* fix(acp): derive tool_call input from kind+title fallback
Gemini 2.5 Flash and 3 Flash Preview omit rawInput entirely on
tool_call events while emitting prose (non-JSON) thoughts. Neither
the existing rawInput path nor JSON-thought hoisting fires, so the
UI shows "Input: null" alongside a perfectly readable title like
"README.md" or "ls -la /tmp".
Add a conservative fallback that maps known kinds to a minimal
input shape:
read -> { file_path: title }
execute -> { command: title }
search -> { pattern: title }
think -> null (topic-update prose has no clean arg mapping)
unknown -> null (no guessing on shapes we have not verified)
Priority: rawInput > hoisted JSON thought > kind+title derive.
Lock the new behaviour with synthetic unit tests (8 cases) and a
real-Gemini fixture suite captured from gemini-3-flash-preview
and gemini-2.5-flash via ACP stdio (4 fixtures, 33/27/13/4 raw
sessionUpdate events). The fixtures double as regression guards
against future ACP handler changes.
* fix(web): suppress duplicate subtitle when equal to tool title
Gemini ACP emits a tool_call whose title field is a human-readable
summary (often the verbatim shell command or file path). Combined with
the kind+title input fallback, an unknown-tool card ends up with the
same string in both the title and subtitle slots — e.g. title
"cat /tmp/hello.txt" over subtitle "cat /tmp/hello.txt".
Add a guard in getToolPresentation's unknown-tool branch: emit
subtitle only when it differs from toolName. The known-tool and
mcp__* branches are unaffected.
* test(acp): align Gemini fixtures to current model set
- Drop gemini-2.5-flash fixtures: the captures came from a model that
is not part of the PR's evidence model set, and re-running the
capture is gated on quota that is not currently available.
- Refresh gemini-3-flash-preview read_file / run_shell fixtures with
a fresh live capture so they reflect the latest ACP shape (e.g.
a `kind: think` tool_call expressing reasoning when the model emits
no agent_thought_chunk).
- Update fixture-replay expectations: read_file no longer requires
reasoning chunks (zero are emitted on this path) and now requires
>= 2 tool_calls (think + read).
* feat(web): promote semantic title for Gemini ACP tool cards
When the unknown-tool ToolCard would render the same string as both
the title and the subtitle, promote a semantic label to the title
slot so the card reads like a sentence:
cat /tmp/hello.txt → Run shell / cat /tmp/hello.txt
README.md → Read file / README.md
*.ts → Search / *.ts
This is a web-only ergonomic change; the underlying ACP message
shape (tool_name = title, input = derived from kind+title) is
unchanged. Builds on the dedup guard so the title-equals-subtitle
case is now handled by promotion rather than by hiding the subtitle.
* fix(acp): derive tool_call.input for kind=edit from locations[0].path
Gemini's write_file and replace tools both surface as ACP tool_call
with kind="edit" and rawInput omitted. The path lives on locations[0]
from the very first event; the title is prose like "Writing to foo.txt"
or "foo.txt: old => new", which is not safely usable as a file_path.
Extend the kind+title fallback to read locations[0].path when kind is
"edit", and synthesize { file_path } from it. Title fallback is
intentionally not used here so we never feed prose into file_path.
Lock the behaviour in with two new fixtures captured live from
gemini-3-flash-preview (write_file and replace) plus two synthetic
unit tests covering the locations-present and locations-empty paths.
* test(acp): add gemini-3.1-pro-preview fixtures for regression coverage
Captured 4 raw ACP `sessionUpdate` sequences from a live
`gemini-3.1-pro-preview` session via the same isolated hub +
runner + spawn pattern used for the existing flash captures
(read_file 31 events / run_shell 83 events / write_file 4 events /
edit_file 11 events).
The pro tier reuses the same kind/title shape as flash:
`rawInput` is omitted on every tool_call across read / execute /
edit kinds, so the kind+title (and locations[0].path for edit)
fallback is exactly what derives the modal Input. Locking these
fixtures in guards against future regressions on a second model.
The fixture-based regression test gains 4 entries (read / shell /
write / edit) mirroring the flash matrix; assertions are unchanged.
ACP handler suite: 53 -> 57 pass.
* refactor(opencode): declare ModelChange capability and add model field to OpencodeMode
Mark opencode flavor as supporting model change by adding Capabilities.ModelChange
to FLAVOR_CAPS.opencode. Add optional `model` field to OpencodeMode so the
set-session-config handler can carry a model alongside the existing permissionMode.
Pure structural change: no behavior change yet. The mid-session model change RPC
and UI wiring follow in subsequent commits, gated by this capability.
* feat(acp): branch setModel by flavor, capture session models metadata, expose getSessionModelsMetadata on AgentBackend interface
Adds an optional `flavor` argument to `AcpSdkBackend.setModel` so it can
dispatch the right `session/*` RPC for each agent flavor without changing
the call site Gemini already uses. Both Gemini and OpenCode wire to
`session/set_model`; the OpenCode response only carries `_meta.opencode`,
so the backend updates the cached `currentModelId` optimistically while
preserving the previously captured `availableModels`.
Captures `availableModels` and `currentModelId` from `session/new` /
`session/load` / `session/set_model` responses into per-session metadata,
exposed as `getSessionModelsMetadata(sessionId)` on the `AgentBackend`
interface so the hub can forward the snapshot to the web client.
* feat(opencode): accept model in set-session-config RPC and forward to launcher
Mirror the Gemini set-session-config handler so the web UI can change the
OpenCode model mid-session. Validates incoming model strings, persists null
("Default") for keepalive metadata, and pushes a keepAlive immediately so
the hub UI reflects the change without waiting for the next 2s tick.
Forward the model through opencodeLoop and into queued OpencodeMode entries
so the launcher can detect a per-batch model change. Add a setModel helper
on OpencodeSession to store the chosen model on the shared session base.
Wire --model up the runner path: parse --model <value> in commands/opencode.ts
and stop excluding opencode in buildCliArgs so the runner spawns OpenCode
with the user-selected initial model.
* feat(opencode): switch model mid-session via ACP RPC
Mirror the Gemini pattern from PR #543: when a user picks a different model
between turns, call backend.setModel with flavor='opencode' so the ACP backend
sends session/set_session_config_option (configId='model') to the running
OpenCode CLI. The next turn then runs against the new model.
The first batch on a fresh session seeds currentBackendModel without firing the
RPC — the OpenCode CLI was launched with that model via --model and there is
nothing to switch yet. If the running build does not implement the RPC we learn
that from the first method-not-found response, latch inline switching off, and
notify the user once. Other errors fall back to the previous model and surface
a one-line failure message.
* feat(hub): expose model selection and discovery for OpenCode sessions
Generalize the /sessions/:id/model guard via supportsModelChange so any flavor
that advertises the ModelChange capability becomes accepted automatically. This
piggybacks on the capability SSOT introduced in PR #400 and turns OpenCode on
without listing flavors inline.
Add a /sessions/:id/opencode-models endpoint that mirrors the existing
codex-models pattern. The endpoint forwards a per-session listOpencodeModels
RPC to the running OpenCode launcher, which returns the availableModels and
currentModelId metadata captured from the ACP session/new and
session/set_session_config_option responses. The web UI consumes this to
render the model dropdown without round-tripping ACP itself.
* feat(web): render OpenCode model dropdown in the chat composer
Mirror the Codex pattern in SessionChat: query /sessions/:id/opencode-models
via a new useOpencodeModels hook and feed the result into the composer's
availableModelOptions. The AssistantChat model dropdown now lists the user's
ollama / mlx / OpenCode Zen models with the same provider/model label that the
ACP server reports, so the picker matches the OpenCode TUI.
Stop falling back to the Claude composer model list when the flavor is
opencode and no custom options are supplied — that fallback briefly surfaced
unrelated Claude models in OpenCode sessions before the RPC response landed.
The NewSession flow keeps an empty MODEL_OPTIONS.opencode for now: model
discovery requires an active OpenCode ACP session, so the dropdown becomes
available once the session boots and stays empty (and hidden) at creation
time.
* feat(cli,hub): add cwd-based OpenCode model discovery RPC
Adds a short-lived `opencode acp` probe that runs `initialize` +
`session/new` against a target cwd to read the `availableModels` /
`currentModelId` snapshot, then tears the subprocess down. Results are
cached for 60s per cwd and concurrent probes coalesce into a single
spawn.
Exposes the probe through:
- `listOpencodeModelsForCwd` JSON-RPC handler on the CLI
- `RpcGateway.listOpencodeModelsForCwd` / `SyncEngine.listOpencodeModelsForCwd`
- `GET /api/machines/:id/opencode-models?cwd=...` on the hub
This lets the web NewSession form discover OpenCode models for a chosen
directory before any session is spawned.
* feat(web): add OpenCode model selector to NewSession with loading and default highlight
Adds a `OpencodeModelSelector` panel that the NewSession form swaps in
when the OpenCode flavor is selected. The panel:
- queries the new `GET /api/machines/:id/opencode-models?cwd=...` endpoint
via `useOpencodeModelsForCwd` (TanStack Query, 60s staleTime, no retry),
- shows a labelled spinner + skeleton rows while discovering,
- renders an inline error with a Retry button when probing fails,
- renders an empty-state message when the directory yields no models,
- highlights the OpenCode-reported `currentModelId` with a "Default" badge
and auto-selects it (or the first option) so the form has a sensible
value if the user hits Enter without scrolling.
Selection is reset whenever the agent / machine / directory changes so a
new probe can establish a fresh default. Directory input is wrapped in
`useDeferredValue` so per-keystroke edits do not spawn a fresh
`opencode acp` probe. The chosen model is forwarded on session spawn
via the existing OpenCode `model` parameter.
Adds en + zh-CN locale strings for the loading / failure / empty / retry
/ default-badge labels.
* fix(cli): guard /machines/:id/opencode-models handler with workspace root check
The machine-scoped `listOpencodeModelsForCwd` RPC handler was registered by
`registerCommonHandlers` without any workspace-root check, so a web client
could pass an arbitrary `cwd` and have the runner spawn an `opencode acp`
subprocess plus a `session/new` against that path. That broke runner
isolation, since peer machine-scoped handlers (`list-directory`,
`spawn-happy-session`) already enforce the configured workspace root.
Re-register the handler in `ApiMachineClient` so it reuses the existing
`resolveForWorkspaceCheck` (realpath-based, with missing-tail walking) and
`isWithinWorkspaceRoot` helpers before delegating to the lower-level probe.
The resolved cwd is forwarded down so symlinked-but-contained paths still
work, while traversal attempts are rejected with the same error shape the
peer handlers use. Added unit tests around the new dispatch path. Addresses
HAPI Bot review on PR #558.
* fix(web): gate opencode model discovery on cwd existence
The new-session form previously enabled `useOpencodeModelsForCwd` as
soon as the OpenCode agent, machine, and any non-empty directory string
were present. Because that hook calls `/machines/:id/opencode-models`
and the CLI handler starts an `opencode acp` probe for that cwd, normal
typing through partial paths could launch expensive 30s OpenCode
subprocesses for non-existent directories before the path-existence
result had validated the final cwd.
Reorder NewSession so `useMachinePathsExists` runs before
`useOpencodeModelsForCwd`, then gate the discovery hook on the
directory having been positively confirmed to exist
(`pathExistence[deferredDirectory] === true`). The decision is
factored into a small pure helper `shouldEnableOpencodeModelDiscovery`
so the contract can be unit-tested without provider scaffolding.
* fix(web): keep current opencode model on shortcut without dynamic options
`getNextModelForFlavor` is invoked by the global Ctrl/Cmd+M shortcut in
`HappyComposer`, which is now active for OpenCode sessions because the
agent backend declares the `ModelChange` capability. When the dynamic
OpenCode model list has not yet been loaded — e.g. the user presses the
shortcut before `/opencode-models` returns — the function received an
`undefined`/empty `customOptions` and fell through to the Claude preset
cycler, which would emit `sonnet`/`opus` for an OpenCode session. The
following turn then attempted `session/set_model` with a Claude model id
that no OpenCode provider can serve.
Add an `opencode` branch that returns the (normalized) current model
unchanged when no dynamic options are available, mirroring the existing
empty-list policy of `getModelOptionsForFlavor`. Unit tests cover the
undefined / empty / null-current-model variants and lock the
no-Claude-fallback contract. Addresses HAPI Bot review on PR #558.
When a user selects a different Gemini model from the Web UI mid-session,
the running `gemini --experimental-acp` process kept using the model it
was launched with. The Web UI reflected the new selection, but the next
response was still produced by the original model.
Changes:
- AcpSdkBackend: add `setModel` wrapping the `session/set_model` RPC.
Errors propagate as standard rejections, matching every other
`sendRequest` call in this file.
- geminiRemoteLauncher: detect model changes between turns and call
`backend.setModel` on the live ACP session — no process restart, no
MCP reload. If the running gemini-cli build returns method-not-found,
the launcher learns once, surfaces a single advisory message, then
silently honors the previous model for the rest of the session.
- AgentSessionBase.pushKeepAlive: small helper used by runGemini to
broadcast new config to the hub immediately after `set-session-config`.
- Both layers serialize the switch — the launcher attempts `setModel`
only between batches, and `AcpSdkBackend.setModel` defensively awaits
`waitForResponseComplete()` before issuing the RPC.
Tests:
- New `geminiRemoteLauncher.test.ts` covers: setModel called between
turns when the model differs; not called when unchanged; the
method-not-found capability latch; transient errors continue with the
previous model; setModel is serialized after the prior prompt.
- `runGemini.test.ts` asserts pushKeepAlive fires from the
`set-session-config` handler.
* feat(web): add workspace browser for multi-directory navigation
Add /browse route with a folder browser that lets users navigate
filesystem directories on connected machines and launch sessions
from any folder. Supports saved workspace paths and direct path
input. The "Start Session" action pre-fills the NewSession form.
- CLI: register machine-level `list-directory` RPC handler
- Hub: add POST /machines/:id/list-directory route
- Web: add WorkspaceBrowser component with git repo detection
- Web: add /browse route with navigation from sessions sidebar
- Web: support initialDirectory/initialMachineId in NewSession
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add --workspace-root opt-in scoping for /browse and session spawn
Adds a single new flag, \`--workspace-root <path>\` (with \`~\` / \`~/foo\`
expansion), on \`hapi runner start\` and \`hapi runner start-sync\`.
When set:
- The runner reports the path in machine metadata.
- The list-directory and spawn-session RPC handlers reject paths outside
the root, so the web UI can't escape the configured tree even if
someone crafts a request manually.
- The /browse page in the web UI auto-opens that root, restricts the
breadcrumb / go-up to its subtree, and shows directory entries with
git-repo annotations.
- The /sessions/new form keeps its existing free-text directory input
plus autocomplete + recent-paths chips, and gains a small "Browse"
button (next to the input) that opens /browse for picking a folder.
- Reconnect-time metadata sync ensures stale records get the field
filled in (or cleared when the flag is dropped on a later restart),
so the hub state matches the CLI's intent.
When unset:
- Runner behaves like the legacy hapi (no scoping, no browse feature).
- /browse renders an informative state pointing at the flag instead of
blocking the user.
- The /sessions/new form looks identical to the pre-change behavior;
the "Browse" button is hidden.
Includes a startup banner so \`runner start-sync\` no longer looks like
it hung, and surfaces the workspace-root sync result on stdout.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(hub): preserve workspaceRoot when rehydrating machines from store
MachineCache.refreshMachine() rebuilt the metadata object from an
explicit field allowlist, so any field not in the list (including the
new workspaceRoot) was silently dropped on every read — even though it
was correctly written to the store.
Add workspaceRoot to the zod schema, the Machine interface, and the
hand-rolled projection.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(web): friendlier empty state on /sessions
When there are zero sessions the page used to be a vast blank
rectangle with just the "0 sessions in 0 projects" caption. Render a
centered empty state instead: a calendar/agenda icon, a short heading
and hint, and two buttons — "Start a session" (→ /sessions/new) and
"Browse workspace" (→ /browse).
SessionList gains an optional onBrowse prop. Router wires it on the
sessions page so the secondary button resolves; other callers can leave
it unset to hide that button.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: document --workspace-root flag in cli/README and root README
Add a short paragraph under "Runner management" in cli/README.md
explaining what \`--workspace-root\` enables (scoped /browse tree,
list/spawn enforcement, tilde expansion) and that omitting it keeps
the legacy behavior. Mention the workspace browser in the top-level
README's Features list.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address PR #526 review feedback
Three findings from the review bot:
1. [Major] Workspace-scope check was lexical only. With workspaceRoot
= /safe, a symlink such as /safe/out -> /etc would pass the relative-
path test and let list-directory / spawn-happy-session reach paths
outside the configured root. realpath the workspaceRoot at construction
time, and resolve every incoming path through realpath (walking up to
the nearest existing parent for spawn targets that haven't been
created yet) before the containment check.
2. [Minor] \`hapi runner start --workspace-root\` with no value used to
drop the flag silently and start the runner unscoped. Now treats a
missing or flag-shaped next argument as an error.
3. [Minor] /sessions/new's "Browse" button always opened /browse using
localStorage's last-used machine, ignoring the user's current
selection. NewSession already passes machineId in its callback;
forward it through the /browse search params and seed
WorkspaceBrowser with it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(cli): gate list-directory RPC behind --workspace-root opt-in
Without a configured workspaceRoot, isWithinWorkspaceRoot() returns
true unconditionally, leaving the new list-directory RPC able to
enumerate any path on the runner. The Web UI already hides Browse
for these machines, but the backend should enforce the opt-in too.
Refuse the RPC up front when no workspace root is configured.
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor(agent): extend AgentMessage and CodexMessage unions with reasoning variant
Add a reasoning variant to the shared AgentMessage union that flows
out of the ACP backend, and pass it through to CodexMessage so the
existing web reducer (which already renders { type: 'reasoning' }
parts as collapsible blocks) can consume ACP-sourced thoughts
identically to Codex.
No behavior change yet: the ACP handler still drops thought chunks,
and the remote launchers receive the new variant as a no-op. The
behavior is wired up in the following commit.
* feat(acp): forward agent_thought_chunk as reasoning message
Route ACP thought chunks to the session as reasoning AgentMessages so
OpenCode and Gemini thinking output reaches the web UI's Reasoning
block, matching the existing Codex behavior.
Thought chunks are emitted inline without flushing the pending text
buffer — text and thought live on independent interleave lanes, so
splitting a live text segment on every thought arrival would be
wrong. The inline-emit ordering is documented alongside the test
that depends on it.
extractTextContent is not reused for thought content: its
assistant-audience filter is correct for regular message chunks but
would silently drop thoughts annotated with a non-assistant audience,
which have no meaningful audience to filter against. A direct text
block shape check handles the narrower need.
In the remote launchers, reasoning is surfaced to the local terminal
buffer as a truncated system-role hint prefixed with [Thinking],
matching how the Codex flavor already displays reasoning chunks
in-terminal without mixing them into the assistant reply stream.
* fix(cli): filter raw SSE event JSON from leaking into chat messages
Two types of internal JSON were appearing as visible text in Telegram
Mini App and web chat:
1. `rate_limit_event` — the rate limit parser returned `null` for
unknown statuses, causing raw JSON to pass through as assistant text.
Changed to `{ suppress: true }` so all rate_limit_event variants are
handled; new statuses that need display can be added explicitly.
2. `{ type: "output", data: { ... } }` — internal session metadata
envelopes leaked through the ACP text chunk pipeline. Added an
`isInternalEventJson` filter that catches JSON objects with known
internal envelope types (output, event, queue-operation) before they
enter the text buffer.
Closes#386
via [HAPI](https://hapi.run)
Co-Authored-By: HAPI <noreply@hapi.run>
* fix(cli): narrow internal event filter to match only leaked metadata shape
Address review feedback: the broad type-based filter could suppress
legitimate assistant JSON with type "event" or "queue-operation".
Narrow the check to only match the specific leaked metadata envelope:
{ type: "output", data: { parentUuid, sessionId, userType } }
Add negative tests confirming other JSON types pass through.
via [HAPI](https://hapi.run)
Co-Authored-By: HAPI <noreply@hapi.run>
* fix(cli): suppress malformed rate_limit_event without resetsAt
Address review: rate_limit_event payloads missing resetsAt still leaked
as raw JSON because parseRateLimitText returned null before reaching the
unknown-status suppress. Move the allowed check before the resetsAt
guard and suppress malformed payloads instead of passing them through.
via [HAPI](https://hapi.run)
Co-Authored-By: HAPI <noreply@hapi.run>
* fix(cli): handle parentUuid: null in internal event filter
Root/first-message metadata envelopes have parentUuid: null rather than
a string, so the filter missed them. Accept both string and null.
via [HAPI](https://hapi.run)
Co-Authored-By: HAPI <noreply@hapi.run>
* test(cli): add e2e regression tests for metadata envelope filtering
Add AcpMessageHandler tests that verify leaked { type: "output", data }
metadata envelopes (both parentUuid string and null) are dropped before
reaching the text buffer.
via [HAPI](https://hapi.run)
Co-Authored-By: HAPI <noreply@hapi.run>
* fix(cli): clear buffered prefix when cumulative metadata chunk arrives
When a leaked metadata envelope arrives as cumulative streaming chunks
(first an incomplete JSON prefix, then the full blob), the filter
dropped the full chunk but left the prefix in bufferedText. Clear the
buffer when the detected internal JSON starts with the buffered prefix.
via [HAPI](https://hapi.run)
Co-Authored-By: HAPI <noreply@hapi.run>
* fix(cli): round resetsAt to integer for pipe-delimited format
The web-side regex uses \d+ to parse the timestamp, so a float value
would silently fail to match. Apply Math.round to ensure integer output.
via [HAPI](https://hapi.run)
Co-Authored-By: HAPI <noreply@hapi.run>
* fix(cli): clear buffered prefix for cumulative rate_limit_event chunks
The prefix-clearing logic only applied to the isInternalEventJson
branch but not to the parseRateLimitText branch, so cumulative
rate_limit_event chunks could leave a raw JSON prefix in the buffer.
Hoist the prefix check before both filters and apply uniformly.
Add regression tests for suppressed and displayable cumulative
rate_limit_event scenarios.
via [HAPI](https://hapi.run)
Co-Authored-By: HAPI <noreply@hapi.run>
---------
Co-authored-by: HAPI <noreply@hapi.run>
* refactor(web): extract normalizeTimestamp helper in presentation
Extract the shared seconds-vs-milliseconds normalization logic into
a private `normalizeTimestamp()` helper. No behavior change —
`formatUnixTimestamp()` produces identical output.
* refactor(web): return AgentEvent from parseClaudeUsageLimit
Change return type from `number | null` to `AgentEvent | null` so
the caller doesn't need to construct the event object. No behavior
change — the same `limit-reached` event is produced.
* feat(cli): convert rate_limit_event to standardized text format
Parse undocumented Claude `rate_limit_event` JSON in the CLI adapter
layer (AcpMessageHandler) before it reaches the web.
Converted text format (pipe-delimited):
- "Claude AI usage limit warning|{ts}|{pct}|{rateLimitType}"
- "Claude AI usage limit reached|{ts}|{rateLimitType}"
Status handling:
- `allowed_warning` → warning text with utilization and limit type
- `rejected` → reached text with limit type
- `allowed` → silently suppressed (noise)
- unknown statuses → passed through as-is (forward-compatible)
* feat(web): display rate limit warnings with limit type
Parse standardized pipe-delimited text from the CLI adapter into
`limit-warning` and `limit-reached` events, displaying the rate
limit type (5-hour, 7-day) when available.
- `limit-warning`: "⚠️ Usage limit 90% (5-hour) · resets 2:00 PM"
- `limit-reached`: "⏳ Usage limit reached (5-hour) until 4/2/2026"
- Backward compatible: `limit-reached` without limitType still works
The `reached` regex uses `(?:\|([^|]*))?$` to optionally match the
limitType field, maintaining compatibility with the existing format.
* refactor(cli): move rate limit parsing out of flushText
Remove rate limit detection from flushText() back to plain buffer
flush. The next commit will re-add parsing at the chunk level
(handleUpdate) where it can intercept before buffer merging.
Includes failing tests that demonstrate the mixed-chunk bug:
when a rate_limit_event chunk arrives in the same turn as normal
text, the JSON leaks into the merged buffer.
* fix(cli): intercept rate_limit_event at chunk level, not flush
Move rate limit detection from flushText() to the agentMessageChunk
handler so it fires before the chunk enters the shared text buffer.
Previously, a rate_limit_event chunk arriving in the same turn as
normal text would merge into bufferedText and leak as raw JSON.
Now the chunk is intercepted individually, the existing buffer is
flushed first (preserving prior text), and the converted message
is emitted separately.
* fix(cli): skip flush when suppressing allowed rate_limit_event
Only flush the text buffer when the parsed event will actually be
displayed. Suppressed events (e.g. status: 'allowed') now return
immediately without flushing, preventing a text → allowed → text
sequence from splitting one answer into two agent-text blocks.
* fix(web): include limitType in limit-reached reconcile key
Without this, reprocessing a message from the old format (no
limitType) to the new typed format reuses the stale block and
the (5-hour)/(7-day) suffix never appears.
Move duplicate isObject, asString, asNumber, and safeStringify functions from multiple modules into a centralized shared/src/utils.ts module and update imports across cli, server, and web packages. This eliminates code duplication and improves maintainability.
- AcpStdioTransport: Fix stdout JSON validation to filter non-object JSON (numbers, strings, booleans) that could break protocol
- AcpStdioTransport: Add request timeout with 2-minute default, properly cleared on settle, using unref() for graceful shutdown
- AcpStdioTransport: Add stderr error parsing for rate limit (429), model not found (404), auth errors, quota exceeded
- AcpSdkBackend: Add initialization retry mechanism using withRetry() for initialize and session/new (3 attempts, 1-5s backoff)
- AcpSdkBackend: Add waitForResponseComplete() for safe session swaps and preventing race conditions
- AcpSdkBackend: Add onStderrError() handler and processingMessage getter for error reporting
- AcpSdkBackend: Use Infinity timeout for session/prompt to support long-running tasks
Consolidates duplicate cleanup, signal handling, and state management logic from
runClaude and runCodex into a reusable createRunnerLifecycle factory function.
Extracts mode switching handler and controlled user state updates into utilities.
Adds runLocalRemoteSession wrapper to handle session ready callbacks in loop base.
Implements bidirectional sync of permission/model modes between CLI sessions and web app. Adds Codex-specific permission modes (read-only, safe-yolo, yolo) alongside Claude's modes. Web can now control CLI session state via RPC set-session-config handler, while CLI broadcasts state changes through keep-alive payloads. UI controls are flavor-aware, showing appropriate modes for Claude vs Codex vs Gemini. Type centralization in api/types eliminates circular dependencies.
Implement comprehensive worktree session support allowing users to spawn sessions in temporary git worktrees. Includes backend worktree management, full-stack integration, and refined UI for session type selection.
Backend:
- Add worktree creation/removal utilities with branch management
- Track worktree metadata (basePath, branch, name, path) in session metadata
- Automatic cleanup of worktrees when sessions fail or exit
- Enhanced error handling with stderr tail logging
UI improvements:
- Redesign session type toggle with improved alignment and spacing
- Move worktree description inline with label for cleaner layout
- Add branch name input field that appears when worktree mode selected
- Auto-focus on worktree input when switching modes
- Reduce gap between radio options from gap-3 to gap-1.5
- Update descriptive text and placeholders for clarity
Integration:
- Thread worktree parameters through API client, RPC handlers, and daemon
- Add worktreeEnv utility to read worktree info from environment
- Update session spawning to support both simple and worktree modes
Remove HAPPY_GEMINI_ARGS and HAPPY_GEMINI_COMMAND environment variables.
Refactor gemini.ts to export registerGeminiAgent(yolo) function that
directly configures args instead of reading from environment.
Consolidate process lifecycle management (kill, check alive) into a new
utility module with proper Windows/Unix handling, replacing scattered
process.kill() calls with consistent async APIs.
Added helpful error messages with cause preservation when spawning codex, gemini, or other CLI tools fails because the binary is not found in PATH. This follows the existing error handling pattern from claudeLocal.ts.
Adds a dedicated hook server infrastructure to receive Claude SessionStart
notifications. This allows the CLI to track session ID changes (new sessions,
resume, compact, fork, etc.) without relying on file watchers.
Changes:
- Add SessionFound callback system to AgentSessionBase for session tracking
- Create hook server that listens for POST requests from Claude's hooks
- Generate temporary settings files with hook command configuration
- Implement session hook forwarder CLI command to relay hook data
- Integrate hook server into runClaude with proper cleanup
- Pass hookSettingsPath through local and remote execution paths
- Update SDK query builder to support --settings flag
