Commit Graph

1267 Commits

Author SHA1 Message Date
Mohamed Boudra
e22b497a08 voice: quieter thinking tone, log cleanup, and small ui polish
- Add scripts/lower-thinking-tone.mjs to scale the thinking-tone PCM
  amplitude in-place; apply it at 0.1 so the cue is a soft indicator
  instead of triggering the VAD via mic feedback.
- Drop the "Received first voice_audio_chunk" log that re-fires every
  summary window because the chunk counter is reset.
- Match Spoke message icon and label sizing to the standard tool-call
  badge.
- Append a spoken-input instruction so voice replies route through the
  speak tool.
2026-05-05 19:56:51 +07:00
Mohamed Boudra
91865ba66e Switch voice turn controller to streaming transcription 2026-05-05 19:56:51 +07:00
Mohamed Boudra
4d31cd4013 fix(opencode): forward provider retries instead of swallowing them
OpenCode subproviders (e.g. opencode/kimi-k2.6 on OpenCode Zen) emit
session.status:retry events with messages like "Internal server error"
when the upstream provider returns 5xx. opencode itself retries
indefinitely with backoff and never emits a terminal event for these.

Previously the adapter only surfaced retry messages on a small allowlist
of "fatal" tokens (insufficient balance, invalid api key, etc.) and
silently dropped everything else. The agent appeared hung from the
user's perspective — no message, no spinner update, nothing — until the
upstream eventually recovered or the user manually interrupted.

Forward every session.status:retry as a non-terminal timeline error
item so the user can see what opencode is doing, mirroring opencode's
own TUI. Drop the fatal-token allowlist: classifying which retries are
"really" terminal is opencode's job, and synthesizing turn_failed for
ones we guess at is misleading anyway because opencode keeps spending
upstream while we tell the user the agent is done.

Also a small design pass on the timeline error rendering:
- drop the redundant "Agent error" prefix (the message is descriptive)
- drop the colored box background (visual weight too high for a retry)
- align the icon vertically to the first text line (height+center)
- make the message text selectable so users can copy errors
2026-05-05 19:56:51 +07:00
Mohamed Boudra
0775f59a6f Add --mode to schedule and loop CLI, default background runs to unattended mode
Plumb --mode/--verify-mode through paseo schedule create and paseo loop run.
Mark each provider's unattended mode (claude bypassPermissions, codex/opencode
full-access, copilot autopilot) so loop and schedule services pick it by
default when no explicit modeId is given.
2026-05-05 19:56:26 +07:00
Mohamed Boudra
4cd9e76bd2 Remove unnecessary type assertions across codebase
Add oxlint-tsgolint and configure typescript/no-unnecessary-type-assertion
to flag redundant `!` and `as Foo` casts. Type-aware mode is left off by
default to keep `npm run lint` fast; the rule sits configured for when we
turn type-aware on intentionally. Auto-fix removed ~283 redundant casts;
two manual touch-ups: a real tsgolint false positive in split-container.tsx
and a stale ChildProcess import after a double-cast collapsed.
2026-05-05 19:56:26 +07:00
Mohamed Boudra
78fe3e4df3 Drop subagent task notifications from parent timeline
Subagent task_notification system messages arrive without
parent_tool_use_id but with tool_use_id pointing at the parent's Task
call, so they slip past the sidechain router and render as top-level
"Task Notification" rows in the parent's timeline. Skip them when the
referenced tool_use is a Task call; parent-level background bash
notifications still flow through.
2026-05-05 19:56:26 +07:00
Mohamed Boudra
1e5e17f000 chore(release): cut 0.1.69 2026-05-05 19:40:12 +07:00
Mohamed Boudra
fd4e26ca9b Align script TypeScript lib with server build 2026-05-05 18:54:29 +07:00
Somasundaram Ayyappan
f89e5604d2 fix: normalize Claude AskUserQuestion answers (#755) (#760)
Translate Paseo's header-keyed AskUserQuestion answers into the full question-text keys Claude expects before resolving question permissions.

Also preserve the original question payload when UI callbacks return an answers-only updatedInput, and lock the behavior down with provider-flow regression coverage in claude-agent tests.
2026-05-05 19:50:34 +08:00
Mohamed Boudra
ca3e55813e Keep daemon worker supervision explicit 2026-05-05 18:48:07 +07:00
Mohamed Boudra
3fad128d02 Restart daemon worker crashes in production 2026-05-05 18:42:21 +07:00
Mohamed Boudra
0cb9da17cd Daemon hardening epic 2026-05-05 18:21:10 +07:00
Mohamed Boudra
84478a2dba chore(release): cut 0.1.68 2026-05-05 16:46:10 +07:00
Mohamed Boudra
15a2e3bdcb chore(release): cut 0.1.67 2026-05-04 01:43:24 +07:00
Mohamed Boudra
cf1f849b68 Update MCP create_agent test to match async branch auto-name
7c85341a moved first-agent branch auto-naming out of the worktree
service (sync slugify) into the workflow layer (async LLM call).
The MCP test stubs createPaseoWorktree, bypassing the workflow,
so the placeholder mnemonic branch is never renamed at this layer.
Replace the obsolete sync-slugify outcome assertion with a
placeholder-presence check; the auto-name logic itself is covered
in worktree-branch-name-generator.test.ts.
2026-05-04 00:31:33 +07:00
Mohamed Boudra
12fcfe53eb Make structured response generation ephemeral end-to-end
Plumbs persistSession through the structured response pipeline so
metadata, branch name, commit message, and PR text generators no
longer leave provider-side artifacts behind:

- Codex: passes ephemeral: true on thread/start (no rollout file)
- OpenCode: deletes the session via session.delete on close
- Claude: forwards persistSession: false to the SDK query

Adds a real-credentials e2e test per provider that asserts the
generated title is applied AND no persistence artifact is produced
(rollout for Codex, project JSONL for Claude, leftover session for
OpenCode).
2026-05-04 00:10:50 +07:00
Mohamed Boudra
7c85341a42 Fix worktree creation and archive flow
Server: drop the synchronous branch-name generator dep, use the
worktree slug as the initial branch, and move first-agent branch
auto-naming to an async post-creation step backed by a structured
LLM call. Guards against renaming when the placeholder branch has
already been changed.

App: make workspace and worktree archive optimistic, rolling back
the local hide if the daemon call fails, and suppress incoming
workspace upserts while an archive is pending.
2026-05-03 23:22:54 +07:00
Mohamed Boudra
221b6665a0 chore(release): cut 0.1.66 2026-05-03 20:48:53 +07:00
Mohamed Boudra
0aa4868b31 Fix terminal DSR replies 2026-05-03 19:24:30 +07:00
Mohamed Boudra
38c1b08433 chore(release): cut 0.1.65 2026-05-03 17:20:28 +07:00
Mohamed Boudra
2faacc59f1 chore(release): cut 0.1.65-beta.5 2026-05-03 13:58:46 +07:00
Mohamed Boudra
65cfe4bda4 Reduce agent timeline focus catch-up 2026-05-03 13:57:48 +07:00
Mohamed Boudra
fa20f313d3 Simplify workspace reconnect gating 2026-05-03 13:50:20 +07:00
Mohamed Boudra
b2247450f9 Fix terminal snapshot flushing 2026-05-03 13:25:19 +07:00
Mohamed Boudra
d89ecae615 fix(server): clean up OpenCode process trees
Spawn the shared OpenCode server in its own POSIX process group and terminate provider child process trees with graceful timeout escalation before forcing SIGKILL. Reuse the same helper for Codex app-server cleanup so process-tree behavior is covered consistently across providers.

Add cross-platform unit coverage for macOS/Linux process groups, Windows taskkill cleanup, and timeout escalation. Add the process-tree test to the Windows-critical CI allowlist; Linux full server tests already include it.

Refs #227
2026-05-02 21:44:59 +07:00
Mohamed Boudra
d06e3e9494 chore(release): cut 0.1.65-beta.4 2026-05-02 20:41:37 +07:00
Mohamed Boudra
b7802ae271 chore(release): prep 0.1.65-beta.4 changelog
Update CHANGELOG.md in place per beta policy and add a compat note on the
`sub_agent.actions` field flagging it as drop-on-cleanup once clients
<= 0.1.65-beta.3 are out of the field.
2026-05-02 20:40:41 +07:00
Mohamed Boudra
d53d601043 refactor(server): inline client capability parsing
With capability negotiation in place, the consumer-side tolerance pattern is unnecessary. Drop the dead readDeclaredClientCapabilities helper, inline the parsing in ClientCapabilities.fromHello, delete a tautological assertion in the relay reconnect test, and document the compatibility rules in architecture.md.
2026-05-02 20:30:25 +07:00
Mohamed Boudra
ca318f29cf feat(client): advertise reasoning merge capability 2026-05-02 20:30:25 +07:00
Mohamed Boudra
ee1c7e6956 test(server): pin wire compatibility regressions 2026-05-02 20:30:25 +07:00
Mohamed Boudra
e3e1c08525 fix(server): restore wire compatibility for old clients 2026-05-02 20:30:25 +07:00
Mohamed Boudra
906205f97a Add browser pane element picker (#670)
* feat: add browser pane element picker

Port the browser pane from PR #198 and route picked elements through workspace attachments so the context follows every agent composer in a workspace.

Co-authored-by: Jason Kneen <jason.kneen@bouncingfish.com>

* docs: document electron platform overlays

* fix: harden browser pane navigation

* fix: polish browser tab interactions

* fix: route browser pane focus shortcuts

---------

Co-authored-by: Jason Kneen <jason.kneen@bouncingfish.com>
2026-05-02 19:28:40 +08:00
Mohamed Boudra
49e3011a28 Render sub-agent activity from log 2026-05-02 17:20:22 +07:00
Mohamed Boudra
771f164e26 Stream Codex sub-agents as tool calls (#672) 2026-05-02 17:08:07 +08:00
Mohamed Boudra
ce8dc46054 refactor(server): extract provider turn runner (#668)
Claude, Codex, OpenCode, and ACP each reimplemented the same `run()`
orchestration: pre-start event buffering, turn-id filtering, terminal
event settling, timeline collection, and final-text reduction. Hoist
the loop into `provider-runner.ts` with a small adapter (startTurn,
subscribe, getSessionId) and pluggable final-text reducer.

Net -252 lines across the four providers. Also fixes a latent bug
where a `turn_failed` emitted before startTurn returned was buffered
and silently swallowed instead of rejecting the run.
2026-05-02 15:45:08 +08:00
Mohamed Boudra
6225ec3008 refactor(server): extract foreground run state from agent-manager (#666)
Centralize pending-run, waiter, and finalized-turn bookkeeping in a
new ForegroundRunState module so streamAgent, replaceAgentRun,
cancelAgentRun, reload/close, and stream dispatch share one
coordinator instead of hand-rolling the lifecycle in five places.
2026-05-02 15:34:47 +08:00
Mohamed Boudra
26737d3d70 refactor(server): extract WorkspaceDirectory from session.ts (#667)
Move workspace descriptor map building, fetch_workspaces filtering /
sorting / cursor paging, and archiving overlay state out of the Session
god class into a dedicated WorkspaceDirectory module.

Session keeps thin delegation methods so existing tests and callers see
the same surface; cursor errors are still mapped to SessionRequestError
at the session boundary.
2026-05-02 15:34:19 +08:00
Mohamed Boudra
da85814940 fix(server): apply get_agent_activity limit to projected entries
The MCP get_agent_activity tool sliced the raw timeline before passing
to the curator, so `limit: 5` could land mid-message and return a
trailing fragment of streamed assistant text. Now goes through the
existing projection pipeline so the limit counts whole projected
entries — assistant deltas merged, tool calls collapsed by callId,
reasoning chunks merged.

Same bug fixed in the wait_for_agent timeout's "Recent activity"
preview, which used the same raw slice.

Consolidates the merge logic: activity-curator no longer ships its own
collapseTimeline, it delegates to projectTimelineRows. One source of
truth for "what is a complete message".

Drops the meaningless `provider` parameter that was threaded through
the projection module — merge logic never branched on it. The wire
schema keeps `provider` per entry; session stamps it once at the emit
boundary. Adds `reasoning_merge` to the projection kind enum (additive
wire change).
2026-05-02 14:24:45 +07:00
Mohamed Boudra
03e54a1a21 refactor(server): extract terminal stream router from daemon-client (#665)
Move slot map, listener fanout, binary input encoding, and stream-frame
decoding out of daemon-client.ts into TerminalStreamRouter so the
4.5k-line client no longer owns that bookkeeping. Public DaemonClient
API and on-the-wire behavior unchanged.
2026-05-02 14:56:35 +08:00
Mohamed Boudra
bb889dae99 feat: stream files as binary frames over WebSocket (#659)
Replace base64-in-JSON file transfers with binary WebSocket frames to
unblock the JS thread when assistant markdown messages contain images.
Receive cost (JSON.parse over multi-MB base64) and persist cost (base64
re-encode to disk) both removed.

- Split daemon-client `exploreFileSystem` into `listDirectory` + `readFile`;
  `readFile` returns `{ bytes, mime, size, modifiedAt }`. Encoding stays
  private to the seam.
- New `packages/server/src/shared/binary-frames/` module hosts terminal
  frames (moved from `terminal-stream-protocol.ts`) and new file-transfer
  opcodes (`FileBegin` / `FileChunk` / `FileEnd`) with request-id correlation.
- Add optional `acceptBinary` to `FileExplorerRequestSchema`. New daemons
  emit binary frames when set; legacy JSON path remains for old clients.
  Compat fallback lives only inside `readFile`.
- New `persistAttachmentFromBytes` writes bytes directly: native via
  `expo-file-system` `File.write(Uint8Array)`, web via Blob -> IndexedDB,
  desktop via new `write_attachment_bytes` IPC. `persistAttachmentFromBase64`
  removed.
2026-05-02 14:02:27 +08:00
Mohamed Boudra
b6c43088fb test(server): align worktree tests with explicit PR context 2026-05-02 12:49:31 +07:00
Mohamed Boudra
fdc510d3a0 feat(opencode): add subagent timeline support (#658)
Map OpenCode `task` tool events into the existing sub_agent timeline shape,
enabling live activity tracking for OpenCode subagent sessions.

- Add `childSessionId` (optional) to sub_agent schema
- Make `actions` optional with default [] for backward compatibility
- Parse task tool input/output into sub_agent detail (tool-call-detail-parser)
- Track child session linkage and buffer/flush child tool parts
- Render sub_agent actions and session IDs in the app component
- Add glob tool detail mapping
- Include backward-compat schema test

Co-authored-by: Ryan Swift <ryan@mlh.io>
2026-05-02 13:19:42 +08:00
Mohamed Boudra
2f177dde7a fix(server): rename worktree branches from prompt + attachments
Replace top-level `attachments` and `nameContext` on `create_paseo_worktree_request` with `firstAgentContext: { prompt?, attachments? }`, the single signal driving auto-rename. Drop the `worktreeSlug || …` short-circuits so a random placeholder slug no longer blocks renaming, drop the attachment-as-PR fallback in favor of explicit `githubPrNumber`, and reshape the MCP `create_worktree` tool around a `target` discriminated union (`branch-off` / `checkout-branch` / `checkout-pr`) with concise field descriptions so callers stop misreading `prompt` as a name field.
2026-05-02 12:12:44 +07:00
Ryan Swift
3dae11d292 fix(opencode): include all-mode agents in mode picker (#606) 2026-05-02 12:46:27 +08:00
Mohamed Boudra
4173ac0ca0 refactor(server): extract SortablePager for generic pagination 2026-05-01 23:20:23 +07:00
Mohamed Boudra
9954eefdee refactor(server): extract TerminalSessionController from session.ts
Moves terminal RPC, binary streaming, slot allocation, and exit-subscription
bookkeeping out of the 9.7K-line Session class and into a dedicated controller
with a small facade (dispatch, handleBinaryFrame, killTerminalForClose,
killTerminalsUnderPath, dispose, getMetrics). Session loses 7 fields and 22
methods (-651 LOC) and the cluster's invariants now live next to their state.
2026-05-01 23:05:47 +07:00
Mohamed Boudra
9800203a48 refactor(server): collapse tool-call mapper pass2 zod dance
Replace the duplicated 3-stage Zod pipeline (pass1 -> pass2 envelope
union -> pass2 discriminated union) in each provider mapper with a plain
resolveToolKind(name) function over readonly name sets. Opencode's
toolKind was unused; Claude/Codex used it only as a switch discriminator.
2026-05-01 22:53:14 +07:00
Mohamed Boudra
14d78327c3 refactor: extract tool call status normalization 2026-05-01 22:47:01 +07:00
Mohamed Boudra
6eab2a89e9 refactor(server): extract pagination cursor codec 2026-05-01 22:30:12 +07:00
Mohamed Boudra
c3d2129472 refactor(server): extract AgentActionResponsePayloadSchema
Five set_agent_*_response and update_agent_response payloads were
pixel-identical. Share one named schema so the concept is explicit and
new agent-action responses don't copy-paste the same four fields.
Wire format and inferred types are unchanged.
2026-05-01 21:22:00 +07:00