Commit Graph
160 Commits
Author SHA1 Message Date
362b1fe47e feat(teams,dsh): overview dashboard, lead task auth, and DSH launch tokens
- teams: cross-team overview read model + route/query/page; enforce member
  target visibility and restrict member task creation to the Lead
- dsh: accept 0.2.x launch tokens from the printed URL, HAPI_DSH_TOKEN, or
  HAPI_DSH_TOKEN_FILE; bundled wrapper captures the printed token securely;
  per-session agent availability and remote event/auth handling
- usage: support the 1d range and per-session totals in summaries
- cli/web: team prompt/client plumbing, availability gating, locale and
  route wiring for the overview page

Co-Authored-By: Claude Code <noreply@anthropic.com>
Co-Authored-By: HAPI <noreply@hapi.run>
2026-11-05 02:22:50 +08:00
bc6b1577fa merge: hapi upstream v0.34.1
Merge release tag v0.34.1 into the local deployment fork. Preserve local
features (Agent Team, Studio, session shares, skins, DSH Web runtime,
attachment cache, deploy tooling) while adopting upstream session-list,
composer, steering, model-catalog, native-client, and migration changes.

Regenerate the local chat_attachments migration as v31→v32 behind the
upstream v28-v31 ladder; keep DSH on the Web runtime instead of the ACP
transport added upstream.

Co-Authored-By: Claude Code <noreply@anthropic.com>
Co-Authored-By: HAPI <noreply@hapi.run>
2026-11-05 00:51:11 +08:00
JeeandGitHub e2b2af695b feat(codex): support explicit local model catalog configuration (#2266)
* fix(codex): reuse local model catalogs by default

* fix(codex): verify catalog provenance and native schema before reuse

* fix(codex): keep refresh credentials out of discovery homes

* refactor(codex): reduce catalog support to explicit configuration

* fix(codex): invalidate selected catalogs and resolve shim names
2026-11-04 15:08:54 +08:00
3affdd92c9 fix(cli): silence Cursor post-done harness Briefly inform turns (#2268)
* fix(cli): silence Cursor post-done harness "Briefly inform" turns

After AGENT_NOTIFY_SUMMARY status:done, drop notify_on_output resume
speech/tools/thinking until the next HAPI user prompt so the competing
finished-shell system ping cannot force a second user-visible reply.

Fixes #2267

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): narrow post-done silence to speech; keep soft-steer active

Address cold review + Codex P2: suppress only text/reasoning after
status:done, treat outstanding soft-steer as an active turn, and add a
launcher regression for harness-resume drops.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): discard suppressed harness buffers before next prompt

After a done close, idle-flushed harness speech stays buffered. Clear it
before reopening the silence gate so prompt()'s pre-swap drain cannot
resurrect the redundant reply (Codex P2 on #307).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): keep post-done silence through drain and handler swap

Address upstream bot Minors on #2268: suppress speech after done even
during promptInFlight drain windows, and reopen the gate only once when
promptGeneration advances after the handler swap (not before prompt()).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): seal done footer before quiet-drain harness coalescing

Address #2268 Minor: Cursor can append finished-shell speech during the
post-prompt quiet window onto the same buffer as AGENT_NOTIFY_SUMMARY
done, which hid the end-anchored footer. Seal the done segment when
flavor=cursor at native response return, and truncate buried harness
prose in the launcher as defense in depth.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): harden post-done seal against queue race and false closes

Await sessionUpdateQueue before sealing a Cursor done footer; keep note()
end-anchored; fence-aware truncate with soft-steer exemption and same-line
glue handling so examples and steered speech are not cut (#2268 Minors).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): keep seal end-anchored; harden footer scan edges

Seal only flushes end-anchored done footers (soft-steer truncate stays in
the launcher). Footer scan skips inline-code examples and tracks JSON
string/escape state so braces inside summary values do not break glue
detection (#2268 Minors).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): ignore tilde-fenced done-footer documentation examples

Recognize ~~~ fences with matching opener length alongside ``` so
truncate/seal defense does not treat tilde-fenced footer examples as a
real post-close (#2268 Minor).

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-11-04 15:06:42 +08:00
Junmo KimandGitHub c4847b241e feat(opencode): support mid-turn steering (#1981)
* feat(opencode): support mid-turn steering

Register the per-message Queue/Steer RPC on the OpenCode remote launcher so
a waiting-queue row can be delivered into the active turn as a concurrent
ACP session/prompt (soft inject, no cancel, no mode/model/effort mutation),
reusing the existing reservation/delivery-state protocol shared with Codex
and Cursor ACP.

The steer gate is closed synchronously by every cancelling or terminal path
(normal-prompt finally, abort, switch/exit, teardown, stderr stall cancel),
each steer operation is tracked from the moment its reservation is taken
until completion plus all restore/consumed bookkeeping settles, and the
foreground prompt drains those operations — abort-aware through the original
turn signal — before ready, thinking=false or the next batch. steerability is
published through the existing agentState.steeringActive flag so the web's
queued Steer button is reachable.

Gate the feature on the shared steering flavors (now including opencode) and
update the hub's supported-flavor wording.

* fix(opencode): acknowledge native steering acceptance

* fix(opencode): preserve steering delivery outcomes

* docs(opencode): remove obsolete abort-race comment

* fix(opencode): preserve steering resolution ownership

* fix(opencode): isolate ambiguous steering attempts

* fix(opencode): compare resolved steering settings

* fix(opencode): reconcile steering receipts after dispatch

* fix(opencode): distinguish pending steering delivery outcomes

* fix(opencode): restore receipts after successful native responses

Track native input requests separately from detached steer operations. Resume receipt correlation after inputs quarantined by cancellation return their own successful responses, while keeping uncertain writes on completion-based confirmation.

* fix(opencode): bound receipt proof to unambiguous native inputs

* feat(opencode): steer v2 inputs through native inbox

* fix(opencode): preserve v2 restoration and cancellation ownership

* docs(opencode): describe v2 inbox steering confirmation

* fix(steer): expire Claude confirmation with its owning worker
2026-11-03 18:37:53 +08:00
AnanovoandGitHub 3208199f99 fix(files): optimize exact path and directory search (#1778)
* fix(files): optimize exact path and directory search

* fix(web): preserve incremental file mention search

* fix(cli): contain recursive file search within workspace

* perf(cli): reuse canonical workspace path

* fix(cli): classify archived workspace file stats
2026-11-02 18:08:32 +08:00
7f5d6b17f3 feat(peer): spawn-peer remit + rename-proof Parent UUID stamps (#1922)
* feat(cli): spawn-peer with required remit and MCP spawn_peer

Machine spawn creates an empty composer; stuffing message into that
JSON is stripped. Add hapi spawn-peer and MCP spawn_peer that spawn,
rename, deliver via the ping-peer path, and fail closed unless the
remit is on the new session. Reject message/prompt/text on machine
spawn with 400. Do not auto-approve spawn_peer in default/read-only.

Fixes #1509

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): reject overlong spawn-peer names before spawn

Hub rename max is 255; continuing past PATCH 400 left a live session under a different title. MCP/steer copy now says the hub 400s a spawn-body remit instead of stripping it.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): wait for fresh spawn-peer child instead of resuming it

Machine spawn can return while the hub row is still inactive. ping-peer then POSTed /resume, which can launch a second agent because the original spawn has no existingSessionId for runner dedupe.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): reject flavor-illegal permissionMode before spawn-peer

Codex + bypassPermissions (and Pi + any mode) used to reach the runner and fail after a child existed, or silently drop the mode. Check isPermissionModeAllowedForFlavor when both agent and mode are explicit.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): treat omitted spawn-peer agent as Claude for permissionMode

Hub and runner default agent to claude when spawn omits it. Validate permissionMode against that effective flavor so yolo/read-only fail closed before a child starts.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): resolve spawn-peer dir locally and archive failed children

Relative --dir values were forwarded unchanged, so the runner resolved them against daemon cwd. Remit delivery failures also left the new session running, so a retry spawned a duplicate. Resolve in the caller and best-effort archive the child before rethrowing.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): verify remit before archiving a failed spawn-peer child

A timed-out ping-peer POST can still land the remit. Check the transcript before archive, and only say the child was archived when the hub returns ok.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): swallow spawn-peer transcript GET errors and skip unapplied names

A thrown messages GET after spawn skipped archive and leaked a live child. Treat transport errors as a miss so the verify loop can retry, then clean up. Also do not return a requested name the hub never applied.

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat(spawn-peer): hub peerSpawnDefaults + model/effort spawn surface

Add hub settings peerSpawnDefaults (agent, permissionMode, per-flavor models)
with stock claude/yolo/sonnet fallbacks. spawnPeer resolves explicit args →
hub settings → stock, maps yolo to flavor equivalents, and forwards model/effort
into machine spawn. Settings UI under General → Agents; MCP/CLI optional overrides.

Co-authored-by: Cursor <cursoragent@cursor.com>

* test(hub): use cursor-valid permission mode in peer spawn defaults test

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): teach spawn_peer that omit permissionMode means yolo

MCP copy said "pass permissionMode only when the operator asked", so agents
omitted it and got hub/stock whatever was stored — often approval-gated
default. Clarify omit = yolo via peerSpawnDefaults/stock; pass only to tighten.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub,web): apply peerSpawnDefaults to machine spawn and New Session

POST /api/machines/:id/spawn now resolves omitted agent/permissionMode/model
from hub Settings, and New Session seeds from the same peerSpawnDefaults so
UI create and peer spawn share one authoritative default (stock yolo).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(web): NewSession hub seed respects sticky prefs + QueryClient in tests

Sticky localStorage last-used agent wins over hub seed; machine spawn still
applies peerSpawnDefaults server-side. Tests provide QueryClientProvider.

Co-authored-by: Cursor <cursoragent@cursor.com>

* test(web): mock CREATABLE_AGENT_FLAVORS for settings general peerSpawn UI

Co-authored-by: Cursor <cursoragent@cursor.com>

* test(web): stabilize NewSession tests after hub peerSpawnDefaults seed

Wrap remaining mounts in QueryClientProvider, pre-seed hub settings so a
late useQuery resolve cannot wipe in-test model picks, and use neutral
stock permission defaults in the fixture.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(spawn-peer): address tip Codex Majors for peerSpawnDefaults

Preserve explicit yolo booleans on machine spawn, fail closed when hub
defaults cannot load, validate permission modes against the resolved
agent, remap auto-approval across flavors, and stop late hub settings
from wiping New Session edits. Reject retired agents in spawn defaults
and restore the CLI executable build docs.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(spawn-peer): address follow-up tip Codex Majors

Stop absent Yolo localStorage from beating hub defaults, track New Session
edits before late hub seed, reject incompatible machine-spawn permissions,
resolve MCP spawn_peer paths against the session working directory, and
hide unsupported Codex safe-yolo from Settings spawn defaults.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(spawn-peer): clear tip-2 CI and follow-up Codex Majors

Omit permissionMode for Pi/DSH, preserve explicit Yolo-off across delayed
hub seed, fix settings test mocks for launch permission helpers, and
restore unrelated CLI README lifecycle/ACP docs.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(spawn-peer): tip-3 Majors for seed edits and launchable modes

Skip hub agent seed after permission edits, resolve inherited modes via
the launch catalog (AGY request-review fallback), preserve hub Cursor
models through preference restore, and restore Codex auth README nuance.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(web): tip Minors for Cursor/Grok hub permission seeding

Give Cursor the native permission select so Plan/Ask survive machine
spawn, and re-apply Grok hub permissions after agent-init resets.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(spawn-peer): tip Minors for Cursor select and hub seed remap

Map hub permission through resolvePermissionModeForFlavor, keep native
Default when agent is explicit without a model, and assert Cursor Plan/Ask Mode labels.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(web): tip Minors for delayed hub seed and Default model

Apply hub permission/model to unset fields even with a sticky agent,
preserve explicitly saved auto models, and seed OpenCode/AGY selectors
from hub defaults.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(spawn-peer): tip Minors for model edit sticky and clear override

Mark OpenCode/AGY model picks as edited so delayed hub seed cannot
overwrite them, and treat empty hub model values as clear sentinels.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(spawn-peer): tip Majors for models patch typing and remit page scan

Type the models patch as NonNullable and paginate transcript verification
oldest-ward so a busy child is not archived when the remit leaves page 1.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(web): tip Minor — keep agent after explicit model pick

Do not apply a late hub default agent when the operator already chose a
model; otherwise preference restore drops that selection.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(spawn-peer): tip Cursor YOLO migrate and Codex effort map

Bridge Cursor's saved YOLO toggle (incl. false) into native Default over
hub yolo, and send Codex/OpenCode --effort as modelReasoningEffort.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(web): tip Majors — scoped YOLO bridge and catalog fallback

Keep unsupported saved permission modes at Default instead of hub yolo,
and apply delayed YOLO migration only when the sticky bridge agent matches.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): drop rebase conflict markers in startHappyServer

Both sessionDisplayRename and spawnPeer imports are required after
rebasing onto upstream rename work; markers had slipped into tip.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(web): wrap Kimi NewSession tests in QueryClientProvider

Hub settings useQuery requires a provider; upstream Kimi catalog tests
rendered bare and broke after the spawn-peer rebase onto main.

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat(peer): rename-proof Parent UUID stamp on spawn remits

Orchestrated spawn_peer / spawn-peer remits now auto-stamp a durable
[title](/sessions/<uuid>) Parent chip (fail-closed in-session). MCP copy
forbids inventing titles; UUID stays identity after parent rename.

Refs heavygee/hapi#175

Co-authored-by: Cursor <cursoragent@cursor.com>

* style(peer): plain hyphen in Parent-stamp warning and test comment

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): reject blank remit before Parent stamp

Codex review on #1922: stamping first turned empty remits non-empty and
bypassed the idle-session guard. Also only treat ## Parent blocks as
already-present so bare /sessions citations still get the chip.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): gate New Session Create on hub defaults; require Parent chip

Codex tip review on #1922: block Create while getHubSettings is pending so
stock mount defaults cannot bypass restrictive hub peerSpawnDefaults; skip
Parent stamp only when ## Parent already has a markdown session chip; clarify
codex resume takes a native thread id.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): resolve MCP spawn cwd; Agents settings section

Codex Major on #1922: spawn_peer relative directories now prefer the
launcher cwd (Codex --cd), then skillLookup, then session metadata.path.
Move peerSpawnDefaults UI into the unused Agents settings section.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): pass session cwd to MCP spawn_peer; Agents settings section

Codex tip review on #1922: resolve relative spawn_peer directories from the
launcher working directory (Codex --cd), skillLookup, then metadata.path;
move peerSpawnDefaults UI into the Agents settings section.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): skip archive on unread transcript; validate startingMode after hub agent

Codex tip review: do not archive a child when remit verification cannot read
the transcript; run AGY/DSH remote-only startingMode checks against the
resolved hub agent; update MCP bridge test expectations for workingDirectory.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): treat exhausted remit pagination as unverifiable

Hitting the messages page cap with hasMore still true must not count as an
observed-empty transcript — that would archive a child whose remit may still
exist on older pages.

Co-authored-by: Cursor <cursoragent@cursor.com>

* docs(cli): list HAPI_API_URL as optional with localhost default

Codex tip review: the README had moved HAPI_API_URL under Required even
though configuration defaults it to http://localhost:3006 (and settings can
supply a URL). Also drop trailing whitespace flagged by git diff --check.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): re-verify empty transcript before archiving failed spawn

An earlier observed-absent page plus later unread GETs must not archive a
child whose remit may have landed after the first empty read.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): never auto-archive on spawnPeer failure path

Timed-out remit POSTs and empty-read/archive TOCTOU races can still land
work on the child. Leave the session running with its id for inspection
instead of terminating an in-flight peer.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): classify empty_session from final remit verify

An earlier empty transcript read must not stick as empty_session once
later message GETs become unavailable — report verify_failed instead.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): recognize escaped brackets in Parent chip labels

Titles with ] were escaped in the chip label but the idempotency regex
stopped at the first raw bracket and re-stamped a second Parent block.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): avoid Parent chip regex backtracking on backslashes

Exclude \\ from the single-char label alternative so escaped pairs have
one parse path — long nonmatching backslash runs no longer explode.

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat(cli): MCP/CLI spawn_peer --machine for cross-host remits

Wire optional machine (UUID or hostname via GET /api/machines) through
MCP spawn_peer and hapi spawn-peer into existing spawnPeer({ machineId }).
Skip local directory existence checks for cross-host targets to match the
estate wrapper; keep fail-closed remit verify.

Fixes tiann/hapi#1931

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): reject ambiguous spawn --machine label matches

Tip bot Major on #1922: hostname/displayName selectors that match more
than one online runner now fail closed with ambiguous + UUID guidance.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): preserve cross-OS absolute dirs for spawn --machine

path.resolve on the caller OS was rewriting foreign absolute roots
(C:\… on Linux, /srv/… on Windows) before the hub spawn POST. Detect
POSIX or Windows absolute paths and only resolve relative directories.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(peer): resolve spawn dirs after local vs remote is known

Defer directory resolution until the target machine is selected. Remote
spawns still preserve foreign absolute roots; local spawns use native
path.resolve so Windows drive-less paths like \repo bind to the caller
drive.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(web): apply delayed DSH model defaults without replacing edits

* fix(web): preserve hub permission defaults across form remounts

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: weishu <twsxtd@gmail.com>
2026-11-02 13:17:22 +08:00
weishuandGitHub 7bb2eb914f feat(claude): mid-turn Steer for remote Claude sessions (#2259)
* feat(claude): mid-turn Steer for remote Claude sessions

Queued messages can now be steered into a running Claude turn, the same as
Ctrl+X Ctrl+S in the Claude TUI. The row is written to the live stream-json
stdin and Claude folds it in at its next tool boundary.

- Spawn Claude with --replay-user-messages and tag every stdin message with
  a uuid; the echo acks pickup and is never relayed to chat
- A result that arrives while a steer is still unacked does not end the
  turn: Claude runs a follow-up turn for it, so ready waits for that result
- Launcher registers steer-queued-message: reserve the row, reject control
  commands and mode mismatches, ack the hub after the write, mark consumed
  (steered) on the echo; abort before pickup holds the row indeterminate,
  an unprompted exit requeues it
- Open the shared steer gate and peer/hub wording to Claude (remote only)

* fix(claude): retire completed input before a steer follow-up turn

- Generalize onCompactResultAccepted to onResultAccepted and fire it when a
  result arrives with a steer still unacked, so a stream failure during the
  follow-up turn recovers only the steer instead of replaying the finished
  prompt
- Close the steer target and settle pending steers when query() setup
  throws, so a retry backoff cannot accept a steer nobody will read
2026-11-02 10:12:14 +08:00
013ace8e88 fix(cli): show resolved versions in Claude model labels (#2245)
Co-authored-by: Kiyoshi Guo <kiyoshi.guo@bytedance.com>
2026-10-30 14:37:59 +08:00
AnanovoandGitHub 0f76485ad9 feat(web): support local Markdown images in conversation messages (#2215)
* fix(web): resolve relative Markdown assets in file previews

* fix(web): harden standalone Markdown asset resolution

* fix(web): preserve Markdown URI and image policies

* fix(web): route Markdown file links through app history

* fix(web): preserve session reference navigation in previews

* feat(web): support local Markdown images in conversation messages

* fix(cli): bound session file reads

* fix(cli): avoid blocking bounded reads on FIFOs

* test(cli): run FIFO regression with Bun

* fix(hub): preserve legacy session file RPC calls

* test(web): update markdown preview fixture context

* fix(cli): reject symlinked session files outside workspace
2026-10-29 22:12:57 +08:00
weishu 9384ce031b feat(cli): add Codex-aware auto peer delivery
Default peer CLI and MCP messages to auto, steering eligible Codex turns and queueing otherwise. Preserve explicit delivery modes and uncertain-send safety, and clarify steer guidance for important time-sensitive findings.
2026-10-29 22:02:43 +08:00
2a75984b75 feat(cli): add peer delivery modes for CLI and MCP (#2197)
* feat(cli): select queue or steer for peer messages

* fix(peer): respect per-agent steering availability

---------

Co-authored-by: NightWatcher <hitszzzf@gmail.com>
Co-authored-by: weishu <twsxtd@gmail.com>
2026-10-29 10:55:58 +08:00
weishuandClaude Opus 5.5 23122ccbc0 feat(hub): persist agent turns and report them through hapi usage
Whether a session's agent is thinking lived only in the session cache,
so once a turn ended nothing could say how long the agent had worked,
and a hub restart forgot even the turn in progress. Tools that track
time (Weft, for one) had no way to see when agents on other machines
were busy.

Schema v28 adds session_turns: a row opens when a session starts
thinking (a prompt queued through the hub, the agent reporting it,
or a patch) and closes when it stops, the session ends, or its
keepalives expire, at the last keepalive. Rows are only written on
those transitions, never per keepalive. Turns move with a session
when it is merged away.

At startup the hub closes turns left open by the previous process at
the session's newest message. If the agent carries on thinking within
10 minutes of the restart, the same turn continues, so the work between
that message and the restart isn't lost. The deadline counts from the
restart, and a keepalive or patch reporting idle, the session ending,
or a new prompt ends the chance: those start a new turn.

GET /api/activity returns, for the caller's namespace, each session's
turns in a window (default 24 h, at most 31 days) with what identifies
it (flavor, agent session id, machine, path, title) and the permission
prompts and questions it waited on, taken from agent_state.

`hapi usage [--since] [--until] [--json]` prints a summary or a
hapi.activity.v1 report for other tools, with distinct exit codes for
bad arguments (2), missing or refused credentials (3) and a hub too
old to answer (4). The summary counts only the part of each turn
inside the window and subtracts overlapping waits once. It reuses the
peer commands' token exchange.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 08:48:06 +08:00
Junmo KimandGitHub ae147e85db feat(opencode): import local session history (#1677)
* feat(cli): list local OpenCode sessions over machine RPC

* feat(hub): import OpenCode sessions into HAPI

* feat(web): import OpenCode history from new-session picker

* fix(cli): derive OpenCode imported message ids from part ids

Random ids made every scan differ, so delta classification flagged
unchanged transcripts as diverged on re-import.

* fix(cli): surface unreadable OpenCode db as rpc error

A locked or unopenable opencode.db now fails the listing instead of
reporting an empty success; summaries normalize timestamps and the web
import toast counts only created or actually-appended sessions.

* fix(hub): fail closed on opencode re-import past live HAPI continuation

Imported entries must remain a strict prefix of the native transcript.
Insertions ahead of the imported boundary or new native messages after
the session continued in HAPI now fail closed instead of appending
duplicated or reordered history.

* fix(web,hub): apply selected launch config when importing OpenCode history

Pass the model, reasoning effort, and permission mode chosen in the
new-session picker through the import request and persist them on the
imported HAPI session via applySessionConfig, so reopen launches with
the visible selection instead of stale or default values.

* fix(hub,cli): preserve explicit launch resets and skip streaming parts on import

- Launch config keys are applied by presence, so explicit null/default
  selections from the picker must reach applySessionConfig to clear
  stale model, effort, or permission values on re-import. Requests that
  omit the fields entirely still leave persisted config untouched.
- Assistant text parts are mutable while a response streams. Mirror the
  live scanner gate and import only finished (time.end set), synthetic,
  or user text so an in-progress row can never be stored and later
  finalized as transcript_diverged.

* test(hub): fix launch-config reset assertions to satisfy strict types

* fix(cli): fail opencode transcript reads on query errors instead of partial snapshots

Swallowed SQLite errors could return a truncated message list that the
hub later rejects as transcript_diverged with no repair path. Full
transcript reads now propagate query failures; summary lastUserMessage
extraction stays resilient per message.

* test(cli): cover unreadable-part-table transcript read stays non-partial

* fix(hub): scope launch-config failures to the per-session import result

A thrown applySessionConfig call used to escape the bulk handler as an
unstructured 500 even though transcripts were already persisted. Catch
it per session and report it as a config_failed result so remaining
sessions in a bulk request still import.

Also cover the mid-transcript part-query failure with an injected
opener that rejects instead of returning a holey transcript.

* fix(cli): read opencode transcripts inside a deferred snapshot transaction

Messages and their parts were read in separate statements, so a
concurrent OpenCode write could leave a hole in the imported sequence
that positional re-import checks then reject forever. Wrap each full
transcript read in BEGIN DEFERRED/COMMIT with rollback on failure.

* fix(cli): follow machine path policy for OpenCode imports

* fix(web): use unified permission mode for OpenCode imports

* fix(opencode): harden session import consistency

* fix(hub): preserve metadata on rejected OpenCode imports

* fix(hub): refresh OpenCode import state under lock

* fix(hub): resolve OpenCode imports after locking

* fix(opencode): bind imported resume to source machine
2026-10-28 12:14:18 +08:00
Junmo KimandGitHub 9e5d848796 fix(claude): announce automatic compaction when it starts (#2190) 2026-10-28 12:13:27 +08:00
ffd950a220 fix(codex): drop safe-yolo from Codex permission modes (#2183)
* fix(codex): drop safe-yolo from Codex permission modes

Every Codex session runs on the native shared runtime (runCodex is
runSharedCodex), which rejects safe-yolo. The mode stayed in
CODEX_PERMISSION_MODES and six filters hid it again in the web picker,
composer, hub permission-mode route, hapi set-mode and both native
apps. API callers that validate against the flavor catalog (e.g. a
spawn with permissionMode: 'safe-yolo') still passed it through and
only failed inside the runner.

Remove it from the Codex catalog (shared, iOS, Android, fixture) and
delete the filters. autoReview is the native replacement. Safe Yolo
stays for Gemini, Kimi and Copilot.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* test(ios): Codex option list now has four modes

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 12:12:55 +08:00
Junmo KimandGitHub 01f80e186a fix(peer-delivery): truthful accepted vs consumer-confirmed receipt (#2071)
ping-peer now sends a ping-peer- localId and reports hub-accepted instead
of delivered; the hub exempts those rows from the session-end synthetic
sweep so only a real runtime ACK confirms them; web shows pending vs
delivered badges only on peer rows, excluding failed, indeterminate and
scheduled states.
2026-10-28 12:12:04 +08:00
Junmo KimandGitHub cd0b8e3589 fix(claude): stop locking Claude sessions to three hard-coded model aliases (#1948)
* feat(shared): derive Claude model choices from the CLI catalog

The choices are the rows of the claude CLI's own /model picker, in its
order and with its display names. The stored value is what
claude --model receives: an alias is resolved again each time the
session's claude process starts, a full id stays on its model, so
following and staying need no new field.

Effort support is read per model so a model switch can drop an effort
level the next model does not offer.

* feat(cli): discover Claude models from the CLI's initialize response

A machine RPC starts claude in stream-json mode, sends only an
initialize control request and reads the models it reports, so no turn
runs and no transcript is written.

claude --print runs a directory's project hooks and .mcp.json servers
without a trust prompt, so the probe starts from the home directory
with user settings only, no MCP servers and hooks disabled.

Successful catalogs are cached per claude executable for five minutes
and concurrent requests share one probe; failures are not cached.

* feat(hub): expose the Claude model catalog per machine

GET /machines/:id/claude-models forwards to the runner's
listClaudeModels RPC. A runner that predates the handler answers with
the stable rpc_target_missing code so clients can keep their built-in
list.

* feat(web): offer the machine's Claude models in the model pickers

The composer and the create-session form list the rows the machine's
claude CLI shows in its own /model picker, as it shows them. Built-in
presets the catalog does not list remain selectable after it.

Until the catalog arrives, or on a runner without discovery, the
built-in presets are shown as before. A saved Claude model is no longer
reset to Default when the built-in list lacks it; the create-session
form keeps it and marks it as no longer listed when the catalog
dropped it.

* feat(hub,web): keep Claude effort within what the selected model offers

For Claude sessions the model endpoint accepts an optional effort, so a
model switch and the effort it keeps reach the session as one config
change. Other flavors are refused: Pi, for one, commits the model
before its thinking level. When the machine's catalog says the next
Claude model does not offer the current effort, the composer clears it
in that same request. The create-session form drops such an effort
however the model was set, including a restored preference or draft.

Effort choices in both places narrow to the selected model's levels;
without a catalog every level stays available as before.

* fix(web): retry Claude model discovery after a failed probe

The machine answers a failed probe with success:false over HTTP 200.
The query cached that as an answer for its stale time, so a user who
signed in and reopened a picker within a minute still saw only the
built-in models. A failed probe is now a query error, which is not
kept, and the next picker to mount asks the machine again.

* fix(web): list only the Claude CLI's models once its catalog is known

The built-in presets were kept after the catalog so that a partial list
could not hide Opus. The catalog is the CLI's own /model list, though,
not a partial one, and the presets added entries the CLI does not show
(Sonnet 1M, Opus 1M, Fable 1M). With a catalog the list is now exactly
its rows; a saved model it does not list stays as the current model,
and New Session marks it as no longer listed. Without a catalog the
built-in presets are shown as before.

* fix(shared,web): list earlier Claude versions under Other models

Claude Code's model sheet shows each family's newest model first and
every earlier version under an "Other models" heading. The CLI's
catalog lists models in that order but does not say where the split
is, so the first row of each family is taken as its newest and later
rows of the same family as earlier versions.

The composer's model list and New Session's model select now show the
same two groups, keeping the CLI order within each. Nothing is folded:
every row stays one click away, as it does in Claude Code.

* test(web): pin that Claude 1M variants come from the CLI catalog

Claude Code 2.1.105, 2.1.200, 2.1.240 and 2.1.274 list a 1M choice as
its own catalog row (opus[1m], claude-fable-5[1m]); 2.1.303 and 2.1.310
list none, and on 2.1.310 opus and sonnet run with a 1M context window.
The catalog-only list therefore offers a 1M variant exactly when the CLI
does. Pin that and record why the built-in [1m] presets are not appended.
2026-10-28 12:10:36 +08:00
SSU-WEI HUANGandGitHub 3e68e29110 fix(codex): reuse live model catalogs and extend discovery cache (#1938)
* fix(codex): reuse live model catalogs and extend discovery cache

Closes #1937

* fix(codex): track relative model catalog changes

* fix(hub): expose missing Codex session model RPC code
2026-10-28 12:10:08 +08:00
db4ee82c80 fix(cli): release stdin before handing terminal to local-mode child (#1932)
* fix(cli): release stdin before handing terminal to local-mode child

hapi ships as a Bun-compiled executable, and Bun's tty.ReadStream keeps
an in-flight read on fd 0 even after process.stdin.pause()
(https://github.com/oven-sh/bun/issues/29126).

Remote mode reads stdin (Ink UI in raw mode, for the double-space
switch-to-local gesture). When switching back to local mode,
spawnWithTerminalGuard only paused stdin before spawning the agent TUI
with stdio:'inherit'. The parent's stale pending read kept racing the
child for console input and won: after a remote -> local switch the
agent TUI rendered but received no keystrokes at all — the input box
was dead and even Ctrl-C never reached it. Instrumented at local spawn
time: dataListeners=0, isPaused=true, but _readableState.reading=true.

Fix: destroy stdin outright before spawning the local child
(releaseStdinForChild) — destroy reliably stops the pending read where
pause() does not — and re-create process.stdin via
`new tty.ReadStream(0)` when remote mode starts again
(ensureLiveStdin, called from RemoteLauncherBase.setupTerminal).
hasTTY is now computed lazily since stdin may legitimately be
destroyed at launcher construction time.

Verified end-to-end on Windows with `hapi kimi` by injecting console
input via WriteConsoleInput and checking the agent session wire log:
remote -> double-space -> local -> typed message reaches the agent;
switch to remote again (double-space detection works on the
re-created stdin) -> local -> input works again. Direct local launch
unaffected. `bun run typecheck:cli` and the cli vitest suite pass.

* fix(cli): preserve piped stdin when releasing terminal for local child

Addresses review feedback on #1932: releaseStdinForChild() destroyed
stdin unconditionally, but destroying a piped stdin closes fd 0 and
starves the child spawned with stdio:'inherit'. The Bun stale-read
workaround is only needed for a TTY, so skip destroy() when stdin is
not a terminal; pause() suffices for pipes. Adds regression coverage
for the piped case.

---------

Co-authored-by: Naitian LIU <Liunaitian@users.noreply.github.com>
2026-10-28 12:09:49 +08:00
b450aa8236 fix(cli): discover DSH skills from the DeepSeek Harness home (#1916)
For the `dsh` flavor HAPI's `$` skill menu only scanned `~/.agents/skills`
and `<dir>/.agents/skills`, so skills installed under the DeepSeek Harness
home (for example `~/.dsh/skills/<skill>`, where the clawhub CLI installs
them) never appeared in the completion list even though DSH's own
skill-filesystem provider loads them.

Add the roots that provider uses, plus the `$DSH_HOME` override the other
supported agents already have: `$DSH_HOME/skills` for user skills and
`<project>/.dsh/skills` for project skills. The DSH integration (#1632) did
not extend the per-flavor skill roots, unlike the earlier per-agent
additions (#288/#482/#487 Claude and Codex, #1030 Grok, #1245 Copilot).

Verified with a temporary-home Red/Green check, three new unit tests, a real
DSH session in a Full test environment (its skills endpoint now returns the
previously missing skill), typecheck, build, and the Root
terminal-wrap-fidelity Playwright suite.

via [HAPI](https://hapi.run)

Co-authored-by: Claude Code <noreply@anthropic.com>
Co-authored-by: HAPI <noreply@hapi.run>
2026-10-28 12:09:15 +08:00
AnanovoandGitHub 5d7e13fc5d fix(hub,cli): keep inactive file previews available through runner (#1727)
* fix(hub,cli): keep inactive file previews available through runner

* fix(cli): bound runner workspace file reads

* fix(cli): constrain runner git fallback pathspecs

* fix(cli): allow dot-prefixed workspace paths
2026-10-28 12:07:18 +08:00
xxfadandGitHub fe5950973f perf(codex): optimize session history import (#2206) 2026-10-28 11:02:06 +08:00
00bbbfa780 fix(claude): report thinking for local-mode sessions (#2209)
* fix(claude): report thinking for local-mode sessions

Local Claude sessions have no SDK stream, so nothing ever set the
session's thinking flag and the web UI showed them idle mid-turn.
Derive it from the local hooks instead: UserPromptSubmit/PreToolUse
turn it on, Stop/StopFailure/SessionEnd turn it off. Esc interrupts
fire no Stop hook, so the transcript's interrupt marker also clears
it, and leaving local mode always resets it.

Fixes #1864

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(claude): ignore interrupt markers from an earlier local turn

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 10:31:44 +08:00
weishu e5a845cf9f test(cli): include Codex Auto Review in peer permission coverage 2026-10-26 14:45:02 +08:00
927b4971b9 feat(dsh): model selection for DeepSeek Harness (ACP config options) (#2030)
* feat(acp): flatten Zed-style grouped configOptions choices

DeepSeek Harness 0.2.x (and Zed-style agents generally) nest select
choices one level under group entries that carry no `value` of their
own:

    options: [{ group, name, options: [{ value, name }] }]

Both the per-session config-option descriptor and the model-metadata
merge previously read only flat `{ value, name }` entries, so grouped
pickers surfaced zero choices. Flatten recursively in a shared helper;
flat options are unaffected.

Co-Authored-By: Claude Code <noreply@anthropic.com>

* feat(dsh): runtime model switching through ACP config options

dsh advertises its model catalog as a Zed-style grouped config option
(provider groups with JSON-encoded provider+model tuple values) instead
of session/set_model, so wire it through the generic config-option rail:

- shared: ListDshModels/ListDshModelsForMachine RPC methods, response
  types, and grant dsh the ModelChange flavor capability
- cli: DshMode becomes {model} and rides the queued-batch mode like
  other flavors; the launcher applies model switches per-turn via
  session/set_config_option, discovers the live current model from the
  config option after newSession, rolls back (and warns) when a switch
  is rejected, and serves ListDshModels from session metadata. A
  machine-scoped probe (60s single-flight cache) backs the new-session
  catalog; --model is now accepted by the dsh command
- hub: dsh-models passthrough routes (machine + session scope)

Co-Authored-By: Claude Code <noreply@anthropic.com>

* feat(web): dsh model selector for new sessions and in-chat switching

New-session form gets a Default-plus-catalog picker fed by the machine
probe (opaque tuple values verbatim, friendly names as labels, stale
draft picks dropped when the catalog rotates). Running sessions get the
same catalog over the session-scoped hook; switching rides the existing
generic model-change path now that dsh advertises ModelChange.

Co-Authored-By: Claude Code <noreply@anthropic.com>

* fix(dsh): honor explicit Default reset and cover pending catalog discovery

The launcher now captures the server default before applying any spawn
override, and a queued `model: null` (the picker's "Default" after an
explicit switch) switches back to it instead of silently keeping the
last applied model; DshMode keeps null distinct from undefined all the
way from the config RPC through the queue (runDsh no longer collapses
it). The web model-option helpers get explicit dsh branches mirroring
opencode: pending, failed, or empty ACP discovery renders no Claude
presets and the Ctrl/Cmd+M cycler keeps the current model. NewSession
restores dshSelectedModel from preferred launch settings alongside
agy/opencode (the existing catalog-validation effect drops stale tuples)
with remount, forward-on-create, and fallback tests.

Co-Authored-By: Claude Code <noreply@anthropic.com>

* fix(dsh): keep unset model preferences distinct from Default resets

Two review follow-ups:

- currentModel collapses "no preference yet" into null, so a session
  started without --model on a server that reports no current model
  queued model:null on every ordinary turn — the launcher read each one
  as an explicit "Default" reset and emitted 'Cannot reset the DSH
  model' every turn. The preference is now three-state (undefined =
  nothing requested, null = picker's explicit Default, string = model),
  encoded through dshModeForPreference() so preference-less turns carry
  no model field at all.

- ListDshModels was registered only after initialize/session/new and
  discovery finished; a picker opened during startup hit an
  unregistered-method rejection with no retry path and stayed empty
  until remounted. The handler is now registered before initialization
  and parks on a readiness promise resolved once the session exists and
  discovery has settled (rejected with the startup error otherwise).

Co-Authored-By: Claude Code <noreply@anthropic.com>

* docs: DSH advertises model selection over ACP

The capability blurbs still said HAPI exposes no model pickers for DSH and
that the ACP server has no model switching. Update them to the wire reality:
models are listed via ListDshModels and applied per turn with
session/set_config_option. Resume remains out of scope on this branch.

via [HAPI](https://hapi.run)

Co-Authored-By: HAPI <noreply@hapi.run>
Co-Authored-By: Claude Code <noreply@anthropic.com>

---------

Co-authored-by: Claude Code <noreply@anthropic.com>
Co-authored-by: HAPI <noreply@hapi.run>
2026-10-26 10:02:51 +08:00
62872d80fa feat(cli): HAPI_DISABLE_PEER_TOOLS — hide peer-session tools from wrapped agents (#2052)
* feat(cli): add HAPI_DISABLE_PEER_TOOLS to hide peer-session tools from agents

Wrapped agents with peer tools can browse the session list and message
other sessions, polluting peer contexts on busy runners. Setting
HAPI_DISABLE_PEER_TOOLS=1 (true/yes also accepted) in the runner
environment now removes the peer surface entirely instead of
advertising it and refusing:

- the session MCP server does not register list_peers / inspect_peer /
  ping_peer, and they are dropped from the toolNames consumed by
  Claude --allowedTools and the codex/generic bridge --tools lists
- the stdio bridge filters peer names even when a stale --tools value
  lists them explicitly
- flavor system prompts (claude/codex/opencode) swap the peer steer
  block for a short notice that keeps the hub-path-is-not-a-file guard
  while pointing citations at the user
- the peer core (pingPeer/inspectPeer/listPeerSessions) refuses with a
  new 'disabled' error code before any network call, so shell
  `hapi ping-peer` / `inspect-peer` from inside a wrapped agent fails
  loudly as defense in depth

Operators scope the variable to the runner (systemd/launchd/guard env);
an interactive terminal without it keeps full CLI access.

via [HAPI](https://hapi.run)

Co-Authored-By: HAPI <noreply@hapi.run>
Co-Authored-By: Claude Code <noreply@anthropic.com>

* test(cli): cover peer-tool prompt steer and default bridge tool list

Adds regression tests for the two surfaces the kill switch mutates beyond
the explicit --tools path:

- happyMcpStdioBridge: default tool list (no --tools) keeps the peer tools
  as a positive control, then HAPI_DISABLE_PEER_TOOLS=1 filters them out
  of the same default seed.
- New cross-flavor prompt test: the citation steer baked into the
  claude/codex/opencode prompt consts swaps to the disabled notice under
  the env flag and keeps the flavor-specific "Call \"<tool>\"" instruction
  by default (module consts evaluate env at import, so each mode is
  imported fresh via vi.resetModules + dynamic import).

via [HAPI](https://hapi.run)

Co-Authored-By: HAPI <noreply@hapi.run>
Co-Authored-By: Claude Code <noreply@anthropic.com>

* test(cli): keep peer-tools env set through prompt assertions

Keeps HAPI_DISABLE_PEER_TOOLS applied until after the assertions and
restores it at test end. Some upstream shapes resolve the citation steer
at call time (getSystemPrompt(env)) rather than baking it into the
import-time const, so restoring the env inside the import helper made
those shapes observe the enabled steer and fail.

via [HAPI](https://hapi.run)

Co-Authored-By: HAPI <noreply@hapi.run>
Co-Authored-By: Claude Code <noreply@anthropic.com>

---------

Co-authored-by: HAPI <noreply@hapi.run>
Co-authored-by: Claude Code <noreply@anthropic.com>
2026-10-26 10:02:06 +08:00
d3f7c107d5 feat(pi): display inline tool-result images (#2060)
Build on tiann/hapi#1831, retain bounded image reads, and support current
Pi nested and failed tool results through the existing generated-image path.
Keep conversion synchronous to preserve transport ordering without a new
publication queue.

Co-authored-by: Debin <luodeb@outlook.com>
2026-10-26 10:01:55 +08:00
6bf0a633bb fix(claude): seed local-mode context window from the configured model (#1858) (#2088)
* fix(claude): seed local-mode context window from the configured model (#1858)

Local transcripts carry bare model ids and no usage.context_window, so
local Opus/Sonnet [1m] sessions fell back to the web's 200k heuristic
(190k denominator). At local launch, resolve the model Claude Code
starts with (--model, ANTHROPIC_MODEL, project local/project/user
settings) with its [1m] suffix intact, and stamp a 1M context_window on
assistant messages from that model. Subagent models are left alone.
Register PostModelSwitch in the local hook settings so /model switches
inside the TUI update the seed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(claude): honor --model and --setting-sources when seeding the local context window (#1858)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 10:00:12 +08:00
1488be153a feat(cli): add hapi set-mode to change a session's permission mode (#2094) (#2095)
* feat(cli): add hapi set-mode to change a session's permission mode (#2094)

The CLI could only pick a permission mode at launch; changing it on an
existing session required the web UI or a hand-rolled JWT + curl call.

`hapi set-mode <session-id-or-prefix> <mode>` resolves the session like
ping-peer / inspect-peer, validates the mode against the session flavor's
catalog (printing the allowed list on mismatch), and calls the existing
POST /api/sessions/:id/permission-mode route. Active sessions switch live;
inactive ones keep the mode for the next resume.

No MCP tool is added: raising a peer's mode stays behind the agent's
normal shell-approval path.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix: reject Safe Yolo for shared sessions on the permission-mode route

Shared (concurrentClients) Codex sessions cannot launch with safe-yolo.
The web picker hides it, but the route only checked the flavor catalog,
so `hapi set-mode` (or any API client) could store it on an inactive
shared session and break its next resume. Guard the route and apply the
same filter to the CLI's allowed-mode list.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 09:59:25 +08:00
ee8802784d merge: hapi upstream main 2026-10-19 (34 commits past v0.30.7)
Bring in the post-0.30.7 upstream work while keeping local team, macaron,
requirement, DSH and deployment features:

- runner/hub: cross-platform orphan reap on archive and tracking loss,
  machine-spawn preallocated stubs, keepalive-only sessions reconcile to idle
- hub: prepared-statement cache, stale/canceled permission request handling
- cli: Codex compaction announcements, dynamic Kimi models, MCP bridge reap
- web: session toolbar icon shedding, mark-all-read, unread/active sections,
  Russian locale, external-link preference, 48px search chrome
- ios/android: locale and font-size updates

Conflict resolution keeps local-only behavior (agent team spawns, macaron
skins, collapsible sidebar, workspace markdown images) layered on the new
upstream toolbar and session lifecycle plumbing.

Test infrastructure: skip the Docker-only pwsh integration test quickly when
Docker is unavailable, and exclude the Bun-only usageScan test from vitest.

via [HAPI](https://hapi.run)

Co-Authored-By: HAPI <noreply@hapi.run>
Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-10-23 12:44:05 +08:00
7fe397c595 feat(web,cli): load workspace markdown images from the session machine
Local Markdown image paths now resolve through the session file API and
render from a data URL, with loading/failure/retry states and a portal-based
viewer. Out-of-workspace paths show a resend hint; the display_image prompt
tells agents not to emit local-path Markdown images.

via [HAPI](https://hapi.run)

Co-Authored-By: HAPI <noreply@hapi.run>
Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-10-23 11:43:24 +08:00
AnanovoandGitHub 6f155313ff fix(codex): keep status summaries out of intermediate messages (#2041) 2026-10-20 07:21:21 +08:00
wushenghua baeeb11356 fix: preserve deployed session fixes
Persist paged Codex history checkpoints and bounded, acknowledged delivery.
Keep usage sources and accounting across deleted or merged sessions.
Include native Goal controls, faster peer/session queries, and release guards.
Track the complete deployed source so isolated builds cannot omit local fixes.

Validation: all typechecks pass. The full suite reports 7,997 passing tests
and 46 existing failures, each reproduced against the prior commit.
2026-10-08 19:51:45 +08:00
wushenghua cc1fa87bd4 fix(hub,cli): stream large generated media in bounded chunks
A 19MB video download traveled as one ~26MB base64 socket ack. On a remote
runner behind a slow tunnel (measured ~0.35MB/s k2lab->mini) that exceeds
the hub's RPC budget and Bun's HTTP idle cutoff, so the request died with
an empty reply at ~50s (and at ~240s after the first timeout bump).

The route now probes with a 1MB read that reports total size + mime, then
streams the rest chunk by chunk with Content-Length, honours Range/206 for
players and download tools (416 on unsatisfiable ranges), and falls back
to the legacy full payload when the session process predates this change
(it ignores offset/length and reports no size).

Also gives media/files/upload RPCs a 300s budget and raises the hub HTTP
idle timeout to 240s so a slow transfer is not killed while waiting on the
CLI round-trip.
2026-10-01 00:13:38 +08:00
86c88df93b fix(runner,hub): cross-platform orphan reap on archive / tracking loss (#1911)
* fix(runner,hub): reap detached driver CLI on archive and tracking loss

Archive always verifies via stopRunnerSession; runner stopSession scans
argv orphans and awaits webhook-timeout tree-kill so PPID=1 children
cannot accumulate after KillSession miss or map drop.

Fixes #1910

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): keep --hapi-session-id reap-only; test orphan kill path

Claude/cursor swallow the stamp without bootstrap reuse, and
reapRunnerSpawnedOrphans is unit-tested as the stopSession map-miss path.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): address #1911 CI and bot Majors

Use Vitest in orphanReap tests, add Pi session.on mock, refuse archive
when machine StopSession is unreachable, trust full tree-kill results,
and argv-sweep orphans after every mapped stop.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): gate late-webhook kill on timeout orphans; fail closed on scan error

Track webhook-timeout PIDs separately so recovered shared roots are not
killed, and treat ps-list failures as still_alive rather than empty.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): keep shared Codex wrapper alive when archiving one root

StopSession must detach a single shared root without tree-killing the
wrapper PID while sibling roots remain, including after KillSession has
already marked the runtime inactive.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): keep shared Codex siblings after restart tracking loss

Before persisted-PID or argv orphan kills, consult the durable runtime
registry for active sibling roots on the same wrapper PID so archiving
one root after a runner restart cannot tree-kill live shared sessions.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub,cli): deliver hub-authored archive metadata to reconnecting CLIs

When KillSession misses and archive is written via markSessionArchivedFromHub,
emit Socket.IO update-session to the session room. On reconnect, ApiSessionClient
reconciles GET /cli/sessions/:id metadata so hub-archived still fires.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): argv-scan orphans even when shared siblings remain

Remove session-wide early returns that skipped orphan reaping whenever any
shared wrapper had active siblings. Keep only the PID-specific filter so
older untracked CLIs with the same HAPI id are still reaped.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): protect tracked shared wrappers when runtime registry is empty

Argv orphan sweeps must exclude in-memory shared wrapper PIDs that still
host sibling roots, not only durable registry siblings — otherwise a missing
runtime record lets the sweep tree-kill the wrapper while archiving one root.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): adopt untracked nonshared CLIs after runner restart

When a runner-spawned Claude webhook arrives with no TrackedSession (typical
after restart mid-bootstrap), durably adopt the PID instead of ignoring it so
StopSession can reap. Keep killing only nonshared timeout orphans; never kill
shared Codex wrappers on late webhooks.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): keep recovered shared wrappers for registry siblings

After restart adoption tracks only a newly reported Codex root, archiving
it must consult the durable registry before tree-killing the wrapper PID
so older active sibling roots survive.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub): do not archive on KillSession ack when StopSession is unknown

KillSession returns before cleanupAndExit finishes. When the runner cannot
find the PID (unknown), wait for the session KillSession handler to drop
before archiving; refuse if the CLI socket remains reachable.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub,cli): confirm KillSession pid via StopSession before archive

KillSession now returns the CLI pid. When session-id StopSession is
unknown, archive confirms that OS pid (without treating socket loss as
exit) and still refuses when confirmation stays unknown or still_alive.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner,hub): tree-kill adopted CLIs and require PID start markers

Adopted post-restart runner sessions now use killProcessTreeByPid when no
ChildProcess handle exists. KillSession carries a process-start marker so
raw PID confirmation cannot tree-kill a reused OS pid.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner,hub): verify adopted PID markers and hub-archive after stop

Adopted sessions compare the persisted start marker before tree-kill and
drop stale tracking on mismatch. After confirmed StopSession, hub-authors
archive metadata when the CLI did not finish its flush.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): refuse unconfirmed shared/adopted stops

Keep shared wrappers when siblings remain, but return unknown unless
runtimeControl already ended the root. Adopted PIDs without a start
marker no longer tree-kill by tracked PID alone.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): require inactive binding before sibling-kept archive

Siblings alone must not flip StopSession to stopped on retry, while an
acknowledged inactive Codex registry binding remains stop proof. Handle
PID- markers before any tracked kill so reuse cannot nuke strangers.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): distinguish orphan reap from unknown keep-wrapper base

Pass unknown into finishWithOrphanSweep so a successful argv reap stays
stopped instead of being overwritten by an absent registry binding.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): honor orphan reap when adopted PID lacks a start marker

finishWithOrphanSweep with an unknown base lets a successful argv kill
report stopped instead of forcing unknown after the marker probe fails.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub): confirm archive via metadata.hostPid tombstone

When StopSession(sessionId) is unknown and KillSession supplies no
confirmable pid+marker, probe PID-<metadata.hostPid>. already_gone
allows archive; still_alive/unknown still refuse (#1911 Peer #1820).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): escalate Windows taskkill to /F like SIGTERM→SIGKILL

Soft taskkill /T is refused on win32 console trees; orphanReap left
orphans still_alive. waitForProcessToDie now force-escalates on both
platforms so cross-platform reaping matches.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): widen process.kill mock signal to string | number

Match @types/node process.kill(pid, signal?: string | number) so the
Windows taskkill escalation mocks typecheck on tip 54f141368.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): tasklist liveness + immediate /F after soft taskkill refuse

Windows orphan reap still failed in 5ms on Teemo: soft taskkill refused
but escalate waited on an unreliable process.kill(0) probe. Prefer
tasklist for win32 liveness and escalate to /F as soon as the PID is
still live after soft kill.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): coerce win32 ps-list PIDs and escalate soft taskkill to /F

String PIDs from ps-list made Number.isFinite fail so orphan kill
returned still_alive without calling taskkill. Coerce PIDs, prefer
tasklist liveness, and escalate soft taskkill to /F like SIGTERM→SIGKILL.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): Windows orphan scan via CIM CommandLine + taskkill /F escalate

ps-list/fastlist is missing CommandLine and often missing from single-exe
bundles, so Teemo orphan reap returned scan_failed (logged as live PIDs).
List via Win32_Process CIM, coerce PIDs, escalate soft taskkill to /F.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): grace-wait after successful soft taskkill before /F

Escalate immediately only when soft taskkill is refused. When soft
succeeds but the PID is still draining, honor the existing grace period
before force (Codex Major on #1911).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(runner): re-verify start marker before orphan argv tree-kill

Capture getProcessStartMarker after the argv match list, re-check
immediately before killTree, and skip on mismatch/null-while-alive so
PID reuse cannot tree-kill an unrelated process on the orphan fallback.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub): preallocate HAPI id before fresh machine spawn

Fresh POST /machines/:id/spawn omitted existingSessionId, so argv never
got a reap stamp. Preallocate the hub row (fork/clear pattern) and pass
that id so a runner restart before the first webhook remains reapeable.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): close three post-prealloc unreapable paths

Pass --hapi-session-id into Claude/cursor/kimi/copilot bootstrap so the
preallocated hub row is used. Treat null marker re-check while alive as
still_alive (not stopped). Keep the preallocated stub when spawn-fail
StopSession cannot confirm the child is gone.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): adopt-stub via reservedSessionId, not existingSessionId

`--hapi-session-id` binds a fresh create bootstrap to a hub-preallocated
UUID (getOrCreateSession id) without taking the reopen path. Non-UUID
stamps stay reap-only to match hub create schema. Restores integration
spawn invariants broken by mapping hapi→existingSessionId.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): close Opus cold-read B1–B3 for #1911

B1: capture start markers from the same process snapshot as argv
match (POSIX ps lstart / Win32 CreationDate); re-check before kill.
Continue other orphans when one target is unconfirmed.

B2: Windows killProcessTreeByPid verifies every collected descendant,
not root-only — taskkill /T exit 0 is signalled, not gone.

B3: runner sets childStarted:false on pre-exec rejection; hub deletes
the preallocated stub without StopSession. Post-exec ambiguity still
keeps the row until stop confirms. Terminal archives no longer refuse
when no runner is connected.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): explicit adopt for hub-preallocated session stubs

Fresh machine spawn preallocates with tag machine-spawn:<uuid>; CLI
create with a different tag and the same id 409'd on identity conflict.
Add adoptPreallocatedSession (hub-internal stub check) and POST
/cli/sessions { adopt: true, id } so create binds the reserved row and
overwrites tag/metadata without guessing the hub tag. Tests fail-first
on the real prealloc→CLI create path.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): preserve snapshot markers + unify Windows CIM start markers

Runner stopSession was still on findOrphans (PID-only), discarding same-snapshot
markers and reopening the PID-reuse kill window. Switch both call sites to
findTargets. Force UTC ISO 'o' CreationDate for list and single-PID probe so
ConvertTo-Json cannot disagree with getProcessStartMarker on WinPS 5.1.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): exercise production orphan sweep wiring in tests

Extract findStopSessionOrphanTargets as the stopSession discovery path both
run.ts sweeps call. Add tests that drive that helper end-to-end (not an
injected findOrphans seam), assert run.ts source wiring, and cover CIM-list
ISO vs probe ISO agreement plus the broken WinPS shape mismatch.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub,cli): never delete live spawn on RPC timeout; release stub tags

Ambiguous machine-spawn failures (timeout / unset childStarted) no longer
call stopRunnerSession or deleteSession — that path killed healthy late
boots and CASCADE-wiped transcripts. Pre-exec delete still requires a real
machine-spawn stub (store tag check). Metadata updates release the stub
tag so reopen flavors are not permanently adoptable; adopt refuses
archived stubs. POSIX pgrep ENOENT fails closed instead of root-only verify.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): parseable Windows tree scan + fail closed on CIM failure

Space-joined PowerShell for collectWindowsProcessTree was a WinPS parse
error ($seen=@{} $bfs=@()), so every scan fell open to [root] and B2
false-stopped again. Join with newlines; return scan_failed on error/empty;
killProcessTreeByPid refuses root-only verify. Assert on generated command
text (Teemo-confirmed) so mocks cannot hide the next malformed script.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): reopen stamps existing-session-id; scan-fail signals root

Opus Critical on #1911: runner always stamps --existing-session-id for
known hub ids so Claude/Kimi/Copilot reopen does not hit adopt-stub 409.
On pgrep/CIM tree-scan failure still signal the verified root but never
claim stopped. Archive when both KillSession and machine RPC are missing.
Empty Win process-list stdout and strict Codex registry reads fail closed.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): OK: sentinel for Windows tree scan; adopt CAS

CIM failure under SilentlyContinue printed root-only with exit 0 —
byte-identical to a healthy childless tree, so scan_failed never fired
and killProcessTreeByPid false-stopped (#1911 Overseer B1). Require
ErrorActionPreference=Stop, trap exit 1, and an OK: success sentinel;
parse anything else as scan_failed. Same Stop/trap on the machine-wide
list command. Execute the generated scripts under Docker pwsh in CI
when the image is present. Treat pgrep status=null as scan_failed;
coarsen Windows tasklist poll; wrap adoptPreallocatedSession in a
transaction with stub-tag CAS.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): reservedSessionId for fresh prealloc; signal Win survivors

Fresh machine-spawn stubs must not stamp --existing-session-id — that
sends Codex down reopen without a thread binding (#1911 bot Major) and
re-broke local HTTP non-UUID hints as reopen (round-4). Hub passes
prealloc as reservedSessionId; buildCliArgs stamps --hapi-session-id
for reserved/sessionId and --existing-session-id only for live reopen.
Codex parses --hapi-session-id and adopts via bootstrapSession.

Windows tree kill now taskkills surviving pre-scan PIDs after /T misses
broken intermediate links.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): fail-loud Docker pwsh CI; scope Codex registry; stub leak

CI skipped all four windowsProcessTree.pwsh tests on 48bb (image inspect
without pull). Pull the image in test.yml and throw under CI when missing.
Scope strict runtime-registry failure to Codex stop contexts so one bad
JSON cannot block archive machine-wide. Stamp childStarted:false on
machine RPC outside_workspace_roots. Add Codex reservedSessionId prealloc
and runSharedCodex regression coverage for the #1911 Critical.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): single-use reservedSessionId; skip UUID HTTP hints

Consume the machine-spawn reservation on first prepare() so a second
Codex root/fork cannot re-adopt a consumed stub (409). Stop stamping
UUID local-HTTP sessionId as --hapi-session-id (adopt hard-fail). Update
stale hub spawn mocks for the reservedSessionId arity.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub): archive never-started machine-spawn stubs on unknown

Ambiguous keep-stubs (startedBy=runner, no hostPid, still machine-spawn
tagged) made StopSession return unknown forever while the runner was
online, so archive threw permanently. Treat unknown + prealloc stub +
no hostPid as already_gone. Also reject spawn success when the runner
reports a different id than the preallocated stub.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub,cli): refuse dual-RPC-miss archive; generation-check Win survivors

Both KillSession and StopSession missing is not proof a detached CLI exited —
keep the row unconfirmed until the runner reconnects. Windows tree kill now
re-checks process-start markers before individually signalling survivors so
PID reuse is not killed.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): refuse archived reopen in bootstrapExistingSession

Hub-archived rows could be resurrected when a late-booting child hit
--existing-session-id: buildSessionMetadata stamped lifecycleState=running
and updateMetadata overwrote the archive. Adopt already rejected archived
stubs; reopen now matches. Intentional revive still goes through hub
reopenSession first. Correct stub-hatch comment (no post-archive argv sweep).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub,cli): reject un-archive in updateSessionMetadata CAS

Hub-side transactional guard (Discovery #1911 M1): refuse metadata writes
that clear archived lifecycle unless allowUnarchive (reopen clear). Client
stops infinite updateMetadata backoff when mismatch applies archived.
Clear archive immediately before spawn so Pi/PTY attempt snapshots stay valid.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(hub,cli): success+preserve hub archive; M3 reservedSessionId split

Replace version-mismatch refuse (livelock in CAS backoff) with success +
merge-preserve of hub-archived fields unless allowUnarchive. Ack path
routes through noteHubArchived so the CLI exits (criterion 6). Clear-
before-spawn remains the authorized revive. Thread --hapi-session-id to
reservedSessionId for shared-parser flavors (adopt≠reopen).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): fail-closed orphan ps signal; PID- registry; spawn timeouts

Overseer B1: signalled ps (status null) is scan_failed, not empty table.
B2: unreadable registry on PID-* stops returns null (no soft []).
B3: 10s timeout on process/orphanReap spawn.sync. Narrow bootstrap
archived belt to archivedBy=hub to match hub merge-preserve.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli,hub): hubArchived latch; PTY archiveSnapshot durability

Criterion 6: noteHubArchived latches hubArchived so late
registerKillSessionHandler registrations still EXIT (EventEmitter
does not replay). Mirror Pi: persist archiveSnapshot on
ptyResumeAttempt across clear-before-spawn and quarantine, restore
on failed-resume cleanup (#1911 Discovery Majors).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): Codex hub-archived exit; AC6 latch test production order

C2: SharedCodexRoot registers hub-archived (and latch check) beside
its private KillSession — Codex never called registerKillSessionHandler.
C1: keep latch+subscribe; test write-then-register order Discovery proved.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): type Codex hub-archived end mock for tsc

vi.fn(async () => {}) inferred zero-arg calls; RootHost['end']
signature unblocks end.mock.calls[0][0] (TS2493).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cli): catch hub-archived Codex host.end rejection

void this.host.end() discarded archive-RPC failures as unhandled
rejections; Codex has no unhandledRejection handler, so Node can
exit the shared wrapper and kill sibling roots mid-turn.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-25 09:15:08 +01:00
MiroandGitHub b6a27bdc68 fix(kimi): discover configured models dynamically (#1873)
* fix(kimi): discover configured models dynamically

* fix(kimi): address dynamic model review findings

Probe settlement (Major): parse `kimi provider list --json` on the child's
'close' event instead of 'exit', so stdio is fully drained first, and run the
parse inside a guarded settle() helper. A parser throw previously escaped the
promise from an async event callback and reached the runner's uncaughtException
shutdown handler instead of listKimiModelsForCwd's catch. The helper also
settles the promise exactly once across timeout, spawn error and close, names
the terminating signal when there is no exit code, and tolerates a kill() that
throws.

Running-session discovery (Minor): add a session-scoped Kimi catalog. The
shared RPC method `listKimiModels`, a CLI handler registered on the session
connection with the probe cwd taken from the session metadata (never from RPC
arguments), hub rpcGateway/syncEngine pass-throughs, and
GET /api/sessions/:id/kimi-models gated on an active session of flavor `kimi`.
SessionChat now reads the catalog from that endpoint, so an active session
advertises its models even when no background runner holds the machine socket.
New Session keeps the machine-scoped discovery unchanged, and model switching
still goes through the existing ACP set_model path.

* fix(kimi): register session model discovery before the local/remote loop

The session catalog handler was registered inside the remote launcher, after
ACP initialization. A session started with `hapi kimi` in local mode therefore
answered the web picker's request with an unregistered-handler error, and the
failed query was not retried or invalidated when remote control was taken over.

The catalog is backend independent, so it is now registered in runKimi session
setup alongside the other session-level handlers, using the session's working
directory, and the late registration in the remote launcher is removed. This
covers local, remote and resumed sessions on the same session connection.

Adds cli/src/kimi/runKimi.test.ts asserting the handler is registered after
bootstrap and before the loop, and that the probe cwd is the session's working
directory. The launcher wiring assertion moves out of
kimiRemoteLauncher.test.ts with the registration.
2026-09-21 13:58:59 +08:00
wushenghua 51de344c98 feat(hub,cli,web): requirement layer, smart scroll and default-folded AI chatter
- requirements: a fresh human ask opens one automatically (replies inherit);
  tasks and messages carry requirementId (spawn_peer / team_task / team_send
  taskId); the lead closes one with team_requirement (status + conclusion)
- web: the team timeline groups messages into collapsible requirement cards
  (title, status, conclusion, message count; a card with a pending decision
  opens automatically); unassigned messages fall into an 'Other' card
- web: entering a team scrolls to the newest message, follows new messages only
  while pinned to the bottom, and offers a 'jump to latest' button otherwise
- web: AI-to-AI chatter (status/chat/question/task-update, not addressed to the
  human) folds into a one-line summary by default (runs of >= 2), with the
  participants and latest line preview
- tests: requirement store/service coverage and grouping helper tests
2026-09-17 00:27:07 +08:00
wushenghua 5ae0a9f2cf fix(hub,web,cli): only decisions enter the human inbox
to=human alone is an out-of-band notification, not a request for an answer;
the inbox (待你确认) now only contains kind=decision messages (legacy rows
with awaitingHuman still count). Prompts and tool descriptions now tell agents
to use kind=decision when the human must decide and plain broadcasts for
progress they merely need to see.
2026-09-16 23:25:40 +08:00
ca1fd80afd fix(cursor): pin Auto to CLI --model auto instead of account default (#1819)
* fix(cursor): pin Auto to CLI --model auto instead of account default

Selecting Auto was treated as unset/ACP default[] after the Default→Auto rename. Persist and spawn `auto` so the picker matches `agent --list-models`.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cursor): keep live ACP model until Auto actually applies

Pin session.model to auto for the next `--model auto` spawn, but do not claim the live backend switched when ACP only advertises default[].

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cursor): reject live Auto unless ACP auto or spawn confirmed it

Do not persist Auto when the running catalog has no auto option. Clear the spawn-auto flag after a concrete model apply so Auto → concrete → Auto cannot fake a live switch.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cursor): keep ACP wire ids spawn-safe and apply effort

Cursor's parameterized picker (`clientCapabilities._meta.parameterizedModelPicker`)
advertises bare model bases plus separate `fast` / `thought_level` config options.
`buildCursorModelsSnapshotFromAcp` synthesized every base as
`${base}[fast=${fast}]`, and Cursor rejects any bracket id whose parameter set is
not that model's complete set, so 74 of the 76 published picker ids failed at ACP
`session/new` with `Cannot use this model` (#1818).

- Stop synthesizing wire ids: keep the advertised values verbatim (bare bases are
  accepted by `--model`, defaults applied). Parameter sets differ per model, so a
  synthesized id cannot be validated from the options alone.
- Flag such catalogs as `parameterized` so variant CLI skus still attach to their
  base rows — the ACP apply path expresses them through config options.
- Apply effort in `applyParameterizedCursorModel` (ids `effort`, `reasoning`,
  `reasoning_effort`), applied against the config options Cursor re-advertises for
  the newly selected model, and skipped on models without that axis.
- Match CLI sku bases across Cursor's legacy `cursor-` family prefix
  (`cursor-grok-4.6-high` → ACP base `grok-4.6`) so those variant rows are not
  dropped.
- Version the shared on-disk catalog cache (v2) so runners that already cached the
  rejected synthesized ids re-probe instead of serving them.

Verified with live `cursor-agent 2026.09.10-fd3934a` ACP runs: the catalog no
longer contains bracket ids, every advertised base and sampled variant sku spawns,
and in-session `claude-opus-4-8-low` / `cursor-grok-4.6-low` set the matching
`effort`/`reasoning` option.

* test(cursor): cover aliased effort ids and thinking coexistence

Covers the branches the HAPI bot review called out for #1818: the
`xhigh` → `extra-high` alias on `gpt-5.5` (`reasoning`), the
`reasoning_effort` id used by `gemini-3.8-flash`, and switching effort on a
model that also advertises Claude's separate `thought_level` `thinking`
toggle.

* test(cursor): cover legacy sku base and post-switch effort option

Adds the two apply-path cases the HAPI bot review called out for #1818:
resolving `cursor-grok-4.6-high` onto an advertised `grok-4.6` base, and
reading the effort option Cursor advertises for the newly selected model
(`reasoning` for gpt-5.5 → `effort` for claude-opus-4-8) instead of the
previous model's options.

* test(cursor): create the cache dir in the migration test

The version-envelope test wrote $HAPI_HOME/cache/cursor-models.json without
creating the directory, so running it alone (or filtering with -t) failed with
ENOENT before the assertion; it only passed because sibling tests in the same
file had already created the path. Reported in the HAPI bot review of #1822.

Verified: `vitest run ... -t 'ignores pre-versioned'` → 1 passed, whole file → 4 passed,
and every other changed test file passes when run standalone.

* Clarify Cursor Auto live-switch limitation in session pickers

* Reconcile partial Cursor model changes before acknowledging Auto

* Serialize Cursor model changes across clients with the existing async lock

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-16 08:12:16 +08:00
wushenghua 3eca03be18 feat(hub,cli,web): team config inheritance, reply visibility, task loop, scoped tokens
- spawned members inherit the caller's tool/model/thinking level/permission
  (spawn request schema + hub runtime + spawn_peer tool); explicit overrides win
- replies from turns triggered by teammates (not by the human) no longer vanish:
  system prompt and ACP briefs now require an explicit team_send(to=human) for
  human-facing conclusions produced on those turns
- task loop: team_task tool (list/update), dependsOn gating, deliverable evidence
  required when a member marks done, auto broadcast on change, web shows deps and
  deliverable on the task board
- team-scoped agent tokens (hapi_team_*): issued per team, injected as
  HAPI_TEAM_TOKEN at spawn, restricted by the auth middleware to this team's
  messages/tasks/status and audited via [TeamToken] hub log lines
2026-09-16 07:59:58 +08:00
wushenghua 6c2301ae0f fix(cli): keep team prompt tests out of the workspace
teamPrompt tests ran with the real cwd and wrote .hapi/team memory into the
checkout (one charter.md was accidentally committed in ef33332d). Tests now
pass an explicit temp cwd; getTeamPromptBlock/withTeamInstruction accept a cwd.
Drops the stray artifact and ignores .hapi/ in this repo.
2026-09-16 01:28:47 +08:00
wushenghua 073e08ae47 feat(cli): per-team memory dir with legacy migration and gitignore
- team memory moves to <repo>/.hapi/teams/<slug>-<short-id>/ so several teams
  on one repository no longer share (and clobber) a single charter
- the pre-teams/ shared .hapi/team dir is moved into the first team dir that
  starts after the upgrade
- .hapi/ is appended to the repo .gitignore once (idempotent, best effort)
2026-09-16 01:27:43 +08:00
wushenghuaandCodex 388082ccd4 fix(deploy): gate unavailable agents and bound session scans
Co-Authored-By: Codex <noreply@anthropic.com>
2026-09-16 00:54:18 +08:00
wushenghua ef33332dc5 refactor(hub,cli,web): move team memory into the repo (runner side)
Team memory now lives with the code, like CLAUDE.md: <main repo>/.hapi/team/
on the machine where the agent runs. Worktrees resolve to the main repo so
every member shares one directory. The CLI creates charter.md + handoffs/ at
session start (team env only), points the agent at it in the system prompt,
and reports the path in session metadata; the web reads it through the
session file API, so remote runners work too.

Hub keeps only coordination data (teams.db): members/tasks/messages/status.
Its memory-dir management and the /memory API are removed.
2026-09-15 11:40:51 +08:00
wushenghua b76ae314be feat(hub): bridge human<->member replies into the team group chat
Members replied in their own session and the group chat stayed empty,
which read as 'no response'. The hub now records a pending ping when a
human message is pushed to a member, and on the member's next
thinking->idle transition mirrors its last assistant text into the team
log (deduped: skipped if the member answered via team_send).
Prompts updated: normal replies sync to the group automatically; team_send
is for member collaboration and explicit reporting.
2026-09-15 10:34:04 +08:00
wushenghua b59c0608d4 feat(hub,web,cli): add Agent Team (sessions-as-teammates)
Hub
- independent teams.db (own user_version ladder); feature gate default OFF,
  so a disabled hub never creates the file and team routes simply do not exist
- /api/teams: list/detail/by-session/memory/messages/spawn/tasks,
  human message channel, team rename/archive/delete
- team runtime: spawn members via the existing runner RPC (worktree/yolo
  options), peer message routing (mention/dm push, broadcast pull-only),
  budgets (max members, message rate, reply chain depth), member-offline
  announcements that wake the lead or escalate to the human
- team-attention notifications: in-app toast when visible, web push otherwise
- team memory dir {HAPI_HOME}/teams/<id>/ with charter.md template; read-only
  browse API with path-traversal guards

CLI
- MCP tools: team_status / team_read / team_send / spawn_peer (claude, codex
  bridge and ACP flavors); spawn_peer stays behind manual approval
- HAPI_TEAM_* env for spawned members; system-prompt block for Claude/Codex;
  assignment brief carries team rules for flavors without prompt injection
- RUNNER_CAPABILITIES.agentTeam advertised to the hub

Web
- team group chat route with folded peer threads, key/task filters,
  human composer, member/decision/system message cards
- side panel: live member status, interactive task board (create/status/
  assignee), team memory browser, budget
- team create / add-member / settings dialogs; sidebar team section;
  hub settings toggle for the feature (restart to apply)
- SSE team-updated invalidation

Zero impact when disabled: no teams.db, no routes, no tool or prompt changes.
2026-09-15 07:16:57 +08:00
wushenghua db63079cd2 fix: preserve peer queue local ids 2026-09-13 16:36:14 +08:00
wushenghua cb0dbd7d22 chore: rebase local deployment features onto hapi v0.30.3 2026-09-13 15:55:04 +08:00
weishu 0c4abcb3d1 feat(codex): share sessions across terminal and web
Use one native app-server for terminal, Web and phone clients while retaining the existing CLI and Runner lifecycle.

Synchronize native queues, permissions, question history and steering state; preserve explicit permission precedence and per-turn usage models. Resume inactive clear commands through Runner and reject independent child cold resumes.

Add shared-runtime regression tests, generated protocol fixtures and lifecycle documentation.
2026-09-12 10:59:17 +08:00