and pull requests | Use
owner/repo for repositories. Issues and pull requests share numbers. |
`list_issues`: List issues in a repository, filtered by state, labels,
or assignee.<br>`get_issue`: Get an issue with its comments by
number.<br>`create_issue`: Open a new issue in a
repository.<br>`search_code`: Search code across
repositories.<br>`create_pull_request`: Open a pull request from a
branch. |
| `linear` | Linear issue tracker | Search issues before creating new
ones. Issues belong to teams. | `search_issues`: Search Linear issues by
text.<br>`create_issue`: Create a Linear issue in a team. |
| `peekaboo` | macOS automation | Peekaboo controls macOS apps. Use app
names or bundle IDs. Peekaboo can capture any app window. | `app`:
Launch, quit, relaunch, focus, hide, or switch applications. Targets an
application by name, bundle identifier, or process ID, and can wait
until it is ready.<br>`see`: Capture the app window and describe the UI
elements of the app.<br>`window`: Move, resize, or close a window of an
app.<br>`menu`: Click a menu item in an app.<br>`image`: Take a
screenshot of the screen, an app, or a window. |
| `app` | Thread and queue state of the app | Threads hold messages; the
queue holds pending messages of a thread. | `queue_read`: Read a queued
message of this thread.<br>`thread_read`: Read durable state and a
paginated timeline from any thread. The default view returns user
messages, assistant messages and plans. Continue with afterPosition
until hasMore is false. |
| `docs` | Project documentation | Search the docs before answering
questions about the API. | `search`: Search the
documentation.<br>`read_page`: Read a documentation page by path. |
Before, a tool's search text was its name, the name with `_` as spaces,
its description, and the namespace name and description (no
instructions). After, the name and the namespace (with instructions) are
separate fields.
| Query | Wanted | Before: rank | After: rank | Change |
|---|---|---|---|---|
| `thread_read` | `app__thread_read` | 2 (top: `app__queue_read`) | 1 |
$\color{green}{\textsf{better}}$ |
| `mcp__app__thread_read` | `app__thread_read` | 2 (top:
`app__queue_read`) | 1 | $\color{green}{\textsf{better}}$ |
| `peekaboo app` | `peekaboo__app` | 5 (top: `peekaboo__see`) | 1 |
$\color{green}{\textsf{better}}$ |
| `app` | `peekaboo__app` | 4 (top: `app__queue_read`) | 1 |
$\color{green}{\textsf{better}}$ |
| `read thread messages` | `app__thread_read` | 2 (top:
`app__queue_read`) | 1 | $\color{green}{\textsf{better}}$ |
| `open the peekaboo app tool` | `peekaboo__app` | 5 (top:
`peekaboo__see`) | 1 | $\color{green}{\textsf{better}}$ |
| `launch app` | `peekaboo__app` | 1 | 1 | $\color{gray}{\textsf{same}}$
|
| `create linear issue` | `linear__create_issue` | 1 | 1 |
$\color{gray}{\textsf{same}}$ |
| `search documentation` | `docs__search` | 1 | 1 |
$\color{gray}{\textsf{same}}$ |
| `read docs` | `docs__read_page` | 1 | 1 |
$\color{gray}{\textsf{same}}$ |
| `pull request` | `github__create_pull_request` | 1 | 1 |
$\color{gray}{\textsf{same}}$ |
| `get issue comments` | `github__get_issue` | 1 | 1 |
$\color{gray}{\textsf{same}}$ |
| `screenshot window` | `peekaboo__image` | 1 | 1 |
$\color{gray}{\textsf{same}}$ |
| `describe app` | `peekaboo__see` | 1 | 1 |
$\color{gray}{\textsf{same}}$ |
| `create issue` | `github__create_issue` | 2 (top:
`linear__create_issue`) | 2 (top: `linear__create_issue`) |
$\color{gray}{\textsf{same}}$ |
| `search github issues` | `github__list_issues` | 5 (top:
`github__search_code`) | 5 (top: `github__search_code`) |
$\color{gray}{\textsf{same}}$ |
No regressions on this set. `search github issues` stays at 5:
`list_issues` does not contain "search", so it ties on coverage (2 of 3
terms) with `search_code` and `linear__search_issues`, and their scores
win.
Adds a `beforeProviderRequest` generation hook so extensions can replace
the provider request body before it is sent. It is the durable
counterpart of coding-agent's `before_provider_request`.
Durable calls `streamSimple()`, so apps can't set provider-specific
fields such as Anthropic's `thinking.display: "updates"` (#10804)
without wrapping `Models`. Now it's an extension:
```ts
hook(GenerationTask, {
beforeProviderRequest: ({ model, payload }) => {
if (model.api !== "anthropic-messages") return undefined;
// change payload
return { payload };
},
})
```
In pi-durable, a Code Mode script that called the built-in `read` on an
image got `""` back, so `image(await tools.read({ path: "pixel.png" }))`
threw a TypeError. `read` declared no `structuredOutputSchema`. Code
Mode resolves a schema-less tool with only its text, and drops images on
purpose. `read`'s output for an image is a single image block with no
text, so the script got an empty string. The coding agent fixed the same
problem for #10251.
With this change, `read` declares a `structuredOutputSchema`: a string,
or an image block `{ type: "image", data, mimeType }`. It returns the
matching `structuredOutput`:
- for a text file, its text, so scripts get the same value as before;
- for an image, its `ImageContent`, which `image()` accepts.
The "Read image file" note stays an info diagnostic, as before. The
README section on structured output and the changelog are updated.
**Testing**
- New test in `test/codemode.test.ts`. A script reads a real PNG and a
text file through `tools.read()`, checks the block's type, MIME type,
and data, and passes the block to `image()`. It checks that the script
succeeds, the image is saved and shown, and the text read still returns
its text. The test fails without the change: the script errors because
`image()` gets `""`.
- `test/tools-read-differential.test.ts`: the reference implementation
now includes the new `structuredOutput` field.
- `npm run check`.
- `test/codemode.test.ts`, `codemode-describe`, `tools`, `tools-images`,
`tools-read-differential`, `harness-tools`, `harness-hook-reads`,
`harness-read-only`, and `spec-usage` all pass.
Fixes#11015
Requested by @badlogic
Co-authored-by: triagent <triagent@localhost>
A Session no longer holds its line while a commit is stored. Commits that
arrive while one storage call is in flight go out together in the next call,
each with its own seq and outcome; a job runs until it touches a key an
unpublished commit wrote, then waits for that commit's publication. Outcomes
are delivered in line order; publication is in line order, one commit per
macrotask. The scheduler's decisions run as regions that record the keys they
read and rerun after a wait, with side effects only after a clean check.
Storage.commit(batches, receive, context) replaces commit(writes, adopt,
context): prefix semantics (Durable's own checks refuse a batch and keep the
ones before it; any other failure rejects the call), receipts per stored
batch, optional publishing() scope. Memory, SQLite, JSONL, IndexedDB and
StoreStorage implement it natively; StoreStorage through the new
ChordStore.commitSeries (one store transaction per call), replacing
commitInBatch.
A normal run makes no storage reads: bounded record cache, conversation
tails, task-document index, kept context ranges. A tool slot's running status
and a generation's attempt are stored with the next commit (12 instead of 14
commits per run).
One Harness with 128 conversations over storage with a 4 ms round trip: about
5 -> 440 agent runs per second. Design: packages/durable/docs/group-commit.md.
Registries: shared tokens (defineRegistry), one provider per host (host.serve(R, { compose, accepts })),
contributions from facets and host-lifetime objects, plain values or followed Chord watchables, a table
sorted by plugin, lazy compose in the batch that changed the table, failures left out and reported with
the last good value kept; self.registry as a declared dependency, host.registry outside objects, older
readers mapped by accepts[old].value; keyedEntries and orderedEntries. Native sources: self.writable,
registry values and ref.state. self.retryOn wakes failed objects on registry values. host.root gives code
outside objects a call scope sealed at settle, abort and host.close.
Durable: registryReader(value, context); a Session close ends synchronous observers failed
("session closed"), watches still end ended.
StoreStorage (Durable's storage on Chord v2's store, @earendil-works/pi-durable/storage/store) passes
Durable's storage conformance suite and runs Durable's harness tests (npm run test:store). The store
gets owner names and claims, one id allocator, Durable's Storage semantics for refused steps, history
none/latest/rewindable with reads at a point, archive revisions and applyBatch. self.follow follows
Durable's synchronous observers as Chord sources. Persisted jobs: records and state in the owner's
store, restarts as Durable's tasks, abort stored, deferred state. Chord's ./next export returns for
the adapter surface.
A database an earlier unreleased build wrote at pi.live version 2 has a run
without run.turns; a run in flight across the upgrade then counted NaN turns
and failed its next tool round with "Value contains a non-finite number and
is not strict JSON". Version 3's migrate adds turns: 0 wherever it is
missing.
GenerationHooks.afterRun asks, after a run answered, for durable tasks
(runEndTask(task, input)). The answer commits and the run's inputs settle
done first; the generation then creates the tasks as its children in a
finish phase and waits for them in drain, keeping pi.live.run (run.afterRun)
and the conversation busy, so idle waits include them, Stop aborts them and
a crash resumes them. Queued input is placed when they are terminal.
pi.live.run.first and runFailure.first name where a run's history starts,
also for a continue after a failure.
closes#11141
HookApi.entry() and entries(), and TaskRuntime.entries(): a hook or task
reads the conversation's raw history, which compaction never changes, so a
range bounded by entry IDs reads the same before and after a compaction and
in a rerun.
Conversation.submit(tx, draft) and ConversationHandle.submit(tx, draft) run
the same admission inside the caller's commit and return the submission ID,
so a host's own checks and writes and the admission are stored together or
not at all. Admission must come before the commit's first table write, once
per commit, and throws ReadAfterWrite otherwise on every path. A first
argument that is not a draft is taken as a transaction; one of another
Session, or a wrapped one, is refused. The handle form also rejects once its
invocation is aborted. The pi.durable.submit span covers the admission only.
closes#11149
An input with whenIdle: "reject" is refused with the new ConversationIdle
when the conversation has no run, before any write, so it never starts a
run. With whenBusy: "steer" it steers the current run or is refused.
Request-ID deduplication runs first.
Chord's shared watch: listeners take a tagged call, { kind: "value", value, ops, retired } or
{ kind: "failed", error }; a recoverable failure keeps the watch open and the next value arrives as
[["r", value]]; WatchEnd is tagged by kind, and an aborted context ends a watch "aborted".
Durable: observers take the watch's shapes (advance(call, ctx), end(end)); onReport(report) with
report.kind and report.error, session_failed is storage_failed; subscribeCommits is observeCommits;
SessionEnd and ReportFrom are tagged by kind; FileChange is tagged and file watchers stop with
stop(ctx); CompactionFailure and CompactionStatus name their trigger (pi.live version 2 with a
migrate); the task_outdated report uses the scheduler's reasons; TaskInspection's ready is pending;
DocumentCommitChange is tagged. Stored formats are unchanged.
A generation whose request or poll fetch was in flight at a host death counts
one failed attempt of the retry policy (backoff, the partial kept, the same
deferred handle polled again); without retries left the run ends with
runFailure interrupted. restartLimit ends every other task visibly instead of
parking it (tool error result, compactionFailure, runFailure restart_limit,
faulted extension tasks) and reports task_interrupted; retryTask, task_parked
and the restart_limit blocked reason are removed.
closes#11139
ConversationView.entries is a window over the fork-aware history with before;
conversation.watch(ctx, { from, min, max }) and observeConversation take the
window. ConversationTranscript merges windows into a client's transcript with
gaps, loadEarlier, fillGap and resume. pi.live.runFailure says why a run ended
without an answer. watchEvents and its event types are removed; the changelog
has the migration guide.
closes#11327
The Node driver takes the count from node:sqlite; the Durable Object driver reads
SELECT changes() after the statement, since the cursor's rowsWritten also counts
index writes (verified in workerd). run is unchanged and costs nothing more.
Durable publishes a stored commit inside Storage.commit's adopt: the
telemetry events, its own observers (document watches, conversation
views, task graph, scheduler, waits), and a dispatch of host
subscribeCommits listeners one microtask later, before every wait and
abort the commit triggers. A commit the storage rejects after adoption is
published before the Session fails; a throwing telemetry adapter is
reported as host_error "telemetry" instead of rejecting a durable commit.
Chord's watch listeners take one change object, { value, ops, retired }
({ value } for native watches); retirement is a flag, not an end.
Durable's document watches follow their address, and a task document's
watch ends after its retirement call. New synchronous observers for
adapters: observeDoc, observeConversation, observeTaskGraph; the watches
are built on them. The env file watcher's change type is renamed
FileChange.
- ai: OAuth logins only accept http(s) URLs from servers (shared
trustedHttpUrl, now also checked by Radius); pi-messages rejects
contentIndex values that are not the next or an existing block; the
CLI auth file is written with mode 0600
- ai: OpenCode DeepSeek V4.1 Flash (renamed from V4 Flash upstream) no
longer sends prompt_cache_retention
- tui: setTitle() replaces control characters; export
replaceControlCharacters()
- coding-agent: the login dialog only opens web URLs and never prints
control characters from sign-in, device-code, or info URLs
- durable: partial commits no longer merge a new __proto__ member into
Object.prototype
A commit may be marked deferrable ({ persistence: { kind: "deferred", withinMs? } }) on Session, Conversation,
TaskRuntime and a tool's api.commit. When every write changes an existing conversation document with history
"latest" and fork "initial", it is adopted in memory and shown to watches at once, and stored with the next commit
that reads or writes the document, before the document leaves memory, at close, or within withinMs (default
settings.progress.persistWithinMs, 1000 ms). The generation partial throttle and the tool output throttle use it.
subscribeCommits() gets these commits only once stored, with exactly what was stored; internal observers get
memory-only publications. Spec §1/§13 changed, new §4.1. 32 streams over SQLite: storage transactions 562/s -> 99/s,
disk 14.3 -> 4.9 MB/s, CPU 29% -> 22% of one core. A crash loses up to about 1 s of streamed content.
- chord/delta: PendingOps (push, size, take -> PendingTake): raw pending ops, r drops everything
before it, a leaf index merges appends and primitive sets per path (cleared by any other op),
past 10,000 ops only "replace with the current value"; one batch is kept by reference and
received ops are never mutated
- chord: Watch queues frames in PendingOps while its listener is busy or not started and delivers
one call with the newest value, the folded ops (or [["r", newest]] after an overflow) and the
newest frame's context; replaces the 100-frame collapse. NativeWatch is unchanged and takes an
optional replace()
- durable: watchEvents keeps every event batch in order (NativeWatch with a snapshot replace);
document, view and task-graph watches fold; spec, README, example 04 and tests updated
- tests: fold fuzzers (tracker, appendText, splices/reorders, root arrays, diffRevisions) with
codec round trips, adversarial cases, cap, ownership, cost and GC guards
Follow-up to #9265.
- chord: Delta appendText(draft, key, text) / StringKeys<T> record an append op without the
O(length) prefix compare that a plain `draft[key] += text` costs in prepare()
- durable: partial commits append text and thinking deltas with appendText (assignJson plan,
checked by length), and apply tool-call argument changes from their own StreamingJsonParser
of the raw toolcall_delta text instead of reassigning the arguments snapshot
- durable "." entry-graph budget 73 -> 76 for the parser it now imports
- ai: StreamingJsonParser / ToolCallArgumentsStream read each argument delta once (tolerant,
immutable snapshots, linear cost); every provider, pi-messages and the faux provider use it
and keep stream state (partialJson, partialArgs, index, customInput, streamIndex, Bedrock
reasoning bytes) off the content blocks; grammar tool input appends per delta
- agent: streamProxy uses the same parser
- chord: Delta append ops own their text (ownedSlice), so ops and replicas no longer keep the
whole growing string alive
- durable, ai, mcp: bounded error excerpts and summaries own their characters
- coding-agent: tool calls render streamed arguments once per frame, not once per delta
HarnessOptions.readOnly opens a viewer of a session another process drives, such as a synced copy on a device that only shows it. Open leaves running tasks as committed, commits with writes reject with ReadOnlySession before they reach Storage, and resume() and every call that would run tasks reject with it.
Breaking changes:
- Durable Storage.commit(writes, adopt, context): storages call adopt(seq) once,
synchronously, when the batch is durable and before their next commit
- Chord traceIn(options, fn, context): context last
- WatchHandle and WatchEnd move to Chord (Durable re-exports them); end reasons
ended (was session_closed) and failed (was session_failed); retirement is an
explicit source event, and an ended watch drops its references into the Session
- Removed Session.documentState(), Conversation.viewState(), Harness.taskGraph()
and DocumentState; use watchDoc(), watch(), watchTaskGraph()
Move two post-release entries out of the 1.3.0 sections, add missing entries, duplicate user-facing ai and tui changes into coding-agent, and add New Features.
Every built-in storage implements ReplayableStorage: head(), replay() at an explicit sequence, and export() of the current state as a log that replays to the same reads. SQLite schema version 3 adds sequence indexes so export streams. @earendil-works/pi-durable/sync adds ReplicatingStorage, which appends each committed batch to an outbox with fork copies resolved, compactRecords(), and versioned JSON log lines.
- ClientAttribution is { name, url, categories? } with required name and url, so
OpenRouter always gets an HTTP-Referer. identity.ts maps the fields to each
provider's headers; NVIDIA gets the name with its first letter upper-cased.
attribution: null turns it off. PI_ATTRIBUTION is pi's, including the
cli-agent category; agent-core, durable, and the coding agent use it.
- Categories are a string array, joined for OpenRouter.
- withClientIdentity() is a typed wrapper instead of a Proxy and keeps a
MutableModels mutable. Durable no longer caches wrappers in a WeakMap.
- The Codex originator stays pi; login agentName no longer follows attribution.
- Models and the coding agent's ModelRuntime add x-opencode-session for custom
providers pointing at OpenCode, replacing the coding agent's transformHeaders.
pi-ai gets a ClientIdentity request option and createModels() default that choose the User-Agent (detailed with version, short, or custom) and provider attribution headers for OpenRouter, NVIDIA NIM, and OpenCode. Attribution is off by default in pi-ai and on by default in pi-agent-core and pi-durable (HarnessOptions.identity). pi-coding-agent sets its identity from the telemetry setting instead of adding headers itself.
Breaking change: defineDoc and defineDocFamily now require an explicit checkpointWhen predicate; no default is supplied. Set policies on built-in documents, examples, tests, and triage state, and document the required API.
- pi-ai: AI_TELEMETRY_SCHEMA; pi.ai.request and pi.ai.poll spans around Models requests via a lazyStream observer
(no provider changes), first_chunk and block events (never per delta), usage/cost end attributes, provider_error
status with a bounded message, aborted stays ok; duration, first-chunk, token and cost metrics; option renamed
telemetryContext -> telemetry (a parent span)
- pi-telemetry: TelemetryContext carries readonly metrics and propagation capabilities on every span
- chord/context: Context.telemetry is always a TelemetrySpan (NOOP default); withTelemetry takes spans
- durable: DURABLE_TELEMETRY_SCHEMA; pi.durable.submit (inputs start their own trace linked to the caller) and
pi.durable.phase spans for every task phase; stored carriers on submissions and tasks (TaskOptions.trace, links);
entry, submission, checkpoint, replay and report events after commit; resumed tasks stay in their trace; phase
duration, active task and report metrics; failed phases carry fixed categories with bounded messages
