A session spawned into another worktree recorded a parent that no
listing contained, so the row showed only "parent unavailable" and its
parent's row looked childless. Both facts were accurate and useless:
neither said where the related session actually was.
Report both directions from the session store instead. A missing
parent's cwd and id come from its own file header, so one 4 KB read per
distinct missing parent resolves it without listing other workspaces;
children are counted by listing sibling workspaces and matching the
parent path they already recorded, needing no header reads. Reads are
memoized per path because Pi writes headers once, and the cache is
released on dispose. Both directions are best-effort: an unreadable
header or an unlistable worktree leaves a session unannotated rather
than failing the listing.
In the browser, an orphan child keeps the same child marker as a nested
one, dimmed, so it no longer renders as a root; whereabouts are stated
once on the meta line ("parent in feature/foo", "2 children
elsewhere"), where a clamped title cannot hide them. A "Go to parent
session" action switches to the owning workspace and selects the
parent. Live session.created events keep child counts current instead
of leaving them stale until the next listing.
Session and workspace paths reach the browser from two producers: store
enumeration for a listing, and the live runtime for a broadcast. They
are now compared through one normalizing helper, so tree nesting and
child counts cannot silently miss a link when only a trailing separator
differs.
Extract the shared "workspaces of the project containing this cwd"
lookup out of ProjectScopedSpawnTargetResolver so spawn targeting and
child counting share one implementation, and register it regardless of
whether spawning is enabled: children can predate a config change, and
the tree should stay honest about them either way.
Startup progress rides the per-session activity channel with an "active"
phase, because a startup phase really is in progress. But isSessionActive()
treated any active activity as work, so a session that was merely *opening*
enabled "Stop Active Work", disabled "Reload from disk" with the misleading
"Stop current session activity before reloading" tooltip, showed the row's
active-work indicator, and — for any caller that hands a startup activity to
WorkspaceActivityService — reported the whole workspace as busy. Selecting an
archived, read-only session reported active work while it opened.
Starting is not working. publishStartupProgress now marks its reports with a
new optional SessionActivity.startup field, and isSessionActive() does not
count a marked activity. Every affected consumer — the session list, the core
actions, the app's activity-transition handling, and the server's workspace
aggregation — reads that one helper, so the correction lands in all of them at
once.
The marker is a new field rather than a new phase on purpose: six readers test
phase === "active" directly, including the pending row's "creating · " prefix,
the chat dock's active styling, and the daemon's own heartbeat re-publication.
It can only ever remove the activity-phase reason for being active, so
streaming, bash, compaction, and queued prompts still report as active through
the status even while a startup report is the latest activity. The chat dock
still shows the startup text; this changes what counts as work, not what is
shown.
The browser's own pending-create row keeps its previous appearance: it borrows
only the daemon's phase text and drops the marker, since that row stands for a
create the user is waiting on rather than a session the daemon is opening.
Integrate the pending-ask store into the session service so an open ask is
visible, observable, and closable.
- `statusFromSession` projects `pendingAsk`, so a browser rehydrates an open
ask from `GET /sessions/:sessionId/status` after reload or a web/API restart.
- `openAsk` publishes `ask.opened`, and publishes `ask.closed` first when the
new ask supersedes an unanswered one.
- `submitAsk` / `cancelAsk` close the ask and hand the outcome to the model as
a `pi-web.ask.answers` follow-up custom message (`triggerTurn`,
`deliverAs: "followUp"`), the same delivery subsession notices use. A stale
ask id is reported, not thrown: losing the race against a supersede or
another browser is ordinary. Cancel still reports every question as
unanswered so the model is not left waiting for a promised message.
- The open ask is forgotten when its runtime closes; nothing is left to
receive the answers.
- `POST /sessions/:sessionId/ask/{submit,cancel}` behind the existing
`/api/sessions/*` daemon proxy, allowlisted for machine federation.
Startup progress could still be shown on the wrong session's row. Routing by
known session id first closed the case where the browser knew the other
session, but left open the case where it does not -- which the browser is
designed to produce. While a create is pending for a workspace,
applyCreatedSession deliberately withholds a session.created event for that
workspace and stashes it, to avoid a duplicate row. So during exactly the
window this feature exists for, a session created by an agent's spawn or by
another tab is intentionally absent from the session list. Its startup events
carried an unrecognised id and a matching cwd, and were routed onto the user's
pending create row, showing a phase and a label belonging to another session.
Workspace path was never evidence of identity; it was the only key both sides
happened to share. Give them a real one. The browser already invents a
temporary row id for a pending create, so it now sends that id with the create
request as an opaque startupToken; the daemon carries it through construction,
echoes it on the startup events it publishes for that construction, and the
browser matches it exactly. The token is a throwaway label the daemon never
interprets. It never becomes the session id: activity.sessionId still carries
Pi's SessionManager id, which remains how an open of an already-known session
is routed.
With exact identity available, the guessing is deleted rather than gated.
startupProgressPendingStart goes entirely, and with it the selected-machine
comparison, the cwd filter, and the single-match ambiguity rule: a second
concurrent create carries a different token, and a foreign workspace or
non-selected machine carries no token this browser is waiting on, so those
cases stop existing rather than needing detection. One Map lookup replaces a
filtered scan. cwd comes off the event, since it existed only as the routing
key and nothing else read it.
No compatibility path is needed. session.startup is unreleased -- checked
against the published tarball, not only git tags -- so no deployed daemon
emits these events and no deployed browser parses them. An older daemon
ignores the extra request field; a newer daemon talking to an older browser
degrades to the pre-existing generic wording, as does any unmatched token.
One silent behaviour change to state plainly: startupProgress guarded on
`sessionId === "" || cwd === ""`. Removing cwd from the event removes the
meaningful half of that guard, and that half had no test. The session-id half
is kept, which is the half that actually protects honest reporting.
The replaced ambiguity test is rewritten rather than dropped, so the same three
scenarios still pin the user-visible guarantee -- no match means the generic
wording stays -- now including the reproduced foreign-session case, which fails
against the previous code. Session creation ordering, semantics, and queueing
are unchanged; the token is a passthrough label read only to build an event.
Register a core ask_user custom tool that posts a question set to the user's
browser and terminates the run instead of awaiting an answer. The tool is thin:
it shapes its TypeBox params into domain questions, lets PendingAskStore own
validation, and reports a superseded unanswered ask back to the model.
Gated by the askUser config key, threaded through PiSessionServiceDependencies
and sessiond. Unlike the delegation tools, ask_user is available to tracked
children too: the questions reach the user of the asking session.
Creating or opening a session could stall for reasons the daemon knew
about and never shared. The browser invented the whole message it showed
while waiting -- "Creating session: Waiting for the backend session to be
ready" -- which says that we are waiting but never what for. A shared
ModelRuntime read during startup can be handed a network refresh that is
already in flight, and extensions may do their own network I/O while
loading, so the wait is real and previously unattributable.
The pre-session gap turned out to be a missing shared key rather than a
missing channel: publishActivity needs the PiAgentSession being built, but
the session id and cwd are both known before the first await. So create()
now publishes a new global session.startup event carrying an ordinary
SessionActivity, routed by cwd -- the one identity a browser row waiting
for a session id can match, since the client-invented pending id is
unknown to the daemon and the daemon's id is unknown to the browser.
Two phases are reported, each published before the await it describes so
the label changes during the wait rather than after it: "Starting the Pi
session" and "Loading session extensions". Both are facts, because the
service awaits exactly one call for each. A concurrent background catalog
refresh is appended as a note ("provider model lists are refreshing"),
never as the cause: the refresher can prove a refresh is running but not
that this startup joined it. ModelCatalogRefresher gains only a read-only
isRefreshInFlight() getter; cadence, timeout, and coalescing are untouched.
Reporting is event-only and synchronous. It writes no activities entry, no
workspace activity, and no unread state, so a failed creation leaves
nothing stranded, no await is added, and creation ordering and semantics
are unchanged. The window-ending idle report is skipped when a real
activity was published during startup, so an extension error survives.
The browser applies startup progress only when it can prove the target:
one non-discarded pending start in that cwd on the selected machine, or a
session whose id it already knows. A foreign workspace, another machine,
or two concurrent starts in one workspace keep today's generic wording
rather than showing one row the phase of another. An idle report restores
that generic wording, including the queued-messages variant.
docs/config.md said nothing a request triggers waits on a catalog fetch.
That is not strictly true for a refresh already in flight, so both it and
the generated docs/config.html now state the exception and say PI WEB
reports it while it happens.
Bump @earendil-works/pi-coding-agent, pi-ai, and pi-agent-core to 0.82.1
together and raise the peer range to >=0.82.1 <0.83. All three must move in
lockstep: bumping only two leaves a duplicate pi-ai copy in the tree, which
surfaces as misleading type-identity errors rather than real API breaks.
Pi 0.82 removed ModelRuntime.reloadConfig() and merged it into refresh(),
which now does ModelConfig.load, configureRadiusProviders, and rebuildProviders
before refreshing. Port the five production call sites literally, passing no
options so refresh() keeps defaulting allowNetwork to modelNetworkEnabled --
which the shared runtime pins to false by constructing under PI_OFFLINE. No
call site passes allowNetwork: true.
The auth tests lose reloadConfig() as an observation seam, so the offline
regression cases now drive removeRuntimeApiKey(), the surviving public mutation
that still forwards the construction-time network flag to refresh().
Relaxes the provider policy from 'global config only' to 'global sources':
providers registered by agent-dir (global) extensions are learned once at
daemon startup and allowed on the shared runtime; project-extension
registrations are still rejected with a session warning. Global extensions
load identically for every session, so their providers are daemon-consistent
and cannot leak project state (#76).
- Shim now allows allowlisted ids through and also covers Pi 0.81's native
provider path (registerNativeProvider), closing a bypass.
- Startup learning step loads only global extensions against a scratch cwd
and diffs the runtime's registered provider ids.
- Bumps @earendil-works/* dev/peer ranges to >=0.81.1 <0.82; adapts to the
Agent.streamFn -> streamFunction rename.
- Docs, changeset, unit and acceptance tests updated (global-extension allow
path, late re-registration a la pi-tensorx, native provider rule).
PI WEB only supports globally configured providers (Pi built-ins,
agent-dir models.json, environment credentials). A daemon-wide shim on
the shared ModelRuntime swallows extension registerProvider calls and
makes unregisterProvider a no-op, so one workspace's extensions can no
longer corrupt the provider set of concurrent sessions (issue #76).
Rejections during a services load surface as session warnings through
the existing diagnostics pipeline; late registrations from session
event handlers broadcast a notification to active sessions. Everything
else extensions register keeps working.
Requires manual restart of pi-web-sessiond.service (daemon wiring changed).
Pass modelRuntime to createAgentSessionServices instead of authStorage +
modelRegistry; carry ModelRuntime on PiAgentSession; make modelRuntime a
required PiSessionService dependency (sessiond already injects auth.runtime).
Switch anthropicSubscriptionWarning to readStoredCredential, and rederive
model reads (availableModels/setModel/syncCurrentModelAuthWarning) via the
runtime (getAvailableSnapshot/getModel/hasConfiguredAuth). sessiond.ts and
piSessionService.ts now typecheck; only slice-5 test/support files remain.
Show a pinned banner at the top of the session view with resource and
runtime diagnostics (skills, prompts, themes, extension load errors) plus
the Anthropic subscription-auth billing notice, recomputed live from the
current runtime so they stay accurate across browser reloads.
Warnings carry an optional dismiss capability; the Anthropic notice is
dismissable and durably suppressed through pi's own anthropicExtraUsage
warning setting. Also fixes the testing-guide skill frontmatter so it
loads.
Seed the in-flight partial assistant message (text, thinking, and
in-progress tool calls) when opening or reconnecting to a session that is
mid-stream, then continue streaming live deltas on top of it. Replaces the
blocking "Catching up..." placeholder and the end-of-turn transcript reload.
Server stamps every per-session UI event with a monotonic seq at the
SessionEventHub publish choke point and exposes
GET /sessions/:sessionId/stream-snapshot returning { seq, partial }. The
client fetches the snapshot on join, seeds the normalized partial into the
in-memory transcript (never the history cache), and applies buffered/live
events using the seq watermark for exactly-once delivery.
The snapshot is a progressive enhancement: a 404 from an older remote
pi-web or a not-yet-restarted session daemon falls back to an empty seed
(seq 0, drops nothing), so sessions still open and stream normally. The
stream-snapshot route is registered in the federation allowlist for
remote-machine proxying.
Rewrite sessionNameGenerator.ts to consume a StreamFn-shaped dependency
(sourced from PiAgentSession.agent.streamFn, wired in leg B) instead of
ModelRegistry plus a dynamic @earendil-works/pi-ai/compat import.
streamFn resolves auth/headers/retry internally, so the explicit
modelRegistry.getApiKeyAndHeaders(model) call and apiKey/headers stream
options are no longer needed.
Deletes now-dead compat-loading machinery: getPiAiProviderRegistryModule,
loadPiAiProviderRegistryModule, importOptionalPiAiModule,
isModuleUnavailableError, hasGetApiProvider, PI_AI_COMPAT_MODULE,
ModuleImporter, SessionNameApiProvider, PiAiProviderRegistryModule, and
the module-level provider registry cache.
Updates the maybeGenerateSessionName call site in piSessionService.ts to
pass session.agent.streamFn instead of this.modelRegistry, and updates
both test files: sessionNameGenerator.test.ts gains coverage for the new
streamFn-driven generateShortSessionName signature (success and error
paths), and piSessionService.test.ts gains an end-to-end test proving a
first prompt generates a session name through the wired agent.streamFn
fake.
sessionNameGenerator.ts no longer imports @earendil-works/pi-ai/compat
or references getApiProvider anywhere.
Add a narrow `agent: { streamFn: StreamFn }` field to the PiAgentSession
interface, sourced structurally from the real AgentSession.agent (Agent,
from the stable @earendil-works/pi-agent-core package). This is the
resolved-auth/headers/retry "call this model" function pi's own
compaction/branch-summarization code uses internally, and will let
sessionNameGenerator.ts drop its dependency on the deprecated pi-ai
/compat provider registry in a follow-up leg.
No adapter object was needed: AgentSession's real .agent field already
structurally satisfies the new narrow shape, so defaultCreateAgentRuntime
needed no changes.
Adds a unit test proving the field is wired end-to-end via the injected
runtime creator. sessionNameGenerator.ts itself is untouched (leg C).
Split subsession inspection into two tools: check_subsession gives a quick
glance (status + latest assistant output), while read_subsession reads through
a child's transcript with role/content filters, full-content substring search
(including tool-call args), optional per-value maxChars truncation that flags
clipped parts, includeToolArgs, and pagination.
Filtering and search run on full untruncated content; truncation is an explicit,
caller-owned final projection (no default) so a narrow read never silently hides
a match. Empty page-windows are distinguished from zero-match results.
Add spawn_subsession / list_subsessions / read_subsession tools that let an
agent start child sessions it stays attached to: the child records its parent
in the session tree, the parent is notified (as a system-authored custom
message that wakes an idle parent and queues behind in-flight work) when the
child stops working, and the parent can inspect children's status and result.
Gated behind a beta flag, off by default, mirroring spawnSessions: enable via
PI_WEB_SUBSESSIONS, the subsessions config key, or the Settings toggle. Also
requires spawnSessions.
Also fix the release skill so the version step resyncs package-lock.json
(npm install --package-lock-only) and the commit step refuses a release where
package.json and package-lock.json versions disagree.
