approve_workflow_step
ChatGPTApprove or reject the manual quality gate currently pausing a workflow run, bound to the exact expected code revision (and optionally the approval digest of the reviewed outputs). Every decision records an approval receipt that downstream nodes can read; rejection cancels the run. Only the run owner or an organization admin may decide.
cancel_workflow_run
ChatGPTCancel a queued, running, or paused workflow run. Only the run owner or an organization admin may cancel.
get_started
ChatGPTUse this when a user wants to start using aictrl, asks what they can do with their account, or attempts a repository action whose setup prerequisites are unknown. Returns current readiness and the single best next action. Do not use for general product questions or when repository readiness is already known in the current turn.
get_task_execution
ChatGPTGet the current status and privacy-minimal durable result of a task execution started through public MCP. A PR Explanation execution returns its durable explanation once stored. A Code Review execution reports status only — its findings are delivered as review comments on the pull request.
get_workflow
ChatGPTGet one published workflow definition, with secret trigger configuration removed.
get_workflow_run
ChatGPTGet status, progress, and node results for one workflow run.
list_organizations
ChatGPTList organizations available to the authenticated principal for use with organization-scoped tools.
list_pr_findings
ChatGPTRead all recorded findings for a PR (any lifecycle status) so verdicts can be recorded by exact id. Returns the recorded id and the platform-owned githubCommentId to join against GitHub review comments (exact for findings the platform delivered inline; null for older / un-anchored findings), plus the full claim (description, suggestion, snippets), lifecycle, and the latest verdict and verification. Set include_history for the append-only judgment chains. Judgments written by YOUR OWN run are never returned — a run must not be shown its own prior conclusion as evidence. Findings the obsolescence sweep has resolved are excluded unless include_obsolete is set. Read-only — records nothing.
list_tasks
ChatGPTList the first-party aictrl tasks that can run for one live-authorized repository. It reports only tasks aictrl provisions — Code Review and PR Explanation — and never templates authored inside the organization. An empty result means no first-party task is available for this repository right now; it is not a statement about any other aictrl capability. Listing never starts work.
list_workflow_runs
ChatGPTPage through org-scoped runs with issue, epic, status, starter and date filters. needs_attention returns failed or approval runs you started or on native issues you own. Items use the same safe projection as get_workflow_run plus native issue identity; unavailable issues are null. Read-only; never starts or changes a run.
list_workflows
ChatGPTList published workflows across organizations available to the authenticated principal. Each workflow includes its owning organization. Optionally filter by organization ID.
query_context
ChatGPTUniversal entry point for exploring project context. Query code, architecture, issues, backlog, agent skills, and stack layers. Use this tool whenever you need to DISCOVER or READ information about the project.
record_finding_verdict
ChatGPTApply a post-hoc triage verdict to a finding that was previously recorded via record_finding. Used by the /reply-to-code-review flow to persist whether a finding is TRUE / FALSE / UNCERTAIN and the FIX / DEFER / IGNORE action taken. The finding is located only by the exact finding_id returned by list_pr_findings, on ANY lifecycle status (open, fixed, or dismissed — so verdicts still apply after a PR is merged and findings were swept to dismissed). Only findings recorded into the data layer (the aictrl-dev MCP path) can receive a verdict. Idempotent: re-applying overwrites the prior verdict. A not_found response is an application error; call list_pr_findings to refresh stale IDs and do not treat the write as successful. judged_at_sha is required: send the full 40-hex commit SHA of the code you actually read. A SHA that is neither the review SHA nor a later commit of the same PR is rejected with validation_error. reasoning is required too (#5364): a verdict whose reasoning cannot be audited later is not worth storing. Each write appends to the finding's judgment history; a re-judge from the same run at the same commit updates that run's own row rather than appending a duplicate. A FALSE verdict on an OPEN finding of severity MINOR or NIT (medium/low/info) also dismisses it as a false positive, with your reason as the note; on MAJOR or BLOCKER (high/critical) it stays a suggestion a person confirms. The result reports autoDismissed (and autoDismissReason when false). A dismissal is not reopened by this tool; a person can restore the finding from the pull-request page.
start_task
ChatGPTStart one task returned by list_tasks for an exact pull-request revision. Call only after the user explicitly asks to run that task in the current turn. Retrying the same request with the same idempotency key returns the same execution.
start_workflow
ChatGPTStart a published workflow with validated workflow-level inputs. The selected workflow may perform its declared external side effects, such as creating a pull request, only within its configured gates and policy.
update_backlog
ChatGPTCreate or update tasks within an Epic. Used by the Planner Breakdown step to materialise a plan into stored tasks with stack-layer assignments and dependencies.
