mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-14 01:50:39 +09:00
Harden control-plane safety and issue identifiers (#5292)
## Thinking Path > - Paperclip relies on issue identifiers, execution policies, and agent heartbeat rules to keep autonomous work auditable. > - Safety checks need to reject ambiguous agent handoffs, and identifier parsing needs to support Cloud tenant prefixes. > - Agent instructions also need to make final-disposition rules explicit so work does not stall in vague states. > - This pull request isolates backend correctness and governance hardening from the UI and recovery-system-notice branches. > - The benefit is safer in-review transitions, better identifier compatibility, and clearer agent operating contracts. ## What Changed - Fixed run-aware confirmation ordering and interrupted-run state cleanup. - Added Cloud tenant identity bootstrap and alphanumeric issue identifier support across shared parsing and server routes. - Guarded agent-authored `in_review` updates unless a real review path exists. - Tightened heartbeat disposition instructions in adapter utilities/default AGENTS/Paperclip skill. ## Verification - `pnpm install --frozen-lockfile` - `pnpm exec vitest run packages/shared/src/issue-references.test.ts server/src/__tests__/issue-identifier-routes.test.ts server/src/__tests__/issue-execution-policy-routes.test.ts packages/adapter-utils/src/server-utils.test.ts` initially had the first execution-policy test hit Vitest's 5s timeout under the parallel bundle while the rest passed. - `pnpm exec vitest run server/src/__tests__/issue-execution-policy-routes.test.ts --testTimeout=20000` passed with 10/10 tests. - Follow-up: `pnpm run typecheck:build-gaps` passed. - Follow-up: `pnpm --filter @paperclipai/ui typecheck` passed. - Follow-up: `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/company-portability.test.ts server/src/__tests__/costs-service.test.ts` passed. - Follow-up: `pnpm vitest run ui/src/context/LiveUpdatesProvider.test.ts ui/src/lib/issue-chat-messages.test.ts ui/src/lib/issue-reference.test.ts ui/src/lib/issue-timeline-events.test.ts` passed. ## Risks - Medium control-plane risk: in-review update validation changes agent behavior. The error message is explicit and tests cover allowed review paths. ## Model Used - OpenAI GPT-5 Codex via Paperclip `codex_local` adapter, with shell/git/GitHub CLI tool use. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
This commit is contained in:
parent
a1b30c9f35
commit
68f69975a4
17 changed files with 875 additions and 90 deletions
|
|
@ -418,6 +418,9 @@ describe("renderPaperclipWakePrompt", () => {
|
|||
it("keeps the default local-agent prompt action-oriented", () => {
|
||||
expect(DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE).toContain("Start actionable work in this heartbeat");
|
||||
expect(DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE).toContain("do not stop at a plan");
|
||||
expect(DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE).toContain("clear final disposition");
|
||||
expect(DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE).toContain("evidence, not valid liveness paths by themselves");
|
||||
expect(DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE).toContain("keep `in_progress` only when a live continuation path exists");
|
||||
expect(DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE).toContain("Prefer the smallest verification that proves the change");
|
||||
expect(DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE).toContain("Use child issues");
|
||||
expect(DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE).toContain("instead of polling agents, sessions, or processes");
|
||||
|
|
@ -451,8 +454,10 @@ describe("renderPaperclipWakePrompt", () => {
|
|||
|
||||
expect(prompt).toContain("## Paperclip Wake Payload");
|
||||
expect(prompt).toContain("Execution contract: take concrete action in this heartbeat");
|
||||
expect(prompt).toContain("use child issues instead of polling");
|
||||
expect(prompt).toContain("mark blocked work with the unblock owner/action");
|
||||
expect(prompt).toContain("clear final disposition");
|
||||
expect(prompt).toContain("evidence, not valid liveness paths by themselves");
|
||||
expect(prompt).toContain("Use child issues for long or parallel delegated work instead of polling");
|
||||
expect(prompt).toContain("named unblock owner/action");
|
||||
});
|
||||
|
||||
it("renders planning-mode directives for assignment and comment wakes", () => {
|
||||
|
|
|
|||
|
|
@ -93,7 +93,9 @@ export const DEFAULT_PAPERCLIP_AGENT_PROMPT_TEMPLATE = [
|
|||
"",
|
||||
"Execution contract:",
|
||||
"- Start actionable work in this heartbeat; do not stop at a plan unless the issue asks for planning.",
|
||||
"- Leave durable progress in comments, documents, or work products with a clear next action.",
|
||||
"- Leave durable progress in comments, documents, or work products, then update the issue to a clear final disposition before ending the heartbeat.",
|
||||
"- Comments, documents, screenshots, work products, and `Remaining` bullets are evidence, not valid liveness paths by themselves.",
|
||||
"- Final disposition checklist: mark `done` when complete; use `in_review` only with a real reviewer, approval, interaction, or monitor path; use `blocked` only with first-class blockers or a named unblock owner/action; create delegated follow-up issues with blockers when another agent owns the next step; keep `in_progress` only when a live continuation path exists.",
|
||||
"- Prefer the smallest verification that proves the change; do not default to full workspace typecheck/build/test on every heartbeat unless the task scope warrants it.",
|
||||
"- Use child issues for parallel or long delegated work instead of polling agents, sessions, or processes.",
|
||||
"- If woken by a human comment on a dependency-blocked issue, respond or triage the comment without treating the blocked deliverable work as unblocked.",
|
||||
|
|
@ -631,7 +633,7 @@ export function renderPaperclipWakePrompt(
|
|||
"Focus on the new wake delta below and continue the current task without restating the full heartbeat boilerplate.",
|
||||
"Fetch the API thread only when `fallbackFetchNeeded` is true or you need broader history than this batch.",
|
||||
"",
|
||||
"Execution contract: take concrete action in this heartbeat when the issue is actionable; do not stop at a plan unless planning was requested. Leave durable progress with a clear next action, use child issues instead of polling for long or parallel work, and mark blocked work with the unblock owner/action.",
|
||||
"Execution contract: take concrete action in this heartbeat when the issue is actionable; do not stop at a plan unless planning was requested. Leave durable progress and then give the issue a clear final disposition before ending the heartbeat: `done`, `in_review` with a real reviewer/approval/interaction path, `blocked` with first-class blockers or a named unblock owner/action, delegated follow-up issues with blockers, or `in_progress` only when a live continuation path exists. Use child issues for long or parallel delegated work instead of polling. Comments, documents, screenshots, work products, and `Remaining` bullets are evidence, not valid liveness paths by themselves.",
|
||||
"",
|
||||
`- reason: ${normalized.reason ?? "unknown"}`,
|
||||
`- issue: ${normalized.issue?.identifier ?? normalized.issue?.id ?? "unknown"}${normalized.issue?.title ? ` ${normalized.issue.title}` : ""}`,
|
||||
|
|
@ -648,7 +650,7 @@ export function renderPaperclipWakePrompt(
|
|||
"Use this inline wake data first before refetching the issue thread.",
|
||||
"Only fetch the API thread when `fallbackFetchNeeded` is true or you need broader history than this batch.",
|
||||
"",
|
||||
"Execution contract: take concrete action in this heartbeat when the issue is actionable; do not stop at a plan unless planning was requested. Leave durable progress with a clear next action, use child issues instead of polling for long or parallel work, and mark blocked work with the unblock owner/action.",
|
||||
"Execution contract: take concrete action in this heartbeat when the issue is actionable; do not stop at a plan unless planning was requested. Leave durable progress and then give the issue a clear final disposition before ending the heartbeat: `done`, `in_review` with a real reviewer/approval/interaction path, `blocked` with first-class blockers or a named unblock owner/action, delegated follow-up issues with blockers, or `in_progress` only when a live continuation path exists. Use child issues for long or parallel delegated work instead of polling. Comments, documents, screenshots, work products, and `Remaining` bullets are evidence, not valid liveness paths by themselves.",
|
||||
"",
|
||||
`- reason: ${normalized.reason ?? "unknown"}`,
|
||||
`- issue: ${normalized.issue?.identifier ?? normalized.issue?.id ?? "unknown"}${normalized.issue?.title ? ` ${normalized.issue.title}` : ""}`,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue