Commit Graph

278 Commits

Author SHA1 Message Date
alan 3bfb3d6b44 Fix decide-after-finish refusal and run size loop data race
A run stays in r.active after finishRunState persists its terminal status
until its goroutine finishes notifying, so a decision in that window was
refused as "already active". decide now refuses only runs whose terminal
state is not yet durable; a finished run gets ResolveDecision's
already-decided / not-waiting answer, and an executing run is still refused.

Tests overwrote runner.artifactsRoot after Handler/newRunner had started
background goroutines (sizeLoop, session export jobs) that read it. The
root is now fixed at construction through newRunnerAt, which
HandlerWithOptions uses for Options.ArtifactsRoot, and tests configure it
there instead of mutating the field afterwards.
2026-11-01 18:58:14 +00:00
alan 70cdf985c5 Show server-queued chat prompts from the server, with Remove
The thread reads the session's queued prompts from the chat_subscribe reply
and chat_queue frames: a reload draws them as Queued after the transcript,
a delivered one enters the transcript as Sent, a refused one becomes Not
sent, and Remove sends chat_unqueue. A prompt the server reports queued is
dropped from the device unsent store; the any-frame queued heuristic is
used only with a server that does not report its queue.
2026-11-01 18:42:10 +00:00
alan e42f9cc031 Send mid-turn chat prompts to the harness and queue the rest durably on the server
Claude Code (stream-json stdin) and Codex (turn/steer pinned to the active
turn) receive a prompt sent while a turn runs immediately. Other harnesses
(OpenCode) get a durable chat_prompt_queue row owned by the session: it
survives the last client detaching and a server restart, is delivered in
order when the turn ends with or without a client, and is deduplicated by
operation id. chat_subscribe carries the queue, chat_queue frames report
delivered/removed/failed changes, and chat_unqueue removes a waiting prompt.
2026-11-01 18:30:20 +00:00
alan d35739cb49 Release session export gates whose recovery is exhausted or overdue
An exhausted export recovery job left its run parked forever in the
export wait, reserving the workspace and refusing later scheduled runs
(runs 221/226: OpenCode sessions above the 8 MiB export bound are
always truncated, so every retry stays partial).

A gate is now releasable when its job is exhausted: the visit keeps its
partial/unavailable evidence and diagnostic (still repairable), the run
continues to its next stage or terminal, and the workspace is freed.
Gates older than 15 minutes with a pending, lease-expired or missing job
are exhausted by a bounded wait. The worker reconciles on its first
tick after startup and every 30 seconds, so existing wedged runs recover
after a restart. Truncation diagnostics now name the size bound.
2026-11-01 17:24:56 +00:00
alan d1846441cc Stream ntfy notifications to app clients over /connect
Record every notification published to ntfy (run outbox, stage notify
hooks, chat question/approval/reply) in a persisted app_notifications
outbox and stream it to subscribe_notifications clients with an after
cursor; clear_notifications and ack_attention clear across devices, as do
runs leaving waiting, deleted runs and answered chat questions. Add the
notify.ntfy_enabled setting (default on) to stop only the ntfy publish.
2026-11-01 02:03:58 +00:00
alan 4d4aac5f81 Merge: run sizes and delete_runs 2026-10-31 22:11:56 +00:00
alan 31e89e872b Add run size_bytes and delete_runs to free disk space
Every run summary carries size_bytes (artifact tree, server-created Pi
session directories and an estimate of the run's database rows), cached in
pipeline_runs.size_bytes, invalidated by triggers, measured when a run
finishes and backfilled in the background. delete_runs removes terminal
runs with every scoped row and server-owned file, refuses active ones with
a reason, and pushes runs_removed to subscribers. pipelines runs rm is the
CLI form; retention apply now shares the complete row deletion.
2026-10-31 22:11:14 +00:00
alan 429e175b95 Report a busy chat on subscribe after a reload
The room that records a server-run turn is torn down when its last client
leaves, so a page reload re-subscribed to a new room that no longer knew the
turn was running and never replayed the step-started marker. Claude Code does
not re-announce a running turn to a new stream either, so the activity row and
Stop control vanished until the next streamed delta.

chat_subscribe now also replays the marker when the room's stream announced a
turn (CLI-originated or re-announced on attach) or when the broker reports its
own turn in flight through the optional chatTurnReporter (Claude Code reads its
in-process running flag; the chat manager routes it without I/O).
2026-10-31 22:09:11 +00:00
alan d7ad468b78 Stop repeating streamed Claude text when assistant blocks arrive split
Claude Code emits one assistant event per content block, so a text block that
streamed at index 1 after a redacted (empty) thinking block arrives alone at
index 0 of its event. The translator aligned completed blocks by that local
index and cleared stream state after every event, found no streamed text, and
re-emitted the whole paragraph as a new text part. Claim the streamed block of
the same kind whose text prefixes the completed one, and keep stream state for
the whole message (reset on message_start or a new message id).
2026-10-31 20:37:48 +00:00
alan f5dc6f7c91 Merge branch 'worktree-agent-a7e9b8048d7b8edf3' into integrate/notify-marked 2026-10-31 16:55:40 +00:00
alan 0c34704f06 Attach Codex and Claude chat backends lazily after startup
A harness missing at server start (e.g. codex mid-reinstall) is probed
again on chat_backends and on session create/adopt, throttled to once
per 10s while unavailable. Attached clients are never replaced.
2026-10-31 16:52:31 +00:00
alan b109ab3e06 Notify on run end only for runs marked Notify me
Auto runs no longer alert on failure or success; only notify_mode on does,
unless the run_finished setting (now 'Notify when any run ends', default off)
opts into every run end. Waiting still notifies auto and on runs. The setting
is stored under a new key so a value saved under the old meaning is ignored.
2026-10-31 16:52:04 +00:00
alan be932c846f Catch up a moved main in the delivery gate before landing
When canonical main is not an ancestor of the item HEAD, the gate now
merges main into the item workspace under the delivery lock, re-runs the
declared checks on the merged commit, and fast-forwards main to it. A
conflicting merge is aborted with the workspace verified unchanged and a
diagnostic naming the files. Successful catch-ups are logged.
2026-10-31 15:24:12 +00:00
alan f4b3ef17cc Persist and broadcast shared attention acknowledgements 2026-10-31 12:23:51 +00:00
alan 13c4035175 fix(turns): keep the run task in every stage's input
Later visits' input.md held only the previous stage's output, so the
operator's task reached only the first stage; when a Prepare stage
summarised (paths, HEAD), Code never saw the task or its acceptance
checklist and either blocked (run #202) or did part of it (#195, #197,
#198). Later inputs now carry the run prompt under '# Run task' (headings
demoted) before '# Previous turn output'.
2026-10-31 02:52:16 +00:00
alan ef07c95b0c fix(claude): list background commands and agents as running tasks
A Bash call with run_in_background and an Agent call return at once
('Command running in background…' / 'Async agent launched…'), so the
chat's task list counted them finished immediately and showed 0 tasks.
They now stay running until Claude Code's task notification (the
<task-notification> text or the SDK's task_notification message)
reports completion, with the exit code from its summary.
2026-10-31 00:16:06 +00:00
alan 498c6f17a6 Add server notification settings with app checkboxes
Persist three global ntfy switches in server_settings: run_finished
(default on: auto-mode runs notify on success, read inside the
transition transaction; on/off modes unchanged), chat_needs_you
(default on: gates chat question/approval alerts) and
chat_reply_finished (default off: one alert per finished assistant
turn). Expose notification_settings / set_notification_settings over
the websocket protocol, add a Phone notifications section with
Material and Cupertino checkboxes in Settings, document the settings,
and keep the cli, tui, stage and pipeline test packages from
inheriting a real ntfy configuration.
2026-10-30 21:36:27 +00:00
alan 39d9150c3a Merge branch 'worktree-agent-ae487572986d7a387' into integrate/chat-ntfy-attachments 2026-10-30 21:05:32 +00:00
alan 8c421952db feat(chat): show sent images as thumbnails with a full-screen viewer
Operator-attached images render as rounded thumbnails above the user
bubble and open a zoomable Material/Cupertino viewer. Inline data: URIs
decode locally; file:// attachment-store URIs load through the new
chat_attachment_image websocket request, which serves only regular image
files directly inside the private attachment store (os.Root, <= 4 MiB,
sniffed raster types). Missing files show an 'Image no longer available'
placeholder; other files keep the file row.
2026-10-30 20:53:03 +00:00
alan 40ba2ac117 Open ntfy notifications in the app and notify chats that need the operator
Run notifications now always click through to pipelines://run/<id>; a valid
PIPELINES_WEB_PUBLIC_URL adds an "Open in browser" ntfy view action instead
of replacing the click. Queued rows derive links from the run id at delivery,
so legacy rows holding a web URL still open the app.

Unresolved chat questions/forms and permission requests publish one async,
bounded notification to the system destination (pipelines://chat/<id> plus the
browser action), deduplicated per form/request id across reconnects and
replays. stage.PublishNtfy gains optional, strictly validated view actions.
Server tests now clear the operator's real ntfy environment.
2026-10-30 20:40:06 +00:00
alan 6d430948a6 feat(chat): per-chat permission modes for Claude, Codex and OpenCode 2026-10-24 18:16:10 +01:00
alan 819473c7b2 fix(chat): Claude chats sign in with the operator's login file when the service's default login is not signed in 2026-10-24 00:37:01 +01:00
alan d50deecf98 feat(cli): pipelines update forwards to the installation's lifecycle 2026-10-23 23:41:15 +01:00
alan b490728c55 feat(chat): Claude Code chats use a service token from a private file when the server runs in the background 2026-10-23 23:09:52 +01:00
alan cdedf06e35 docs(cli): chat-adopt help names every harness 2026-10-23 22:17:30 +01:00
alan 67c80ffb11 merge: land chat-adopt-claude 2026-10-23 22:09:46 +01:00
alan 5a65526d29 feat(chat): chat-adopt finds Claude Code and Codex sessions, not only OpenCode 2026-10-23 22:03:08 +01:00
alan 8527506da1 chore: remove the JavaScript web client and the Kotlin Android app; the Flutter app replaces both 2026-10-23 21:46:58 +01:00
alan e507f554c3 feat(chat): files upload over HTTP before the prompt, up to 100 MiB each 2026-10-23 21:25:41 +01:00
alan 0acd7346bb feat(chat): add Claude Code chat backend 2026-10-22 18:20:10 +01:00
alan fac055da6e fix(pipeline): let a re-saved visit keep the newest evidence 2026-10-22 00:25:59 +01:00
alan a5de5cd7ff fix(pipeline): treat an identical step-evidence replay as success 2026-10-21 23:48:45 +01:00
alan ceffd5d0d1 fix(stage): retain inline audit payloads once without losing native evidence 2026-10-21 16:59:20 +01:00
alan 22801a9b06 fix(stage): align session export render cap with artifact bound
Six computed Flutter runs stopped at the export handoff gate because the
rendered session.html cap was 2 MiB while their complete sessions (well inside
the 8 MiB source read bound) rendered between 2.25 and 4.28 MiB once html
escaping and the readable projection duplicated native text.

Raise SessionExportFileLimit to 8 MiB, the server's existing per-artifact file
bound, so a complete export is still listed and served. Normal export
verification, versioned repair and the handoff gate keep using the single
shared constant. The source read bound is unchanged, and an over-cap render is
still visibly truncated and recorded partial.

Add focused regressions for a complete export above the old cap, an over-new-cap
file rejected as partial, repair above the old cap leaving original evidence
untouched, the gate accepting the larger repair, and the constant staying inside
the artifact file bound. Update the artifact, handoff-gate and operations docs
and record the diagnosis in docs/notes/session-export-render-cap.md.
2026-10-21 15:26:29 +01:00
alan 184ce78b65 fix(notify): resolve web links for transactional outbox deliveries 2026-10-21 13:16:20 +01:00
alan 9ee2e003bf fix(notify): open configured web run pages from ntfy 2026-10-21 13:05:10 +01:00
alan 1e4654381e feat(web): manage independent schedules and restore recorded stage navigation 2026-10-21 02:06:15 +01:00
alan fe02d153f1 Preserve saved schedule run-level write scope 2026-10-21 01:04:43 +01:00
alan 8c3f116190 Bind legacy schedule workspaces only at execution startup 2026-10-21 00:56:37 +01:00
alan 4d8b34939d Separate saved run schedules from pipeline definitions 2026-10-21 00:48:34 +01:00
alan 910028a75c Keep last reported OpenCode metrics while the newest assistant is in flight
Read a bounded newest-first page of eight assistants (4 MiB, no cursor traversal), selecting context and completed generation rate independently from the latest valid measurement matching Session.Info.model provider/id. Require assistant model identity; never pair an old model's measurements with the selected model's window. Context remains unknown across a newer compaction until a subsequent prompt reports usage; the last completed matching rate may survive compaction.

Unknown model metadata is cached for 15 seconds instead of five minutes, while known capacities retain their five-minute cache. Provenance remains canonical V2 Model.Ref, TokenUsage and request-created/streamed/completed fields cited in chat_usage.go. No live endpoint access, inference or service changes.

Isolated HTTP regressions cover in-flight/null/empty newest tokens with prior known metrics, post-compaction boundaries, independent prompt/rate selection, switched/missing model identity, duplicate known-zero measurements, over-limit page rejection and metadata recovery. Checked full internal/opencode suite, focused usage race suite, go vet ./internal/opencode and git diff --check.
2026-10-21 00:26:48 +01:00
alan ce3482b057 Expose native OpenCode chat usage snapshots and replay session metrics
Read V2 session accounting, latest assistant prompt/cache components and native request-to-stream boundary. Resolve capacity by location/provider/catalog id with bounded metadata caching. Coalesce active/final readbacks; retain message-less session snapshots without changing admission or compaction state.

Provenance: https://opencode.ai/v2/openapi.json and anomalyco/opencode V2 4617210822bdbb31e5749751afbfb4584ccedac8: packages/schema/src/token-usage.ts, session-event.ts; packages/core/src/session/usage.ts, projector.ts, message-updater.ts, runner/step.ts. Native output is visible output, reasoning separate. Session totals include all five non-overlapping components. Generation rate uses created-to-streamed, not tool-inclusive completion.

Limitations: metrics remain unknown for missing components, absent timing/model metadata, reads beyond bounded latest-message/catalog budgets, or context preceding compaction. No local pricing, token estimation or default capacity. V1 gets no invented cumulative metrics; older V2 events remain available when readback is unavailable. No deployment or protocol/web/docs changes.

Checks: go test ./...; focused usage/stream race tests; go vet ./internal/opencode ./internal/server; go build ./...; git diff --check.
2026-10-21 00:13:51 +01:00
alan 83b60990d2 feat(codex): retain native session usage snapshots for chat
Verify typed ThreadTokenUsage/TokenUsageBreakdown/Thread/Turn against openai/codex@6fb1c3903d. Use native totalTokens and latest-call context tokens without re-adding cached/reasoning subsets. Replay bounded per-connection snapshots and clear on room/source release.

Cost stays unavailable: no subscription USD usage is reported by this notification. Throughput stays unavailable even with native Turn.durationMs because neither last-call nor cumulative-session output is a compatible turn-specific numerator. Thread readback exposes no token usage; no extra reads, resume, or live provider calls added.

Checks: go test -race ./internal/codex; go vet ./internal/codex; go test ./internal/server ./internal/protocol; git diff --check.
2026-10-21 00:07:12 +01:00
alan 3e62ed7979 feat(protocol): distinguish reported chat metrics from unavailable values 2026-10-21 00:01:17 +01:00
alan 724de27561 feat(stage): honor per-stage reasoning effort across native harnesses 2026-10-20 23:51:14 +01:00
alan 9ce2c5d143 feat(stage): apply and verify Pi reasoning effort before prompting 2026-10-20 23:45:17 +01:00
alan 2aaf7fe2cc feat(pipeline): parse optional reasoning effort for model stages 2026-10-20 23:40:14 +01:00
alan 4969d667b3 Expose native chat compaction activity and retained replay 2026-10-20 22:17:41 +01:00
alan e29be1181f fix(audit): reserve bounded repair capacity outside user file quota 2026-10-20 22:00:43 +01:00
alan d3c7e6e784 fix: allow cold managed service discovery only at stage admission 2026-10-20 21:53:52 +01:00