mirror of
https://gh-proxy.org/https://github.com/klinsmaya/multica.git
synced 2026-11-10 10:26:46 +08:00
admin-workspace-create2
34
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Jiayuan Zhangandmultica-agent
|
231dedb552 |
MUL-8034: chore: clean historical comments across the codebase (#9274)
* chore: clean historical comments (MUL-8034) Co-authored-by: multica-agent <[email protected]> * docs: preserve pending Composio expiry contract Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: multica-agent <[email protected]> |
||
|
Bohan Jiangandmultica-agent
|
624648cc14 |
fix(daemon): offer a Git Bash variant of the Windows reply cookbook (MUL-7554) (#8634)
The Windows brief only knew PowerShell: the per-turn reply cookbook and the Comment Formatting cleanup line assumed every Windows agent pastes into PowerShell. The daemon knows the host OS, not the shell behind the agent's command tool. Claude Code runs Git Bash for its Bash tool, and a user who turns off its PowerShell tool (CLAUDE_CODE_USE_POWERSHELL_TOOL=0, GitHub #8627) gets a cookbook whose 'if ($LASTEXITCODE ...)' line is a bash syntax error that fires AFTER the post succeeded, so the agent sees a failure and may re-post. Render one variant per shell on Windows (PowerShell with the $LASTEXITCODE gate, Git Bash with '&&') and tell the agent to pick the one its command tool runs. The shell-execution test now selects the block by shell and adds a windows/git-bash case that runs the bash variant under sh. Co-authored-by: multica-agent <[email protected]> |
||
|
|
f39debf8d1 |
MUL-7344: skip the issue read and the comment scan when the server already answered them (#8377)
* feat(daemon): read the comment delta with one --since, not a roots scan (MUL-7344) A resumed follow-up turn whose claim carried a server-computed issue-wide comment delta was still told to run the workflow's two-step scan: a `--roots-only --summary` pass to discover which threads moved, then a `--thread ... --since ...` expansion per thread. That rediscovers, in two or more calls, an answer the server already has. `--since <anchor>` without `--thread` IS that answer. ListCommentsSinceForIssue returns every comment on the issue created after the anchor, in every thread and at every nesting level, with no folding, on the same `created_at > since` predicate CountNewCommentsSince counted with. It is a strict superset of what the roots scan could surface: roots-only `last_activity_at` is MAX(created_at) over a thread, so any comment able to move a thread's activity is already in the `--since` result. So BuildNewCommentsHint now hands over exactly one wide read and says it answers step 2's scan — the same rule BuildResumedCommentsHint already applies to a server-computed EMPTY delta. The optional second command stays a THREAD read on `--tail 30` for the reply itself; it is never the wide read, and it never combines `--thread` with `--since`, which drops the thread root. Brief step 2 and the multica-platform skill's bounded-reads rule both gain the matching static sentence, so an agent is not left choosing between the hint and two surfaces that contradict it. Cold start, dropped resume and unknown-delta paths are untouched, byte for byte: only an affirmative server report may stand in for the scan. Co-authored-by: multica-agent <[email protected]> * feat(claim): compare the issue against the last run so a resumed turn can skip the read (MUL-7344) A follow-up turn that resumes its provider session already holds the issue it read minutes ago, and was still told, unconditionally, to run `multica issue get` before doing anything. On an issue that did not move, that read returns bytes the session already has. The claim now answers the question instead. Each claim records the comparable state of the issue it built its payload from — status, assignee, priority, and sha256 of title and description — in a new `agent_task_queue.issue_snapshot` JSONB column, and compares against the snapshot the SAME agent's previous run on the SAME issue recorded. The response carries `issue_state_delta_known`, `issue_changed_fields`, and the current `issue_status` / assignee. Why a per-claim snapshot and not a `content_revision` on `issue`: a revision column has to be bumped by every writer that touches one of those five fields, and the first one missed reports "unchanged" forever with no symptom. A snapshot taken at claim time has exactly one writer. It also rides the anchor the comment delta already uses (agent_id, issue_id, started_at DESC), so both deltas on a claim mean "since your last run" in the same sense. The daemon renders one of three things, gated on a REAL resume: - unchanged → reported as workflow step 1's answer; the read survives only as "if resumed memory is not enough". - changed → the changed field NAMES plus the read, so the agent knows what to look for instead of diffing blind. - otherwise → the pre-existing instruction, byte for byte. `issue_state_delta_known` carries the same contract as `new_comments_delta_known` (MUL-6984), and for the same reason: a cold start, a missing prior snapshot, a read error, a foreign shape version and an old server all produce an empty changed-field list, identical to a genuine "nothing changed". Only the flag separates them, and only the affirmative one may stand in for the read. The compared set is named in full in the prompt rather than summarised as "the issue": labels, parent, due date, stage, project and metadata are NOT compared, and an agent told "unchanged" has to be able to see that. The snapshot write is NOT gated on the task being comment-backed — an assignment run that recorded nothing would leave the next run with no baseline. It shares the receipt's CAS, so a stale handler cannot write over a newer reclaim or after execution starts, and a snapshot that fails to encode is simply not recorded: the next run reports "not compared" and reads the issue. Co-authored-by: multica-agent <[email protected]> * fix(claim): renumber the migration past main and fold in review nits (MUL-7344) CI caught a real collision: main landed 471_comment_deleted_at through 474 while this branch was open, so 471_agent_task_issue_snapshot shared a numeric prefix and TestMigrationNumericPrefixesAreUnique failed. Renumbered to 475 after merging main; no other migration references it. Review nits from the PR review, all non-blocking, all cheap to take now: 1. Brief step 2's closing sentence told the agent that a resumed run's scan surfaces moved threads via `last_activity_at`. That is now true only on the path where the delta is UNKNOWN — when the server hands over a `--since` delta there is no scan to read it from. Rewritten to attach the `last_activity_at` guidance to the scan itself, wherever the scan happens. Done in this PR rather than deferred because this PR already moves brief bytes, so it costs no extra prompt-cache invalidation. 2. The two per-claim anchor reads are now one. GetLastTaskStartedAtForIssueAndAgent and GetLastTaskIssueSnapshotForIssueAndAgent selected the same row with the same WHERE and ORDER, differing only in projection; they are replaced by GetLastRunAnchorForIssueAndAgent returning started_at and issue_snapshot together. A comment-triggered claim is back to ONE anchor read, as before this branch. The saved round trip is the smaller half. The real gain is that "since your last run" is now a single resolved fact on a claim instead of two independently-resolved ones that could disagree. The shared read also shares a failure mode, and both consumers already degrade the same safe way: comment scan required, issue comparison unknown. 3. The hint's `%d new comment(s)` excludes the injected trigger and the agent's own comments; the `--since` read it hands over has no such filter, so the row count is legitimately higher. Narrowing the read to match would mean a second count-shaped query for no gain, so the text now states the mismatch and its direction outright instead of leaving the agent to reconcile two numbers. New test pins the merge: one claim, one prior run, both deltas resolved from that single anchor row. Co-authored-by: multica-agent <[email protected]> * fix(migrations): renumber the issue-snapshot migration to 478 (MUL-7344) main landed 475_issue_status_key_not_reserved through 477 while the previous renumber was in flight, so 475_agent_task_issue_snapshot collided in turn. Merged main again and moved to 478. TestMigrationNumericPrefixesAreUnique passes, and the full ledger applies cleanly from scratch through 478. Co-authored-by: multica-agent <[email protected]> * fix(claim): measure both deltas from the run whose session is resumed (MUL-7344) Review found a real correctness bug, not a performance one: the claim could tell a resumed agent "the issue is unchanged" while the session it handed back predated the change. Both deltas were anchored on the most recently STARTED run for (agent, issue). The session the daemon resumes is chosen by a different rule, and the two are not the same row: - GetLastTaskSession skips poisoned and retired sessions, so a newer run that died on an unprocessable conversation is passed over for an OLDER healthy one. - A manual rerun resumes the exact source task the operator clicked. So: an old session remembers description A, the user edits it to B, a newer run records B and then dies unresumable. The next follow-up resumes the OLD session but compares B against B, reports "unchanged", and the agent keeps working from a context that still says A. PriorSessionResumeUnavailable does not catch this — it flags a missing Codex rollout, which is only one of the ways the resumed session can be older than the newest run. The fix binds both deltas to the run actually being resumed. GetLastTaskSession now returns that row's started_at and issue_snapshot alongside its session, the rerun path takes them from its source task, and the delta computation moves after resume resolution so it can only ever read the adopted row. Where no session is adopted — no prior session, a session on another runtime, a forced-fresh retry, a rerun whose source failure poisoned the conversation — no delta is reported and the daemon performs the reads it always has. That makes the standalone anchor query unnecessary: the anchor is now a projection on a row the claim already fetched, so a claim reads no extra row at all (GetLastRunAnchorForIssueAndAgent is removed). The precondition is now visible in the fixtures: a prior run has to be resumable for a delta to exist, so the comment-delta tests seed a session_id. The regression test covers both paths and was verified to fail against the previous anchor — both sub-cases report an empty changed-field list, which is exactly the wrong "unchanged". Also renumbers the migration 478 → 491; main landed 478_issue_status_category_expand through 490 while the branch was open. Co-authored-by: multica-agent <[email protected]> * fix(claim): a never-started anchor row may date neither delta (MUL-7344) Final review found the last corner of the resumed-run bug. Binding the anchor to the resumed SESSION was necessary but not sufficient: GetLastTaskSession returns that session's latest TERMINAL row, and that row is not always a run that ran. A retry child can inherit the session, be claimed — which writes its snapshot — and then fail before the agent ever starts: runtime offline during prepare, cancelled while dispatched. Its snapshot describes the issue as of ITS claim, while the session's memory stops at the last run that actually executed. If the description was edited in between, the current issue matches that snapshot and the claim reports "unchanged" to an agent whose context predates the edit. The started_at gate now covers both deltas rather than only the comment one. The comment delta was already immune because it read StartedAt directly; the issue delta read only the snapshot, so it had no such guard. Hoisting the check makes the row's requirement explicit — a row that never ran dates nothing — and the inner duplicate is dropped so no reader has to wonder what each guards. Regression test reproduces the exact fixture and was verified to fail without the gate: known=true with an empty changed-field list, i.e. the false "unchanged". Also from review: - Adopt the no-adopted-session table (missing session, session on another runtime, force-fresh retry, poisoned rerun source). Each seeds a usable snapshot AND an unread comment, so a regression has something to report and the assertion cannot pass on an empty fixture. - The resumed-run regression test asserted a comment anchor that never executed: both sub-cases created only the trigger comment, which the count excludes, so NewCommentsSince was empty and the branch was dead. A comment between the two runs now makes it run and pins known/count/since. - Rewrite the migration header, which still described the old "(agent_id, issue_id, started_at DESC)" anchor and an index rationale for a column that is never a lookup key. Co-authored-by: multica-agent <[email protected]> * refactor(claim): compare title, description and status only (MUL-7344) The snapshot compared five fields. The comparison answers exactly one question — must the agent run `issue get` again? — so a field earns a place only if changing it alters what the agent does AND its current value is not already in the per-turn message. Assignee fails the second test: the claim ships the current assignee outright, and "is this mine now" is answered by that value, not by whether it moved. Priority fails the first: it is reachable only by reading the issue, but it does not change what the agent does. Both are dropped. Status stays even though it is also shipped as a current value, so comparing it is strictly redundant for "what is it now". It earns its place as a signal rather than a value: "changed: status" is the clearest evidence that somebody intervened between the runs — a push back from in_review to todo means the delivery was rejected — and it costs nothing to carry. Narrowing the set means a narrower claim, so the prompt now says "compared title, description and status". An issue whose only change is assignee or priority is reported as unchanged, which is correct and now pinned by a test that also asserts the current assignee still ships — without that second assertion the fixture's UPDATE could silently not apply and the test would pass on nothing. Snapshot version goes to 2, because the rule is that the version tracks the compared SET. No deployment has written a v1 row, but the gate is what makes narrowing safe in general: a v1 row read by v2 code is "not compared", which degrades to the unconditional read. Test fixtures now build snapshots at issueSnapshotVersion rather than a literal 1, so a future bump cannot quietly turn them into not-compared tests while they keep passing. The foreign-version case stays explicit at +1. Also renumbers the migration 491 -> 495; main landed 491 through 494 while the branch was open. Fifth renumber. Co-authored-by: multica-agent <[email protected]> * refactor(claim): keep the snapshot at v1 (MUL-7344) The previous commit bumped issueSnapshotVersion to 2 when it narrowed the compared set. That was the version rule applied past its purpose. The rule — "bump when the compared SET changes" — exists to stop a stored snapshot from being compared against a differently-shaped one. It protects DEPLOYED rows. This column is introduced by this same unmerged PR: the migration exists only on this branch, main has neither the column nor the writer, and no environment has ever stored a row with the wider set. There is nothing for the bump to protect, and shipping v2 as the first version the column has ever held would leave a reader hunting for a v1 that never existed. Back to 1. The `v` field and its unknown-version gate stay exactly as they were — those are what make a real narrowing safe later. The comment now says which version this is and why the review-time narrowing did not earn a bump, so the rule still has a stated precedent without a burned number. No behaviour change: the compared set is still title, description and status, and fixtures build at issueSnapshotVersion rather than a literal, so they followed the constant back down. Co-authored-by: multica-agent <[email protected]> * fix(claim): only a completed run may date a delta (MUL-7344) Final review found a window one step later than the never-started case. A snapshot is written at CLAIM time. The daemon then writes started_at (TaskService.StartTask) and only afterwards launches the provider. So a run can carry both a snapshot and a started_at while its prompt never reached the session: the daemon exits during prepare, the runtime drops, orphan recovery marks the row failed. Anchoring there compares the current issue against a snapshot describing an edit that session never saw — reporting "unchanged" across a real change, and dating the comment delta late enough to hide every comment older than that row's start. Reproduced on the real CreateRetryTask -> claim -> StartTask -> RecoverOrphanedTasksForRuntime -> follow-up claim path. Nothing on the row separates "failed after the provider ran" from "failed before it ran". session_id is inherited by CreateRetryTask at insert, so it does not mean the session was fed; started_at precedes the launch, so it does not mean the turn began. The only terminal status that PROVES delivery is 'completed' — a run cannot finish a turn it never started. So failed and cancelled sources now date neither delta. Their SESSION is still resumed exactly as before, and GetLastTaskSession still accepts them on purpose; those runs simply perform the context reads they always did. That is the cheap side of the trade: a follow-up after a failure or a stop is already recovering from something, while the case the optimization exists for — an ordinary follow-up after a healthy run — is untouched. Both conditions now live in newResumedRunAnchor rather than at the use site, so "which run may date a delta" is answered once, and GetLastTaskSession carries the status needed to answer it. Regression test is the reviewer's repro, verified to fail without the rule: known=true with an empty changed list AND a computed zero comment count, i.e. both a false "unchanged" and a false "no new comments". Also: - Renumber the migration 495 -> 499; main landed 495 through 498. Sixth renumber. - The migration's content_revision rationale named the old five-field set while arguing about hypothetical issue-row writers; it now refers to "any compared field", which is what the argument actually depends on. Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
b62cce56da |
MUL-7359 perf(runtime): avoid echoing final comment bodies (#8390)
* perf(runtime): avoid echoing final comment bodies * refactor(daemon): keep the file-first guardrail as the Comment Formatting lede The receipt-mode rule opened the section, pushing the file-first guardrail (MUL-2904 / #4182 / MUL-4252) out of the lede. The guardrail is the section's correctness red line — a shell-mangled body is a wrong comment — while the receipt mode only decides how much of an already-correct comment is echoed back. Move the rule after the guardrail in both OS variants; it is now a single const so the two branches cannot drift. Co-authored-by: multica-agent <[email protected]> * docs(skills): drop the duplicated final-comment-receipt section issues.md states its own charter as "Product contracts the runtime brief does not fully encode", and SKILL.md gives the brief ownership of "when to comment". The brief's ## Comment Formatting now carries this rule in full, so the copy here duplicates a brief-owned instruction against the single-owner convention (MUL-6984 #7971, MUL-5825 #6517). It was also unreachable by the documented routing: the section was added to the file's own table of contents, but SKILL.md's Routing row for issues.md was not updated, so no task would route here for this topic. Co-authored-by: multica-agent <[email protected]> * fix(daemon): gate final-comment cleanup on the post succeeding Agents hand the reply cookbook to one shell call. With cleanup as its own statement, a failed post is followed by a cleanup that SUCCEEDS, so the call exits 0 and ./reply.md is deleted. Under `--output table` a failed and a successful post both write nothing to stdout, which leaves the exit status as the only machine-checkable signal — masking it lets an agent end its turn believing an unposted final result was delivered, and drops the body it would need to retry with. The brief already told agents to check the posting command's exit status; the rendered snippet made that impossible. POSIX chains with `&&`. PowerShell 5.1 has no `&&` (it landed in 7), so the Windows variant propagates $LASTEXITCODE instead. Both keep ./reply.md on disk when the post fails. The guard EXECUTES the rendered snippet against a stub CLI: this is a shell-composition property, and the handler-level test can only prove the command returns an error, not that the pasted block preserves it. Verified to fail on the previous two-statement form. The pwsh case runs wherever PowerShell is installed, including Linux runners, and skips otherwise. Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
2efe1b2a43 |
MUL-6984 fix(daemon): let workflow step 2 alone decide the comment scan (#7972)
* MUL-6984 fix(daemon): let workflow step 2 alone decide the comment scan
The brief's step 2 called the catch-up scan mandatory while the per-turn
hints in the same context made it conditional ("Need cross-thread
background?", "Only if you need context from the other threads", "If your
reply depends on thread context"). Step 2 now owns the modality; the hints
carry facts and this turn's exact commands and hand the scan over as the
wide read. Hint dispatch keys on PriorSessionID before the delta so a run
whose resume the daemon dropped takes the fresh-session path instead of the
resumed delta hint. The assignment pointer drops the parenthetical that
implied only assignment turns treat the read as mandatory.
Measured on 537 comment-triggered runs: 1 in 10 scans opened a thread the
prompt had not named; 0 of 36 non-scanning runs did; scan median 434 B.
Co-authored-by: multica-agent <[email protected]>
* fix(daemon): only waive the comment scan on a delta the server actually computed (MUL-6984)
Addresses review on #7972.
[P1] NewCommentCount == 0 was read as "nothing else was said on this issue",
and used to tell the agent its scan is already answered. The producer in
buildClaimedTaskResponse is best-effort: it writes the count fields only when
the anchor lookup and the count query both succeed AND the count is positive.
A failed anchor read, a failed count query, a cold start with no prior run, a
true zero, and an old server that never sends the fields therefore all arrive
as the same zero — and only the true zero looked at the issue. On a resumed
run a single failed count query was enough to delete the mandatory scan
exactly when the run could least afford it.
The claim now carries new_comments_delta_known, set on the success path
whatever the count. The count fields still stay suppressed at zero (there is
no delta hint to render from a zero), so the flag is the only thing that
separates a checked zero from an unchecked one. Absent on old servers, which
reads as "not authoritative" and keeps the scan — the safe direction in both
mixed-version pairings. The resumed path with no authoritative delta now
renders BuildResumedUnknownDeltaCommentsHint, which keeps the session facts
and hands the scan over as a command instead of claiming it is answered.
Workflow step 2 is tightened to match: only an explicit server report waives
the scan, and silence is not that report.
[P2] The warm path was selected on PriorSessionID != "" alone. MUL-5305 lets
the server withhold a more recent Codex session whose rollout is missing and
return an OLDER fallback session instead: PriorSessionResumeUnavailable is
true while PriorSessionID is non-empty. That older session may resume cleanly,
but it is not the turn this run continues from, so the run was taking the warm
path — and on an empty delta could skip both the full trigger-thread read and
the scan — on the strength of context it does not have. It now requires
!PriorSessionResumeUnavailable and reconstructs from the record instead, which
is what the continuity notice already tells the user happened.
Tests cover the states the existing suite could not see: an older fallback
session with every other warm-path precondition satisfied, resumed-with-delta-
unavailable versus resumed-with-authoritative-zero as siblings, and a
server-side computed zero carrying the flag. Each was verified against the
un-fixed code, where it fails. TestBuildPromptResumedNoDeltaDoesNotForceThread-
Read now sets the flag: its subject is the waiver branch, which is exactly the
branch that requires an authoritative answer.
Co-authored-by: multica-agent <[email protected]>
* docs(handler): correct the new-comment delta's scope on the claim wire (MUL-6984)
Review should-fix on #7972. NewCommentCount's doc comment still described it as
"trigger-thread comments since last run", while the query that produces it
(CountNewCommentsSince: "ACROSS THE WHOLE ISSUE, every thread, not just the
triggering one"), the daemon-side mirror field, and the NewCommentsDeltaKnown
comment directly beneath it all say issue-wide. One struct carrying two
mutually exclusive readings of the same field is worse than either.
Also records on NewCommentsSince that it is suppressed together with the count
at zero, so the next reader does not mistake a non-empty anchor for the signal
that the server looked — NewCommentsDeltaKnown is that signal.
Comment text only.
Co-authored-by: multica-agent <[email protected]>
* fix(daemon): stop calling an older-fallback resume a fresh session (MUL-6984)
Under MUL-5305 the server hands back an OLDER session with the continuity
gap flagged, and the daemon resumes it (ResumeSessionID is not gated on the
flag). The cold hint opened with "This run starts a fresh session on this
issue" and the readable continuity notices said "you are on a fresh one";
both were false in that state, and a test pinned the first.
The cold hint now states nothing about the session — none of the four runs
it serves (first run, dropped resume, explicit fresh, older fallback) makes
a different decision on it, and all four reconstruct from the issue record
with the same two reads. The three readable notices say the run "does not
continue" the lost session and that the memory gone is "from the turns
that did not come back", true in both the fresh and the fallback case.
TestBuildPromptOlderFallbackSessionRequiresReconstruction (renamed) asserts
the reconstruction commands and the notice, and bans "fresh session" and
"fresh one"; the resumed-path negative anchors now key on a phrase only
the cold hint carries.
Co-authored-by: multica-agent <[email protected]>
---------
Co-authored-by: Bohan-J <[email protected]>
Co-authored-by: multica-agent <[email protected]>
|
||
|
|
545d890dae |
feat(cli): add --compact to issue comment list, adopt it in every agent read command (MUL-5442) (#6546)
* feat(cli): add --compact to issue comment list, adopt it in every agent read command (MUL-5442) The #5999 follow-up its closing note asked for, now that the workspace measurements exist: the two bounded reads the agent workflow prescribes are dominated by reader-noise metadata, and every byte of it enters the conversation history at full price once and is replayed at cache-read price by every later call of the session. --compact (JSON output only, opt-in) drops per comment: the issue_id echoed from the request path, source_task_id, updated_at when identical to created_at, null-valued fields, and empty arrays. Content, identity, and thread-summary fields pass through untouched; a real edit timestamp or non-empty array is never dropped. Measured on MUL-5442 (production data): --roots-only --summary scan 6,117B -> 4,738B (-23%); --thread --tail 30 deep read 47,359B -> 39,349B (-17%). Adoption: all nine runnable comment-list command templates in the per-turn channel (prompt.go, reply_instructions.go) now carry --compact, and the brief's Available Commands line and workflow step 3 document it (+~40B one-time, byte-stable). Command pins updated accordingly; new unit test pins the drop/keep contract and the help-contract test pins the flag's rendered usage. Known local-env failure: TestResolveWorkspaceID_AgentContextSkipsConfig fails identically on clean origin/main in this agent runtime (agent context env interference) — unrelated. Co-authored-by: multica-agent <[email protected]> * test(cli): wire-level --compact coverage and zero-value keep pins (MUL-5442) Review nits on #6546: TestRunIssueCommentListCompactWiring drives runIssueCommentList against an httptest server both ways — default JSON keeps every field, --compact drops the reader-noise set while zero-value scalars (reply_count: 0, content_truncated: false, folded_count: 0) survive, pinning that null pruning never generalizes to zero pruning. Same zero-value pins added to the pure-function test. Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: Bohan-J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
6ca6b27ce3 |
refactor(daemon): converge multi-thread fan-out cookbook into Comment Formatting pointer (MUL-5825) (#6517)
The cross-thread reply fan-out block embedded a full file-operations cookbook (body file -> --content-file -> cleanup, the inline/stdin bans, the \n-escape rule, plus two example command pairs) that triple-wrote the mechanism already carried by the brief's ## Comment Formatting and the single-thread cookbook. The block now keeps only what is multi-thread-specific — fan-out announcement + override, posting order, per-thread --parent targets, the DISTINCT-body-file-per-thread delta, and the squad leader's whole-block no_action scope sentence — and points at ## Comment Formatting for the mechanism. Dropping the embedded commands removes the only OS-dependent text, so the windows/unix cookbook variants collapse and the block no longer branches on runtimeGOOS; the OS split lives solely in the brief. Measured (2-thread, 36-char-UUID fixture): ordinary 1,657B (linux) / 1,675B (windows) -> 919B both; leader 1,870B / 1,888B -> 1,132B both. ~-740-760B per coalesced multi-thread turn. Pins updated per discipline: ordinary unconditional form and the leader scope-ordering assertions are retained (obligation strings track the new text, ledger comments record the mapping); retired cookbook strings get negative guards in the block test and the assembled-prompt test; a new non-parallel test pins OS-invariance. Co-authored-by: Bohan-J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
d6d1996210 |
refactor(daemon): retire the generic no-reply rule — ordinary agents always post one comment (MUL-5442) (#6493)
* refactor(daemon): retire the generic no-reply rule — ordinary agents always post one comment (MUL-5442) Owner decision (MUL-5442, 2026-08-06): the no-reply / silent-exit behavior is squad-leader-only by design. Mechanically it always was — computeCommentAgentTriggers routes agent-authored comments only via explicit @mentions (the sole implicit wake is the squad-leader path), so loop prevention lives in the Mentions discipline, and the generic rule only suppressed one terminal noise comment on an already-enqueued run while giving every ordinary agent a legal silent-exit path that risks silently dropped results. - prompt.go: delete the per-turn agent-trigger warning block entirely (−728B per agent-triggered turn; supersedes #6484's compression). - runtime_config_sections.go: delete the Reply-mode reply-warranted bullet and step 5's conditional pointer; the reply bullets become unconditional (−472B one-time in the brief). Squad-leader no_action bullets and the Mentions section are untouched. - reply_instructions.go: 'If you decide to reply, post it' → 'Post your reply' (−16B per Reply turn); the leader's no_action block states its own exception. - Tests: retired pins are converted to negative guards with ledger comments (brief and per-turn both must NOT carry the retired apparatus); attribution, member-leak, and no-MUST-respond guards stay. Co-authored-by: multica-agent <[email protected]> * fix(daemon): scope the reply imperative with the leader's no_action carve-out, close the pin-ledger gaps (MUL-5442) Review catches by Elon on #6493, both accepted: 1. The leader's only silent path was contradicted later in the same prompt: the no_action rule said EXIT without commenting, then the cookbook and the brief's mandatory bullet said post unconditionally. Both now branch on squad leadership — agent configuration, never per-run state, so each agent's brief stays byte-identical across turns and issues (cache-safe): leaders get 'Unless your outcome is no_action, post your reply…' in the cookbook and 'Unless your outcome is no_action (Squad leader rule above), posting your reply as a comment is mandatory' in the brief; ordinary agents keep the unconditional wording byte-for-byte. New tests render the COMPLETE leader prompt and leader brief and assert the carve-out is present AND the unconditional capital-P imperative is absent — the scope relation, not two isolated Contains. 2. The retirement ledger named five brief pins but guarded only two, and the per-turn 'If you decide to reply' had no guard. Added the four missing negative guards in ordinary-agent scope (the leader's 'DO NOT post any comment' matches none of them) plus a leader-leak guard on the ordinary brief. Co-authored-by: multica-agent <[email protected]> * fix(daemon): scope the multi-thread fan-out under the leader's no_action carve-out (MUL-5442) Ports the per-turn half of #6493 review rounds 2-3 into the slimmed PR (the brief role-independence refactor moves to its own sub-issue/PR per owner decision): BuildMultiThreadCommentReplyInstructions takes the leader flag, and the leader lead sentence scopes the ENTIRE fan-out block — every later obligation sits under the 'Otherwise' — with index-order test guards. Ordinary fan-out output is byte-unchanged. Also repairs a truncated TestFreshSessionMayHelp from the earlier rebase conflict resolution (missing closing braces). Co-authored-by: multica-agent <[email protected]> * docs: correct the taskIsSquadLeader comment — leadership is a per-task role (MUL-5442) Review nit on #6493: the helper's comment still claimed leadership is 'agent configuration, never per-run state' — the disproven premise that drove the earlier review rounds. State the per-task-role fact and point at MUL-5811 for the role-independence work. Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: Bohan-J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
2bb13667c6 |
refactor(daemon): cross-channel command dedup — brief states the loop, per-turn carries the commands (MUL-5442) (#6421)
* refactor(daemon): move the workflow's command templates to the per-turn channel (MUL-5442) Cross-channel dedup, brief side. MUL-5721 measured that every issue-turn variant of the per-turn message already carries the ready-to-run commands with real ids (issue-get line, reading hints, reply cookbook), fresher than the brief's static copies. The six workflow steps now state the loop shape — command names and flag mnemonics only; full templates and every embedded issue UUID leave the brief. The Ownership status commands and the squad-activity call switch to <issue-id> placeholder form. Doctrine pins stay on the brief side (mandatory catch-up, scan-first order, both motivation anchors); command-template pins re-anchor to names and mnemonics. Two design-consequence test updates: the static-catch-up assertion repoints at the doctrine (the full command now lives in every per-turn variant), and the byte-identity non-vacuity guard varies agent identity instead of issue id — because the brief is now deliberately issue-id-independent, which opens the cross-issue prefix-cache door. Co-authored-by: multica-agent <[email protected]> * refactor(daemon): point the reply cookbook at Comment Formatting instead of restating it (MUL-5442) Cross-channel dedup, per-turn side. The cookbook's prose restated the brief's Comment Formatting rules (file-first rationale, inline-content and HEREDOC hazards, the full Windows $OutputEncoding mechanics) around the command that already demonstrates the shape. It now keeps the file-first order, the ready-to-run command, the literal-newline rule, and the pointer; the hazard mechanics live once, in the brief section the pointer names. Default cookbook: 639 -> 494 bytes (-145 per reply turn, uncacheable channel); the Windows variant sheds ~200 more. Pins re-anchor from the deleted prose to the surviving anchors (file-first order, the pointer, the command form); the MUL-2904/#4182 banned-shape negative guards are untouched. Co-authored-by: multica-agent <[email protected]> * fix(daemon): narrow the per-turn coverage claim, test the cross-issue invariant, strip the command shape from the guest-visible prohibition (MUL-5442) Review catches by Elon on #6421 plus the CI failure, all three related: 1. The steps header overstated what the per-turn message carries — it ships the issue id and ready-to-run context-read commands; other calls are assembled from Available Commands. Reworded to say exactly that (a factual claim in a prompt cannot rely on the reader discovering it is wrong). 2. The cross-issue byte-equality this PR claims as a design benefit is now asserted directly per provider (same stable inputs, different 36-char issue UUIDs, byte-identical brief) — a Contains-based negative cannot catch truncated/transformed/conditional id use. 3. CI: the squad guest-leader contract test bans any runnable 'issue status <issue-id> in_review' shape in guest-visible text; the placeholder rewrite made the leader dispatch rule's NEGATIVE sentence match that ban. The prohibition now states itself without a command form ('do NOT move it to in_review or done on this turn') — negative sentences should not carry copy-pasteable command shapes at all. Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: Bohan-J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
18f8f78af5 |
refactor(daemon): per-turn message slimming — OPT-1 UUID dedup + OPT-2 initiator prose (MUL-5721) (#6382)
* refactor(daemon): drop duplicate UUID commands from per-turn comment hints (MUL-5721) OPT-1 from the MUL-5721 measurement: within one hint, a second full `multica issue comment list <uuid> ...` command restated the issue UUID (and, in the resumed hint, both anchors) for no routing value. The warm hint's issue-wide catch-up and the cold hint's roots scan become flag swaps on the thread command they follow; the resumed hint loses its anchor-restating sentence (the read command carries the thread anchor, the reply cookbook carries the trigger id as --parent). Fixture-measured: warm hint 555->481, resumed 551->417, cold 429->396; reply-turn totals -74/-134/-33 B. Ownership prompt and the reply cookbook (with its concrete --parent command) are untouched. Every dropped duplicate gets a deny assertion so it cannot silently return; the demoted fallbacks get semantic anchors in its place. Co-authored-by: multica-agent <[email protected]> * refactor(daemon): compress Task Initiator attribution prose (MUL-5721) OPT-2: the block's 400 B attribution paragraph carried two derivable restatements ("in a workspace many people can reach", "so this attribution does not widen what you can read or write"). The compressed paragraph keeps every rule: per-person privacy/access rules apply, the initiator (not the runtime owner) is who you are answering, credentials stay scoped to the runtime owner, and the initiator may not see everything you can. Both MUL-2645 test-pinned phrases survive verbatim; the fact line and heading are untouched. Fixture-measured: block 513->370 B (member+email form). The two previously unpinned surviving rules gain anchors ("is who you are answering", "do not assume the initiator can see everything you can"). Co-authored-by: multica-agent <[email protected]> * refactor(daemon): restore initiator read/write authorization boundary (MUL-5721) Review must-fix (#6382): the compression treated "attribution does not widen what you can read or write" as derivable from credential scoping and dropped it. It is an independent boundary: credential scoping names whose credentials run, the visibility sentence constrains disclosure — neither stops the model from treating an initiator's request as extra authorization. Restored as a short explicit negation with a semantic anchor. Initiator block 370 -> 440 B (still -73 vs the original 513); typical reply turn 2,191 B (net -147 for the PR). Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: Bohan-J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
e45a8f6c12 |
fix(daemon): scan comment roots before bulk reads in agent catch-up (MUL-5372) (#6093)
* fix(daemon): scan comment roots before bulk reads in agent catch-up The mandatory step-3 catch-up in the issue runtime brief asked for `--recent 10`. `--recent N` caps THREADS, not comments: each returned thread carries its root plus every descendant with no depth bound, so on an issue with fewer than N root threads it returns the entire comment history. Because the step is mandatory and fires on every run, every reply turn re-read the whole issue -- and on comment-triggered turns it duplicated the bounded thread read the per-turn message had already pointed at, so the same bytes were fetched twice. Lead the step with `--roots-only --summary` instead: every top-level thread with reply_count and last_activity_at, contents clipped. That keeps the property the step exists for -- the agent still sees every thread that exists, so it cannot act on stale context -- and makes the drill-down into `--thread <id> --tail 30` explicit. `--recent 10` stays documented for when several complete threads really are needed, now with its saturation semantics spelled out. Measured on a live 2-thread issue: 21,249 -> 1,518 bytes for the mandatory read (-93%), and the duplicate 11,082-byte thread read is gone. The brief stays byte-identical across runs of a session (MUL-5377): the new text interpolates only the issue id, no per-run state. The three per-turn pointers that express the same rule move with it so the two layers cannot drift. MUL-5372 Co-authored-by: multica-agent <[email protected]> * refactor(daemon): keep comment-read flag semantics in one place The previous commit fixed the payload shape but restated the read surface in four places: the workflow step, both per-turn prompt fallbacks, and the cold-start hint each explained what `--recent 10` does. `## Available Commands` is already the brief's single discovery point for these flags, and `TestInjectRuntimeConfigStaticCatchUp` pins it as such -- so those restatements were duplicated reference text, and the per-turn ones were paid on every turn rather than once in the cached prefix. Move the `--recent N` saturation warning into the `comment list` line in Available Commands, next to the flags it qualifies, and add `--roots-only` and `--summary` to that signature so the bounding options are discoverable where an agent already looks. Workflow steps and per-turn hints now name only the reads they actually want run. Per-turn prompt sizes: assignment 1170 -> 749 bytes (-36%), cold-start comment turn 1550 -> 1355 (-13%). Step 3 is 1065 bytes and no longer carries a ready-to-paste bulk read. MUL-5372 Co-authored-by: multica-agent <[email protected]> * docs(daemon): address review nits on comment-catchup change Three cosmetic follow-ups from review: - `--recent N` saturation warning said it hands back "the entire history"; resolved threads are still folded by default on that read, so say so. - Rename two tests whose names still advertised `--recent` after their assertions stopped mentioning it, plus the one added in this branch whose name referenced a bulk read the step no longer contains: MentionsRecent -> ScansRootsFirst, ScansRootsBeforeBulkRead -> ScansRootsFirst. - Fix the stale doc comment that still described the mandatory read as bounded to "the recent active-thread window". No behavior change. MUL-5372 Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: Bohan-J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
3c417ea631 |
fix(MUL-4348): authorize + chronologically order per-thread coalesced replies (#5211)
Testing surfaced two problems with the per-thread fan-out:
1. Authorization (blocker): CreateComment rejected any agent comment on the
task's issue whose parent_id != task.TriggerCommentID, so replies to the
OTHER coalesced threads were denied ('parent_id must equal this task's
trigger comment id') and those threads never got a reply. Allow the trigger
comment OR any comment the task coalesced (taskCoversReplyParent: trigger ∪
coalesced_comment_ids); every other parent on the issue is still rejected,
so this stays scoped to the set the run was actually given to answer.
2. Ordering: the agent answered the newest (triggering) comment first. The
fan-out instruction now numbers the targets and explicitly requires posting
OLDEST thread first, the newest/triggering thread last, so replies land in
chronological order. commentReplyThreads already lists oldest-first.
Tests: TestTaskCoversReplyParent (allow-list) and chronological-order
assertions in the cross-thread prompt test.
Co-authored-by: Eve <[email protected]>
Co-authored-by: multica-agent <[email protected]>
|
||
|
|
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 <[email protected]> * 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 <[email protected]> * 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 <[email protected]> --------- Co-authored-by: Eve <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
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 <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
8ad673fdb7 |
MUL-3560: gate slim runtime brief behind runtime_brief_slim feature flag (#4449)
The MUL-3560 slim runtime brief — kind-driven dispatcher, per-section
gating, prose compression for ~7k chars saved on the typical
comment-triggered task — now ships behind the `runtime_brief_slim`
feature flag wired via the framework-level service from MUL-3615.
Default: OFF in every environment (production stays on the legacy
brief that has shipped for ~2 years). Staging opts in via the YAML
rule set; ops can override per-process with `FF_RUNTIME_BRIEF_SLIM=true`.
Production is held back until staging has burned in long enough that
we are confident the slim brief does not regress agent behaviour.
Architecture (one toggle point, two code paths, both fully tested):
buildMetaSkillContent (runtime_config.go)
│
└─ useSlimBrief() → false (default)
│ → fall through to the legacy verbose body that ships on
│ main today — byte-for-byte unchanged, no migration risk
│
└─ useSlimBrief() → true
→ buildMetaSkillContentSlim (runtime_config_sections.go)
→ classifyTask → 5-way kind switch → per-section writers
BuildCommentReplyInstructions takes the same gate, so the per-turn
comment prompt and the runtime brief stay in sync on which template
they emit.
What's in this PR:
- runtime_config_flag.go (new): package-scope `runtimeFlags` atomic
pointer + `SetFeatureFlags` setter + `useSlimBrief` toggle point.
Nil-safe: a daemon that forgets to wire the service falls back to
legacy, no panic.
- runtime_config_kind.go (new): `taskKind` enum + `classifyTask` +
`hasIssueContext` predicate. Used only by the slim path.
- runtime_config_sections.go (new): the slim brief itself —
`buildMetaSkillContentSlim` + per-section `writeXxx` helpers
+ `writeAvailableCommandsQuickCreate` minimal variant +
`writeBackgroundTaskSafetySlim` compressed safety section. The
Section × Kind matrix is documented inline on
`buildMetaSkillContentSlim` and the test below checks the
dispatcher does not diverge from the spec.
- reply_instructions.go: `BuildCommentReplyInstructions` gains a
short slim-or-legacy prelude; new `buildCommentReplyInstructionsSlim`
is the compressed cookbook (defers the shell-hazard rationale to
`## Comment Formatting`).
- runtime_config.go: `buildMetaSkillContent` gains a 2-line
dispatcher at the top; the legacy body is otherwise untouched.
- runtime_config_kind_test.go (new): canaries for both paths.
- TestClassifyTask: 5 kinds + 3 tiebreak cases.
- TestTaskKindHasIssueContext: predicate semantics.
- TestSlimFlagOffUsesLegacy: nil flag service → legacy path
(renders "Get full issue details.", a legacy-only substring).
- TestSlimFlagOnUsesSlim: flag on → slim path (renders "full
issue.", a slim-only one-liner) AND must NOT render legacy
"Get full issue details.".
- TestBuildMetaSkillContentSlimKindMatrix: locks the per-kind
section set; heading match is line-anchored so inline references
don't trip absence assertions.
- TestSlimQuickCreateAvailableCommands: locks the minimal-variant
content for quick-create (issue create present, every other
Core command absent).
- TestSlimBriefIsSubstantiallyShorter: ≥ 30% reduction guard so
a future change can't accidentally re-bloat the slim path back
to legacy levels.
- cmd/server/main.go: now calls `execenv.SetFeatureFlags(flags)`
immediately after constructing the feature flag service.
Measured impact (slim vs legacy, claude provider, realistic fixture
with 2 repos + 2 skills + member initiator):
legacy = 19567 chars
slim = 11868 chars Δ = -7699 (-39.3%)
Verification:
- go vet ./internal/daemon/... ./cmd/server/... ok
- go test ./internal/daemon/... ok
- go test ./pkg/featureflag/... ok
- TestSlimBriefIsSubstantiallyShorter logs the 39.3% ratio
- TestSlimFlagOffUsesLegacy + TestSlimFlagOnUsesSlim pass both
directions, so the dispatcher is locked in code.
The pre-existing `internal/handler` test failures
(TestLeaveWorkspace_RevokesOwnRuntimes,
TestDeleteMember_CancelsTasksFromAgentReassignment,
TestDeleteMember_NoRuntimes_DeletesMember) reproduce on plain
`origin/main` with the same `relation "channel_user_binding" does
not exist` SQL error — they are a missing-migration bug from the
recent channels foundation PR (
|
||
|
|
b79777caec |
feat(comments): resolve-aware fold for agent comment reads (MUL-3555) (#4463)
* feat(comments): resolve-aware fold for agent comment reads (MUL-3555) Agents reading a long issue paid tokens for settled discussion. The human timeline already folds resolved threads, but the agent read path (`comment list`) ignored resolved_at entirely — humans saw the conclusion, agents got the full raw discussion. Add an opt-in `fold=true` projection to ListComments that collapses each resolved thread to root + conclusion (reply-resolved) or root only (root-resolved), reusing the human timeline's deriveThreadResolution semantics. The resolved thread's root carries `thread_resolved` + `folded_count`; `--full` brings the dropped comments back. Fold is rejected on partial-thread reads (since/tail) and roots_only, where a resolution comment could be unfetched and silently dropped. CLI `comment list` folds by default on the complete-thread reads (default, --recent, untailed --thread) with a `--full` escape hatch; the agent prompts and runtime brief document the fold + escape. No new endpoint, no human UI change, no SQL/migration change — in-memory projection, same precedent as summary/roots_only. Co-Authored-By: Claude Opus 4.8 <[email protected]> Co-authored-by: multica-agent <[email protected]> * refactor(daemon): dedupe fold prompt restatements per review (MUL-3555) Howard's PR review flagged DRY redundancy: the resolve-fold rule was restated in full in the task prompt (prompt.go:41/:182) and the brief workflow steps (runtime_config.go:673/:692, reply_instructions cold hint) even though the canonical command catalog (runtime_config.go:477) — always present in the brief — already documents it in full, and the task prompt explicitly defers to it ("follow the rule in your runtime workflow file"). Keep the catalog entry full (the canonical reference); shrink the five inline restatements to a short "resolved threads come back folded — `--full` to expand" pointer. No loss of signal (the agent always has the full catalog in context), ~80-120 tokens/run saved on the worst-case assignment / cold paths. Co-Authored-By: Claude Opus 4.8 <[email protected]> Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: Claude Opus 4.8 <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
BeliyDym
|
5fd3d01d13 |
MUL-3502: OST-1161: Bound assignment comment catch-up
Squashed PR #4392. Updates assignment/comment catch-up guidance to use recent 10 and aligns related examples. |
||
|
|
18a58e80c0 |
MUL-3316: fix(execenv): switch agent prompt to --content-file to prevent heredoc flag swallowing (#4182) (#4191)
* fix(execenv): switch agent prompt to --content-file to prevent heredoc flag swallowing (#4182) The Linux/macOS reply template recommended --content-stdin with a quoted HEREDOC. That pattern is safe for the trivial single-flag comment-add case that BuildCommentReplyInstructions emits, but as soon as a model wraps extra flags around the heredoc on multica issue create / update — assignee, project — the bash heredoc/flag boundary is fragile in two ways the model cannot see: - A 'BODY \\' terminator with a trailing token is not recognised as the heredoc end, so flag lines after it are swallowed into the description (OXY-78: residual flag text leaked into the description, command exit 0). - A clean terminator turns the trailing '--assignee ...' line into a separate failing shell statement, while the create itself already exited 0 with no assignee (OXY-76: assignee silently dropped, no residual text). In both cases the CLI never receives the swallowed flags, the API request omits the fields, and the daemon has no visibility. The created issue lands with assignee_id: null / project_id: null. This commit: * Switches the Linux/macOS branch of BuildCommentReplyInstructions to --content-file with a 3-step recipe (write file, post, rm) so the body never reaches the shell and all flags live on one shell-token line. There is no heredoc boundary for flags to leak across. * Adds a parallel cleanup step (Remove-Item) to the Windows branch so the cross-platform template is one shape. * Rewrites the runtime_config.go ## Comment Formatting non-Windows section to mandate --content-file and explicitly ban --content-stdin HEREDOC for agent-authored comments, citing #4182. * Reorders the Available Commands menu lines for issue create / update / comment add to put --content-file / --description-file ahead of the stdin variant and add a per-line note pointing at #4182. * Updates and renames the affected tests (TestBuildCommentReplyInstructionsCodexLinux, TestBuildCommentReplyInstructionsNonCodexLinux, TestInjectRuntimeConfigLinuxCommentFormattingEmphasizesFile, TestInjectRuntimeConfigIssueMetadataCodexFormattingUnchanged) so the new file-first contract is pinned and the old HEREDOC mandate is in the banned-strings lists. This converges Linux/macOS with the long-standing Windows file-only path, so the cross-platform guidance is now one shape. It also strictly improves on the previous MUL-2904 guardrail by eliminating shell exposure of the body entirely (no body ever reaches the shell, so backtick / $() / $VAR substitution cannot corrupt it). Closes GitHub multica-ai/multica#4182. No CLI or backend changes — --content-file / --description-file already exist. Co-authored-by: multica-agent <[email protected]> * docs(prompt): correct stale BuildPrompt comment to file-first (#4182) --------- Co-authored-by: Eve <[email protected]> Co-authored-by: multica-agent <[email protected]> Co-authored-by: CC-Girl <[email protected]> |
||
|
Naiyuan Qingandmultica-agent
|
b9334dd59f |
fix: anchor comment triggers to thread roots (#3746)
Co-authored-by: multica-agent <[email protected]> |
||
|
|
888186b183 |
fix(daemon): make comment-posting guardrail provider-agnostic (MUL-2904) (#3654)
* fix(daemon): make comment-posting guardrail provider-agnostic (MUL-2904) Agents inlining a backtick-wrapped token into `multica issue comment add --content "..."` had the shell run it as a command substitution, silently deleting the token; the stored comment never matched the model's intent, so it retried forever — spamming OKK-497 with duplicate comments. The corruption is shell-driven, not provider-driven, so extend the "never inline --content; use --content-file / quoted-HEREDOC --content-stdin" rule from Codex-only to ALL providers: - BuildCommentReplyInstructions: collapse the Linux/macOS non-Codex inline branch into the unified quoted-HEREDOC stdin template. - buildMetaSkillContent: rename "Codex-Specific Comment Formatting" -> "Comment Formatting" and emit it for every provider; strengthen the Available Commands entry and the assignment step-6 examples to steer away from inline --content. - Windows behavior unchanged (file-only; avoids PowerShell ASCII drop). Tests: flip the non-Codex Linux reply test into a MUL-2904 regression, broaden the stdin-emphasis test across providers, and pin the provider-agnostic guardrail. Co-authored-by: multica-agent <[email protected]> * fix(daemon): keep Windows assignment brief file-only (address review) Review catch on #3654: the previous commit added platform-agnostic prose recommending "--content-file or --content-stdin" in the Available Commands entry and the assignment-triggered step-6 example. The assignment path has no BuildCommentReplyInstructions OS override, so on Windows an agent following step 6 literally would pipe its final comment through PowerShell and drop non-ASCII bytes (#2198 / #2236 / #2376) — contradicting this PR's own Windows file-only rule in the ## Comment Formatting section. Make the platform-agnostic surfaces defer to the OS-aware ## Comment Formatting section (the single source of truth) instead of naming stdin. The flag synopsis still lists all three modes. Add TestInjectRuntimeConfigWindowsAssignmentBriefStaysFileOnly: a Windows assignment-triggered brief must not contain any prescriptive "... or --content-stdin" recommendation. Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: J <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
Naiyuan Qingandmultica-agent
|
4ae4722ef0 |
fix(comments): preserve direct parent on replies (#3579)
Co-authored-by: multica-agent <[email protected]> |
||
|
|
973a43923f |
fix(comments): revert since-delta to issue-wide, steer to parent thread first (#3535)
#3509/#3523 scoped the comment-trigger since-delta count to the triggering
thread, so an agent resuming a busy issue only saw "+N in this thread" and
lost visibility of new comments in other threads. Revert the count to
issue-wide (every thread), keeping the trigger-comment + agent-own
exclusions, and reshape the warm-path hint to:
- report the issue-wide new-comment volume,
- steer the agent to read the triggering (parent) thread FIRST
(`--thread <trigger> --since`, or `--tail 30` for full context),
- demote the issue-wide `--since` catch-up to an only-if-needed fallback
("don't read them all blindly").
Also fixes the now-stale "scoped to the triggering thread" wording in the
resumed-session no-delta hint (it's issue-wide zero now).
Co-authored-by: Claude Opus 4.8 <[email protected]>
Co-authored-by: multica-agent <[email protected]>
|
||
|
|
d1c7d478e1 |
MUL-2785: clarify thread-scoped comment delta (#3523)
Co-authored-by: Eve <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
|
9616d78e47 |
MUL-2785: optimize resumed comment reads (#3509)
* feat(comments): skip default thread read on resumed comment sessions Co-authored-by: multica-agent <[email protected]> * fix(comments): scope since delta to trigger thread Co-authored-by: multica-agent <[email protected]> * chore(comments): address thread delta review nits Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: Eve <[email protected]> Co-authored-by: multica-agent <[email protected]> |
||
|
Naiyuan QingandClaude Opus 4.8
|
3187bbf90c |
feat(comments): re-add since-delta + cold-start thread read + parent-root write normalization (#3494)
* feat(comments): since-delta new-comment hint + default-on comment session resume (#3432) * feat(db): add unresolved comment count + list filter queries Add CountUnresolvedComments (excludes the agent's own comments) and ListUnresolvedCommentsForIssue. Both are additive — existing callers stay on the unfiltered queries — so old clients are unaffected. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * feat(handler): support unresolved-only comment listing Wire an additive `unresolved` query param into ListComments. Defaults off so an old CLI that never sends it gets unchanged behavior; only true/1 enable it. Rejects combining unresolved with thread/recent (whole-issue filter vs navigation models). Includes filter + count query tests. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * feat(handler): plumb unresolved count + thread root into claim, gate comment resume Populate trigger_parent_id (thread root of the trigger comment) and unresolved_count (excludes the agent's own comments) on comment-triggered claim responses. Both fields are omitempty so old daemons ignore them. Gate comment-triggered session resume behind MULTICA_RESUME_COMMENT_SESSION (default off): resumed comment turns can inherit the prior turn's "Done." final message, so this stays an explicit rollout switch. The runtime-match and poisoned-session guards still apply regardless of the flag. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * feat(daemon): inject unresolved-comments hint + resolve step into agent brief Add a shared BuildUnresolvedCommentsHint helper rendered on both the per-turn prompt and the CLAUDE.md workflow (kept in sync per PR #2816). It ships only the count and the relevant CLI call — never comment bodies — so the server stays cheap. Thread case points at --thread <root>; issue case points at --unresolved. Suppressed when the count is 0. Also add a workflow step telling the agent to `multica comment resolve <thread-root>` once a thread is fully handled, so the unresolved set converges. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * feat(cli): add comment list --unresolved and comment resolve command Add an --unresolved filter to `issue comment list` (wired to the server's unresolved param, rejected when combined with --thread/--recent) and a top-level `comment resolve <id>` command that POSTs to the existing /api/comments/{id}/resolve endpoint, letting an agent close threads it has fully handled. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * refactor(comments): since-delta new-comment hint + default-on comment resume Simplifies the comment-triggered agent flow down to what's actually needed: - New-comment awareness is now a pure time delta: the claim response carries new_comment_count + new_comments_since (anchored on the prior run's started_at, never completed_at so a long run can't miss comments). The per-turn prompt and CLAUDE.md workflow render one line — "N new comment(s) since your last run, --since <ts>" — via a shared BuildNewCommentsHint so the two surfaces can't drift. Cold start (no prior run) falls back to a plain read. - Comment-triggered tasks resume the prior session by default (same runtime), dropping the MULTICA_RESUME_COMMENT_SESSION rollout gate. The "Focus on THIS comment" prompt guard defends against inheriting the prior turn's "Done." marker; GetLastTaskSession still excludes poisoned sessions. - Drops the resolved-based machinery from the first draft: CountUnresolvedComments / ListUnresolvedCommentsForIssue queries, the `comment list --unresolved` flag, the `multica comment resolve` command, and the resolve workflow step. - Removes the verbose cursor-pagination paragraph from the comment prompt; the --thread/--recent/--since flags stay in the CLI/API, just no longer explained inline every turn. Compatibility: new claim fields are omitempty (old daemons ignore them). Comment resume is default-on and affects even old daemons, which already consume prior_session_id. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]> * feat(comments): collapse reply parent_id to thread root on write Comment threads are a 2-level model (root + flat replies, like Linear/Slack), enforced today only by the UI and the agent path — the CreateComment handler stored whatever parent_id it was handed, and the agent-side flatten walked just one level, so a reply-to-a-reply could land at depth 3+. Add GetThreadRoot (a recursive walk to the parent_id=NULL root) and run both write paths (handler.CreateComment, service.createAgentComment) through it, so every stored reply's parent_id IS its thread root. Readers can now treat parent_id as the thread root without re-walking. The agent-drift guard still compares the raw parent_id to the trigger comment before normalization. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> * feat(comments): cold-start reads triggering thread, warm keeps --thread pointer The since-delta rework dropped the thread-first read on the COLD path: a first-time agent fell back to the flat `comment list` dump (oldest-first, cap 2000), burying the trigger's context in ancient chatter. Point cold start at the triggering conversation instead via a shared BuildColdCommentsHint (`--thread <trigger> --tail 30` + a --recent pointer for cross-thread background). On the WARM path, --since is a pure time delta and can miss the triggering thread's pre-anchor history, so BuildNewCommentsHint now also emits a --thread pointer. Both surfaces (per-turn prompt + CLAUDE.md workflow) render via the shared helpers so they cannot drift (PR #2816 rule). Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]> |
||
|
Naiyuan Qing
|
d90732750f |
Revert "feat(comments): since-delta new-comment hint + default-on comment ses…" (#3455)
This reverts commit
|
||
|
Naiyuan QingandClaude Opus 4.7
|
5e78e5100a |
feat(comments): since-delta new-comment hint + default-on comment session resume (#3432)
* feat(db): add unresolved comment count + list filter queries Add CountUnresolvedComments (excludes the agent's own comments) and ListUnresolvedCommentsForIssue. Both are additive — existing callers stay on the unfiltered queries — so old clients are unaffected. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * feat(handler): support unresolved-only comment listing Wire an additive `unresolved` query param into ListComments. Defaults off so an old CLI that never sends it gets unchanged behavior; only true/1 enable it. Rejects combining unresolved with thread/recent (whole-issue filter vs navigation models). Includes filter + count query tests. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * feat(handler): plumb unresolved count + thread root into claim, gate comment resume Populate trigger_parent_id (thread root of the trigger comment) and unresolved_count (excludes the agent's own comments) on comment-triggered claim responses. Both fields are omitempty so old daemons ignore them. Gate comment-triggered session resume behind MULTICA_RESUME_COMMENT_SESSION (default off): resumed comment turns can inherit the prior turn's "Done." final message, so this stays an explicit rollout switch. The runtime-match and poisoned-session guards still apply regardless of the flag. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * feat(daemon): inject unresolved-comments hint + resolve step into agent brief Add a shared BuildUnresolvedCommentsHint helper rendered on both the per-turn prompt and the CLAUDE.md workflow (kept in sync per PR #2816). It ships only the count and the relevant CLI call — never comment bodies — so the server stays cheap. Thread case points at --thread <root>; issue case points at --unresolved. Suppressed when the count is 0. Also add a workflow step telling the agent to `multica comment resolve <thread-root>` once a thread is fully handled, so the unresolved set converges. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * feat(cli): add comment list --unresolved and comment resolve command Add an --unresolved filter to `issue comment list` (wired to the server's unresolved param, rejected when combined with --thread/--recent) and a top-level `comment resolve <id>` command that POSTs to the existing /api/comments/{id}/resolve endpoint, letting an agent close threads it has fully handled. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * refactor(comments): since-delta new-comment hint + default-on comment resume Simplifies the comment-triggered agent flow down to what's actually needed: - New-comment awareness is now a pure time delta: the claim response carries new_comment_count + new_comments_since (anchored on the prior run's started_at, never completed_at so a long run can't miss comments). The per-turn prompt and CLAUDE.md workflow render one line — "N new comment(s) since your last run, --since <ts>" — via a shared BuildNewCommentsHint so the two surfaces can't drift. Cold start (no prior run) falls back to a plain read. - Comment-triggered tasks resume the prior session by default (same runtime), dropping the MULTICA_RESUME_COMMENT_SESSION rollout gate. The "Focus on THIS comment" prompt guard defends against inheriting the prior turn's "Done." marker; GetLastTaskSession still excludes poisoned sessions. - Drops the resolved-based machinery from the first draft: CountUnresolvedComments / ListUnresolvedCommentsForIssue queries, the `comment list --unresolved` flag, the `multica comment resolve` command, and the resolve workflow step. - Removes the verbose cursor-pagination paragraph from the comment prompt; the --thread/--recent/--since flags stay in the CLI/API, just no longer explained inline every turn. Compatibility: new claim fields are omitempty (old daemons ignore them). Comment resume is default-on and affects even old daemons, which already consume prior_session_id. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]> |
||
|
Bohan Jiangandmultica-agent
|
046e4b1efa |
fix(execenv): switch every provider's Windows reply template to --content-file (#2411)
Three user reports converge on the same Windows-shell encoding bug: - #2198 / #2236 — Chinese, Codex on Win11. Comments / descriptions generated by the agent arrive as `?`. - #2376 — Cyrillic, non-Codex agent ("Ops Lead") on Win11 Desktop. Title preserved (argv → CreateProcessW UTF-16), description / agent reply garbled (stdin → shell-codepage re-encoding). woodcoal's independent diagnosis on #2198 confirms the root cause: Windows PowerShell 5.1's `$OutputEncoding` defaults to ASCIIEncoding when piping to a native command, so non-ASCII bytes are silently replaced with `?` before they reach `multica.exe`. The CLI's stdin parsing is fine; the bytes are corrupted upstream, in the agent's shell layer. This PR ships the fix that supersedes the codex-only attempt in PR #2265 (which is closed in favour of this one): ## CLI Add `--content-file <path>` to `multica issue comment add` and `--description-file <path>` to `multica issue {create,update}`. The CLI reads bytes off disk via `os.ReadFile` and skips the shell entirely; UTF-8 survives end-to-end regardless of `$OutputEncoding` or `chcp`. The three input modes (`--content`, `--content-stdin`, `--content-file`) are mutually exclusive. ## Runtime config `buildMetaSkillContent`'s Available Commands section is rewritten as a neutral three-mode menu. The previous unconditional "MUST pipe via stdin" / `--description-stdin` mandate (over-spread from #1795 / #1851's Codex-multi-line fix) is gone for non-Codex providers; the strong directive now lives only in the Codex-Specific section, which branches on host: - Codex / Linux+macOS: `--content-stdin` + HEREDOC (preserves MUL-1467 fix against codex's literal `\n` habit). - Codex / Windows: `--content-file` (PowerShell ASCII pipe is the exact bug we're patching). ## Per-turn reply template `BuildCommentReplyInstructions` now takes a provider arg and branches provider × OS: - Windows + any provider → `--content-file` (the bug is shell-layer, not provider-layer; #2376 shows non-Codex agents on Windows also hit it). All providers write a UTF-8 file with their file-write tool and post via `--content-file ./reply.md`. - Linux/macOS + Codex → stdin/HEREDOC (MUL-1467 protection). - Linux/macOS + non-Codex → lightweight pre-#1795 inline `--content "..."`. The CLI server-side decodes `\n`, so escaped multi-line works; the agent retains stdin / file as escape hatches for richer formatting. `BuildPrompt` and `buildCommentPrompt` gain a `provider` arg; `daemon.runTask` already has it in scope. ## Tests - `TestResolveTextFlag` — file-source verbatim with non-ASCII (`标题 / Заголовок / 中文段落`), missing-file error, empty-file rejection, three-way mutual exclusion. - `TestInjectRuntimeConfigAvailableCommandsIsNeutral` — every non-Codex provider × {linux, darwin, windows} pins the three-mode menu present + over-spread "MUST stdin" substrings absent. - `TestInjectRuntimeConfigCodexLinuxEmphasizesStdin` + `TestInjectRuntimeConfigCodexWindowsUsesContentFile` — Codex section's per-OS branch. - `TestBuildCommentReplyInstructionsCodexLinux` + `TestBuildCommentReplyInstructionsNonCodexLinux` + `TestBuildCommentReplyInstructionsWindowsUsesContentFile` — the reply-template provider × OS matrix. - `TestInjectRuntimeConfigWindowsCommentTriggerHasNoStdin` — end-to-end AGENTS.md / CLAUDE.md on Windows has no prescriptive stdin directive, for claude / codex / opencode. `go test ./...` and `go vet ./...` clean. Closes #2198, #2236, #2376. Co-authored-by: multica-agent <[email protected]> |
||
|
Bohan Jiang
|
d964d37f97 |
Revert "fix(cli): add --content-file / --description-file for non-ASCII on Wi…" (#2252)
This reverts commit
|
||
|
Bohan Jiangandmultica-agent
|
9650788709 |
fix(cli): add --content-file / --description-file for non-ASCII on Windows (#2247)
* fix(cli): add --content-file / --description-file for non-ASCII on Windows Windows PowerShell 5.1 (the Win11 default) and cmd.exe re-encode HEREDOC content through the active console codepage before piping it to a child process. Characters the codepage cannot represent are silently replaced with `?`, so agents on Chinese Win11 hosts emitting `--content-stdin` / `--description-stdin` HEREDOCs land all of their Chinese as `?` in the issue body and comments. The daemon log shows the original Chinese correctly because slog writes to a file directly, so the regression hides until the user opens the issue page. Add a `--content-file <path>` / `--description-file <path>` source to `resolveTextFlag`: the CLI reads the file straight off disk, preserves UTF-8 bytes verbatim, and skips the shell entirely. The runtime config injected into AGENTS.md / CLAUDE.md now surfaces this as the canonical Windows fallback when the daemon host runs on Windows; non-Windows hosts keep the existing stdin/HEREDOC guidance untouched. Closes #2198, #2236. Co-authored-by: multica-agent <[email protected]> * fix(execenv): route every Windows-host stdin directive at --content-file GPT-Boy on PR #2247 caught that the previous patch only inserted a Windows fallback into the Available Commands section. Two later prompt surfaces still hard-coded `--content-stdin` and overrode it for the agent: - The Codex-specific paragraph in `buildMetaSkillContent`, which always said "always use `--content-stdin` with a HEREDOC". - `BuildCommentReplyInstructions`, which is re-emitted on every turn for comment-triggered tasks (both via the AGENTS.md/CLAUDE.md workflow and the daemon's per-turn prompt) and mandated the same HEREDOC pipe. On Windows hosts we now branch both surfaces to a file-based template: the agent writes the body to a UTF-8 file with its file-write tool and posts via `--content-file <path>`. Non-Windows hosts keep the existing stdin/HEREDOC guidance untouched. Tests: - `TestBuildCommentReplyInstructionsWindowsUsesContentFile` pins the Windows / non-Windows reply-instruction text directly. - `TestInjectRuntimeConfigWindowsCommentTriggerHasNoStdin` asserts that the end-to-end CLAUDE.md / AGENTS.md surface for a comment-triggered Windows task has no remaining `--content-stdin` directive that could override the Windows fallback (covers Claude + Codex providers). Co-authored-by: multica-agent <[email protected]> * fix(execenv): make Windows comment block file-first, pin tests by GOOS GPT-Boy's second review on PR #2247 flagged two follow-up blockers: 1. The Windows comment/description block in `buildMetaSkillContent` was "stdin first, file caveat appended" — agents on Windows still saw "Agent-authored comments should always pipe content via stdin" / "MUST pipe via stdin" / `--description-stdin` directives before reaching the Windows fallback, so the contradicting instruction was live in the same prompt. Rewrite the entire Available Commands bullet for Windows hosts as file-first: the headline line names `--content-file`, the bulleted rules name `--content-file` / `--description-file`, and stdin only appears in anti-prescriptive "do NOT pipe via …" prose. 2. The existing non-Windows tests (TestBuildCommentReplyInstructions IncludesTriggerID, TestInjectRuntimeConfigDirectsMultiLineWritesToStdin, TestInjectRuntimeConfigCodexEmphasizesStdinForFormattedComments, TestInjectRuntimeConfigCommentTriggerUsesHelper) all depended on `runtimeGOOS` defaulting to non-Windows; they would silently fail on a Windows test runner. Pin them to `runtimeGOOS = "linux"` via save+restore and drop t.Parallel so they don't race with the GOOS-mutating Windows tests. Test additions: - TestInjectRuntimeConfigWindowsRecommendsContentFile now asserts the Windows AGENTS.md does NOT contain prescriptive stdin phrasings (`MUST pipe via stdin`, `use --description-stdin and pipe a HEREDOC`, `<<'COMMENT'`, `Agent-authored comments should always pipe content via stdin`, `always use --content-stdin`) on top of the file-first positive assertions. The ban list pins prescriptive substrings, not bare flag names, so anti-prescriptive prose like "do NOT pipe via --content-stdin" doesn't trip the ban. - TestInjectRuntimeConfigWindowsCommentTriggerHasNoStdin gets the same expanded ban list across the Available Commands, Codex paragraph, and per-turn reply template surfaces. - The non-Windows side of TestInjectRuntimeConfigWindowsRecommendsContentFile pins that the Linux stdin/HEREDOC contract is still in place, so a future refactor can't accidentally move every host to file-first. Co-authored-by: multica-agent <[email protected]> --------- Co-authored-by: multica-agent <[email protected]> |
||
|
devv-eveandDevv
|
365e84b920 |
fix(execenv): prefer stdin for formatted comment replies (#1851)
Co-authored-by: Devv <[email protected]> |
||
|
devv-eveandDevv
|
9587a577e2 |
fix: guide codex multiline comments (#1795)
Co-authored-by: Devv <[email protected]> |
||
|
Bohan Jiang
|
e0e91fc792 |
feat(daemon): harden agent mention-loop instructions (#1581)
* feat(daemon): harden agent mention-loop instructions Two agents that mention each other via `mention://agent/<id>` can fall into an infinite reply loop — each says "I'm done" in prose but keeps `@mentioning` the other, which re-enqueues their run. Adding hard caps on agent-to-agent turns conflicts with Multica's design principle of giving agents the same authorship freedom as humans, so this change hardens the instructions that the harness injects instead. - Replace the terse "mentions are actions" blurb with a full Mentions protocol: `side-effecting` warning, explicit "when NOT to mention" (replying to another agent, sign-offs, thanks) and "when a mention IS appropriate" (human escalation, first-time delegation, user asked). - Add a pre-workflow decision step for comment-triggered runs: decide whether a reply is warranted at all, decide whether to include any `@mention`, and clarify that the post-a-comment rule is mandatory *if* you reply — silence is a valid exit for agent-to-agent threads. - Thread the triggering comment's author kind + display name (`TriggerAuthorType` / `TriggerAuthorName`) from the claim endpoint through the daemon task type, per-turn prompt, and CLAUDE.md workflow. When the author is another agent, both surfaces now name that agent and warn against sign-off mentions. - Soften the old closing line that told agents to `always` use the mention format — the word generalized to member/agent mentions and encouraged the very behavior that causes loops. Refs GH#1576, MUL-1323. * fix(daemon): remove MUST-respond conflict and sanitize trigger author name Addresses two blocking points on PR #1581: 1. buildCommentPrompt told the agent "You MUST respond to THIS comment" and unconditionally appended the reply command — directly conflicting with the new agent-to-agent silence-as-valid-exit workflow. Models were likely to keep following the older must-reply rule and fall back into the loop this PR is trying to close. Rewrite the header as "Focus on THIS comment — do not confuse it with previous ones" (keeps the anti-stale-comment signal) and change BuildCommentReplyInstructions to open with "If you decide to reply, post it by running exactly this command" so the reply command is available but conditional across both prompt surfaces. 2. Raw agent/user display names were being embedded directly into the high-priority prompt and CLAUDE.md via TriggerAuthorName. Agent and member names are only validated as non-empty at write time, so a name containing newlines, backticks, or fake mention markup would turn the field into a cross-agent prompt-injection surface. Add execenv.SanitizePromptField — strip control runes, collapse whitespace, drop markdown structural characters (backtick, asterisk, brackets, pipe, angle brackets, hash, backslash), truncate to 64 runes — and apply it at both embed sites (per-turn prompt and CLAUDE.md). Defense-in-depth at the consumption layer so this works for already-stored names without a migration. Tests: TestSanitizePromptField covers the policy; TestBuildPromptSanitizesAgentName plants an attack payload in TriggerAuthorName and checks the rendered prompt does not leak the newline-anchored injection or the fake mention markup. TestBuildPromptCommentTriggered*{,ByMember} updated to lock in the conditional reply-command framing. * refactor(daemon): trim redundant CLAUDE.md preamble and drop name sanitizer Per PR #1581 feedback: 1. Remove the `if ctx.TriggerAuthorType == "agent"` preamble block in runtime_config.go. It duplicated what workflow steps 4 and 5 already say ("Decide whether a reply is warranted", "Never @mention the agent you are replying to as a thank-you or sign-off"), so the signal lands the same without the extra ~7 lines of CLAUDE.md. The per-turn prompt preamble in prompt.go stays — that surface has no numbered workflow below it and would otherwise lose the silence-as-exit signal. 2. Delete execenv.SanitizePromptField + its test. Workspace agents are created by trusted team members, so the cross-agent name-injection surface it defended isn't realistic in the current trust model. 3. Drop TriggerAuthorType/Name from execenv.TaskContextForEnv and stop populating them in daemon.go — they're no longer read by the execenv package. The same fields on daemon.Task stay because prompt.go still needs them to label the triggering author in the per-turn prompt. Tests simplified to match the leaner shape: CLAUDE.md regression guards now assert that the anti-loop phrases live in the numbered workflow, and the sanitizer-specific tests are removed. |
||
|
Bohan Jiang
|
951f51408a |
fix(agent/comments): prevent resumed sessions from reusing stale --parent UUID (#1374)
* fix(agent/comments): re-emit trigger comment id every turn + server-side parent_id guard Resumed Claude sessions keep prior turns' tool calls in context, so a comment-triggered task could reuse the PREVIOUS turn's --parent UUID instead of the current trigger's. The reply landed in the wrong thread (MUL-1125): backend stored exactly what the agent sent, but the agent pulled a stale UUID from its own conversation memory. Two layers of defense: 1. Extract BuildCommentReplyInstructions so daemon.buildCommentPrompt and execenv.InjectRuntimeConfig emit the same "use this exact --parent, do not reuse values from previous turns" block. The per-turn prompt now carries the current TriggerCommentID, which it previously relied on CLAUDE.md for (and CLAUDE.md isn't re-read mid-session). 2. Handler-side guard in CreateComment: when an agent posts from inside a comment-triggered task (X-Agent-ID + X-Task-ID, task has TriggerCommentID), require parent_id == task.TriggerCommentID or return 409. Assignment-triggered tasks are untouched. * fix(agent/comments): scope parent_id guard to the task's own issue Two issues from CI + GPT-Boy's review: 1. Guard was too broad: the CLI stamps X-Task-ID on every request, so an agent legitimately commenting on a different issue while its current task was comment-triggered would get 409'd with the wrong issue's trigger comment id. Narrow the guard to fire only when the request's issue matches the task's own issue — cross-issue agent activity stays unblocked. 2. The integration test tried to insert a second queued task for the same (agent, issue), which hits the idx_one_pending_task_per_issue_agent unique index. Replace the assignment-triggered-task sub-case with a cross-issue regression test (the scenario we now need to cover anyway): post on issue B while X-Task-ID points at a comment-triggered task on issue A, expect 201. |