Commit Graph

106 Commits

Author SHA1 Message Date
Nicolas Lenepveu e527310fb8 fix(mcp): report the agent profile that will actually launch (#2329) 2026-08-06 15:57:35 +01:00
Carlos Florêncio acfbf58646 fix: harden remote contribution launch safety (#2294) 2026-08-06 12:07:13 +01:00
Carlos Florêncio 84fe8132a1 feat: support remote contribution tasks (#2265) 2026-08-05 19:25:58 +01:00
Carlos Florêncio ad70426d46 feat: rename generated task branches (#2262) 2026-08-05 18:23:57 +01:00
Alassane ae31fa85a9 feat(gitlab): add task MR lifecycle notifications (#2125)
Co-authored-by: Carlos Florencio <carlosmflorencio@gmail.com>
2026-08-05 18:22:31 +01:00
José Almeida c95d44193c fix: make walkthrough MCP failures actionable (#2209) 2026-08-03 16:34:04 +01:00
Carlos Florêncio 1e5fce99c4 feat: run completion actions on cancelled turns (#2186) 2026-08-03 13:37:34 +01:00
Carlos Florêncio 2a2c9d3118 docs: clarify generated task title guidance (#2171) 2026-08-02 21:15:49 +01:00
Carlos Florêncio f51a83e4d3 fix: publish clarification task state updates (#2174) 2026-08-02 20:42:57 +01:00
Carlos Florêncio 62d4522e0f feat: add file-backed diagnostic log bundles (#2087) 2026-08-02 20:14:53 +01:00
Carlos Florêncio 3b00a22589 feat: add optional agent-generated task titles (#2104) 2026-08-02 15:53:46 +01:00
Carlos Florêncio 1d70a0df6d feat: enforce task title length limit (#2134) 2026-08-01 19:42:23 +01:00
Carlos Florêncio 1bccadf8f9 fix: validate MCP tool arguments (#2123) (#2128) 2026-08-01 18:18:08 +01:00
Carlos Florêncio 167ab6b778 feat(mcp): add session attachment diagnostics (#2061) 2026-07-30 20:49:07 +01:00
João Salavisa 744aabee96 fix(mcp): keep spawner attribution on a spawned session's first turn (#2047)
* fix(mcp): keep spawner attribution on a spawned session's first turn

A session started through spawn_session_kandev never learned who spawned
it, so it had no way to report back. The MCP handler did prepend a
<kandev-system> attribution block, but the first-turn canonicalizer
(sysprompt.canonicalizeKandevContext) drops every system block it cannot
attribute to server state — and the spawn block was not on the trusted
list, so it was deleted before the agent ever saw it. Spawns are always a
first turn, so this happened every time.

Generate the block at the launch site instead, from server-resolved
identity, and whitelist that exact content for the injector — the same
pattern entity references already use:

- config/prompts/spawned-session.md holds the attribution template.
- sysprompt.SpawnedSessionContext builds it; sysprompt.StripTags (lifted
  out of the handlers' stripSystemTag) keeps embedded IDs from closing
  the block early.
- LaunchSessionRequest.SpawnOrigin carries the spawner identity and is
  kept off the wire (json:"-") so a WS client cannot forge a trusted
  system block.
- startTask prepends the block and passes the identical content as
  trusted content to both the task and Office injectors. Its trailing
  env/route parameters move into a startTaskOptions struct rather than
  growing the positional list again.
- The MCP handler now only fills SpawnOrigin (including the spawner's
  session name) and passes the prompt through untouched.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(mcp): derive spawn attribution from the verified spawner session

Addresses both PR review findings.

CodeRabbit: spawnOrigin copied sender_task_id / sender_session_id straight
out of the request, so an unknown or cross-task sender_session_id became
trusted launch attribution — the spawned agent would be told to report to
a session that never asked for it. Resolve the spawner session once, up
front, require it to belong to the claimed sender task, and derive the
origin (and the inherited agent profile) from that row. An unverifiable
claim now yields no attribution instead of a forged one. This also drops
a duplicate session lookup.

Codex: passthrough profiles skip the Kandev MCP wrap, so the new
attribution never reached a spawned passthrough session even though it
gets MCP configured and can reply. Give that path plain-text attribution
(no <kandev-system> markup, which would show up raw in the TTY the user
is watching). The wrap branch moves into applyLaunchPromptContext, which
keeps startTask under the nesting limit.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-29 22:51:40 +01:00
Luan Martins 04a5c4e4ee feat(github): add task PR lifecycle notifications (#2038) 2026-07-29 18:13:02 +01:00
Carlos Florêncio f501346d15 feat: add visible WIP overflow queues (#2001) 2026-07-28 15:46:16 +01:00
Carlos Florêncio d705b3c2f3 fix(mcp): restore live add-branch worktrees (#1990)
* fix(mcp): restore live add-branch worktrees

* fix(mcp): reject deferred live branch additions

* docs(mcp): clarify live branch response contract
2026-07-27 22:08:18 +01:00
João Salavisa b118a4fe98 fix(mcp): honor explicit task_id in plan/walkthrough/review tools (#1984)
* fix(mcp): honor explicit task_id in plan/walkthrough/review tools

resolveTaskID silently discarded the caller-supplied task_id whenever the
MCP server was session-bound (every agent session) and substituted the
caller's own task. A parent reading a child's plan got the parent's empty
plan back ("No plan exists"), and a cross-task create/update would have
written to the wrong task — all with no error, despite the tool schemas
advertising task_id as a usable parameter.

Honor an explicitly provided task_id and fall back to the session-bound
task only when the argument is absent, matching how message_task_kandev /
stop_task_kandev already address other tasks. Cross-task access stays safe:
internal/mcp/scope attaches the stream owner's identity (from the agent's
own execution, never the payload), and the plan/walkthrough/review services
gate the target task_id through the same workspace-ownership check every
other cross-task surface uses — an out-of-reach task is rejected, not
served. The review service gains the SetTaskAuthorizer wiring the plan and
walkthrough services already had, so publish_review_findings is covered too.

Tool descriptions now document the default-to-current / cross-task-within-
reach behavior. Tests cover the resolution precedence (explicit wins /
fallback to bound / neither errors), a session-bound-to-A reads/creates a
plan for B regression, and the review authorizer allow/deny paths.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(mcp): drop mcp.Required() from task_id on session-defaulting tools

The plan, walkthrough, and publish-review tools default task_id to the
session-bound task when it is omitted, so advertising it as required
contradicted that documented behavior (flagged by Codex and CodeRabbit on
the PR). Mark task_id optional on all eight; handler behavior is unchanged.
The genuinely cross-task tools (update/move/delete/archive_task,
message_task, get_task_conversation) keep task_id required.

Adds a schema test asserting task_id is present-but-optional on every
session-defaulting tool.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(mcp): cover review scoping + walkthrough/review tool-desc reach

Addresses two non-blocking review findings:

- Extend TestPlanAndWalkthroughScoping to exercise ReviewService through the
  assembled AuthorizeTaskAccess → SetTaskAuthorizer → PublishFindings path, so
  all three task-scoped services are covered uniformly (foreign owner denied
  with ErrTaskNotFound; real owner passes and the finding is stored).
- Document the default-to-current / cross-task-within-reach semantics in the
  top-level descriptions of the walkthrough and publish-review tools (was only
  in the task_id parameter description), since LLMs read the tool description
  first. Broaden the description test to assert all eight session-defaulting
  tools carry it.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(mcp): assert review finding persists through the auth gate

Follow-up to review: query repo.ListTaskReviewFindings after the owner
publish in TestPlanAndWalkthroughScoping and assert exactly one finding was
stored, so the test verifies the write landed in the repository rather than
only the service's returned slice.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-27 18:34:55 +01:00
Carlos Florêncio 06d72a1215 fix: enforce workflow-step WIP limits on task creation (#1980) 2026-07-27 16:14:13 +01:00
João Salavisa bb72d70586 refactor(backend): remove dead code and deprecated shims (#1965)
Delete unreachable/unused backend symbols confirmed by staticcheck U1000
and golang.org/x/tools/deadcode, plus deprecated back-compat aliases kept
alive only by their own tests.

Removed (unused):
- parseGitHubRepoURL, syncTaskStateForBulkWorkflowMove (task/service)
- resolvePrimaryRepoInfo (orchestrator/executor)
- resolveWorkflowAgentProfile, workflowDefaultAgentProfile wrappers (mcp/handlers)
- cleanupExitedContainer (runtime/lifecycle) + orphaned fmt import
- VscodeManager.setEnv (agentctl/server/process)
- repoRootDir const (cmd/preview)

Removed (deprecated shims):
- Canceller.CancelSessionAndNotify alias -> callers use DetachSessionAndNotify
- ScriptPlaceholder type alias (live scriptPlaceholders var kept)
- Placeholder{QueueRun,ClearDecisions,QueueRunForEachParticipant}Callback
  no-op structs and their self-referential test

No behavior change; build, vet, and affected-package tests pass.

Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-26 17:54:12 +01:00
João Salavisa 57adf1449c feat(review): native code-review agent with inline findings in the Changes panel (#1957)
* feat(review): persist and publish native code-review findings

Adds the backend core for reviewing a task's working diff before a PR
exists: task-scoped review runs and anchored, advisory findings that the
Changes/Review panel can render as inline comments.

- task_review_runs / task_review_findings schema, models, and repository,
  with supersede-on-re-review and a restart sweep that cancels in-flight
  runs rather than leaving them looking alive.
- ReviewService as the single write path, publishing bus events that the
  WS gateway forwards to the client.
- internal/review: reviewer-identity resolution (agent profile > code-review
  utility agent > user default, failing closed on passthrough-only profiles),
  change-set collection, prompt batching, response parsing, anchor
  extraction, and run orchestration.
- publish_review_findings_kandev MCP tool plus the task.review.* WS actions.
- Go djb2 that matches apps/web/lib/utils/hash.ts, asserted from shared
  fixtures on both sides so stale detection agrees across the wire.

Spec: docs/specs/native-code-review/spec.md
Plan: docs/plans/native-code-review/plan.md

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* feat(review): add run_code_review workflow step and wire the review runner

Makes a review pass triggerable both ways and actually runnable end to end.

- run_code_review on_enter action across models, engine compile, and an
  orchestrator callback that logs rather than propagates failures, so a task
  never gets stuck in a step because no reviewer was configured.
- The step's optional agent_profile_id is what lets a step review with a
  different model than it implemented with; export/import swap it for a
  portable agent name/model/mode so it survives a cross-workspace round trip
  instead of carrying a dangling id.
- Concrete adapters for reviewer identity, changed-file collection, prompt
  rendering from the code-review utility agent's editable prompt, and
  inference (session-bound agentctl, falling back to the host instance so a
  review works on a task whose agent is not running).
- Boot sweep cancels review runs interrupted by a restart; the E2E reset
  clears review state before deleting the tasks that own it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* feat(web): add review findings state, helpers, and live updates

Frontend plumbing for native code review, ahead of the UI that renders it.

- Review types, WS message map, and an API client that preserves the backend's
  machine-readable failure code so the surface can show an actionable message.
- A review store slice that merges findings by id (a re-publish refreshes an
  issue rather than listing it twice) and keeps a bounded run history.
- Findings helpers: composite file keys matching reviewFileKey, staleness via
  the same per-file diff hash that drives review marks, and best-effort
  re-anchoring from the stored anchor text so a moved finding follows the code
  it was written about instead of pointing at whatever now occupies its line.
- Hooks for backfill, resolve/dismiss/reopen with optimistic rollback, and
  sending a finding to the agent as follow-up context without changing its
  status — handing a finding to an agent is not the human accepting it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* feat(web): render review findings inline in the Changes diff

Findings now appear where the code is, in the same annotation surface as
anchored review comments, with the run control that produces them.

- ReviewFindingCard: severity chip, category, Markdown body, and the three
  advisory actions. A suggestion is labelled "not applied automatically"
  because it is display-only in this iteration. Resolved and dismissed
  findings collapse to one muted line with an Undo, so a reviewed diff does
  not stay cluttered while the human can still change their mind.
- A review-finding annotation type threaded through the diff viewer, anchored
  from the same per-file diff hash the backend stamped. A finding whose diff
  moved is re-anchored from its stored text when that text survives, and
  otherwise reported as unanchored rather than placed against unrelated code.
- Review changes control with idle / running / cancel / failed states, and an
  inline Settings link for the one failure the user can actually fix.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* feat(web): make the review control reachable from the Review toolbar

Mounts the Review changes control next to the walkthrough action and lets an
inline finding wire its own actions.

The finding card container now reads the active task and session from the store
instead of taking four callbacks threaded through FileDiffViewer and DiffViewer;
an inline finding annotation only exists when the active task has findings, so
the store is always present and every other diff consumer is spared the
plumbing. Staleness likewise hashes the diff the viewer already holds, which is
already normalized, so it matches the hash the backend stamped without passing
it down.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* feat(web): surface stale review findings above their file's diff

A finding whose diff moved and whose anchor text is gone had nowhere to render,
so it was silently dropped. It now appears in a collapsed per-file banner above
the diff: the finding may still be valid, and placing it at its stored line
would point at whatever code now occupies that line instead.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* docs(review): mark the landed native code-review plan tasks done

Tasks 01-09 (backend persistence through inline diff rendering) are
implemented, tested, and committed. Tasks 10-13 — findings overview and step
editor, mobile parity, E2E, and public docs — remain pending.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* test(review): cover the on-demand review path end to end

Adds the mock-agent review responder and a Playwright spec, so both the happy
path and the no-reviewer path are verified against a real backend.

The mock agent answers any prompt carrying the review sentinel with fenced JSON,
deriving its anchors from the prompt's own diff rather than hardcoding them, so
findings land on files and lines the fixture really changed. It includes one
deliberately malformed entry to exercise the rejected-entry path.

Writing it caught an off-by-one shared by three diff walkers: splitting on "\n"
leaves an empty element after a trailing newline, which carries no diff marker
and was being counted as a context line, pushing new-side numbering one past the
end of a hunk. Interior blank lines still count, since a whitespace-stripped
blank context line legitimately appears as "".

Also adds a listInferenceAgents helper: default_utility_agent_id needs the
registered agent-type id, and an agent row UUID is rejected as not
inference-capable.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(review): close review-run races and stale client findings

Addresses the three blockers and three suggestions from the PR #1957 automated
reviews. Two independent reviewers found each blocker separately.

- Launch claimed the task slot only after inserting the run row, so two
  concurrent launches both created a run and the loser returned a pending row
  with no goroutine behind it — a review that never finished until the next
  restart. The slot is now claimed before any DB write, and freed on every
  early return.
- Cancelling only marked the row. The goroutine ran on the shared background
  context, finished inference, and its completion overwrote the cancelled
  status and published findings the user had declined. Runs now carry a cancel
  handle, the WS action routes through the runner so the live context is
  cancelled, CompleteRun/FailRun refuse to resurrect a terminal run, and a
  cancelled pass neither publishes nor re-reports itself as failed.
- The backend deletes a superseded finding and inserts a replacement with a new
  id, but the publish event carried only the new one, so every open browser
  showed both at the same anchor until a reload. The event now names the
  superseded ids and the slice drops them.
- Run() waited on the shared WaitGroup, blocking on every other task's review;
  it now waits on its own pass only.
- createReviewSlice is typed over the `set` it actually uses, so call sites no
  longer pass superfluous arguments (CodeQL js/superfluous-trailing-arguments).
- A GetAgentProfile fault no longer collapses into "profile not found", which
  would have told the user to configure an agent they already have.

The cancel bug exposed a hole in the original tests: they asserted cancel could
not override a terminal run, but never the reverse. Both directions are covered
now, along with the concurrent-launch race, per-run waiting, and the supersede
path on both sides of the wire. Test fakes now mirror the service's terminal
guard rather than hiding it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-26 15:05:56 +01:00
Carlos Florêncio 45ba6691c9 fix: isolate task state when switching workspaces (#1951) 2026-07-26 10:40:40 +01:00
Carlos Florêncio bc218dfbbe feat: add workspace sources from files panel (#1900)
* feat: add workspace sources from files panel

* fix: preserve worktree identity during recovery

* feat: unify workspace source actions

* fix: validate recovered workspace repositories

* fix: harden workspace source filesystem boundaries

* test: split workspace repository chip coverage

* fix: restrict repository rescan recovery paths

* fix: stabilize workspace source CI checks

* test: canonicalize workspace source paths

* test: align workspace source container paths

* fix: populate direct workspace repository names

* test: preserve git fixture rewrites across restarts

* test: isolate backend git fixture config

* fix: resume remote workspace executions before creation

* fix: preserve ssh agent identity during resume

* fix: preserve SSH workspace across backend restart

* fix: simplify workspace actions trigger

* fix: refine add workspace repositories UX

* docs: narrow workspace source UX updates

* fix: avoid phantom turn on session resume

* test(web): normalize workspace source request headers

* feat(web): streamline workspace source picker

* docs: remove trailing spaces from workspace source plan

* fix: prevent resume status from creating phantom turns

* fix(web): stabilize workspace source attachment

* refactor(web): extract workspace source store contract

* fix: avoid phantom turns on idle agent resume

* fix: address backend static analysis findings

* fix: preserve agentctl readiness status value

* fix: preserve resume messages without active turns

* fix: resume agents from promoted workspace root

* chore: merge origin/main into feature/add-new-repo-folder-d97

* feat(web): explain workspace source consequences

* test(websocket): count session activity subscription
2026-07-25 21:29:53 +01:00
João Salavisa 103878047c fix(auth): scope in-session agent MCP calls to the task owner (#1937)
* fix(auth): scope in-session agent MCP calls to the task owner

The MCP tools an agent gets automatically inside its own session are
relayed over the agent's WebSocket stream, which carries no credential.
The backend dispatched them on the raw stream context, so the task
service saw no identity — its signal for an internal caller (event bus,
pollers, office schedulers) — and served the request unscoped. An agent
that supplied another user's task_id or workflow_id was given their
data, violating the rule that knowing an ID must not grant access.

Resolve the owning user from the stream's own AgentExecution (task ->
workspace -> owner) and attach that real stored identity before
dispatch, so the existing authorize* checks apply exactly as they do on
the PAT-authenticated /mcp endpoint. The owning task never comes from
the agent-supplied payload: honoring a payload session_id would let an
agent name another user's session and inherit their identity.

Tool handlers are unchanged. Auth disabled stays unscoped, unclaimed
pre-auth workspaces stay visible to everyone, and a lookup failure
denies the dispatch rather than falling back to full access.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(auth): never leave in-session MCP dispatch unscoped

Review follow-up. Three paths still returned an identity-free context
under enforced auth, and "no identity" is exactly what the task service
reads as an internal caller and serves unscoped:

- Unowned workspace. CreateWorkspace only stamps an owner for scoped
  callers, so internal callers keep producing owner_id='' rows after
  setup. Those streams got full cross-user access. Scope them to a
  sentinel user ID no account can hold: the service's "empty owner_id or
  my own ID" rule then limits them to the unowned rows that are public
  by the compatibility contract, and nothing else.
- Task with no workspace. Same treatment, same reasoning.
- Missing task or workspace row. A lookup that reports not-found as
  (nil, nil) fell through to unscoped; treat it as a resolution failure.

Also deny, rather than fabricate a member identity, when the owner's
account is gone or disabled. Disabling a user revokes their sessions and
PATs, so a still-running agent session was the one remaining way into
their workspace.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-25 09:56:47 +01:00
Carlos Florêncio d475cdf597 fix: scope Office agent tools and task mutations (#1867) 2026-07-23 16:31:37 +01:00
Carlos Florêncio c041dbee0e fix(orchestrator): separate office task session ownership (#1893) 2026-07-23 14:12:58 +01:00
João Salavisa ac6d8eb3be feat: resolve @prompt references in workflow prompts (#1865)
* feat: resolve @prompt_name saved-prompt references in workflow step prompts

Workflow step prompts, the GitHub review-watch task prompt, and the CI
auto-fix prompt now resolve "@name" references to saved custom prompts
(Settings > Prompts) at invocation time, appending the referenced
content as hidden context while keeping the mention visible - matching
how chat messages and message_task already resolve @mentions. Editing
a saved prompt now propagates to every workflow step that references
it without needing to update each step individually.

Adds a Monaco "@" completion provider to the step-prompt and
review-watch editors, alongside the existing "{{placeholder}}"
provider.

* fix: address PR review findings on prompt-reference expansion

- Make AppendReferenceExpansions idempotent: a prompt that already
  contains a previously-appended expansion block is returned unchanged,
  since the block's own "### @name" headers would otherwise be
  re-scanned as fresh mentions on a second call.
- Skip "@name" expansion entirely for CLI-passthrough sessions: their
  prompts are written raw to a PTY with no <kandev-system> stripping,
  so the hidden block would otherwise leak into the terminal verbatim.

* fix: fail safe on passthrough lookup error in startTask

A session-lookup error while resolving isPassthrough for the Kandev
MCP wrap and prompt-reference expansion previously defaulted to
false (non-passthrough), risking a hidden <kandev-system> block
leaking into a real passthrough session's PTY on a transient error.
Extracted resolveIsPassthroughForLaunch, which now fails safe by
defaulting to true (skip injection) and logs a warning.

* fix: scope expansion idempotency marker to system blocks

The idempotency guard added in a prior commit checked for the
expansion marker anywhere in the prompt, which could falsely
suppress a legitimate first-time expansion if caller-controlled
text happened to contain that literal phrase. Add
sysprompt.HasSystemMarker, mirroring the existing HasKandevContext
pattern, so the marker is only recognized inside a formatter-
produced <kandev-system> block. Also strengthens a passthrough test
assertion that didn't actually distinguish the snapshot path from
the fail-safe default.

* fix: match exact expansion-block prefix in idempotency guard

The prior scoping fix accepted the marker anywhere inside any
<kandev-system> block, which could still false-positive against an
unrelated system block (e.g. a plan-mode prefix or MCP context
wrap) that happens to mention the marker phrase without it being
the block's own content. Check for the exact literal prefix this
package's formatter produces instead: the opening tag immediately
followed by the marker, with nothing in between.

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
2026-07-23 13:14:54 +01:00
Alassane 21b0003b32 fix: surface orphaned tasks in pipeline view after step deletion (#1809) 2026-07-21 21:37:50 +01:00
Carlos Florêncio 33aa7af67e feat: configure profiles for MCP-created tasks (#1797) 2026-07-19 23:18:06 +01:00
José Almeida f7f1d10996 feat: add parent-controlled task stopping via MCP (#1803)
* feat: add parent-controlled task stopping via MCP

* fix: harden parent task stop lifecycle

* fix: preserve rejected task rollback state
2026-07-19 20:23:46 +01:00
José Almeida 1a42c07abe fix: keep queued messages parked after agent cancellation (#1796) 2026-07-19 13:50:03 +01:00
João Salavisa 9b7fa0ec9c fix(mcp): provide bounded access to CREATED sibling task descriptions (#1773)
* fix(mcp): provide bounded access to CREATED sibling task descriptions

Include the task description in the list_related_tasks_kandev projection so a
coordinating agent can read dependency metadata (e.g. a "Depends on:" line)
from a related task — including a CREATED sibling that has no session yet —
without falling back to an unbounded list_tasks_kandev call.

The relation graph is the bound: only parent/children/siblings/blockers are
ever projected, so descriptions never leak from unrelated tasks or across
workspaces. ListSiblings already returns CREATED (unstarted) tasks and loads
their descriptions from storage; only the MCP projection was dropping the
field.

Closes #1772

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(mcp): gate related-task descriptions by caller access

Address PR review: list_related_tasks_kandev ignored caller_task_id and
projected any named task's description, so a caller that learned an unrelated
or cross-workspace task ID could read it. Add ListRelatedForCaller, which
enforces the same relation/workspace read guard the document tools use
(self/ancestor/descendant/sibling/blocker, same workspace) for non-self
targets, and wire the MCP handler through it (access-denied maps to forbidden).
The un-gated ListRelated stays for trusted internal callers (GetTaskContext).

Add tests for the blocker/blocked-by description projection and the caller
access guard (unrelated + cross-workspace denied, relations allowed).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor(mcp): align related-tasks error mapping and empty-caller guard

Address PR review nits: route handleListRelatedTasks errors through
mapHandoffError (logging only non-access-denied errors) for parity with the
document handlers, and make ListRelatedForCaller deny an empty caller against a
non-self target instead of silently delegating to the ungated ListRelated.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-18 13:22:32 +01:00
João Salavisa 9381a6a9f7 feat(mcp): session spawning, sibling messaging, and renameable tabs (#1734)
* fix(scripts): launch dev-isolated backend via __backend subcommand

The kandev binary became a bundle launcher with the restart supervisor
(ADR 0019) and exits without KANDEV_BUNDLE_DIR when invoked bare; the
isolated dev instance must run the backend entrypoint directly.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(mcp): session spawning, sibling messaging, and renameable tabs

- spawn_session_kandev spawns an additional agent session on an existing
  task (default: the caller's own) via LaunchSession(IntentStart), with
  optional agent_profile_id (defaults to the spawner's profile) and a
  session name; the initial prompt carries spawner attribution and reply
  instructions.
- message_task_kandev accepts an optional session_id to target a specific
  session, enabling same-task sibling messaging. Explicit targets are
  pinned through dispatch so the idle-path primary-session re-resolution
  cannot reroute a sibling message back to its sender (regression-tested).
- task_sessions gains a name column (migration ordered after the
  agent_execution_id-drop rebuild), a session.rename WS action, and inline
  tab rename UI; custom names take precedence over derived agent/model
  labels across the tab, agents dropdown, mobile list, chat header, and
  dockview panel titles.
- Inter-session messages stamp sender_session_name into metadata so the
  sender badge shows which session sent the message.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(mcp): address review findings on session spawn/rename/messaging

- include name in task-session DTOs (list + full, no omitempty) so
  persisted tab names survive list hydration and clears propagate
- sanitize sender task/session ids embedded in <kandev-system> blocks
- reject cross-workspace spawn targets; require sender_task_id
- truncate session names by runes, not bytes
- distinguish not-found from internal errors in message target lookup
- guard TabRenameInput blur-commit after Enter/Escape resolution
- cap optimistic rename length client-side and toast on rename failure
- add tests: spawn launch-failure and cross-workspace paths, renameSession
  API client

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(mcp): round-two review fixes for spawn/rename lint and hardening

- extract spawn validation/authorization helpers (cyclop/nestif limits)
- make stripSystemTag replace until stable to block nested tag evasion
- load session before rename so a durable rename can never skip its
  broadcast; surface lookup failures to the caller instead
- drop redundant sessionLauncher nil check (guarded registration)
- add maxLength to the rename input matching the server cap
- add tests: nested sanitizer evasion, spawn rename-failure tolerance

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-16 17:26:50 +01:00
Carlos Florêncio 2617df7deb fix: prevent cross-task acknowledgement loops (#1712) 2026-07-15 19:32:05 +01:00
Clément Fiere 84e40ee4c8 feat: interrupt busy child task turn on parent message_task_kandev (#1653) 2026-07-14 09:07:58 +01:00
Carlos Florêncio 248e8bf48e feat: add workflow WIP pull system (#1613) 2026-07-13 12:18:57 +01:00
José Almeida 3e237e177a feat: add agent-authored code walkthroughs (#1647)
* feat: add code-walkthrough backend (MCP tool, service, persistence, WS events)

* feat: render agent code walkthroughs as line-anchored cards + editor window

* test: add code-walkthrough re-emit mock-agent scenario

* fix: rework code-walkthrough UX (floating card, line reveal, minimize, clickable file)

* fix: improve code walkthrough editor UX

* fix: backfill walkthrough launcher after websocket connect

* fix: improve walkthrough requests and editor anchors

* fix: clear walkthrough highlights on close

* feat: add walkthrough discard and prompt customization

* fix: send walkthrough requests through saved prompt

* fix: support postgres built-in prompt seeding

* fix: address walkthrough review feedback

* fix: address walkthrough review follow-ups

* fix: harden walkthrough lifecycle races

* fix: reuse walkthrough notification cleanup

* fix: guard stale walkthrough file opens

* fix: abort stale file opens before paint

* fix: stabilize github settings e2e readiness

* fix: use stable github settings e2e selector
2026-07-10 08:34:57 +01:00
José Almeida f236c90416 fix: inherit parent scope for mcp subtasks (#1638)
* fix: inherit parent scope for mcp subtasks

* fix: clarify mcp subtask parent shorthand

* fix: simplify mcp subtask scope fallback

* fix: ignore subtask workflow step overrides

* fix: add mcp subtask workspace mode

* fix: simplify mcp task scope defaults

* fix: clarify mcp workflow defaulting

* fix: forward mcp subtask workspace mode

* fix: sanitize mcp workflow validation
2026-07-09 23:15:20 +01:00
Carlos Florêncio 1953420939 fix: sync task completion with terminal workflow steps (#1639) 2026-07-09 21:37:56 +01:00
Carlos Florêncio e2eaad01ed fix: expand nested custom prompts (#1637) 2026-07-09 21:37:22 +01:00
Carlos Florêncio 2b8504a913 fix: handle config MCP executor listing (#1628) 2026-07-09 08:09:11 +01:00
Carlos Florêncio fd3cc64d12 fix: expose signal-gated workflow steps in config MCP (#1629) 2026-07-09 08:08:53 +01:00
Carlos Florêncio 67a16732ce fix: repair office agent launch context (#1601) 2026-07-06 19:10:12 +01:00
Carlos Florêncio 3869dee489 fix: pause on clarification timeout (#1580) 2026-07-02 20:07:31 +01:00
Carlos Florêncio 7893a5e33e fix: trigger workflow on agent task messages (#1555)
* fix: trigger workflow on agent task messages

* fix: harden agent task message dispatch

* fix: preserve completed task message sessions

* fix: restore review step on task message failure

* test: cover completed task message handoff

* fix: publish task message rollback events

* fix: restore task message session rollback

* fix: avoid orphaned task message rows

* docs: explain task message prompt recording

* fix: harden task message rollback cleanup

* fix: complete task message rollback cleanup

* fix: restore task message dispatch side effects

* fix: restore task state after capture failure

* fix: simplify task message rollback cleanup

* fix: preserve task message rollback snapshots

* fix: restore task message turn-start snapshots

* fix: preserve task message queue snapshots

* fix: fail closed on office task lookup

---------

Co-authored-by: root <root@kandev.ts.net>
2026-06-30 18:28:28 +01:00
Carlos Florêncio f7d519db78 fix: inherit current task profile for mcp tasks (#1546)
* fix: inherit current task profile for mcp tasks

* fix: respect workflow-switched mcp task profiles

* test: cover mixed mcp task profile inheritance

* fix: tag reused workflow sessions

* fix: tag matching workflow sessions

* fix: inherit routed session launch metadata

* fix: harden mcp profile inheritance

* fix: preserve routed executor inheritance

* test: simplify workflow move provenance assertion

---------

Co-authored-by: root <root@kandev.ts.net>
2026-06-29 23:06:46 +01:00
Carlos Florêncio 3836f0e9a7 fix: persist profiles for deferred MCP tasks (#1503) 2026-06-26 14:04:39 +01:00
Carlos Florêncio 6118201c20 fix: enforce single workflow start step (#1507) 2026-06-26 13:59:55 +01:00
Carlos Florêncio cb7aa3fa71 fix: prevent invalid MCP task sessions (#1494) 2026-06-25 18:30:33 +01:00