mirror of
https://github.com/multica-ai/multica.git
synced 2026-07-27 21:33:41 +02:00
transcript-all
229 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Bohan Jiang
|
ffa8e16369 |
MUL-5228 fix(usage): bill Grok at xAI's reported cost, fix $0 resumed sessions (#5841)
* fix(agent): attribute Grok usage from the turn's own model id A resumed Grok session with no configured model recorded its entire spend under the model id "unknown", which matches no pricing row — so the task reported $0 cost instead of its real spend. grok.go only learned the model from the session handshake, and ACP's `session/load` carries no model id (only `session/new` does). When neither the agent nor MULTICA_GROK_MODEL pins a model, `daemon.go` legitimately passes an empty model, leaving nothing to attribute the usage to. Every Grok turn stamps `result._meta.modelId` with what it actually billed against. Parse it in the shared ACP result parser and use it as the fallback in grok.go. Other ACP backends are untouched — they keep whatever the handshake gave them. Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> * fix(metrics): price the Grok catalog in server-side cost metrics server/internal/metrics/pricing.go carried no Grok rows at all, so RecordLLMUsage took the unpriced branch for every Grok turn: llm_cost_usd reported zero Grok spend while the tokens accumulated in llm_unpriced_tokens. Internal cost monitoring simply could not see Grok. Add the six SKUs xAI publishes rates for, mirroring the frontend table in packages/views/runtimes/utils.ts. Aliases are anchored exact matches like the gpt-5.6 rows, so `grok-composer-*` (in the catalog, absent from the price sheet) stays unmapped instead of inheriting a guessed rate. Short-context tier on purpose: xAI bills a request at 2x once its prompt reaches 200K tokens, but a usage record aggregates every model call in a turn and cannot say which tier an individual request hit. A regression test re-derives the cost of a real grok 0.2.106 turn from the table and checks it against the costUsdTicks xAI returned for that turn. Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> * docs(changelog): scope the Grok cost claim to what was actually fixed The v0.4.9 entry promised "accurate cost" in all four languages, but the fix corrected catalog pricing and cached-input double-counting — it did not implement xAI's 2x long-context tier, so a turn whose requests reach 200K prompt tokens still under-reports by up to 50%. Say what was fixed instead. Also correct two stale claims in the pricing comment: the daemon tags usage rows with the runtime provider `grok`, not `xai` (the bare `grok-*` keys are what make them resolve), and record why thresholding the long-context tier on an aggregated row would be worse than not pricing it at all. Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> * feat(usage): carry the provider's own cost through to the usage record Cost has always been derived client-side as tokens x a static rate, which cannot express request-level pricing rules. xAI bills a Grok request at 2x once its prompt reaches 200K tokens, and a task_usage row aggregates every model call in a turn — so the stored token counts genuinely cannot say which tier any individual request hit. Thresholding on the aggregate would be worse than the status quo: it turns a bounded 50% under-estimate into an unbounded over-estimate for turns made of many short requests. Grok already reports what it charged, per turn, in `_meta.usage.costUsdTicks`. Parse it, carry it through agent -> daemon -> API, and store it on task_usage as a nullable BIGINT of 1e-10 USD ticks (integer, so sub-cent turns stay exact end to end). NULL means the provider reported no cost — every pre-existing row and every provider that doesn't return one. No backfill: there is no authoritative figure to recover for those, and inventing one is the guess this removes. A single hourly bucket can mix rows that carry a cost with rows that don't, so task_usage_hourly gains both halves: `cost_usd_ticks` sums the authoritative side, and `uncosted_*_tokens` carry exactly the tokens that still need a rate-table estimate. Consumers report authoritative + estimate(uncosted), which degrades to today's behaviour when nothing in the bucket is authoritative. The existing token columns keep covering every row, so token displays are untouched. The new columns are additive with defaults, so the unique key, the dirty-queue shape, and migration 102's triggers are unaffected. Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> * feat(usage): prefer the provider's own cost over the rate table With the authoritative figure now stored, both cost consumers use it: the usage dashboard (estimateCost / estimateCostBreakdown) and the server-side llm_cost_usd metric. Each reports `authoritative + estimate(uncosted tokens)`, so a row or bucket that mixes priced and unpriced sources stays whole. The static rate tables remain, but for Grok they are now a fallback — they still price usage recorded by a daemon too old to report cost, and every provider that reports none. Custom pricing overrides likewise apply only to the estimated half: they are a user's guess at a rate, and the authoritative half is not a guess. A model with no rate-table row but a provider-reported cost now also drops out of the "unmapped models" banner, since asking the user to supply a rate for it would invite overriding a real bill. llm_cost_usd is labelled by token_type and the provider reports one number per turn, so the charge is distributed across the buckets in the rate table's own proportions. Only the total is authoritative; the split stays an estimate, which is why this scales the existing buckets rather than inventing a label. estimateCostBreakdown does the same, keeping the stacked chart summing to the headline figure instead of silently under-drawing every Grok row. Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> * docs(changelog): say Grok cost now follows xAI's actual charge The earlier wording scoped the claim down to catalog pricing and cached input because the long-context tier was still unhandled. It is handled now — the cost comes from what xAI charged for the turn — so the entry can say so. Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> * fix(usage): keep the provider's cost when the model has no rate row Both cost consumers bailed out before reading the authoritative figure when the rate table had no row for the model. A `grok-composer-*` turn — in the Grok Build catalog, absent from xAI's price sheet — was therefore reported as $0 spend even though xAI told us exactly what it charged. Worse on the client: estimateCost returned the real cost while estimateCostBreakdown returned zeros, so the headline and the stacked chart disagreed on precisely the rows whose cost is exact — and the unmapped-models banner was (correctly) hidden, so nothing explained the discrepancy. Handle the charge before the rate lookup in both places. Without rates there is nothing to split a total by, so it lands whole in the `input` bucket, the same fallback distributeAuthoritativeCost already uses when it has no shape to scale. Tokens with no rate keep going to llm_unpriced_tokens: "unpriced" describes the rate table, not the money. Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> * perf(usage): drop the historical rewrite from the cost-split migration Migration 213 rewrote every existing task_usage_hourly row to seed the uncosted counters. That is a full-table UPDATE inside a schema migration — lock time, WAL and bloat all scaling with table size — for rows this issue explicitly does not care about. Deleting the UPDATE alone would have zeroed historical cost: with `NOT NULL DEFAULT 0`, an untouched row asserts "nothing here needs estimating", so every pre-split bucket would report $0 until the rollup happened to touch it. Make the uncosted columns nullable with no default instead. NULL means "never recomputed since the split existed", readers COALESCE it to the row's own token total ("estimate all of it"), and the pre-split behaviour is preserved exactly — with nothing to seed, so no rewrite. A bare ADD COLUMN is metadata-only, so this is now fast DDL. Rows heal into the split naturally as the rollup recomputes their buckets. Verified on a fresh database: a legacy-shaped row reads back as its full tokens to estimate, and a group mixing legacy and post-split buckets sums to the authoritative cost plus both rows' estimable tokens. Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Bohan-J <bohan@devv.ai> Co-authored-by: J <agent@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
6992c58de3 |
MUL-5185: add Codex Fast mode (#5821)
* feat(agents): add Codex fast mode (MUL-5185) Co-authored-by: multica-agent <github@multica.ai> * fix(agents): make Codex Fast override authoritative Co-authored-by: multica-agent <github@multica.ai> * fix(agents): remove Codex Fast config conflicts Co-authored-by: multica-agent <github@multica.ai> * chore: refresh checks after conflict resolution Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Jiayuan Zhang
|
e8746c5030 |
fix(onboarding): eliminate Desktop runtime-step false-negative flash + parallelize daemon version detection (MUL-5119) (#5756)
* perf(daemon): parallelize runtime version detection during registration (MUL-5119) Registration probed each agent CLI's `--version` serially, so total latency was the sum of every probe. On an onboarding host with several coding tools installed that stacked into many seconds before runtimes registered — long enough that the desktop runtime step timed out into its empty 'no runtime found' state while the daemon was still working. Fan the probes out with a bounded errgroup so total latency tracks the slowest single probe instead of their sum. Each probe still self-heals a vanished pinned path and re-detects the live version (no cross-registration caching, so an in-place upgrade is still reported correctly); failures are logged and skipped as before. Results are sorted by provider for a deterministic payload. Co-authored-by: multica-agent <github@multica.ai> * fix(onboarding): stop the runtime step flashing 'no runtime found' while the daemon probes (MUL-5119) The runtime step flipped from scanning to the empty 'no runtime found' state on a fixed 5s wall-clock, so a machine that does have coding tools installed saw a false-negative flash whenever registration outlasted the timeout (cold start, slow/wedged CLI, many CLIs). Gate the empty flip on a desktop-only `runtimesPending` signal derived from the local daemon's live status (booting, or running with agent CLIs detected on the host): while pending, keep the scanning skeleton past the soft timeout. An absolute hard-timeout ceiling still guarantees a fallback so a wedged probe can't pin the step on the skeleton forever. Web omits the signal and keeps the plain wall-clock timeout. Also drop the two dead/duplicated affordances on the step: the permanently disabled 'Start exploring' button now renders only in the found phase, and the empty state's duplicate footer 'Skip for now' is removed in favour of its own Skip card. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Lambda <lambda@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Jiayuan Zhang
|
5d9295ac65 |
feat(agents): add per-agent runtime skill controls (#5686)
* 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> |
||
|
Bohan Jiang
|
a5a42846e6 |
fix(daemon): retry with a fresh session only when the resume was actually rejected (MUL-4966) (#5715)
* 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> |
||
|
Bohan Jiang
|
fbe00ca164 |
fix(daemon): run Codex unsandboxed on Windows to stop reject-by-policy (MUL-4957) (#5672)
* fix(daemon): run Codex unsandboxed on Windows to stop reject-by-policy (MUL-4957) Windows has no Landlock/Seatbelt-equivalent filesystem sandbox that the daemon configures, so the per-task `sandbox_mode = "workspace-write"` it wrote was unenforceable. Worse than having no sandbox, it pushed Codex into rejecting non-safe mutation commands "by policy": `multica issue create` fails with "was rejected by policy" because Codex can neither sandbox the command nor (under approval_policy = "never") escalate it to the daemon's auto-approver, so the request never reaches the approver. Mirror the existing macOS fallback and give Windows danger-full-access so those commands run. Also generalize the danger-full-access warn log so it no longer hardcodes "on macOS" and only surfaces the macOS-specific upgrade hint on macOS (new codexSandboxPolicy.Hint field). Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): correct Windows sandbox rationale and respect user windows.sandbox (MUL-4957) Addresses two review must-fixes on #5672: 1. Correct a false security fact. The comments and log Reason claimed Windows has no filesystem sandbox backend. Codex 0.144.5 does ship a native Windows sandbox (windows.sandbox = "unelevated"/"elevated"); it is experimental with open upstream reliability bugs, so the daemon defaults to danger-full-access as a deliberate compatibility choice. Enabling the native sandbox is tracked as separate follow-up work. 2. Stop silently downgrading users who opted into isolation. The fallback was unconditional. Add codexSandboxPolicyForConfig: on Windows an explicit windows.sandbox = unelevated|elevated keeps workspace-write so Codex enforces task isolation with the user's chosen backend; danger-full-access applies only when windows.sandbox is absent, disabled, or unparseable. This is also the branch point for a future native-sandbox rollout (flip the default; callers unchanged). Adds fixture tests locking the priority (user opt-in kept vs. unconfigured fallback) plus predicate coverage for codexSandboxPolicyForConfig. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): fail closed on undecidable Windows sandbox config, honor -c windows.sandbox (MUL-4957) Second review round on #5672. Two must-fixes. 1. Undecidable config no longer fails open. The old bool detector collapsed "unparseable / invalid value / failed copy" into "unconfigured" and then loosened to danger-full-access. Replaced with a tri-state (absent/native/undecidable): only exact-lowercase unelevated|elevated (the sole values Codex accepts — verified: any other value makes Codex refuse to load the config) counts as native; any other present value, unparseable TOML, a read error, or a missing per-task config when a shared ~/.codex/config.toml exists (i.e. the copy failed) is undecidable and fails closed to workspace-write — it never loosens — logged at error level. 2. windows.sandbox set via `-c`/`--config` custom args is now honored. Such args never land in config.toml, so config-only detection silently downgraded those users' isolation. The effective Codex args (daemon defaults + profile-fixed + per-agent custom_args) are threaded through PrepareParams/ReuseParams/CodexHomeOptions into the sandbox decision and scanned for a windows.sandbox override (inline, two-token, quoted, spaced; last-wins). Also drops issue-status-bound source comments (openai/codex#24098 has since closed). Adds unit coverage for config/args classification, the fold precedence (undecidable > native > absent), and the copy-failed fail-closed path. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): fail closed on config-sync errors and honor shell-quoted -c windows.sandbox (MUL-4957) Round-3 review must-fixes: 1. resolveWindowsSandboxState now takes the config.toml sync error and a tri-state shared-config presence instead of re-stat-ing inside. A failed sync (stale/absent per-task copy) or an un-stat-able shared source is undecidable and keeps workspace-write, closing the fail-open where a failed sync was read as "unconfigured". Splits IO from the decision so the paths are unit-testable without faulting the filesystem. 2. The Windows sandbox decision consumes agent.NormalizeCodexLaunchArgs (the shared helper buildCodexArgs now uses) so a shell-quoted -c windows.sandbox opt-in is normalized identically to launch, instead of being missed by a raw-token scan and silently downgraded. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): abort when the Codex sandbox block cannot be written (MUL-4957) Round-4 review must-fix: ensureCodexSandboxConfig failures were warn-and-continue, so a computed fail-closed workspace-write policy could stay only in memory while config.toml kept a stale danger-full-access from a prior run — the decision failed closed but the effective config failed open. prepareCodexHomeWithOpts now returns the error, which blocks startup on both paths: fresh Prepare fails the task, and Reuse leaves env.CodexHome unset, which configureCodexTaskShellEnvironment already refuses to start. Regression covers the full reuse scenario (stale danger-full-access + failed config sync + failed managed-block write); it fails with "got nil" without the fix. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Bohan-J <bohan@devv.ai> Co-authored-by: multica-agent <github@multica.ai> Co-authored-by: J <j@multica.ai> |
||
|
Bowser
|
f8bf6cd8b9 |
feat(runtime): add Qwen Code runtime (MUL-5015)
Merge approved PR #5666. |
||
|
Bohan Jiang
|
ed57707bb2 |
MUL-4923: bound daemon task preparation time (#5584)
* fix(daemon): bound pre-start task preparation Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): isolate pre-start env preparation Run execution-environment Prepare and Reuse in a killable helper process so a timed-out attempt cannot keep writing after retry. Add FIFO lifecycle and squad Stage retry regression coverage. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): terminate Windows prepare process trees Assign the pre-start helper to a kill-on-close Job Object before releasing its request, wait for all job members to exit on cancellation, and add a Windows runtime regression job. Co-authored-by: multica-agent <github@multica.ai> * ci: target Windows prepare tree regression Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Bohan-J <bohan@devv.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
099e145611 |
MUL-4937: preserve daemon terminal callbacks during shutdown
Merge approved after review; CI checks passed. |
||
|
Multica Eve
|
f738e8ca1f |
MUL-4952: pass agent custom env secrets to Codex shells
Merge approved after review; all CI checks passed. |
||
|
Xisheng Parker Zhao
|
21613131c9 |
fix(kiro): stop repeating runtime brief every turn (#5605)
Co-authored-by: Xisheng-Zhao <zhaoxisheng@xiaomi.com> |
||
|
ZIce
|
92676fbe51 |
fix(daemon): recover from uncertain ws claims
Squash merge approved after review and regression verification. |
||
|
Multica Eve
|
90ee83e10a |
MUL-4925: fix Linux Codex Git metadata writes (#5575)
* fix(daemon): isolate Linux Codex git metadata (MUL-4925) Co-authored-by: multica-agent <github@multica.ai> * refactor(daemon): address isolated-checkout review nits (MUL-4925) - rename sameFilesystemPath -> sameResolvedPath (it compares resolved paths for equality, not same-device), with a clarifying doc comment - prune earlier tasks' agent/* branches when reusing an isolated checkout so a long-lived reused workdir stops accumulating one local branch per checkout; deleteLocalBranches now takes a keepBranch arg and the prune is non-fatal - cover the prune in TestCreateWorktreeReusesIsolatedGitMetadata * fix(repocache): preserve user branches on reuse (MUL-4925) Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
ZIce
|
910671b185 |
Fix Codex task MULTICA_TOKEN passthrough (ZIC-82)
Merge approved PR after independent final review; all required CI checks passed. |
||
|
Naiyuan Qing
|
1507997272 |
fix(agent): stop agents shipping local-path links, make Desktop 404 recoverable (MUL-4899) (#5557)
Agents were writing runtime-local paths into deliverables as clickable links (`[screenshot](/Users/agent/work/shot.png)`). Two root causes, both fixed here. A. The brief never stated the delivery contract. Add an always-on delivery invariant (outside writeOutput's kind switch, so no task kind can inherit none) plus a per-surface file-delivery line for each of the five surfaces. Chat splits into two: `attachment upload` works only on web/mobile chat, never on an IM channel, so ChatChannelType is now threaded into TaskContextForEnv. The claim path only ever looked up Slack bindings, so a Feishu session reported as a web chat and got upload guidance for a channel that cannot carry attachments. Probe every channel type. The chat policy is two independent layers and stays that way: delivery keys off "is there a channel at all"; the `chat history` / `chat thread` commands stay Slack-only because both endpoints are hardwired to h.SlackHistory and there is no Feishu reader — ChatInThread only selects between those two commands, so it stays Slack-only too. Add a CLI hard-fail lint on `issue comment add` / `issue create` / `issue update` as the enforcement backstop. Scoped narrowly, since a false positive blocks a real deliverable: agent task context only (a human's PAT run is untouched), real CommonMark link/image/autolink destinations only via goldmark (a path in a code span or fence — how an agent quotes a path it is discussing — is structurally invisible), and three high-confidence signals only (`file://`, inside the workdir, or an existing local file). A bare `/foo` is a valid origin-relative URI and is deliberately allowed. `issue update` has no --attachment flag, so its hint redirects to `comment add` rather than naming an argument it rejects. B. Desktop presented the resulting router 404 as an unknown crash. 8 of 18 desktop_route_error reports were users clicking such a link and being told the app broke and to file a bug. Split the 404 into a first-class Not Found view: no crash framing, no Report error. Its recovery entry comes from the tab store's active workspace, never from the failed pathname — deriving a slug from `/Users/me/shot.png` yields "Users" and a button to `/Users/issues`, a second 404. Also add a will-navigate trusted-origin guard via the shared loadRenderer (main + issue windows). This is origin hardening only, NOT the mechanism for in-app links: client-side routing never fires will-navigate, so app paths never reach it. Issue windows need no 404 work — their router only accepts paths validated by parseIssueWindowPath and they do not listen for multica:navigate, so a bad path cannot reach them. Server-side completion observation is metric/log only and never blocks: it is lexical (`file://` + task work_dir prefix) because the server cannot stat the daemon's filesystem, and the metric label is a closed enum so no path or reply text reaches Prometheus. Verified: pnpm typecheck/lint/test (3582 tests), go vet, full Go suite including new claim-path integration tests. cmd/multica was verified outside the daemon workdir — inside one, 93 of its tests fail identically on origin/main because the suite walks up and finds the runtime's own task marker. Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
18d41151eb |
feat(gc): batch issue reconciliation (#5534)
Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Wangjue Yao
|
3547201bbe |
fix(daemon): reuse managed workdirs for squad leaders (#5429)
Squad-leader follow-ups on the same issue now reuse the prior daemon-managed workdir and provider session instead of starting fresh, while never binding or locking a user-provided local_directory. Reuse eligibility is keyed off a Prepare-time .managed_env.json provenance marker, so it does not race the completion→GC-metadata write. Closes #5535 Co-authored-by: Bohan <bohan@devv.ai> |
||
|
milymarkovic
|
983545b34d |
KAP-867: retry safe Codex initialize timeouts
Merge reviewed changes after fresh approval and green CI. |
||
|
Multica Eve
|
cf1fc64671 |
MUL-4824: fail closed on incomplete Claude-style result streams (#5522)
* fix(agent): fail closed on incomplete stream results Co-authored-by: multica-agent <github@multica.ai> * fix(agent): tighten empty result fallback Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
5251a0958d |
fix(daemon): bound silent OpenCode streams (#5523)
Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
b13b6d06bc |
fix(daemon): writable per-task HOME for Linux Codex sandbox (MUL-4856) (#5508)
Give Linux codex tasks a writable per-task HOME (+ XDG/npm_config_cache) so npm/Prisma stop hitting EROFS on the read-only sandbox home. Gated to Linux; macOS/Windows and non-codex providers unaffected. Note: does NOT resolve the worktree git-metadata read-only problem tracked in multica-ai/multica#2925 — Codex workspace-write resolves the worktree .git pointer and force-protects the real gitdir read-only even inside writable_roots, so that needs a separate Codex metadata-write permission path. |
||
|
Sanjay Ramadugu
|
06d79c1750 |
feat(agent): add Grok Build CLI as an ACP runtime (#5285)
Add xAI Grok Build (`grok`) as a first-class Multica runtime over ACP (`grok --no-auto-update agent --always-approve stdio`), reusing hermesClient like traecli and kimi. Includes daemon discovery, protocol_family migration 174, model discovery, MCP passthrough, thinking effort, frontend branding, and product docs. Follows xAI's documented headless ACP flow: after `initialize`, read the advertised `authMethods` and send `authenticate` (preferring xai.api_key when XAI_API_KEY is set, else the cached login token) before any session operation — a real, logged-in CLI rejects session/new and session/load without it. Model discovery performs the same handshake so it returns the live catalog instead of the static fallback. `--no-auto-update` is passed as a global flag (and kept daemon-owned in the blocked custom-arg set) so a background update check can't stall an unattended ACP task. Thinking effort uses the current `--effort` flag, and the minimum grok version is 0.2.89 (ACP + authenticate + session/load + session/set_model + MCP + --effort). Closes #2895 |
||
|
YYClaw
|
9eddcaff10 |
fix(chat): defer cancellation-time finalization until the task transcript is stable (#5246)
A quick Stop before the agent's first token no longer races a late reply. Started-but-empty cancellations defer the empty/non-empty judgment until the daemon acks its transcript flush (or a grace-period sweeper fires), then settle to a single outcome. Empty outcomes persist a durable, creator-authorized draft restore (fetched/consumed via a dedicated endpoint, reconnect-safe and at-most-once) instead of broadcasting the prompt over the workspace bus. Closes #5219 |
||
|
Bohan Jiang
|
6cc553e5a3 |
fix(daemon): isolate Codex sessions per task to unblock initialize (MUL-4424) (#5360)
* fix(daemon): isolate Codex sessions per task to unblock initialize (MUL-4424) Codex 0.143+ backfills a per-home session-state DB by enumerating every rollout visible under sessions/ during `initialize`. The per-task CODEX_HOME symlinked the shared ~/.codex/sessions in, so a machine with a large accumulated history (one reporter: ~2000 rollouts / ~22 GiB) stalled `initialize` for tens of seconds — the app-server started but the task produced no output before it was cancelled (github #5273). Give each task its own local sessions/ directory instead: - Fresh task: create an empty local sessions/ so backfill is trivial. - Reused task with a real sessions/ dir: it is authoritative — leave it. - Reused task still holding a legacy symlink (older build): migrate in place. Replace the symlink with a real dir; when resuming, symlink only the single rollout being resumed (never copy — a rollout can be GiB and this is on initialize's critical path); and drop the stale, rebuildable session-state DB (state_*.sqlite*, session_index.jsonl) so Codex re-indexes the task-local sessions. Unrelated per-task DBs (goals_*, logs_*, memories_*) are left intact. Also point the token-usage fallback scan at the backend's per-task CODEX_HOME instead of the daemon-global home, so usage isn't lost now that sessions are isolated there. Complements the #5319 handshake watchdog (which turns a silent stall into a loud, phased timeout); this removes the underlying cause. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): address Codex session isolation review (MUL-4424) Resolves the three blockers from Elon's review of #5360: 1. local_directory context loss. local_directory tasks get a fresh codex-home per task ID (the daemon never reuses their workdir), so task-local isolation stranded every follow-up run with an empty sessions dir and silently restarted the conversation. Their only stable, GC-safe cross-task store is the user's own ~/.codex/sessions (a persistent store under WorkspacesRoot would be orphan-GC'd), so keep the shared-sessions symlink for them (IsLocalDirectory). Managed tasks stay isolated. 2. Migration resume robustness. - Rollout lookup now covers the flat layout and background-compressed .jsonl.zst rollouts, not just nested YYYY/MM/DD *.jsonl — both are legitimate Codex 0.144 history that were previously judged "not found", silently dropping resume. - Exposure hard-links first, then symlinks, never copies — hard links need no privilege and work on Windows within a volume, so the zero-copy path is exercised identically on CI. - The daemon now verifies the rollout is actually present in the task CODEX_HOME (execenv.CodexResumeRolloutPresent) before the brief is generated; if absent it clears the resume from both the backend and the brief instead of telling the agent it is continuing a lost thread. 3. session_index.jsonl is no longer deleted during migration — Codex uses it as the authoritative thread-id -> name store (not rebuildable from rollouts). Only the rebuildable state_*.sqlite* is reset. Tests: 2-round local_directory resume across task IDs; compressed/flat lookup; hard-link zero-copy (os.SameFile); session_index preserved; CodexResumeRolloutPresent + the daemon gate helper (present keeps / absent drops / non-codex + empty no-op). Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): scope Codex sessions to a per-issue store; disclose lost resumes (MUL-4424) Addresses the three blockers from Elon's second review of #5360. 1. local_directory still enumerated the whole machine history. The prior fix re-linked the entire ~/.codex/sessions into every fresh local_directory codex-home, so Codex still backfilled from thousands of unrelated rollouts on `initialize` (measured ~8.3s with 3450 rollouts; the reporter's 22 GiB could exceed the 30s watchdog). Point sessions/ at a persistent, per-(agent, issue) store under the shared Codex home (multica-sessions/<agent>/<issue>) that holds only this issue's rollouts. It is keyed stably across task IDs and lives outside the task-scoped envRoot the GC reclaims, so follow-up runs resume it while `initialize` only ever sees this issue's history. 2. Windows cross-volume resume was lost. Exposing a single rollout by hard-link (same-volume only) then file symlink (needs Windows privilege) can't cross a volume boundary. The store now lives on the shared Codex volume, so the resume rollout is hard-linked there zero-copy, and sessions/ is exposed to the task home via a directory link — a symlink on Unix, a junction on Windows — which crosses volumes without privilege and never copies a (possibly GiB) rollout on initialize's critical path. There is no remaining per-file cross-volume link. 3. An unavailable resume was a silent downgrade. Both resume gates (gateResumeToReusedWorkdir, gateCodexResumeToRolloutPresence) now set PriorSessionResumeUnavailable, and the runtime brief renders a Session Continuity Notice telling the agent to disclose to the user, up front in its reply, that the previous conversation context could not be restored and this run starts fresh — turning a silent restart into a user-visible one. The task is not failed: it can still do useful work without the prior context. Managed fresh / reused-real-dir tasks keep their task-local, GC-collected sessions dir unchanged; only the legacy-symlink migration with a resume routes through the store (cross-volume-safe), and a home already linked to the store is treated as authoritative on reuse. Tests: local_directory per-issue store (only this issue's history, no whole- machine leak); no-key fallback to an empty dir; two-round resume across task IDs through the store; legacy migration routed through the store with a zero-copy hard link; reused store link stays authoritative; both gates set the resume-unavailable flag; brief renders the continuity notice only when a resume was lost. execenv + daemon + pkg/agent packages, go vet, and gofmt all pass. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): disclose live resume-RPC loss; bound Codex session store lifecycle (MUL-4424) Addresses the two blockers from Elon's third review of #5360. 1. A real thread/resume failure was still a silent new session. The brief's Session Continuity Notice only covers losses the daemon detects before launch (workdir not reused, rollout absent). But when the rollout is present yet Codex rejects the live thread/resume (corrupt/incompatible rollout, server-side thread GC, schema drift), startOrResumeThread falls back to thread/start and the run succeeds on a fresh thread with no user-facing signal. Carry the original resume intent into the backend as ExecOptions.ResumeExpected (set from the post-gate PriorSessionID, so a pre-flight drop still routes through the brief and never double-notifies), and when a resume was expected but the backend landed on a fresh thread, prepend the same continuity notice to the first turn/start input. This also covers the daemon's transport-error fresh-session retry, which clears ResumeSessionID but not ResumeExpected. 2. The persistent per-issue store had no data lifecycle. multica-sessions stores live outside the task-scoped envRoot the GC reclaims (so resume survives across task IDs), which meant a done/abandoned issue's prompts and full rollouts (one reporter: a single 1.5 GiB rollout) accumulated forever and were never freed on issue/agent/workspace deletion. Add PruneCodexSessionStores: the daemon GC loop reclaims any store untouched for GCCodexSessionTTL (default 14 days, configurable via MULTICA_GC_CODEX_SESSION_TTL, 0 disables). A store's newest rollout mtime is its last activity, so an active or recently-resumed task keeps its store fresh and is never reclaimed, while a deleted issue's store ages out — an eventual reclamation guarantee without needing deletion events. Tests: codexTurnInput discloses on resume fallback and stays silent on success / fresh start (paired with the existing live-RPC fallback test); store pruning reclaims aged stores, keeps recent ones, isolates issues, cleans empty agent dirs, and is disable-able. execenv / daemon / pkg/agent, go vet, gofmt all pass. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): protect a reopened Codex session store from GC mid-mount (MUL-4424) Addresses Elon's fourth-review blocker: reopening an issue idle past GCCodexSessionTTL could lose context, because mounting its per-issue session store (MkdirAll + rollout lookup + task-home link) never refreshed the store's mtime, so a GC cycle firing before the resumed turn wrote its first rollout saw a >TTL-old store and reclaimed it — a stat->remove race with no in-use guard. Two complementary defenses: - Activity refresh: linkCodexSessionsToStore now os.Chtimes the store to now after linking, so codexStoreStat (which reads the newest mtime as last activity) sees a just-used store. This fixes the sequential repro — a mount immediately followed by a prune keeps the store. - In-process active-store guard: the daemon marks the per-issue store in-use (execenv.CodexSessionStorePath) from before Prepare/Reuse mounts it until the task ends, and PruneCodexSessionStores now takes an isActive predicate and skips any store a live task holds. Because prepare and prune run in the same process, this closes the remaining concurrent stat->remove window the mtime refresh alone cannot. Reference-counted, mirroring the env-root guard. Tests: a reopened >TTL store survives a GC cycle after remount and stays resumable; an idle-on-disk store marked active is skipped, then reclaimed once inactive; the existing idle-reclaim / isolation / disable / empty-agent-dir cases still pass. execenv + daemon, go vet, gofmt all pass. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): make Codex store delete atomic with mark-active (MUL-4424) Addresses Elon's fifth-review blocker: the active-store guard's check and delete were not one atomic step. PruneCodexSessionStores called isActive (which locked, read, and unlocked) and only then RemoveAll'd, leaving a window where a task could markActiveCodexStore between the check and the removal and still lose its store — the exact mark-then-delete interleaving Elon reproduced. Replace the point-in-time isActive predicate with a reserve-for-deletion protocol that shares one lock with mark-active: - reserveCodexStoreForDeletion(store) atomically refuses when a live task holds the store (or another delete already reserved it) and otherwise marks it reserved, all under one activeCodexStoresMu acquisition. PruneCodexSessionStores reserves before RemoveAll and commits after, so confirm-inactive and remove are effectively atomic against a concurrent mark. - markActiveCodexStore now waits (on a sync.Cond) while a store is reserved, so a task never mounts a store mid-removal; committing the removal wakes it and the store is recreated fresh by Prepare (with the continuity notice). So mark-before-reserve keeps the store (reserve refused); reserve-before-mark removes it and blocks the late mark until the removal commits. The genuinely idle case still reclaims. Tests (daemon, run under -race): mark-then-reserve is refused; reserve blocks a concurrent mark until commit then the store reads active; a second reserve is refused mid-flight. The execenv prune tests move to the reserve seam; the activity-refresh / reopen-then-prune / isolation / disable cases still pass. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): namespace Codex session stores per profile for cross-daemon safety (MUL-4424) Addresses Elon's sixth-review blocker: the in-process reservation guard cannot span processes, but Multica supports multiple profile daemons on one machine (e.g. production + staging) that share the same ~/.codex. Each daemon's GC scanned the whole multica-sessions root, so a staging daemon could reclaim a store a production task was actively resuming — its reservation lived only in the other process's memory. Isolate by profile instead of trying to lock across processes: - Store path is now <shared>/multica-sessions/<namespace>/<agent>/<issue>, where namespace is the daemon's profile (empty -> "default"). PrepareParams/ReuseParams carry Profile; codexSessionStoreKey and CodexSessionStorePath fold it in. - PruneCodexSessionStores takes the profile and scans ONLY that namespace, so a daemon never even sees another profile's stores, let alone deletes them. The per-profile trees are disjoint, so the in-process guard is sufficient within a namespace (profiles get separate daemon state, so no two daemons share one). Test: a "staging"-owned idle store is untouched by a default-profile prune and reclaimed only by staging's own prune. Existing prune/guard/reopen tests move under the namespace. execenv + daemon under -race, go vet, gofmt all pass. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): make the Codex store profile→namespace map injective (MUL-4424) Addresses Elon's seventh-review blocker: the per-profile namespace was derived by dropping unsafe characters, which is not injective. The CLI treats the empty (default) profile and a profile literally named "default" as separate daemons, yet both mapped to namespace "default"; likewise "staging.prod" and "stagingprod" both mapped to "stagingprod". Two distinct daemons then shared one store tree, so one could again reclaim the other's live session — the cross-process blocker reopened for those profile names. Make codexSessionStoreNamespace injective: the empty profile gets a reserved bare literal "default", and every named profile is hex-encoded (bijective, filesystem-safe) under a "p_" prefix a bare literal can never collide with. So "" -> "default" while "default" -> "p_64656661756c74", and "staging.prod" / "stagingprod" get distinct hex segments. sanitizeCodexPathSegment stays for the UUID agent/issue segments (injective for real UUIDs); only the user-controlled profile needed the encoding. Tests: codexSessionStoreNamespace is distinct for "" vs "default", punctuation variants, case variants, and an encoded-looking name; and end-to-end, pruning one profile never reclaims the other's store for the "" vs "default" and "staging.prod" vs "stagingprod" pairs. execenv + daemon under -race, go vet, gofmt all pass. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): fixed-length Codex store namespace so long profiles fit (MUL-4424) Addresses Elon's eighth-review blocker: hex-encoding the full profile doubled the namespace segment length. A profile can be as long as a filesystem segment allows (~255 bytes) and the CLI persists it as its own config dir, but the store namespace "p_" + hex(profile) reached 2 + 127*2 = 256 bytes at 127 chars, overflowing the 255-byte single-segment limit — the profile's own dir created fine, then the session store failed with "file name too long". Derive the namespace from a fixed-length hash instead: a named profile is now "p_" + hex(sha256(profile)) — a constant 64 hex chars (66 with the prefix), filesystem-safe and collision-resistant. The empty (default) profile keeps its reserved bare literal "default", which the "p_"-prefixed 66-char segment can never equal. Still injective across the CLI's distinct-daemon cases; just no longer length-expanding. Test: the namespace stays <=255 bytes and creatable for profiles up to the 255-byte segment limit (127- and 255-char cases that overflowed under hex); the prior injectivity and cross-profile prune-isolation tests still hold. execenv + daemon under -race, go vet, gofmt all pass. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Rusty Raven
|
ef9b334408 |
MUL-4398: fix Hermes bound-skill discovery with per-task overlay (#5308)
* fix(execenv): overlay per-task HERMES_HOME so Hermes discovers bound skills Hermes has no workspace-relative skill discovery — it scans <HERMES_HOME>/skills first, then skills.external_dirs from config.yaml (verified against the bundled agent/skill_utils.py). The daemon wrote assigned skills to the generic .agent_context/skills/ fallback, which Hermes never reads, so they silently never took effect (#5242). When (and only when) an agent has skills bound, redirect HERMES_HOME to a minimal per-task compatibility overlay; a skill-less Hermes task keeps its real home and original behavior: - mirror every top-level entry of the shared home via symlink except the overlay-owned ones (denylist), reconciling entries deleted from the shared home; - derive a task-local config.yaml whose skills.external_dirs references the shared skills dir plus the user's existing external_dirs, expanded against the sanitized effective child env (unknown vars preserved, blocklisted keys resolved to the process value) and normalized to absolute paths; - write only the bound skills into the task-local skills/ dir (home skills scanned first, so they win); global skills are referenced, not copied; - keep memories/ overlay-owned (fresh per-task dir) AND disable the external memory.provider, so neither on-disk memory nor a shared backend crosses tasks; - keep active_profile/profiles out of the overlay so Hermes can't follow a sticky profile and redirect past it at startup. Profile handling mirrors hermes_cli.profiles: the daemon reads -p/--profile with agent.HermesProfileFromArgs and seeds the overlay from that profile's home via ResolveHermesSourceHome (default/invalid -> base, valid name -> <base>/profiles/ <name>, validated; a missing named profile fails closed). The profile flags are stripped from the acp argv ONLY when the overlay is active (hermesLaunchArgs), so a skill-less task's profile passes through unchanged. HERMES_HOME is no longer custom_env-blocklisted: no skills -> user value passes through; skills -> overlay overrides after layering. Fail closed — Prepare errors, Reuse returns nil. Task home 0700, derived config 0600 via atomic replace. Platform-native default home (%LOCALAPPDATA%\hermes, incl. the LOCALAPPDATA-missing fallback, on Windows). Tests span execenv/daemon/agent: no-skill no-op, child-env layering + env sanitization, profile parse/unquote + conditional strip + final args/env per scenario, custom/profile/default/invalid/missing/Windows source home, sticky- profile not mirrored, memory dir isolation + external provider disable, mirror reconciliation, external_dirs rebasing + sanitized/unknown-var expansion, local-precedence slug, perms, fail-closed, resume teardown. Docs (en + ja/ko/zh). Fixes #5242 * fix(hermes): make profile selection one resolver contract matching Hermes Round 5 review: the profile chain approximated Hermes' semantics in three separate places (argv parsing, source-home selection, arg filtering), so it diverged from native Hermes in several merge-blocking cases. Collapse it into one authoritative resolution: - agent.ParseHermesProfileArgs replaces HermesProfileFromArgs/ FilterHermesProfileArgs. It reproduces _apply_profile_override step 1/1b (first occurrence, value-flag skipping, `--` and `mcp add --args` boundaries, space-form profile-id guard) and returns the exact argv occurrence to consume; StripHermesProfileArgs removes only that occurrence. - execenv.ResolveHermesProfile replaces ResolveHermesSourceHome. It derives the Hermes root exactly like get_default_hermes_root (an already-profile-scoped HERMES_HOME roots at its grandparent), selects an explicit profile first, otherwise trusts a profile-scoped home (step 1.5) and only then the sticky <root>/active_profile (step 2), and validates via normalize/validate_profile_name (reserved hermes/test/tmp/root/sudo and empty inline `--profile=` are hard errors). Profiles always resolve under the root, so `-p default` re-roots and `-p <sibling>` is a sibling, never nested. - The daemon runs one parse + resolve, fails the task closed on a reserved/ invalid selection (matching Hermes' sys.exit(1)), and exports the selected source home as the effective env's HERMES_HOME so ${HERMES_HOME} in a profile's skills.external_dirs expands against the selected profile home (as native Hermes does before loading config.yaml), not the root or the overlay. Regressions added: root + sticky named profile selection; already-profile-scoped home with no flag; that home with -p default and -p <sibling>; reserved and empty inline profile values; and a selected profile whose external_dirs contains ${HERMES_HOME}. * fix(hermes): overlay-owned derived .env + symlink-resolved root Round 6 review, two remaining overlay-bypass paths: 1. A source `.env` could redirect HERMES_HOME after profile resolution. Hermes runs `_apply_profile_override()` then `load_hermes_dotenv()`, which loads `<HERMES_HOME>/.env` with override=True — so a mirrored source `.env` carrying an out-of-band `HERMES_HOME=` overwrote the overlay's home, repointing skill discovery and memory back at the source. `.env` is now overlay-owned and DERIVED (writeDerivedHermesEnv): it preserves the source's credentials/settings but strips any `HERMES_HOME` assignment and pins `HERMES_HOME` to the overlay last (single-quoted, literal), written 0600 via atomic replace. It is written even when the source has none, so Hermes' project-`.env` fallback (override=True only when no user `.env` loaded) can't relocate the home either. 2. Root derivation was lexical-only, diverging from `get_default_hermes_root`, which compares `env_path.resolve()` with `native_home.resolve()`. A HERMES_HOME symlinked into `<native>/profiles/<x>` was treated as its own root, so `-p default`/`-p <sibling>` resolved wrong. `hermesRootFromHomeFor` now resolves symlinks (Path.resolve(strict=False)-style best effort) for the containment decision while keeping the returned root unresolved, matching Hermes. Regressions: source `.env` with HERMES_HOME replayed through the override=True dotenv order (bound skill + task memory stay on the overlay; creds preserved); minimal overlay `.env` created when the source has none; and a symlinked profile home resolving `-p default`/`-p <sibling>` to the native root. |
||
|
Multica Eve
|
a91a390d48 |
fix(cli): recover daemon executable path (MUL-4514)
* fix(cli): recover daemon executable path Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): reuse executable fallback for restart Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
af9d90bd83 |
fix(daemon): wake queued tasks after predecessor exits (#5379)
Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
34d5445007 |
fix(daemon): self-heal pinned agent executable path after in-place upgrade (MUL-4486) (#5355)
The daemon pins each agent CLI's symlink-resolved absolute path at startup to
block PATH-redirect of a task launch. A version manager (Homebrew Cask, nvm/fnm)
upgrading in place deletes the pinned versioned directory and repoints the stable
name, leaving the daemon on a path that no longer exists — every codex task, model
list, and version detection then hard-fails with "executable not found" until the
daemon restarts.
resolveAgentEntry now self-heals a vanished pin by re-resolving the recorded
command once, version-detecting and min-version-gating the candidate before
adopting it, and publishing {path, version} atomically so callers key policy off
the binary that actually runs. Coalesced with singleflight; a live heal wins over
a reappearing stale path; custom runtimes and custom-only hosts are untouched.
Applied at task launch, model listing, and registration.
MUL-4486
|
||
|
Multica Eve
|
ac62f72c2a |
MUL-4480: make daemon workspace sync event-driven (#5354)
* feat(daemon): make workspace sync event-driven Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): preserve trailing workspace changes Co-authored-by: multica-agent <github@multica.ai> * fix(workspace): reconcile failed creates Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
c3dd9ec845 |
Machine-level batch task claim endpoint (MUL-4257) (#5193)
* feat(daemon-claim): machine-level batch task claim endpoint (MUL-4257) Collapse the per-runtime /tasks/claim poll fan-out into a single machine-level batch claim to cut /api/daemon claim request volume. Server: - agent.sql: = ANY(runtime_ids) batch variants of the claim queries (ListQueuedClaimCandidatesByRuntimes, PromoteDueDeferredTasksForRuntimes, ReclaimStaleDispatchedTasksForRuntimes); runtime.sql: GetAgentRuntimes(= ANY) so a whole machine's runtimes are resolved/promoted/reclaimed/listed in a constant number of queries instead of N. - service.ClaimTasksForRuntimes: claim up to max_tasks across a runtime set, preserving per-(issue,agent) serialization, the concurrency cap, the empty-claim cache short-circuit, and every dispatch side effect. Batch promote replays the per-row side effects (task:queued + empty-cache Bump). - handler.ClaimTasksByRuntime (canonical POST /api/daemon/tasks/claim, with a transitional /claim alias): validates daemon_id (required; must match the mdt_ token) and rejects runtimes bound to a different daemon (group-ownership check mirroring the WS path); resolves+authorizes each runtime_id; claims; and finalizes each task through the SAME FinalizeTaskClaim as the per-runtime endpoint (atomic token + delivered_comment_ids receipt), requeueing the exact claim and omitting it on failure. buildClaimedTaskResponse is extracted from the per-runtime handler and returns the delivered-comment ids plus a structured *claimBuildFailure so both paths share identical payload building and failure semantics (workspace-isolation, chat-input load/empty). - max_tasks: negative -> 400, zero -> empty (never coerce to 1), positive capped at 32. runtime_ids parsed with non-panicking util.ParseUUID. Daemon: - Client.ClaimTasks posts daemon_id + runtime set + free-slot count to the canonical path under a short request-scoped timeout, bounding the head-of-line coupling the per-runtime pollers avoid (MUL-1744). Tests: service batch drain / max_tasks cap / deferred-promote receipt / finalize-failure rollback+requeue; handler routing + token, cross-workspace skip, cross-daemon skip, daemon_id required, owner-missing cancel, max_tasks=0/negative, invalid-uuid skip, comment delivery receipt, stale-reclaim replacement receipt; client posts/parses (daemon_id + canonical path). Follow-up: cut the daemon pollLoop over to a single batched poller (flips the MUL-1744 isolation contract; needs its concurrency tests redesigned). Co-authored-by: multica-agent <github@multica.ai> * feat(daemon-ws): generic WS request/response transport for daemon RPC (MUL-4257) Add a generic daemon->server request/response layer over the existing WS control connection, the transport for WS-first claim (HTTP fallback): - protocol: daemon:rpc_request / daemon:rpc_response envelopes with a correlation request_id + method + body, and an rpc-v1 capability gate. - daemonws.Hub: SetRPCHandler + goroutine-dispatched handleRPCFrame (bounded by a per-connection in-flight cap) that echoes the request_id; missing handler / saturation return non-2xx so the daemon falls back to HTTP. Read limit raised to 64KB for rpc requests carrying a runtime set. - hub tests: round-trip, handler-error->non-2xx, no-handler->503. Co-authored-by: multica-agent <github@multica.ai> * feat(daemon-ws): WS-first task claim over the generic RPC transport (MUL-4257) Bind claim to the WS request/response layer, with HTTP fallback: - server: handler.DaemonRPCHandler adapts a daemon:rpc_request (method tasks.claim) to the existing HTTP ClaimTasksByRuntime via a synthetic in-process request carrying the WS connection's identity (daemon_id + workspace + capabilities), so all auth / payload-building / finalization is reused unchanged. Wired via daemonHub.SetRPCHandler. ClientIdentity now captures X-Client-Capabilities so capability gating matches the HTTP path. - daemon: wsRPCClient correlates responses by request_id over the shared WS connection; attached to the live connection's write channel (guarded so a Call racing teardown never sends on a closed channel) and detached on disconnect. rpc_response frames are routed in the read loop. Daemon.ClaimTasksWSFirst issues tasks.claim over WS and falls back to the HTTP claim endpoint on any transport failure (no conn / buffer full / timeout) — wired into the poller at the poller cutover. - tests: handler tasks.claim RPC end-to-end (claims + dispatches) + unknown method 404; daemon wsRPCClient round-trip / timeout / unavailable / server-error / detach-fails-pending (all under -race). Co-authored-by: multica-agent <github@multica.ai> * feat(daemon): cut claim poller over to machine-level ClaimTasksWSFirst (MUL-4257) Replace the per-runtime HTTP poll loop with a single batch poller: each cycle acquires all free execution slots (slot-before-claim) and issues ONE ClaimTasksWSFirst across every runtime the daemon hosts (WS-first, HTTP fallback), dispatching each returned task to its runtime. Wakeups (targeted / catch-up / runtime-set change) collapse to one nudge. Removes runRuntimePoller + runtimePollOffset. The WS handshake now advertises the same capabilities as HTTP (+ rpc-v1) so WS-built claim payloads keep skill-ref / coalesced-comment gating. Trades per-runtime isolation (MUL-1744) for one request, bounded by the short per-request WS timeout / client timeout. Tests: batch poller claims across runtimes + skips-at-capacity + pollLoop shutdown drain (replacing the per-runtime poller tests); heartbeat isolation + runtime-set watcher kept. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon-ws): WS RPC disconnect-race panic + batch stale-comment-plan repair (MUL-4257) Two PR #5193 review blockers: 1) WS RPC send-on-closed-channel race, both ends: - server: give each connection a cancelable ctx (cancelled on readPump teardown) and run the RPC handler under it, so a slow claim stops on disconnect; guard c.send with sendMu/sendClosed (trySend) so a late RPC response goroutine never writes to the closed channel. Heartbeat ack routed through the same guard. - daemon: wsRPCClient.deliver now sends under the mutex, serialized with attach(nil)'s close+delete, so a delivered response can't hit a channel the detach path just closed. - regressions (-race): daemon deliver-vs-detach; server disconnect-during-handler-response. 2) batch claim now runs the stale-comment-plan repair: extracted the per-runtime handler's repair (trigger deleted, only coalesced survive -> cancel + replay survivors) into shared repairStaleCommentPlanIfNeeded, called by both claim paths. Prevents the batch path (now the default poller) from finalizing+dispatching a task with no comment input and silently dropping the surviving user comment. Regression: batch omits the stale task, cancels it, and rebuilds the survivor into a new trigger plan. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon-ws): server-side RPC deadline + legacy claim fallback (MUL-4257) Two review blockers: 1) WS RPC timeout/fallback (GPT-Boy): the daemon's WS wait didn't cancel server-side claim, so a slow WS claim could commit after the daemon fell back to HTTP, leaking dispatched tasks and breaking the free-slot bound. Fix: RPC envelope carries TimeoutMs; the server bounds the handler ctx by it (so ClaimTasksByRuntime's tx is cancelled/rolled back at the deadline), and the daemon waits budget + grace so a claim that committed before the deadline still reports back. A committed-then-unreported claim degrades to the same stale-reclaim safety net as HTTP, never a double effective claim. Regression: server-side TimeoutMs cancels the handler. 2) Backward compat (Terra-Boy): a new daemon against a server without the batch route (/api/daemon/tasks/claim 404) couldn't claim. Fix: ClaimTasksWSFirst falls back to the legacy per-runtime ClaimTask loop on a batch 404 and caches 'batch unsupported' (reset on WS reconnect to re-probe after a server upgrade). Regression: server exposing only the legacy route. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon-ws): no double-claim on WS teardown/detach (MUL-4257) Sol-Boy review blocker: on reconnect, teardown failed the pending RPC (→ HTTP fallback) but then flushed the queued tasks.claim frame to the still-alive socket, so the server committed the WS claim on top of the HTTP one — double claim, WS batch orphaned to stale reclaim, breaking the free-slot bound. - Teardown now closes the connection FIRST, so runWSWriter discards the queued RPC frame (write error path) instead of delivering it. - A detach while a claim's frame is already in flight now returns a distinct errWSRPCUncertain; ClaimTasksWSFirst does NOT HTTP-fall-back on uncertain (the WS claim may have committed) — it skips the cycle and lets reclaim / the next poll recover. Genuine 'not sent' / timeout still fall back (safe: the server-side deadline guarantees no uncommitted claim by budget+grace). - Regression: detach during an in-flight WS claim asserts zero HTTP claims (at most one path claims); plus the existing detach/deliver-race and server-timeout tests. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon-ws): cancelable RPC frames close the backpressure double-claim (MUL-4257) Sol-Boy review blocker: the client's response budget starts at enqueue, but the socket write is async (10s write deadline). A backpressured writer could hold a tasks.claim in the local queue past the client timeout — the daemon HTTP-fell-back, then the writer woke and delivered the stale WS frame, so the server committed it too: same free slots claimed twice. No detach occurs, so the prior errWSRPCUncertain fix did not cover it. - WS frames are now cancelable (wsOutbound{sent,canceled} under a mutex). The writer calls beginWrite() before WriteMessage and skips cancelled frames. - On give-up (timeout / detach / ctx), Call cancels the queued frame: if it was still pending the cancel wins and the frame is guaranteed never delivered (errWSRPCUnavailable → safe HTTP fallback); if the writer already began sending it the cancel loses and the outcome is errWSRPCUncertain (no fallback). The decision is atomic, so at most one transport claims. Tests: wsOutbound cancel-before-write vs write-before-cancel; Call timeout cancels an unsent frame (writer then drops it) vs uncertain when already sent; plus the updated detach and existing timeout/race tests. Co-authored-by: multica-agent <github@multica.ai> * fix(batch-claim): return partial success instead of dropping committed claims (MUL-4257) Sol-Boy review blocker: ClaimTasksForRuntimes reclaims (step 2) and claims per agent (step 6) in independent transactions, but a step-4 candidate-SELECT error or a mid-loop ClaimTask error did 'return nil, err' — discarding tasks already committed as dispatched. The handler 500s; the daemon sees a definite (non- uncertain) 500 and HTTP-falls-back, claiming a SECOND batch into the same free slots while the first batch waits for stale reclaim — the double-claim this PR removes. - Both error paths now prefer partial success: if any task has already committed (claimed non-empty), return it (nil error) so the handler finalizes and returns 200; the errored candidates stay queued for the next poll. The remaining error is logged. Only a genuinely empty result still returns the error (safe: no committed claim to lose, HTTP fallback just re-fails). Regression (internal/service, DB-backed, fault-injected): - PartialSuccessOnSecondAgentClaimFailure: fail the 2nd ClaimTask's Begin → the first agent's committed task is returned, not dropped. - PartialSuccessOnCandidateQueryFailureAfterReclaim: a stale dispatched task is reclaimed, then the candidate SELECT fails → the reclaimed task is returned. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
69ad806881 |
MUL-4472: fetch runtime profiles on demand
Merge approved after review; includes WS reconnect reconciliation and regression coverage. |
||
|
Multica Eve
|
ab54c2be54 |
MUL-4471: refresh workspace repos on demand (#5334)
Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
41b3045efa |
MUL-4424: bound Codex app-server startup RPCs (#5319)
* fix(codex): bound app-server startup RPCs Co-authored-by: multica-agent <github@multica.ai> * test(codex): de-flake bounded-handshake test The single 500ms handshake bound was shared by the successful preamble RPCs, so a slow fork/exec of the /bin/sh fake app-server could make initialize spuriously time out under parallel load. Raise the test bound to 3s (still below the 5s semantic timeout and 10s harness ceiling) and loosen the elapsed assertion to match. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> Co-authored-by: J <j@multica.ai> |
||
|
Jiayuan Zhang
|
a14098288b | feat: redesign agent Skills and MCP capabilities (#5277) | ||
|
YYClaw
|
7a405fd1cf |
fix(daemon): keep the task transcript ordered and complete (#5210)
Two daemon-side fixes to the persisted task transcript: - Wait for the drain goroutine to flush the final message batch before every terminal return (result, timeout, idle-watchdog, upstream cancel), so a consumer reading the transcript at completion can't see a truncated tail. Bounded (10s, then cancel + 12s) so a backend that never closes its message channel cannot stall the terminal transition. - Share the message seq counter across a resume-failure retry so the retry's rows keep ascending seq values instead of restarting at 1 and interleaving with the failed attempt's rows. Server-initiated cancellation read timing is tracked separately in #5219. Closes #5209 MUL-4369 |
||
|
Multica Eve
|
f599333f97 |
[MUL-4348] Route coalesced replies per root thread (#5202)
* feat(daemon): route coalesced replies per root thread (MUL-4348) When a busy agent coalesces multiple @mentions into one run, the run used a single --parent (the newest trigger), so questions raised in separate root threads were answered in one merged comment while the other threads were left unanswered. Group the trigger + coalesced comments by root thread server-side in the prompt builder (commentReplyThreads). When the run spans >=2 distinct threads, emit a per-thread reply plan (BuildMultiThreadCommentReplyInstructions) that instructs one reply per thread with the exact --parent, explicitly overriding the general 'one comment per run' rule. Multiple @mentions from the SAME thread collapse to a single group upstream, so same-thread follow-ups keep the ordinary single --parent=trigger path and can never be split into duplicate replies. Single-thread / non-coalesced runs are unchanged. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): sync workflow-brief reply step with per-thread fan-out (MUL-4348) Review of #5202 found the cross-thread fan-out was injected only into the per-turn prompt (buildCommentPrompt), while the persistent workflow brief (writeWorkflowComment step 7) still emitted the single --parent=trigger cookbook for every comment task. A cross-thread run therefore got two slightly conflicting reply instructions, so the fan-out guarantee rested on prompt wording/precedence rather than structure. Carry the computed thread targets on TaskContextForEnv.CommentReplyTargets (populated from the same commentReplyThreads() the prompt uses, so the two surfaces cannot drift). When >=2 targets, the workflow reply step now emits the per-thread fan-out plan too; same-thread follow-ups collapse to a single group upstream and keep the single-parent cookbook, so they still can never be split. Also clarified the multi-thread cookbook to show a distinct file per reply (reply-1.md / reply-2.md). Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): reply under the specific mentioning comment per thread (MUL-4348 review nit #1) Non-trigger threads previously replied under the thread root, while the trigger's thread replied under the trigger comment — asymmetric, and it put the answer at the top of the thread instead of next to the actual question when the mention was a mid-thread reply. Reply under the NEWEST triggering comment in each thread instead (inputs are chronological, so last-write-wins per thread), making every thread consistent and nesting each answer beside its question. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
8e0fbecab5 |
fix(models): codex empty-model effort validation + exact 5.6 aliases (MUL-4347) (#5196)
Follow-up to #5188 addressing the second-round review. - ValidateThinkingLevel now fails an empty codex model closed instead of borrowing the flagged Default (gpt-5.6-sol). An empty model follows config.toml, which can resolve to any installed model; Sol alone advertises `ultra`, so the old borrow green-lit levels Luna / gpt-5.5 don't support and Codex doesn't reject. Checked before ListModels so a discovery error can't fail it open. Frontend pickModelEntry mirrors this (no per-model effort preview for an empty codex model); the persisted-orphan clear path stays. - parseCodexDebugModels drops efforts without a known label so the picker never advertises a level the Create/Update enum gate would 400 on save; the contract test now drives the real parser with an unknown effort instead of comparing two hand-written maps. - gpt-5.6 price aliases anchor to a literal dot (not the [.-] class), so dashed variants like gpt-5-6-luna surface as unmapped on both backend and frontend rather than silently borrowing a tier. Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
ZIce
|
fe46dfdbf6 |
MUL-4203: Fix Cursor MCP auth source seeding (ZIC-52)
Merge approved PR. |
||
|
beast
|
aecd47b59f |
fix(daemon): mark workspaces root so escaped subprocesses still fail closed (#5044)
Write a persistent daemon-task marker at the workspaces root so a subprocess that lost all MULTICA_* env vars and escaped above its workdir still fails closed instead of falling back to the user's config PAT. Includes daemon-startup pre-ensure, per-task and reuse-path self-heal, torn-marker reclaim, atomic write, and non-fatal degrade. Fixes #5043. |
||
|
Multica Eve
|
0c2e48ded2 |
refactor: retire FF_RUNTIME_BRIEF_SLIM, make slim runtime brief the only path (MUL-4297)
The runtime_brief_slim feature flag has burned in; the slim runtime brief is now the sole path. - execenv: buildMetaSkillContent / BuildCommentReplyInstructions delegate to the slim assembler unconditionally; delete the legacy verbose brief body and writeBackgroundTaskSafetyInstructions. - Remove the runtime_brief_slim flag and the daemon-bound flag delivery subsystem built solely for it: execenv flag wiring (runtime_config_flag.go, server_snapshot_provider.go), the featureflagdispatch package, the DaemonFeatureFlagSnapshot heartbeat protocol field, and the server/daemon wiring in router.go, handler, daemon.go, main.go, cmd_daemon.go. - Keep the generic server/pkg/featureflag engine (still used by composio_mcp_apps). - Update tests to slim-only expectations and docs/feature-flags.md. Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
528d3c7fbb |
fix: use short task temp dirs for agent env (#5140)
Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
LinYushen
|
77a05fb731 |
Revert "feat(daemon): worktree_pool mode for local_directory (MUL-3483) (#4986)" (#5037)
This reverts commit
|
||
|
YOMXXX
|
e002ee5a6b | fix(daemon): isolate agent temp dirs (#5005) | ||
|
Multica Eve
|
7bb8076ed0 |
feat(daemon): worktree_pool mode for local_directory (MUL-3483) (#4986)
* feat(daemon): add worktree_pool mode for local_directory (MUL-3483) ## What changed Squad workflows bound to the same `local_directory` resource used to serialise on a single path mutex — a documented pain point from GitHub issue #4377. This introduces an opt-in `worktree_pool` mode on the `local_directory` project resource. When enabled, each task gets its own `git worktree add` under a daemon-managed pool root, so sibling tasks on the same base repo now run truly in parallel while `git worktree add/remove/prune` stays serialised behind a per-repo mutex. ## Shape - `local_directory.resource_ref` gains three optional fields: `mode` ("in_place" default / "worktree_pool"), `pool_root` (defaults to `<parent>/.multica-worktrees/<base>`), `max_parallel` (defaults to 4). Legacy rows are byte-identical after round-trip: the server validator strips the pool fields on the default in_place path so older clients keep behaving exactly as before. - New `WorktreePoolManager` (`server/internal/daemon/worktree_pool.go`) owns pool allocation, per-repo git-metadata mutex, and cleanup. - `acquireLocalDirectoryLockIfNeeded` now branches on the ref's mode. in_place stays on `LocalPathLocker` and the shared tree; worktree_pool routes through the pool manager, publishes a lease keyed by task ID, and pins the agent to the freshly allocated worktree in `execenv.PrepareParams.LocalWorkDir`. - Pool saturation is a structured wait_reason (`worktree_pool saturated (N/M) on <path> (holders: ...)`), retrying on the existing cancel-poll interval — same UX as the historical path-mutex wait. ## Safety guardrails (also known footguns from prior art) - Repos with initialised submodules are refused up front. Multi-checkout of a superproject is explicitly unsupported by `git worktree(1)` BUGS and the per-worktree `modules/` directories bloat disk by pool size ×. - Dirty worktrees are NEVER `--force` removed on release. If the agent left uncommitted changes behind we keep the directory (and free the slot) so users can inspect. This is the failure mode claude-code#55724 documented and the pool must not regress into. - The per-repo mutex covers every `git worktree add/remove/prune` and `submodule status` invocation for a given base, matching the in-process-queue fix Anthropic settled on for claude-code#34645 (`.git/config.lock` races on concurrent add). - Task UUID is the source of truth for both branch (`multica/<uuid>`) and worktree path (`<pool_root>/<uuid>`) so a single agent running multiple worker tasks in parallel can never collide. - Non-empty leftover directories at the target path abort the allocation instead of silently starting the agent in an unknown state. ## Explicit MVP non-goals (deferred, tracked as follow-up work) - Windows worktree-remove retry (permission-denied on locked handles). - Detached-HEAD fast path for read-only exploration tasks. - `post-checkout` hook opt-out / serialisation. - Automatic `git lfs install`. - UI surfacing of the pool state / dirty worktree list. ## Tests - `worktree_pool_test.go` (new): full acquire→release lifecycle, parallel allocation, saturation with holder list, slot re-use after release, dirty-worktree preservation, concurrent-acquire serialisation (the config.lock guard), submodule refusal, missing base rejection, pool root auto-mkdir, non-empty leftover refusal, ctx cancel. - Handler validator gains three rejection cases (unknown mode, relative pool_root, negative max_parallel) and a round-trip test that pins the normalised JSON shape for both modes. - Daemon `localDirectoryRef` helpers get a defaults test and the pool root path derivation is pinned. ## Wire-compat and rollout - Default off. Existing rows keep the historical shape (no `mode`, `pool_root`, or `max_parallel` in the JSON) and behave exactly as before. - Opt-in via `--ref '{"local_path":"...","daemon_id":"...","mode":"worktree_pool"}'` today. CLI flag shortcuts (`--mode`, `--pool-root`, `--max-parallel`) can follow in a small tail PR — not blocking. - No DB migration. No UI change required. Co-authored-by: multica-agent <github@multica.ai> * feat(daemon): address worktree_pool review nits (MUL-3483) Follow-up to #4986. Three non-blocking review points from GPT-Boy: 1. **Daemon integration test for lease → runTask plumbing.** `TestAcquireLocalDirectory_WorktreePoolPublishesLease` (and its in_place counterpart) pin the exact contract runTask relies on when it reads `d.localLeases.Load(task.ID)` and feeds `lease.WorkDir` into `execenv.PrepareParams.LocalWorkDir`. A future refactor that drops the Store, mistypes the key, or swaps back to `assignment.AbsPath` on the pool branch will now fail here rather than silently defeat the whole point of worktree_pool mode. 2. **Untracked-only dirty case now classifies as dirty.** `worktreeIsDirty` used `--untracked-files=no`, which meant a worktree with only untracked files was reported "clean" and hit the `git worktree remove` branch — git itself would then refuse the removal because the file exists (so no data was lost), but the log path lied about what happened on disk. Switching to `--untracked-files=normal` routes agents' fresh drafts directly through the "leaving on disk for user inspection" branch, and `TestWorktreePool_UntrackedOnlyIsKept` pins the guarantee so nobody quietly reverts the flag later. 3. **Skill doc note on default `pool_root` location.** `multica-projects-and-resources/SKILL.md` now spells out the three new ref fields (`mode`, `pool_root`, `max_parallel`), the default `<parent>/.multica-worktrees/<repo>` location (next to the repo, not inside it), the write-permission requirement on the parent directory, and the submodule restriction — so agents advising self-host users hit the right doc line rather than reading source. Existing test suite still green: - `go vet ./...` clean - `go test ./internal/daemon/... ./internal/handler/... ./internal/service/...` all pass Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
ZIce
|
b2db309618 |
Skip local directory lock for squad leaders (#4951)
Co-authored-by: multica-agent <github@multica.ai> |
||
|
LinYushen
|
cb68669c73 |
feat(composio): gate MCP apps behind feature flag (#4876)
* feat(composio): server-side connect flow + connections REST (Notion MVP) (MUL-3720) (#4608)
* feat(composio): server-side connect flow + connections REST (Notion MVP) (MUL-3720)
Compose the merged server/pkg/composio SDK into a user-facing connection
manager: signed-state connect handshake, local user_composio_connection
mirror, idempotent disconnect, and a per-user MCP session helper (not yet
wired into task dispatch).
- migration 127_user_composio_connection (no FK/cascade, per DB rules)
- sqlc queries: upsert (idempotent on user_id+connected_account_id), list
active, owner-scoped get, mark revoked
- internal/integrations/composio: signed HMAC-SHA256 state, BeginConnect,
CompleteCallback (idempotent upsert), ListConnections, Disconnect
(upstream 404 = idempotent success), CreateMCPSession (no-op when empty,
pins connected_accounts per toolkit), CallbackRedirect
- REST handlers under /api/integrations/composio (user-scoped, 503 when
COMPOSIO_API_KEY unset): connect/init, callback (302), connections list,
delete
- router wiring gated by COMPOSIO_API_KEY; COMPOSIO_AUTH_CONFIGS_JSON maps
toolkit->auth_config (MVP: notion); state secret from COMPOSIO_STATE_SECRET
or derived from JWT_SECRET; callback base from COMPOSIO_CALLBACK_BASE_URL
or MULTICA_PUBLIC_URL
- tests: state (expire/tamper/wrong-secret), service (mapping, callback
idempotency, non-success, disconnect owner/404 idempotency, MCP pin),
handlers (httptest), redact regression for Bearer mcp_ tokens
MVP scope: Notion only; no task-dispatch overlay, sharing, or webhook
event handling (later stages).
Co-authored-by: multica-agent <github@multica.ai>
* fix(composio): bind callback account to user + idempotent revoked disconnect (MUL-3720)
Address PR 4608 review (CHANGES_REQUESTED):
- callback: verify connected_account_id with Composio before mirroring it.
The signed state only proved user/toolkit/exp, so a valid state paired with
a tampered connected_account_id would be written verbatim. CompleteCallback
now calls ListConnectedAccounts and fails closed (ErrAccountVerification)
unless the account belongs to the state's user (composio_user_id == multica
user id) and was created under the toolkit's auth config. No row is written
on mismatch / unknown account / upstream error.
- disconnect: short-circuit to a no-op when the local row is already revoked,
before touching upstream. Previously a second DELETE re-hit Composio and a
non-404 upstream error surfaced as a 502, breaking the 204-idempotent
contract.
- CreateMCPSession: document the v1 single-active-connection-per-(user,toolkit)
constraint and make duplicate selection deterministic (newest-wins, rows are
connected_at DESC) instead of order-dependent map overwrite. Stage 3 owns the
real single-account-enforcement vs multi-account-shape decision.
Tests: tampered/wrong-auth-config/unknown-account callback rejection, revoked-row
disconnect no-op (asserts upstream not re-hit). composio pkg 85% coverage; all
green.
Co-authored-by: multica-agent <github@multica.ai>
* feat(composio): list all toolkits + dynamic auth-config resolution (MUL-3720)
Yushen's follow-up to the Notion MVP: surface the full Composio toolkit
catalog, render it in Settings, and drop the static env mapping in favor of
dynamic auth-config discovery.
Config correctness (per Composio docs):
- Remove COMPOSIO_AUTH_CONFIGS_JSON entirely. The toolkit→auth_config mapping
is now resolved at request time from the project's /auth_configs (cached,
5-min TTL), so enabling a toolkit is a dashboard action, not a redeploy.
- Do NOT add COMPOSIO_PROJECT_ID. The project API key (x-api-key) authenticates
to exactly one project; the project is resolved from the key. Only org-level
endpoints use x-org-api-key, which this integration never calls.
Backend:
- SDK: server/pkg/composio/auth_configs.go — ListAuthConfigs (toolkit_slug,
is_composio_managed, show_disabled, limit, cursor).
- service: dynamic resolver (authConfigMap cache; betterAuthConfig prefers a
custom/white-label config over Composio-managed, newest wins); BeginConnect
and CompleteCallback resolve via it; ListToolkits fetches the full catalog
(paginated, capped) annotated with connectable = has an enabled auth config,
connectable-first ordering.
- handler + route: GET /api/integrations/composio/toolkits (user-scoped, 503
when COMPOSIO_API_KEY unset) returning slug/name/logo/category/connectable.
Frontend:
- core: ComposioToolkit/ComposioConnection types, api client methods, and
composio query options (@multica/core/composio).
- views: Settings → Integrations now has a Composio section rendering every
toolkit as a card with search. Connect is gated on `connectable`;
non-connectable toolkits show a muted "not configured" hint instead of a
dead button. Connected toolkits show a badge + Disconnect (with confirm).
- i18n: composio block added to en/zh-Hans/ja/ko settings.
Tests: SDK + service (dynamic resolution, custom-over-managed preference,
connectable flag, resolver-error soft-degrade) and handler toolkits endpoint;
composio pkg 85.7% coverage. go build/vet/gofmt clean; core+views typecheck,
core+views lint, and core tests (691) all green.
Co-authored-by: multica-agent <github@multica.ai>
* fix(composio): close cross-toolkit callback fail-open by signing auth_config_id into state (MUL-3720)
Re-review blocker: CompleteCallback resolved the toolkit's auth config at
callback time and ignored a resolve error/empty result, while
verifyAccountOwnership skipped the auth-config comparison when the expected
value was empty. A user could then pass another toolkit's connected_account_id
into this toolkit's callback — the owner check passed and it was written under
the wrong toolkit_slug/account binding.
Fix: the auth_config_id is already resolved in BeginConnect (before the state
is signed), so sign it into the state and compare it exactly at callback. No
re-resolve, no fail-open. verifyAccountOwnership now fails closed when the
expected auth config is empty (rejects instead of skipping) and requires an
exact match — closing the cross-toolkit binding gap.
Tests: state round-trips auth_config_id; BeginConnect signs it; callback
rejects wrong/cross-toolkit auth config and an empty (no-mapping) auth config
fails closed. composio pkg 85.2% coverage, all green.
Frontend (non-blocking): the Composio settings tab now surfaces an error when
the connections query fails instead of silently rendering everything as
unconnected.
Co-authored-by: multica-agent <github@multica.ai>
* fix(composio): hide Settings section entirely when integration unconfigured (MUL-3720)
Decision (option 2, hide-then-merge): don't show a card that leaks the internal
COMPOSIO_API_KEY env-var name to every end user. IntegrationsTab now gates the
whole Composio section (heading + body) on the toolkits query — a 503 means the
key is unset, so the section is withheld instead of rendering the not-configured
card. Admin-only setup guidance is a later, role-gated affordance.
Removed the notConfigured card (and now-unused ApiError import) from
ComposioTab; it only mounts when configured. views typecheck + lint clean.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(composio): Stage 2 frontend polish — callback toast, last_used & expired UI, e2e (MUL-3718) (#4688)
* feat(composio): callback toast + refresh, last_used & expired UI, e2e (MUL-3718)
Co-authored-by: multica-agent <github@multica.ai>
* fix(composio): real callback redirect route + StrictMode-safe toast dedup (MUL-3718 review)
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(composio): callback endpoint should not require Multica auth (MUL-3843) (#4709)
* fix(composio): move OAuth callback out of the Auth group (MUL-3843)
Composio 302-redirects the browser to /api/integrations/composio/callback
at the end of the OAuth flow, but PR #4608 mounted it inside the cookie-auth
middleware group. When the session cookie is absent (expired session,
SameSite=Strict / Safari ITP, private window, self-hosted callback subdomain)
the Auth middleware returned a hard 401 and a JSON blob instead of the
settings redirect, breaking the flow.
Identity never came from the cookie anyway: it is carried by the HMAC-signed
state param that CompleteCallback verifies (signature, expiry, replay) and
cross-checked by verifyAccountOwnership; h.Composio == nil still 503s. So the
callback is registered alongside the other public OAuth/webhook routes; the
other four composio endpoints stay session-gated.
Refs MUL-3843, MUL-3715.
Co-authored-by: multica-agent <github@multica.ai>
* fix(composio): correct stale callback routing comments (MUL-3843)
The package header and ComposioCallback doc comments still described the
callback as sitting under the Auth middleware group. After the route was
moved out (this PR), update both to state it is a public route whose identity
comes from the signed state — addressing review nit from 张大彪.
Refs MUL-3843.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(composio): inject MCP overlay into agent runtime at task dispatch (MUL-3721) (#4704)
Stage 3 of the Composio epic. Wires the per-user Composio MCP session into
every agent task so the agent process sees the initiator's connected tools
without any prompt-time plumbing.
Server side
- Migration 128 adds agent_task_queue.runtime_mcp_overlay JSONB plus a
BEFORE-UPDATE trigger that wipes the column on any transition into a
terminal status (completed / failed / cancelled). A trigger is the single
source of truth — future queries that flip status cannot bypass it.
- composio.Service.BuildTaskOverlay(userID) reuses CreateMCPSession and
emits the Claude-style { mcpServers: { composio: { type: http, url,
headers } } } shape the daemon's existing sidecar generators consume.
Returns (nil, nil) on zero active connections so we never burn a
Composio session for a user with nothing to call.
- TaskService grows a Composio ComposioOverlayBuilder seam, wired in
router.go after composiointeg.NewService succeeds. Five enqueue paths
(issue / mention / quick-create / chat / auto-retry) attach the overlay
after CreateAgentTask returns and before the daemon is notified — so
every claim reads a settled row, with no second daemon hop. Best-effort:
a builder failure logs and proceeds with no overlay.
- resolveInitiatorFromTriggerComment derives the initiator user from the
trigger comment when it was authored by a member. Agent-authored
triggers are not treated as initiators (their connected-apps view is
empty by construction).
Daemon side
- handler/daemon.go claim path merges task.runtime_mcp_overlay onto
agent.mcp_config via mergeMCPOverlay before populating
TaskAgentData.McpConfig. Overlay wins on server-name collisions
because it carries the live user-scoped session URL. Errors fall back
to the agent config unchanged — a bad overlay must not surprise-disable
saved MCP tools. The existing execenv sidecar generators (cursor /
codex / openclaw / opencode / hermes-kiro) need no changes: they keep
consuming the merged result through TaskAgentData.McpConfig.
Tests
- 9 merge cases (mcp_overlay_test): both-nil short-circuit, agent-only
pass-through, overlay-only canonicalization, two-side merge, name
collision (overlay wins), top-level key preservation, malformed agent
fallback, malformed overlay fallback, non-object server rejection.
- 4 dispatch cases (composio): zero-connections returns nil without
CreateSession, happy-path emits the right shape with the right user
id, empty-URL defensive branch, SDK error surfacing.
- 4 TaskService helper cases: nil Composio is a no-op (Queries-safe),
invalid initiator does not call the builder, nil overlay skips the
UPDATE, builder error swallowed without panic.
- Migration 128 verified to roll up + down + up cleanly against the test
database.
Out of scope (deferred): assignment-triggered enqueue paths with no
trigger comment get no overlay attached today (no initiator UUID flows
through enqueueIssueTask in that case). Retry paths recompute the overlay
fresh from the parent's initiator_user_id instead of inheriting the bearer
from the parent row, so a stale token can never resurface on a retry.
Co-authored-by: Eve <eve@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
* feat(composio): per-agent allowlist + originator-scoped MCP overlay (MUL-3869) (#4736)
* feat(composio): per-agent allowlist + originator-scoped MCP overlay (MUL-3869)
Stage 3.1 of the Composio epic (MUL-3721 parent). PR #4704 wired in the
runtime_mcp_overlay column and a per-task dispatch hook; this change
inverts the default from "all-on" to opt-in and locks the overlay to the
agent owner's own connected apps:
- Agents carry composio_toolkit_allowlist TEXT[]. NULL or [] => no MCP.
Owner-only read/write; non-owner GET/PUT silently redacts/drops the
field (same shape as mcp_config).
- agent_task_queue carries originator_user_id UUID. Set from the
top-of-chain HUMAN at every enqueue path:
* issue/mention comment by member -> author_id
* issue/mention comment by agent -> inherit via comment.source_task_id
-> parent task originator_user_id
* quick-create -> requester_id
* chat -> initiator_user_id
* retry -> SQL-inherited from parent row
* autopilot -> NULL (system-driven)
- BuildTaskOverlay (composio dispatch) now takes (ctx, originatorUserID,
agent) and short-circuits on five gates: invalid originator,
originator != agent.owner_id, empty allowlist, empty intersection of
allowlist ∩ active connections, defensive empty session URL. Composio
CreateSession is called with BOTH `toolkits.slugs` (the intersection)
AND `connected_accounts` (the pinned account ids), narrowing the
tool-router twice.
- The originator-vs-owner gate closes the agent-fanout privacy hole: any
workspace member who can @-mention a public agent used to project the
owner's connected apps into their run. Now the overlay only mounts
when the human at the top of the chain IS the agent owner.
Tests:
- dispatch_test.go covers all 5 gates plus uppercase/whitespace slug
normalisation.
- task_runtime_mcp_overlay_test.go covers the no-op gates of the new
applyRuntimeMCPOverlay signature.
- agent_composio_allowlist_test.go (handler): owner roundtrip
(list/empty/null), workspace-admin silent-drop, owner-only GET
visibility, pure normaliseComposioToolkitAllowlist.
- resolve_originator_test.go (service, DB-backed): member-authored,
agent-authored inherits via comment.source_task_id, invalid id.
Migration 129 up/down/up verified against docker postgres.
Co-authored-by: multica-agent <github@multica.ai>
* chore(composio): gofmt + regenerate sqlc with v1.31.1 (MUL-3869 review nits)
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Eve <eve@multica-ai.local>
Co-authored-by: multica-agent <github@multica.ai>
* fix(composio): accept nested connected account auth config
* feat(views): creator-only MCP tab for per-agent Composio allowlist (MUL-3870) (#4743)
Stage 3.2 frontend on top of the Stage 3.1 backend (MUL-3869,
|
||
|
Xisheng Parker Zhao
|
4b9ea4aa68 |
feat(agent): add ByteDance TRAE CLI (traecli) as an ACP backend (#4724)
Adds the official ByteDance TRAE CLI (the `traecli` binary documented at https://docs.trae.cn/cli — the product paired with the Trae IDE, not the open-source bytedance/trae-agent) as a built-in agent backend. traecli is ACP-native, so it is driven over the standard ACP JSON-RPC transport via `traecli acp serve --yolo`, reusing the shared hermesClient exactly like the Kiro and Qoder backends. Validated end-to-end against the real traecli v0.120.42 with a logged-in account: initialize advertises loadSession:true + mcpCapabilities{http,sse}; session/new returns result.sessionId + models.availableModels (18 models discovered); session/prompt streams session/update notifications with sessionUpdate=agent_message_chunk (hermesClient already normalizes this Zed-ACP wire shape); a real board task ran 14 tool calls and completed in ~47s. Implementation: - server/pkg/agent/traecli.go: ACP backend; session/load resume (loadSession:true), session/set_model, MCP via ACP mcpServers, --yolo bypass-permissions for headless runs, blocked-arg filtering (acp, serve, --yolo, --print, --output-format, --permission-mode) - agent.go: New() + launch header "traecli acp serve" - models.go: discoverTraecliModels via the shared discoverACPModels - daemon/config.go: auto-detect the `traecli` binary (MULTICA_TRAECLI_PATH / MULTICA_TRAECLI_MODEL) - daemon.go: inline the runtime brief (traecli reads .trae/rules/, not AGENTS.md) and surface the runtime as "Trae" (providerDisplayName) - execenv: AGENTS.md + .traecli/skills wiring; ~/.traecli/skills local root - packages/core mcp-support: traecli consumes mcp_config - frontend: official Trae provider logo - docs: providers.mdx matrix + section, CLI_AND_DAEMON.md, README Tests: fake-ACP unit tests matching the real wire format (streaming, blocked-arg filtering, session/set_model failure, session/load resume) plus a gated real-binary smoke test (TestTraecliRealACPSmoke) that skips when traecli is absent or not logged in. Built-in provider only (mirrors qoder): not in SupportedTypes / RUNTIME_PROFILE_PROTOCOL_FAMILIES, so no migration is needed. Resolves #4376. |
||
|
xiawiie
|
93028d303b |
fix(daemon): reconcile in-flight task and workspace state on WS reconnect (#4718)
After a WebSocket disconnect, the daemon's view of running tasks and workspace state can lag the server for up to 5s (per-task cancellation poll) or 30s (workspace sync) because both loops park on coarse tickers that do not observe the WS wakeup channel. This change adds a small fan-out broadcaster (`reconcileBroadcaster`) that the WS connect path fires once per (re)connect. `watchTaskCancellation` and `workspaceSyncLoop` subscribe and re-check immediately on broadcast, without disturbing the ticker cadence. The broadcaster is edge-triggered with a one-slot replay so a broadcast that lands before a subscriber is ready is not lost (closes the daemon-startup race), and back-to-back broadcasts inside 1s are debounced so a flapping connection cannot fan out into a request stampede. Existing behaviour is preserved: shouldInterruptAgent still decides whether to interrupt, the 5s/30s ticker still bounds the worst case, and the WS heartbeat / HTTP heartbeat coordination is untouched. Closes #4665 |
||
|
Multica Eve
|
f59cb2f494 |
MUL-3834: harden daemon websocket reconnect (#4699)
* MUL-3834 harden daemon websocket reconnect Co-authored-by: multica-agent <github@multica.ai> * MUL-3834 stabilize daemon websocket liveness tests Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
dfa384ffa2 |
fix(daemon): resolve skill bundles per-skill with size-scaled timeout (#4505) (#4530)
* fix(daemon): resolve skill bundles per-skill with size-scaled timeout (MUL-3650, #4505) Cold-start skill resolution downloaded the agent's entire bundle in one atomic request bounded by the shared 30s control-plane http.Client timeout. On a slow/jittery link a large bundle (15+ skills) could not finish the body read in 30s, and because the cache was only written after the whole batch succeeded, nothing was persisted on failure — so every dispatch re-downloaded the full bundle and timed out again, never converging. Resolve each missing bundle in its own request and cache it the moment it arrives: - daemon: per-skill resolve with a deadline scaled to the bundle's declared size (floor 30s, cap 5m, ~50KB/s floor throughput) instead of the fixed control-plane timeout; each success is persisted independently, so a dispatch that fails on one skill still caches the rest and the next dispatch only re-fetches what is missing. - client: dedicated bundleClient with no fixed Timeout (deadline comes from ctx), a singular ResolveSkillBundle, and a short transient-retry schedule. Tests cover the size-scaled timeout and the cross-dispatch incremental caching / convergence (a failed skill does not discard its siblings, and cached skills are not re-fetched). Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): accept server-side skill updates in per-skill resolve (MUL-3650) Address review on #4530: resolveSkillBundle validated the returned bundle against the claim-time ref, which pinned it to the requested hash. The resolve endpoint intentionally serves the agent's current bundle and hash when the requested hash is stale (the skill can be edited between claim and prepare), so a legitimate updated bundle was rejected as invalid and the task failed. Confirm only that the server returned the requested skill (source/id), then validate self-consistency against a ref derived from the returned bundle and cache it under its own hash — matching the documented endpoint contract. Adds a regression test covering a stale-hash request answered with an updated bundle. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |