dave/storkit
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 7 Wiki Activity

story-kit: start 70_story_server_owned_agent_completion_remove_report_completion_dependency

Browse Source
This commit is contained in:
Dave
2026-02-23 14:39:11 +00:00
parent d6fd446ca5
commit 5142584691
1 changed files with 13 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
.story_kit/work/2_current/70_story_server_owned_agent_completion_remove_report_completion_dependency.md
View File

@@ -1,18 +1,27 @@
--- ---
name: "Server-owned agent completion: remove report_completion dependency" name: "Server-owned agent completion: remove report_completion dependency"
test_plan: pending test_plan: approved
--- ---
# Story 70: Server-owned agent completion: remove report_completion dependency # Story 70: Server-owned agent completion: remove report_completion dependency
## User Story ## User Story
As a ..., I want ..., so that ... As a developer using story-kit, I want the server to automatically run acceptance
gates and advance the pipeline when an agent process exits, so that the pipeline
does not stall when an agent forgets or fails to call `report_completion`.
## Acceptance Criteria ## Acceptance Criteria
- [ ] TODO - [ ] When an agent process exits normally, the server automatically runs acceptance gates (uncommitted changes check + cargo clippy + tests)
- [ ] When acceptance gates pass on natural process exit, the agent status is set to `Completed` and the pipeline advances
- [ ] When acceptance gates fail on natural process exit, the agent status is set to `Failed` and the pipeline handles the failure appropriately
- [ ] `report_completion` is removed from the MCP tools list (agents no longer see or call it)
- [ ] The default agent prompt no longer instructs agents to call `report_completion`
- [ ] If a completion was already recorded before the process exits (legacy path), the server does not run gates a second time
## Out of Scope ## Out of Scope
- TBD - Removing the concept of a `CompletionReport` struct (still used internally)
- Changing the pipeline advancement logic itself
- Frontend changes