* feat(agents): add per-agent runtime skill controls
Co-authored-by: multica-agent <github@multica.ai>
* fix(agents): renumber runtime-skill migration and broadcast agent:status on toggle
Address the MUL-5101 review blockers on PR #5686:
- Rebase onto main and renumber the runtime-skill-disable migration
202 -> 203. main added 202_runtime_profile_add_qwen, so the pair
collided on prefix 202 and migrations_lint_test would reject the
duplicate. 203 is the next free prefix.
- Publish an "agent:status" event after persisting a
disabled_runtime_skills override, mirroring the workspace-skill toggle
in writeUpdatedAgentSkills. The realtime layer keys off this event to
invalidate workspaceKeys.agents, so other open web/desktop/mobile
clients now drop their stale toggle state instead of only the
initiating tab refreshing. Reload junction-table skills before the
broadcast so it doesn't signal cleared skills (#3459).
- Add a handler regression test proving the broadcast fires on both
disable and enable.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
Co-authored-by: Walt <walt@multica.ai>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(daemon): gate fresh-session retry on tools executed, not session id (MUL-4966)
Switching provider accounts leaves the stored session id pointing at a
conversation the new account does not own. The daemon still passes it to
--resume, the provider rejects it, and the task dies before doing any work.
The existing fresh-session fallback was supposed to catch this but was
gated on `result.SessionID == ""`, which is not a lifecycle fact:
- Too narrow: a backend that echoes the requested id back when it rejects
a resume keeps SessionID non-empty, so the fallback never fired — the
reported bug.
- Too broad: a provider 401 before the first stream message also leaves
SessionID empty, so an unrecoverable auth failure burned a second full
run.
Gate on `tools == 0` instead. That states the property that actually makes
a retry safe — the agent executed no tool, so it mutated nothing, so
re-running cannot double-post a comment (comment creation has no
idempotency key and a duplicate re-fires its @mention triggers), reopen a
PR, or re-plan on top of its own half-finished work in the reused workdir.
Auth failures are excluded, mirroring retryableReasons in service/task.go.
The predicate is extracted to shouldRetryWithFreshSession so the tests
exercise production logic; both existing fallback tests re-implemented the
condition inline and would not have caught a regression in it.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): gate fresh-session retry on a positive resume-rejected signal (MUL-4966)
Review of the previous commit was right: `tools == 0` plus "not an auth
error" answers whether re-running is *safe*, not whether a new session can
*fix* the failure. Those are orthogonal, and answering the second by
exclusion inverts the burden of proof — the failures a fresh session cures
are a small enumerable set, while the ones it cannot are open-ended.
Concretely, the previous predicate fresh-retried on provider_network,
429/529, quota, 5xx and unclassified startup failures. provider_network is
the sharpest conflict: internal/service/task.go marks it resume-safe
(MUL-4910) specifically so the platform retry inherits the session and
continues the truncated conversation. Resetting the session first made that
contract unsatisfiable, silently discarding conversation context on a
transient blip — and rate limits got an immediate no-backoff re-run.
Replace the inference with positive evidence: agent.Result gains an explicit
ResumeRejected field, set only when a backend has proof the resume itself
was refused. claude/codebuddy/qwen derive it from resumeWasRejected, which
promotes the predicate resolveSessionID was already computing and encoding
as the side effect of blanking SessionID — using an empty string to carry
that meaning is what made the original bug possible. SessionID keeps being
dropped for a rejected resume (a dead pointer must not be persisted), but it
is no longer the signal the daemon reads to decide *why* a run failed.
The six ACP backends that recover from "session not found" set the flag at
the same points they already clear the id, so their existing recovery is not
caught by the narrower gate. codex needs nothing: thread/resume already falls
back to thread/start in-process, and deliberately does not on transport
errors.
Matching now includes the account-switch guardrail reported in #5704
(Claude Code 2.1.207, zh-CN): "400 此 session 已绑定另外的ai账号，请执行
/new 开启新 session". The en-US wording of the same guardrail has not been
captured yet, so those variants are marked inferred in the source; a miss
degrades to a terminal failure carrying the provider's raw text rather than
a mis-routed run.
Tests: backend-level fixtures drive ResumeRejected from real stream-json for
both the account-binding 400 and a network drop, and the predicate now
covers network/rate-limit/quota/5xx/auth/unclassified as explicit
non-retries.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): restore fresh-session recovery for backends with no rejection signal (MUL-4966)
Final review caught qwen regressing: its verified rejection string
("No saved session found with ID ...", already captured in
testdata/qwen-code-0.20.0-resume-not-found.stderr.txt) was not in the phrase
list, and qwen reports no session id on that path, so the new inclusion gate
turned a working auto-recovery into a terminal failure.
Auditing the other 17 resume-capable backends showed qwen was not alone.
antigravity, copilot, cursor, deveco and opencode all recovered from a
refused resume purely by reporting an empty SessionID, and none of them has
any rejection detection to convert into ResumeRejected — copilot's own
comment documents the hole (session.error before session.start), and
antigravity's helper returns "" when "the CLI exited before dispatching".
Making ResumeRejected the sole gate silently removed recovery from all five.
Fixing that by guessing rejection phrases for five more CLIs is the wrong
trade: no real output has been captured for any of them, and a false
positive discards a recoverable session pointer. So the gate is now two
tiers. Positive evidence (ResumeRejected) decides on its own where a backend
can produce it. Where none is available, an empty SessionID still gates the
retry — it proves no session was established, which is exactly what the
pre-change behaviour relied on — minus the classes a fresh session provably
cannot cure (network, rate limit, quota, provider 5xx, auth). That keeps the
resume-safe contract in internal/service/task.go intact while restoring what
these five backends had.
Also renames claudeResumeRejectedPhrases to resumeRejectedPhrases: it is
matched by claude, codebuddy and qwen, so a qwen-only string living under a
claude-prefixed name would be actively misleading.
Tests: qwen's existing missing-resume fixture now asserts ResumeRejected
(verified failing without the phrase), and the predicate covers the
no-signal tiers — retry when nothing was established, no retry once a
session exists or the failure classifies as uncurable.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): scope the no-signal fallback to backends that cannot detect rejections (MUL-4966)
Final review caught the compatibility path applying to every backend, not
just the five it was justified for. shouldRetryWithFreshSession only saw
(Result, priorSessionID, tools), so a false ResumeRejected could not be told
apart from a backend that has no way to answer — and claude/codebuddy/qwen/ACP
startup failures with no session id still fell through to the exclusion
branch. That contradicted both the stated intent and the function's own doc
comment ("where a backend can produce it, it is the whole answer").
Make the capability explicit. agent.ResumeRejectionUndetectable names the
five backends that scrape SessionID out of stream output and have no
rejection detection at all; the daemon takes provider and consults it, so a
capable backend reporting false is now taken at its word. Membership is
opt-in, so a new backend fails closed instead of silently inheriting a
guess-based retry.
Also completes the exclusion set: missing config, unavailable model, missing
executable, unsupported runtime version and (defensively) agent timeout all
have defined non-session remedies and were reaching `default: true`. What is
left through stays narrow — unknown, process failure, unparseable output,
context overflow — because a real rejection from these five most likely
surfaces as a non-zero exit or unparseable output, none of them reporting one
explicitly.
Tests: one identical result asserted across all five undetectable backends
(retries), twelve capable ones (no retry), and an unregistered provider
(fails closed), plus table cases for each newly excluded reason. Classifier
inputs were verified to map to the intended reasons rather than passing by
accident.
Also updates the ResumeRejected doc comment, which still said the daemon
gates on it alone.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Bohan-J <bohan@devv.ai>
Co-authored-by: multica-agent <github@multica.ai>
Detect the root/sudo + bypassPermissions launch condition before starting Claude Code and fail fast with an actionable error (run as non-root, or set IS_SANDBOX=1 in a genuine container/sandbox).
Closes#3278
MUL-4095
* fix(daemon): bound runtime --version probe so one wedged CLI can't block all runtimes
A CLI whose `--version` never returns (e.g. a brew-installed claude wedged
by a bun regression) stalled the daemon's sequential runtime registration
loop forever. Registration runs inside the blocking preflight that gates
/health, so the daemon never flipped from "starting" to "running" and every
runtime on the host appeared disconnected — not just the broken one.
detectCLIVersion now derives a 10s timeout context and sets cmd.WaitDelay so
a node/bun shim that leaves a child holding the stdout pipe open can't defeat
the timeout. A wedged probe now fails fast; the existing per-agent error skip
isolates the broken runtime and the rest register normally.
MUL-3812
Co-authored-by: multica-agent <github@multica.ai>
* test(agent): reap the hang script's orphaned child instead of leaking it
The MUL-3812 regression test spawned a background `sleep 60` that outlived
the killed parent and lingered for up to 60s on CI. The hang script now
records the child's PID and t.Cleanup reaps it, so no temporary process is
left behind.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
Active long-running sessions are no longer killed by a fixed wall-clock deadline. Liveness is delegated to the idle watchdog (MULTICA_AGENT_IDLE_WATCHDOG, default 30m) with a larger in-flight-tool budget (MULTICA_AGENT_TOOL_WATCHDOG, default 2h). MULTICA_AGENT_TIMEOUT is an opt-in absolute cap (default 0 = no cap). The server-side 2.5h sweeper is unchanged as a coarse backstop.
Fixes#3745.
* fix(agent): stop stripping user-facing CLAUDE_CODE_* config from child env
isFilteredChildEnvKey blanket-removed every CLAUDE_CODE_* var from the
spawned Claude Code child's environment. The intent was only to keep the
daemon's internal session markers from leaking, but CLAUDE_CODE_* is also
Anthropic's user-facing config namespace. On Windows this stripped the
user-set CLAUDE_CODE_GIT_BASH_PATH, so Claude Code could not locate
bash.exe, exited immediately, and every task failed with
"write claude input: write |1: The pipe has been ended."
Switch from prefixing the whole CLAUDE_CODE_ namespace to an exact-name
denylist of the internal runtime/session markers (CLAUDECODE,
CLAUDE_CODE_ENTRYPOINT, CLAUDE_CODE_EXECPATH, CLAUDE_CODE_SESSION_ID,
CLAUDE_CODE_TMPDIR, CLAUDE_CODE_SSE_PORT), still blanket-stripping the
wholly-internal CLAUDECODE_* namespace. Every other CLAUDE_CODE_* var
(GIT_BASH_PATH, USE_BEDROCK, USE_VERTEX, MAX_OUTPUT_TOKENS, ...) now
reaches the child. The internal-marker set was confirmed against the live
runtime, not guessed.
Fixes the whole class, not just git-bash: Bedrock/Vertex/etc. were
silently dropped the same way.
MUL-2940
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): keep CLAUDE_CODE_TMPDIR in child env
CLAUDE_CODE_TMPDIR is a documented, user-configurable temp-dir override
(public env-vars reference), not an internal per-session marker. Claude
Code creates its own per-session subdir under it, so inheriting it is
harmless — and stripping it would silently break a user's temp-dir
override the same way the broad prefix filter broke CLAUDE_CODE_GIT_BASH_PATH.
Drop it from the internal denylist (which now holds only the undocumented
per-process runtime markers: CLAUDECODE, CLAUDE_CODE_ENTRYPOINT,
CLAUDE_CODE_EXECPATH, CLAUDE_CODE_SESSION_ID, CLAUDE_CODE_SSE_PORT) and
assert it reaches the child.
MUL-2940
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
Bug 1: detect copilot.cmd/.bat on Windows and invoke the sibling .ps1 directly via powershell -File, bypassing cmd.exe %* re-tokenisation that mangled the multi-line -p prompt. Shared rewriteCmdToPS1() now serves cursor, pi, and copilot.
Bug 2: filterCustomArgs (shared by all agent backends) strips one outer layer of shell quotes via unshellQuoteArg() before processing, so shell-style custom args like --deny-tool='write' no longer reach the CLI with literal quotes.
The claude backend wrote the full prompt to the child's stdin and closed
it before starting the stdout reader goroutine. With
--verbose --output-format stream-json the CLI emits a startup banner
before reading its first stdin frame; with no reader draining stdout, the
child blocks on its stdout write, never reads stdin, and our stdin Write
blocks until the per-task context fires. The field symptom is tasks
failing exactly at the 2 h per-task timeout with
"write |1: The pipe has been ended."
Move writeClaudeInput into its own goroutine so the prompt write and the
stdout drain proceed concurrently. Guard stdin close with sync.Once (it
can now be called from both the writer goroutine and, previously, the
result handler). Join the write result at cmd.Wait() and surface a write
failure as a "failed" status only when no result event arrived and no
session was established, so a genuine startup death still reports the
stderr tail.
Add a regression test that re-execs the test binary as a fake claude
which bursts 256 KiB to stdout before reading stdin, with a 128 KiB
prompt pushed at stdin — both past any plausible OS pipe buffer — so a
regression hangs until the test deadline instead of passing.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(agent): surface host OAuth token via env var on macOS isolation (MUL-2603)
Claude Code 2.x scopes the macOS keychain credentials entry by
sha256(CLAUDE_CONFIG_DIR)[:8], so the MUL-2603 isolation path strands
the child at "Not logged in" even after #3261 mirrored .claude.json:
the child looks up `Claude Code-credentials-<scratch-hash>`, the host
token is sitting in the no-suffix `Claude Code-credentials` entry.
Read the host OAuth token from the keychain via /usr/bin/security and
inject it as CLAUDE_CODE_OAUTH_TOKEN, which bypasses keychain lookup
entirely. Linux/Windows continue to use the .credentials.json mirror
(no-op there). Operator-pinned tokens and ANTHROPIC_API_KEY both take
precedence over the keychain reader.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): tighten empty-value auth gate, pin Claude CLI env-scrub assumption (MUL-2603)
Empty-value gate
- `ANTHROPIC_API_KEY=` inherited from a login shell that conditionally
exports auth previously posed as an "operator pinned API-key auth"
choice and disabled the keychain reader, stranding the isolated child
at "Not logged in" even though no auth was actually selected.
- Custom_env `CLAUDE_CODE_OAUTH_TOKEN=""` (stale agent config) had the
same effect, plus would have shadowed a keychain-injected token in
libc env lookups that pick the first match.
- Both are now treated as noise: the empty entry is dropped from the
child env and the keychain reader runs unchanged. Two new unit tests
cover the os.Environ side (`...TreatsEmptyAnthropicAPIKeyAsUnpinned`,
`...HonorsNonEmptyAnthropicAPIKey`) and the custom_env side
(`...EmptyOAuthTokenInCustomEnvAsUnpinned`).
Env-scrub boundary
- Surfacing `CLAUDE_CODE_OAUTH_TOKEN` to the isolated child is only
safe because Claude Code itself drops that variable from the env it
hands to Bash / hook subprocesses, so a model-driven `printenv` can
never echo the secret into the agent transcript.
- Empirically verified against `claude` 2.1.121:
printf '...test -n "$CLAUDE_CODE_OAUTH_TOKEN" && echo SET || echo UNSET...' \
| CLAUDE_CODE_OAUTH_TOKEN=sk-canary-XYZ \
MUL2603_CONTROL=control-value \
claude --print --output-format text \
--allow-dangerously-skip-permissions --allowedTools Bash
returned `UNSET` for the OAuth token while the non-sensitive
`MUL2603_CONTROL` control returned `CONTROL-SET`, proving the CLI
scrubs only the auth env, not the env in general.
- Pinned this assumption in a new skip-gated regression test
(`TestClaudeCLIScrubsOAuthTokenFromBashSubprocess`) that boots the
real CLI with a canary token; failing the test means upstream
Claude Code stopped scrubbing and the passthrough must move off env
vars before MUL-2603 can ship.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): gate keychain passthrough on default host dir, harden scrub test (MUL-2603)
Two follow-ups from the round-2 review on #3267:
1. Custom CLAUDE_CONFIG_DIR no longer pulls the default OAuth token.
Claude Code 2.x maps each config dir to its own suffixed
`Claude Code-credentials-<hash>` keychain entry, so an operator that
pins a managed/custom CLAUDE_CONFIG_DIR via custom_env or the
daemon-host env was getting the *daemon user's* default unsuffixed
entry injected into the isolated child — silently crossing accounts,
exactly the boundary mirrorHostClaudeJSONIfMissing already protects
for `.claude.json`. buildClaudeEnvWith now threads the effective
hostConfigDir through and only calls the reader when that dir is the
default `$HOME/.claude`. The new gate has a unit-level truth table
(TestIsDefaultHostClaudeConfigDir) plus a regression
(TestBuildClaudeEnvIsolatedSkipsKeychainForCustomHostConfigDir) that
makes a t.Fatal-armed reader prove the gate keeps the read off for
custom dirs.
2. Scrub e2e now asserts the control prong and the proof-of-execution
marker, not just "canary absent". The previous assertion would
false-pass on a model refusal, paraphrase, or "Bash gets no env at
all" upstream change. The strengthened version sets a non-secret
MUL2603_CONTROL alongside the canary OAuth token and asserts (a)
canary is NOT in the transcript, (b) CONTROL-SET IS in the
transcript (env propagation works for non-secrets — proves a
targeted scrub), (c) UNSET IS in the transcript (the Bash tool
actually ran AND saw the OAuth var as empty/unset). Code comment in
buildClaudeEnvWith and the test docstring now narrow the
security contract to the Bash tool subprocess only; hook subprocess
env-scrub is no longer claimed because it has not been verified.
Co-authored-by: multica-agent <github@multica.ai>
* test(agent): use per-run nonces in Claude scrub e2e to kill false-pass (MUL-2603)
Elon's round-3 review flagged that TestClaudeCLIScrubsOAuthTokenFromBashSubprocess
still false-passed: the proof markers "UNSET" / "CONTROL-SET" were literal
strings in the prompt, so strings.Contains matched them even when the model
only paraphrased the prompt without spawning Bash.
Replace the hard-coded markers with two per-run random hex nonces passed *only*
via env vars (MUL2603_UNSET_NONCE, MUL2603_CONTROL_NONCE). The prompt now
references the variable names, not the values, so the nonces can land in the
transcript only if a real Bash subprocess inherits the env vars and echoes
them. A paraphrasing or refusing model cannot fake nonces it never saw.
Also update the security-boundary comment in buildClaudeEnvWith to describe
the nonce-based proof.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
PR #3200 introduced per-agent `skills_local=ignore` isolation that
mirrors the host's Claude config dir into a per-task scratch dir,
omitting `skills/` to keep broken local skills out of the CLI's
discovery path. The mirror walks entries inside `hostConfigDir`
(default: `$HOME/.claude/`), but Claude Code's default layout stores
its main config — login state, project history — at
`$HOME/.claude.json`, a *sibling* of `~/.claude/` rather than inside
it. Once `CLAUDE_CONFIG_DIR=$ISOLATED` is set, the CLI looks for
`$ISOLATED/.claude.json`, finds only `backups/.claude.json.backup.*`
(those live inside `~/.claude/` and DO get mirrored), and exits with:
Claude configuration file not found at: …/.claude.json
Not logged in · Please run /login
— so every agent with `skills_local=ignore` on a host using the
default Claude layout dies on the first turn. Flipping the toggle back
to "merge" restores the host CLAUDE_CONFIG_DIR and recovers the agent;
that's the workaround Bohan flagged in MUL-2661.
Fix: after the existing `mirrorHostClaudeExceptSkills`, run a new
`mirrorHostClaudeJSONIfMissing` that pulls `$HOME/.claude.json` into
the scratch dir as `.claude.json` when (a) the dest doesn't already
have one and (b) the host source dir is the default `$HOME/.claude/`.
The custom-CLAUDE_CONFIG_DIR path is left alone because a pinned
custom dir is expected to be self-contained — silently borrowing
`$HOME/.claude.json` from a different account would mask credential
drift.
The helper goes through `createFileLink`, so it inherits the same
symlink → junction → hardlink → copy fallback chain the rest of the
mirror uses on Windows-without-Developer-Mode hosts.
Tests:
- `TestMirrorHostClaudeJSONIfMissing_DefaultLayoutMirrorsParentFile`
covers the happy path with an injected `homeDir`/`fileLink`.
- `TestMirrorHostClaudeJSONIfMissing_AlreadyPresentNoop` asserts a
pre-existing dest `.claude.json` (from a custom CLAUDE_CONFIG_DIR
mirror) is not overwritten.
- `TestMirrorHostClaudeJSONIfMissing_CustomHostDirSkipped` locks in
the custom-host-dir gate.
- `TestMirrorHostClaudeJSONIfMissing_MissingSourceNoop` documents the
env-var-auth-only / fresh-install case.
- `TestClaudeExecuteIsolatesProvidesClaudeJSONFromHome` is the
end-to-end MUL-2661 regression: a fake `\$HOME` with the default
split layout, `skills_local=ignore`, fake claude binary that prints
whatever `.claude.json` reaches the scratch dir. Asserts the file
rides through. Verified the test fails (with the documented
MUL-2661 error message) when the new mirror call is removed.
Verification:
- `go test ./pkg/agent/...` green (full agent suite).
- `GOOS=windows GOARCH=amd64 go vet ./pkg/agent/...` clean.
Co-authored-by: multica-agent <github@multica.ai>
* feat(agent): per-agent toggle to isolate host-machine skills (MUL-2603)
Adds an agent-scoped `skills_local` switch ("ignore" default / "merge") so
shared agents stop inheriting the operator's user-global Claude skill
directory. A single broken local skill on one operator's machine was
crashing the Claude CLI before it ever read stdin — the daemon saw a
"broken pipe" with no recoverable signal (GitHub #3052).
- DB: migration 108 adds `agent.skills_local` (NOT NULL DEFAULT 'ignore'),
with sqlc CreateAgent/UpdateAgent updates and handler validation.
- Claude runtime: when the agent is in "ignore" mode the backend points
CLAUDE_CONFIG_DIR at an empty per-task scratch dir under the task cwd
(fallback: OS temp), strips any inherited override, and cleans up after
the run. Workspace skills under `{cwd}/.claude/skills/` still load.
"merge" preserves the legacy inherit-from-machine behavior; Codex and
other isolated backends are no-ops.
- UI: new Skills toggle in the Create Agent dialog and the Agent → Skills
tab, with EN/zh-Hans copy and SkillsLocalToggle shared between the two.
- Tests: unit coverage for the new env helper, isolation dir lifecycle,
full Claude execute paths (ignore + merge), and the handler tristate
contract. Existing skills-tab test updated for the new copy.
- Docs: updated `/skills` docs (EN + ZH) and added a 0.3.7 changelog entry
in the landing-page i18n.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): preserve claude login + validate skills_local input (MUL-2603)
Address Elon's review on PR #3200:
1. Skill isolation no longer drops the operator's Claude login. The
per-task scratch dir now mirrors every entry under `~/.claude/`
as symlinks except `skills/`, so `.credentials.json`, settings,
plugins, etc. reach the CLI exactly as on the host while the
user-global skills directory stays hidden. Without this, default
`ignore` would have broken every Claude agent on a non-API-key
host the moment migration 108 landed.
2. Internal CreateAgent callers (agent_template, onboarding_shim)
now set `SkillsLocal: "ignore"`. The Go zero value was about to
trip the migration-108 CHECK constraint and 500 template /
onboarding agent creation.
3. Create / update handler validation no longer normalizes garbage
to "ignore". The strict 400 path is now reachable on bad client
input; the drift-safe `normalizeSkillsLocal` stays on the read
side only.
UI copy + docs clarified that the toggle is Claude-only; other
runtimes ignore the setting.
Verification:
- `go test ./...` green (full suite locally).
- `pnpm --filter @multica/views exec vitest run agents/components/tabs/skills-tab.test.tsx` green.
- Handler DB-backed tests still skip locally without docker (same
as Elon's run) — CI will validate the create / update paths
against migration 108.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): mirror effective claude config dir with windows fallback (MUL-2603)
Address Elon's second-round review on PR #3200:
1. The per-task scratch dir now mirrors the *effective* host Claude
config dir, not unconditionally `~/.claude/`. Precedence: agent
`custom_env` CLAUDE_CONFIG_DIR > parent process env > `~/.claude/`.
Without this, an operator who pinned Claude at a managed install
(custom env CLAUDE_CONFIG_DIR) would get the wrong credentials in
the scratch dir, because `buildClaudeEnv` strips that env before
handing it to the child. We resolve the source up front and feed
it to the mirror, so the override env still points at the right
bytes.
2. Mirror entries now go through platform-aware linkers. On Windows
without Developer Mode / admin, `os.Symlink` is denied, which
previously left the scratch dir empty and broke Claude Code auth
on default `ignore`. The new helpers try symlink first, then fall
back to a directory junction (`mklink /J`) for dirs or a hardlink
(same-volume content share) / copy for files. Mirrors the
execenv/codex_home_link_windows.go pattern.
3. Tests:
- `TestResolveHostClaudeConfigDir` locks in the custom_env >
parent_env > `~/.claude` precedence.
- `TestNewIsolatedClaudeConfigDirMirrorsCustomHostDir` confirms
the scratch dir picks up `.credentials.json` from a synthetic
custom host dir, proving the source resolution actually
propagates into the mirror.
- `TestNewIsolatedClaudeConfigDirEmptyHostIsNoop` documents the
env-var-auth-only case (no host source ⇒ empty scratch dir).
- `TestMirrorHostClaudeExceptSkillsWith_FallbackWhenSymlinkFails`
exercises the Windows-no-Developer-Mode path via the new
`mirrorHostClaudeExceptSkillsWith` seam, asserting credentials
and sub-dir children still reach the scratch dir after the
symlink stand-in fails.
- `TestMirrorHostClaudeExceptSkillsWith_PropagatesFirstLinkError`
confirms callers see the per-entry error when even fallback
fails (so the warn-log fires on broken Windows installs).
- `TestCopyFileRoundTrip` covers the last-resort copy fallback
and its EXCL no-overwrite contract.
- `TestClaudeExecuteIsolatesUsesCustomEnvSource` is the
end-to-end check: an agent with custom_env CLAUDE_CONFIG_DIR
reads its credentials from the pinned dir, not `~/.claude/`.
4. Docs: `apps/docs/content/docs/skills.{mdx,zh.mdx}` updated to
describe the effective-source resolution and the Windows
fallback chain so the docs match the runtime behaviour.
Verification:
- `go test ./...` green (full server suite locally, including
`pkg/agent` 23 cases covering the new + existing isolation
paths).
- `GOOS=windows GOARCH=amd64 go vet ./pkg/agent/...` and
`go test -c -o /dev/null` both compile clean, confirming the
Windows-tagged linker file builds.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): default skills_local to merge to preserve legacy behavior (MUL-2603)
Per Bohan's product decision on PR #3200, the per-agent host-skill toggle
defaults to "merge" — the pre-MUL-2603 inherit-from-machine behavior —
so existing personal workflows that rely on locally installed Claude
Skills keep working unchanged. Agent owners explicitly opt into "ignore"
when they need to harden a shared agent against a broken local skill on
one operator's machine (GitHub #3052).
Also audited all 11 runtimes for user-global skill discovery paths and
documented the scope of the toggle. Only Claude reads a user-global
`~/.claude/skills/`; Codex isolates via `CODEX_HOME`, the ACP backends
(Hermes / Kimi / Kiro) and the JSON-stream backends (Copilot / Cursor /
Gemini / Pi / OpenCode / OpenClaw) anchor discovery to the task workdir
and never read a user-global skill directory. UI copy and docs now say
"for runtimes that support it (currently Claude Code)" everywhere so
the scope is explicit.
Changes:
- Migration 108: column default flipped to 'merge'.
- Handler CreateAgent: missing field → "merge"; explicit "ignore" /
"merge" still validated, garbage still 400.
- normalizeSkillsLocal: drift-safe coercion now lands on "merge" for
anything that isn't the exact literal "ignore".
- agent_template.go / onboarding_shim.go: internal CreateAgent callers
send "merge" instead of "ignore" to match the new default.
- Claude runtime (`claude.go`): isolate-mode gate flipped from
`SkillsLocal != "merge"` to `SkillsLocal == "ignore"`, so "" (legacy
daemons / older clients) and "merge" both walk `~/.claude/` directly.
- Create Agent dialog + Skills tab: toggle defaults to on (merge); only
duplicate of an explicit "ignore" agent carries through. The
isolation opt-in is now `skills_local: "ignore"` when the user flips
off; "merge" is omitted from the request body.
- i18n (EN + zh-Hans): copy reframed — "On (default) — merged"; "Off —
ignored. Recommended for shared agents".
- Docs (`/skills`, `/guides/agents.zh`): describe new default and
enumerate which runtimes act on the toggle.
- Landing changelog 0.3.7: retitled "Per-Agent Local-Skill Toggle"; note
the on-by-default behavior + off-to-isolate framing.
- Tests:
- `TestClaudeExecuteIsolatesHostSkillsWhenIgnoreOptedIn` replaces the
old by-default isolation case (now requires explicit "ignore").
- New `TestClaudeExecuteDefaultModeKeepsHostConfigDir` locks in that
default ExecOptions preserve the host CLAUDE_CONFIG_DIR.
- `TestClaudeExecuteIsolatesUsesCustomEnvSource` now explicitly opts
into "ignore" mode.
- Handler tests: omitted → "merge"; explicit "ignore" round-trips;
preserve-existing test seeds "ignore" and asserts "merge" flip-back.
- `TestNormalizeSkillsLocal_DriftStaysSafe`: only literal "ignore"
maps to ignore; everything else → "merge".
- `skills-tab.test.tsx`: toggle ON by default; flip OFF when agent
opted into "ignore". Intro-text matcher anchored to a more specific
phrase so it no longer collides with the toggle hint copy.
Verification:
- `go test ./...` green (full server suite locally).
- `GOOS=windows GOARCH=amd64 go vet ./pkg/agent/...` and
`go test -c -o /dev/null` both compile clean (windows-tagged linker
file still builds).
- `pnpm typecheck` green across all packages and apps.
- `pnpm --filter @multica/views test` 88 files / 771 tests green.
- `pnpm --filter @multica/core test` 43 files / 390 tests green.
- Handler DB-backed tests still skip locally without docker; CI will
validate the create / update paths against migration 108.
Co-authored-by: multica-agent <github@multica.ai>
* chore(landing): drop 0.3.7 changelog entry from this PR (MUL-2603)
The landing-page release notes belong in a separate release-prep PR, not in the feature PR.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): propagate skills_local=ignore to codex user-skill seed (MUL-2603)
Make the per-agent skills_local toggle real for Codex too, not just Claude.
Previously the toggle was only consumed by the Claude backend, while the
daemon's execenv layer always seeded Codex's per-task CODEX_HOME with the
host machine's user-installed skills from ~/.codex/skills/. A shared Codex
agent with skills_local=ignore could still inherit a broken local skill
from one operator's machine.
Now: PrepareParams/ReuseParams carry SkillsLocal; hydrateCodexSkills
skips seedUserCodexSkills when SkillsLocal == "ignore" so the per-task
CODEX_HOME exposes only workspace skills to the codex CLI. Default
("merge", or empty from older servers/clients) preserves existing
inherit-from-machine behavior. UI / docs are updated to reflect the
contract honestly: Claude Code and Codex honor the toggle; other
runtimes (Hermes / Kimi / Kiro / Copilot / Cursor / Gemini / Pi /
OpenCode / OpenClaw) leave $HOME untouched and discover user-level
skills natively, so the toggle is a no-op for them today.
New tests: TestPrepareCodexSkillsLocalIgnoreSkipsUserSeed,
TestPrepareCodexSkillsLocalMergeSeedsUserSkills, and
TestReuseCodexSkillsLocalIgnoreSkipsUserSeed cover Prepare(ignore),
Prepare(merge), and the toggle-flip-on-reuse path.
Co-authored-by: multica-agent <github@multica.ai>
* docs(skills): scope skills_local toggle copy to Claude Code + Codex (MUL-2603)
Off-state hint and Skills tab intro now explicitly call out Claude Code +
Codex as the only runtimes that honor the toggle, with "other runtimes
ignore this setting" wired into both states (en + zh-Hans), so users on
non-Claude/Codex agents don't read "Off" as runtime-wide isolation.
Docs (skills.mdx, skills.zh.mdx, guides/agents.zh.mdx) stop describing
Hermes / Kimi / Gemini / Copilot / Cursor / Pi / OpenCode / OpenClaw / Kiro
as having native user-level skill discovery; the daemon simply does not
manage user-level skill discovery for those runtimes today, and the toggle
is a no-op regardless of where it is set.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(agent): persist thinking_level per agent (MUL-2339)
Adds a nullable `thinking_level` column to the `agent` table so the
backend can route a runtime-native reasoning/effort token (e.g. Claude's
`xhigh`, Codex's `minimal`) through to the agent CLI on every dispatch.
The column is intentionally TEXT rather than an enum — Claude and Codex
publish overlapping but distinct vocabularies and we want the persisted
value to round-trip exactly through whichever CLI receives it. NULL is
the "use runtime default" sentinel that every downstream consumer reads
as "do not inject --effort / reasoning_effort".
This commit is just the storage layer (migration + sqlc); subsequent
commits wire it through the API, daemon, and agent backends.
Co-authored-by: multica-agent <github@multica.ai>
* feat(agent-backend): inject reasoning effort for claude + codex (MUL-2339)
Extends ExecOptions with a runtime-native ThinkingLevel string and wires
it into the Claude and Codex backends. Discovery is driven by the local
CLI so the daemon advertises whatever the host install supports rather
than a hand-maintained list that goes stale.
Per Elon's PR1 review:
- Claude: parses `claude --help` to learn the `--effort` superset and
projects through a per-model allow-list (xhigh is Opus-only; max is
session-only on the smaller models). Falls back to a conservative
static list when the binary is missing or help drift hides the line.
- Codex: drives `codex debug models --output json` so per-model
reasoning subsets and the documented default come directly from the
CLI. The older config-error probe trick is gone — the JSON path is
stable and doesn't pollute stderr with an intentional misconfig.
- Cache key includes (provider, executablePath, cliVersion) so a CLI
upgrade invalidates entries that referenced the older help / catalog.
Per Trump's PR1 constraint, all three Codex injection points
(thread/start.config, thread/resume.config, turn/start.effort) flow
through one helper (`applyCodexReasoningEffort`) so they cannot drift
independently. The shared `codexReasoningCases` fixture in
`thinking_test.go` asserts the same value→{shape, key} contract at
each site for every level the runtimes know about.
Claude's `--effort` is also added to `claudeBlockedArgs` so a user
custom_args entry can't silently outvote the daemon-injected value.
Co-authored-by: multica-agent <github@multica.ai>
* feat(api): wire thinking_level through API + daemon contract (MUL-2339)
End-to-end plumbing for the per-agent reasoning/effort setting:
- AgentResponse / TaskAgentData now carry `thinking_level`; the daemon's
claim response includes it and the daemon's executor passes it through
to agent.ExecOptions, where the Claude and Codex backends already know
what to do with it.
- ModelEntry on the runtime-models wire format gains a `thinking` block
carrying `supported_levels` + `default_level` per model so the UI can
render a runtime-aware picker without the server having to know about
the local CLI install. `handleModelList` projects the agent-package
catalog (including the new Thinking field) into the wire shape.
- CreateAgent / UpdateAgent gate the field with a synchronous provider
enum check (claude / codex only today). UpdateAgent is tri-state:
field omitted = no change, "" = explicit clear (new
`ClearAgentThinkingLevel` query, mirrors the existing mcp_config null
pattern), non-empty = validate then set.
Per Trump's PR1 review, the API NEVER auto-clears on a runtime/model
swap and ALWAYS returns 400 on an unknown literal value — same shape
across CreateAgent, UpdateAgent, and combined patches that move
runtime + level in one request. Per-model combination failures (e.g.
`xhigh` against a model that only supports up to `high`) surface as a
daemon-side task error, not a silent server-side rewrite.
TS types follow the same shape: `Agent.thinking_level`,
`CreateAgentRequest`/`UpdateAgentRequest` add the field, `RuntimeModel`
grows a `thinking` block. Older backends omit the field, which the
front-end treats as "no picker for this model" — installed desktop
builds keep working.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): correct codex debug models argv + pin via runner test (MUL-2339)
`codex debug models --output json` is rejected by codex-cli 0.131.0 —
the subcommand emits JSON on stdout by default and has no `--output`
flag. Drop the flag and add `--bundled` to skip the network refresh
discovery doesn't need. Move the argv to a package-level var and add
a test that runs a fake `codex` to assert the binary actually
receives exactly `debug models --bundled`, so the contract can't
silently drift on the next refactor.
Also teach ValidateThinkingLevel to resolve an empty model to the
provider's default model entry. Without this, every default-model
task with a persisted thinking_level would be misjudged "unknown
model" by the daemon guard.
Co-authored-by: multica-agent <github@multica.ai>
* fix(api): reject runtime switch that would leave invalid thinking_level (MUL-2339)
A PATCH that changed `runtime_id` without touching `thinking_level`
used to silently keep the existing value, so a Claude agent storing
`max` could land on a Codex runtime where `max` is not a recognised
token at all, and the daemon would receive a literal-invalid level.
Hold the same "always 400 on literal-invalid, never silent coerce"
rule on this implicit path. When runtime_id changes and the existing
value is not in the new provider's enum, return 400 with the
recovery options (clear via `thinking_level=""` or re-set in the
same PATCH).
Add coverage for both the kept-when-still-valid and the rejected
cases, plus the two recovery paths (clear and replace).
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): guard runTask with per-model thinking_level validator (MUL-2339)
ValidateThinkingLevel existed but had no call site — `task.Agent.
ThinkingLevel` flowed straight into ExecOptions, so `xhigh` configured
on a non-Opus Claude model, or API-side stale values that escaped the
provider enum gate, would be injected anyway.
Run the validator before building ExecOptions. Invalid combinations
log a warning and drop the level instead of failing the task: the
agent still runs, just at the runtime's default reasoning effort.
Discovery errors fail open (keep the level, let the CLI surface any
objection) so a transient `claude --help` failure can't strand work.
Empty model is forwarded as-is; the validator resolves it to the
provider's default model internally per the cross-package contract.
Co-authored-by: multica-agent <github@multica.ai>
* chore(agent): drop stale `--output json` comments + unused scanner (MUL-2339)
Codex CLI's `debug models` subcommand emits JSON without an `--output`
flag, and `parseCodexDebugModels` never read from the bufio.Scanner.
Sync the comments with the actual invocation and remove the dead init.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): disable Claude AskUserQuestion in non-interactive mode (MUL-2244)
GitHub #2588: when Claude Code calls its built-in AskUserQuestion tool
inside the daemon's stream-json runtime, the question never reaches the
user — there's no UI to render it — so the SDK returns an empty answer
and the agent silently "infers" and continues. From the issue's
perspective, execution looks stuck while the agent is actually charging
ahead on its own guess.
Two-part fix:
- `buildClaudeArgs` now passes `--disallowedTools AskUserQuestion` so
the tool is not exposed to the model at all.
- The Claude-specific runtime brief tells the agent to use a `blocked`
issue comment for genuine clarification, or to state an explicit
assumption and proceed.
Adds a regression test that pins both: AskUserQuestion is forbidden in
CLAUDE.md and is NOT mentioned in the AGENTS.md emitted for non-Claude
providers (the tool is Claude-specific).
Co-authored-by: multica-agent <github@multica.ai>
* refactor(daemon): drop CLAUDE.md AskUserQuestion guidance, rely on --disallowedTools
The --disallowedTools flag already prevents Claude from invoking
AskUserQuestion, so duplicating the rule in the runtime brief just bloats
the prompt without changing behavior. Removes the section and its
regression test; the argv-level test in pkg/agent already pins the flag.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
The gemini CLI's Windows shim emits `Active code page: 65001` (from
`chcp`) to stdout before the real version reaches `--version` output.
The daemon stored the raw concatenation as the runtime version, so the
runtime detail page rendered `Active code page: 65001 0.42.0` instead
of `0.42.0`.
Scan `<cli> --version` line by line and return the first line carrying
a semver-shaped token. Full strings like `2.1.5 (Claude Code)` or
`codex-cli 0.118.0` survive unchanged; unparseable output falls back to
the trimmed raw value.
Co-authored-by: multica-agent <github@multica.ai>
#1674 wired claude's post-handshake error path through withAgentStderr but
left the writeClaudeInput failure branch returning a bare "broken pipe"
error. That branch fires precisely when claude crashes during startup —
exactly when the stderr tail is most useful for root-causing V8 aborts,
Bun panics, or missing native modules. cmd.Wait() before sampling Tail()
flushes os/exec's internal stderr copy goroutine, matching the
Wait→Tail synchronization contract spelled out in stderr_tail.go.
Adds TestClaudeExecuteSurfacesStderrWhenChildExitsEarly mirroring the
codex test: a fake claude binary drains stdin, writes a V8-abort line to
stderr, and exits 3. Locks in the contract that Result.Error carries the
stderr tail in the post-handshake failure path on the claude backend too.
Hoist the existing stderrTail ring-buffer (previously codex-only) into
a shared pkg/agent helper so every Backend that supervises a child CLI
can include the last ~2 KB of that CLI's stderr in Result.Error. Wire
the claude backend through the same path.
Motivation: claude on Windows occasionally exits with a non-zero status
after ~5–8 minutes of a single long-running tool_use, and right now the
daemon only reports "claude exited with error: exit status 3" /
"exit status 0x80000003" — useless for root-causing V8 aborts, Bun
panics, native-module OOMs, or any other CLI-side crash. With the tail
attached, the failure message carries the real signal (panic line, V8
assertion, stderr-printed HTTP error) all the way into the task row's
error field that users see in the API.
Renames withCodexStderr to withAgentStderr(msg, label, tail) so the
helper is self-documenting across providers.
* fix(daemon): suppress agent terminal windows on Windows (#1471)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add hideAgentWindow to detectCLIVersion and avoid SysProcAttr overwrite
- Add missing hideAgentWindow(cmd) call in detectCLIVersion (claude.go:554)
so --version checks don't flash console windows on Windows.
- Refactor hideAgentWindow to preserve existing SysProcAttr fields
instead of overwriting the entire struct.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(server): orphan-task recovery + auto-retry + manual rerun (MUL-1128)
When the daemon process crashed mid-task the issue was stuck at
in_progress for up to 2.5h: the in-flight task timeout was the only
mechanism that ever moved the row, and the runtime heartbeat sweeper
only fires after the runtime stays offline for 45s — a quick restart
beats both windows.
This change implements the A+B plan from the issue thread:
A. lifecycle hygiene
- migration 055 adds attempt / max_attempts / parent_task_id /
failure_reason / last_heartbeat_at to agent_task_queue
- new daemon-auth endpoint POST /runtimes/{id}/recover-orphans:
daemon calls it on every register so the server fails any
dispatched/running tasks the previous process left behind
- new daemon-auth endpoint POST /tasks/{id}/session: persists the
agent's session_id + work_dir mid-flight so a crash doesn't
lose the resume pointer (claude+codex emit MessageStatus with
SessionID; daemon forwards on the first one it sees)
- FailAgentTask / FailStaleTasks / FailTasksForOfflineRuntimes
now set failure_reason ('agent_error' / 'timeout' /
'runtime_offline')
B. auto-retry with resume context
- TaskService.MaybeRetryFailedTask spawns a fresh queued attempt
carrying parent's session_id/work_dir when the failure reason
is infrastructure-shaped (timeout, runtime_offline,
runtime_recovery) and attempt < max_attempts; skips autopilot
- wired into the runtime sweeper paths and TaskService.FailTask
so the user transparently sees a new in_progress run instead of
a stuck row
- new user-auth POST /api/issues/{id}/rerun + multica issue rerun
CLI for the manual escape hatch
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(server): address PR review for orphan-task recovery (MUL-1128)
Three review-must-fix items on top of the A+B implementation:
1. recover-orphans now funnels through TaskService.HandleFailedTasks,
the same shared post-failure pipeline used by the runtime sweeper.
This guarantees task:failed events are emitted, agent status is
reconciled, and issues stuck in_progress with no remaining active
task are reset to todo even when no auto-retry is created
(max_attempts exhausted, autopilot, non-retryable reason).
2. RerunIssue now uses CancelAgentTasksByIssueAndAgent, scoped to the
issue's current assignee. The previous implementation called
CancelAgentTasksByIssue, which would collateral-cancel parallel
@-mention agents on the same issue.
3. GetLastTaskSession now considers both completed and failed tasks
(mirroring GetLastChatTaskSession), ordering by the most recent
timestamp. With UpdateAgentTaskSession pinning session_id/work_dir
mid-flight, an auto-retry or manual rerun of a daemon-crash failure
now actually resumes the prior conversation context instead of
starting fresh — matching the stated B-branch behaviour.
go build / go vet pass; the existing service and agent test suites pass.
runtime_sweeper / handler integration tests require a local DB with the
055 migration (and the pre-existing 050 first_executed_at column).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Surface the actual exec path + argv for every agent backend at INFO
so operators can see the exact command without flipping to debug.
Also add the missing log line in pi.go for consistency with the
other nine backends.
When --resume targets a dead session, claude prints
"No conversation found with session ID: ..." to stderr, emits a stream-json
system init with a fresh session_id, then exits with code 1. The backend
was treating that fresh id as the authoritative session, so
daemon.go's retry-with-fresh-session fallback (SessionID == "" guard)
never triggered. Every subsequent task for the same (issue, agent) pair
stayed permanently broken until the server-side session_id was cleared by
hand.
Fix: when --resume was requested but the emitted session_id differs AND
the run failed, drop the fresh id from Result so the daemon's existing
fallback can do its job. Factored into a pure helper and unit-tested.
Fixes#1284
Co-authored-by: fuxiao <fuxiao@zyql.com>
* fix(agent): add per-agent mcp_config field to restore MCP access
Closes#1111
The --strict-mcp-config flag was added defensively in #592 to prevent
Claude agents from inheriting MCP state from the outer Claude Code session.
It was meant to be paired with --mcp-config <path> to inject a controlled
set of MCPs, but that path was never implemented, which silently stripped
all user-scope MCPs from spawned agents.
This PR completes the original design by:
- Adding a nullable mcp_config jsonb column to the agents table
- Wiring mcp_config through AgentResponse, Create/Update requests
- Piping it into ExecOptions.McpConfig in the daemon
- Serializing to a temp file and passing --mcp-config <path> in buildClaudeArgs
- Blocklisting --mcp-config in claudeBlockedArgs to prevent override
via custom_args
Does not touch Codex provider (tracked separately in #674).
Does not implement Multica MCP auto-injection (out of scope).
* fix: disambiguate JSON null vs absent for mcp_config
Add a debug-level log line in every agent backend (claude, codex,
opencode, openclaw, gemini, hermes) that prints the executable path
and full argument list when spawning the agent process. Helps diagnose
custom args, model overrides, and other CLI flag issues.
* feat(agent): add custom CLI arguments support
Allow users to configure custom CLI arguments per agent that get
appended to the agent subprocess command at launch time. This enables
use cases like specifying different models (--model o3), max turns,
or other provider-specific flags without needing separate runtimes.
Changes:
- Add custom_args JSONB column to agent table (migration 041)
- Update API handler to accept/return custom_args in create/update
- Pass custom_args through claim endpoint to daemon
- Append custom_args to CLI commands for all agent backends
- Add ExecOptions.CustomArgs field in agent package
- Add Custom Args tab in agent detail UI
- Add --custom-args flag to CLI agent create/update commands
Closes MUL-802
* fix(agent): filter protocol-critical flags from custom_args
Add per-backend filtering of custom_args to prevent users from
accidentally overriding flags that the daemon hardcodes for its
communication protocol (e.g. --output-format, --input-format,
--permission-mode for Claude).
This follows the same pattern as custom_env's isBlockedEnvKey: we
only block the small, stable set of flags that would break the
daemon↔agent protocol — not every possible dangerous flag. Workspace
members are trusted for everything else.
Each backend defines its own blocked set:
- Claude: -p, --output-format, --input-format, --permission-mode
- Gemini: -p, --yolo, -o
- Codex: --listen
- OpenCode: --format
- OpenClaw: --local, --json, --session-id, --message
- Hermes: none (ACP is positional)
Includes unit tests for the filtering logic.
* fix(agent): address code review nits for custom_args
- Replace module-level `nextArgId` counter with `crypto.randomUUID()`
in custom-args-tab.tsx to avoid SSR ID conflicts
- Add unit tests for custom args passthrough and blocked-arg filtering
in both Claude and Gemini arg builders
When an agent CLI process hangs (e.g. a tool call blocks on unreachable
I/O), the daemon's scanner blocks indefinitely on stdout, preventing the
Result from ever being sent. This causes tasks to stay in "running"
state permanently with no further events.
Three-layer fix:
1. Agent backends (claude, opencode, openclaw, gemini): add a watchdog
goroutine that closes the stdout/stderr pipe when the context is
cancelled, forcing the scanner to unblock. Also set cmd.WaitDelay
so Go force-closes pipes after 10s if the process doesn't exit.
2. daemon executeAndDrain: add an independent drain timeout (backend
timeout + 30s buffer) with context-aware select on both the message
channel and the result channel, so the daemon never blocks forever.
3. daemon ping path: add context-aware select so pings don't deadlock
if the agent backend stalls.
Closes#925
Co-authored-by: Devv <devv@Devvs-Mac-mini.local>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Claude's stream-json flow can emit the terminal result event while the
child process still waits on open stdin. Closing stdin as soon as the
final result arrives lets the CLI exit cleanly instead of idling until
the daemon timeout fires.
Constraint: Must preserve the existing Claude stream-json protocol and child-process lifecycle
Rejected: Increase ping timeout only | masks the hang without fixing process exit
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep Claude stdin handling aligned with the stream-json terminal result semantics; do not defer closure until goroutine teardown
Tested: Reproduced self-hosted runtime ping timeout locally; verified ping succeeds after closing stdin on result; cd server && go test ./pkg/agent
Not-tested: Full make check; Bedrock/Vertex-specific Claude auth flows
Extract token usage from Claude Code's stream-json output in real-time
during task execution, replacing the inaccurate global JSONL log scanner.
- New `task_usage` table: tracks (task_id, provider, model) level usage
- Agent SDK: parse `message.usage` from assistant messages, accumulate
per-model and return in Result
- Daemon: convert agent usage to entries, send with CompleteTask
- Server: store usage on task completion, expose workspace-level
aggregation APIs (GET /api/usage/daily, GET /api/usage/summary)
- Fix duplicate icons in tool call rows (use chevron only for expand/collapse)
- Show detailed tool information (WebSearch queries, Agent prompts, Skill names)
- Add thinking/reasoning rows with Brain icon and expandable content
- Show tool results as separate chronological entries with previews
- Add TaskRunHistory component for viewing past agent execution logs
- Add listTasksByIssue API endpoint and task-runs route
- Support thinking content blocks in agent SDK (MessageThinking type)
- Improve callID→toolName mapping in daemon message forwarding
Store the Claude Code session ID and working directory when a task
completes. On the next task for the same (agent, issue) pair, look up
the prior session and pass --resume <session_id> to Claude Code so
the agent retains conversation context across multiple tasks on the
same issue.
Changes:
- Migration 020: add session_id and work_dir columns to agent_task_queue
- CompleteAgentTask stores session_id and work_dir on completion
- GetLastTaskSession query retrieves prior session for (agent, issue)
- ClaimTaskByRuntime handler populates prior_session_id in response
- Daemon passes ResumeSessionID through to Claude backend Execute()
- Claude backend adds --resume flag when ResumeSessionID is set
Replace raw fmt/log calls with structured slog logger (Go) and
console-based logger (TypeScript). Add request logging middleware.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix data race on output strings.Builder in codex backend by adding
mutex and waiting for reader goroutine before reading final output
- Fix data race on onTurnDone by initializing it before reader starts
- Fix bug where notificationProtocol zero value "" never matched
"unknown", silently dropping all raw v2 notifications from codex
- Add round-robin polling to prevent runtime starvation in poll loop
- Log errors in claude handleControlRequest instead of silently dropping
- Add 35 tests for pkg/agent covering claude parsing, codex JSON-RPC,
protocol detection, event handling, and helper functions
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Replace deprecated strings.Title with manual capitalize
- Fix race: set codexClient.onMessage before starting reader goroutine
- Remove unused msgCh parameter from codexClient.handleLine
- Route agent stderr through logger instead of dumping to os.Stderr
- Use deterministic agent order in ensurePaired (prefer codex)
- Increase message channel buffer from 64 to 256
- Rename test to match function rename (buildPrompt)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add a reusable Go agent package (server/pkg/agent/) that provides a
unified Backend interface for executing prompts via either Claude Code
or Codex. The daemon now auto-detects which CLIs are available at
startup, registers a runtime for each, and routes tasks to the correct
backend based on task.Context.Runtime.Provider.
Key changes:
- server/pkg/agent/agent.go: Backend interface, Message/Result types, factory
- server/pkg/agent/claude.go: Spawns claude CLI with stream-json, parses output
- server/pkg/agent/codex.go: Spawns codex app-server, JSON-RPC 2.0 protocol
- server/cmd/daemon/daemon.go: Multi-runtime registration, round-robin polling,
provider-based backend selection. Removes old runCodexExec/codexResultSchema.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
