mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-29 21:07:40 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agent Chat lets a person assign work through a conversation. > - Feature and API maps do not prove that a natural request produces the right saved result. > - Product E2E already owns isolated fixtures, browser runs, evidence and cleanup. > - This pull request adds a chat scenario catalog and two real task workflows in that framework. > - Independent checks verify the task, its author, the saved output and the reply in chat. > - The benefit is a small executable foundation for broader chat coverage. ## Linked Issues or Issue Description **What existing behavior does this improve?** It adds real task creation and delegation coverage for Agent Chat. **Current behavior** Existing maps describe features and agent access. Existing chat evals cover specific protocols and handoffs. They do not connect a broad human-request catalog to independent saved-state checks. **Proposed behavior** Keep 244 planned scenarios across 35 feature areas. Promote two requests into the explicit-only `chat-features` suite. One saves a backlog task without starting work. The other delegates an announcement and returns the saved result to the original chat. **Reason and benefit** A successful tool call or confident reply does not prove the requested result exists. These evals check public API state, attribution and browser access after a real model run. **Breaking changes** No API or data schema changes. Chat instructions now require actual relative task links. The local E2E private-state scanner recognizes Codex account ownership metadata while continuing to reject credentials and model-visible identity leaks. **Additional context** Related prior work: #13969 and #13762. This improves verification of the existing Agent Chat roadmap item. It does not add a new core product feature. ## What Changed - Add YAML scenarios with capability IDs, starting context, user requests and expected outcomes. Validate all area files against their schema, global ID uniqueness and exact feature-map capability coverage. - Add two local native Codex subscription cells. Send the exact catalog request once through Chromium. - Seed only prerequisites through public APIs. Use shipped agent instructions and explicit disposable budget policies for unpriced subscription usage. - Check task ownership, creation audit, no premature execution, current worker-authored output, automatic completion delivery and usable links after reload. - Keep private Codex account ownership metadata distinct from bearer credentials. Scan rollout message content, all tokens and published evidence as before. - Teach normal chat instructions to use relative task links instead of invented hosts. Update tests, maps and the runbook. - Repair existing E2E contract drift: include the active Copilot identity in the image digest and update Pi profile expectations. Keep global catalog cardinality in its owning catalog test. Product E2E owns the new flow and grader. Its existing launch and report paths remain in use. The shared scanner change is limited to owner-private temporary Codex runtime metadata. Other callers retain the full secret scan. No UI, endpoint, schema or permission behavior changes. ## Verification - `node scripts/check-maps.mjs` passed: 35 areas and 191 capability IDs. - Product E2E typecheck and focused tests passed before rebase: 225 Vitest tests and 137 Node tests. Conversation service tests passed 40/40. Five existing runner turn-binding regressions passed. - Historical live measurement used real Chromium, server, database and native Codex with no automatic retries. The initial same-definition batch passed 5/6 cells. Backlog passed 3/3; delegation passed 2/3. One CEO startup failed because the runner did not receive a provider turn identity. The cause is unresolved. - An unchanged follow-up passed delegation three times and backlog twice. Combined evidence is backlog 5/5 and delegation 5/6. Each attempt passed cleanup. Later passes do not erase the earlier failure or prove a runner repair. - Earlier failed revisions exposed an invented task hostname, private account metadata false positives and missing funding for unpriced subscription usage. Those led to the specific changes above; the failed records remain retained locally. - The runbook records campaign identifiers and definition provenance. Generated result artifacts are not committed. Historical live results predate this branch rebase; fresh PR-source live evidence and final validation are recorded below. - Full workspace typecheck and production build passed on the rebased branch. Product E2E typecheck passed. - The full Product E2E support suite first reproduced four baseline failures: two missing active Copilot image-identity inputs and two stale Pi/catalog expectations. The narrow contract fixes above resolved them. The full rerun passed 4,282 Vitest tests plus 137 Node tests, with two skipped. Image checks verify mutation changes the hash, unchanged input stays stable, and an input closure without Copilot is unaffected. Original failed logs remain retained. - The repo-wide local Vitest run has reported two failures in unchanged service files. The Workspace connection test passed an isolated recheck and its full file passed 469/469 unchanged. The recovery test hit a 15-second timeout; its full file passed 89/89 unchanged. The run later hit explicit PostgreSQL `semget` resource exhaustion and was interrupted after those observed failures; no final aggregate counts or full local pass are claimed. Its complete available log is retained. No assertion or timeout was weakened. Matching remote server CI passed on the same source. - On clean PR head `39ad80b523ce194c90aafafd077d48dd9a36b4c5`, backlog passed in `local-2026-10-26T19-24-13-014Z`. The parallel delegation fixture failed during PostgreSQL initdb, before browser or model execution; its failed cleanup grade is retained. A disposable standalone initdb probe then passed. No semaphore sets or kernel settings were changed before that probe/recheck. After confirming no remaining fixture process, its private temporary files were removed. - One separate delegation recheck passed in `local-2026-10-26T19-29-24-800Z`, with one attempt, zero automatic retries and successful cleanup. Both passing current-source cells use definition `3f2c9ba2d03e3dcddde47ddab3b43bc52de977f25e256fceae0a24c9128e204b`. The earlier bootstrap failure and the historical provider startup failure remain distinct. These local results omit automatic source-SHA metadata; the clean checkout SHA is recorded here from the execution session. - The later broad local run reported `could not create semaphores: No space left on device`. A bounded cleanup removed 32 current-user PostgreSQL sets with 17 members, marker 537, a dead recorded creator and zero waiters. No live process or kernel limit was changed by that cleanup. The test process group was subsequently stopped; no broad rerun is planned. This direct later resource failure does not prove the precise cause of the earlier live initdb failure. - Review follow-up adds only static catalog validation and documentation of the existing five-minute journey bound. The executable definition is unchanged. Focused catalog/oracle tests passed 28/28; no redundant live run is claimed. - Final head `30fcb36ac9ae1f0270a589dbfafcec91ca6a03f3` passed all required and underlying CI checks in [run 40391402347](https://github.com/paperclipai/paperclip/actions/runs/40391402347), including `ci / verify` and `ci / e2e`. Greptile and Paperclip Review both scored this head 5/5, with all review threads resolved. The static follow-up leaves every executable definition input byte-identical to the live-tested source at `39ad80b`. Normal squash auto-merge is enabled. Actual merge is pending eligible code-owner approval for the owned dependency manifest; no protection is bypassed. ## Risks - Live model behavior can vary. One missing turn-start event remains unexplained; this PR does not claim provider reliability or broad catalog qualification. - Subscription costs are unpriced. Explicit fixture funding admits that usage. Run counts and deadlines remain bounded, but the dollar limit cannot cap unknown cost. - Account identity exceptions apply only to known private Codex runtime files. Token reuse, unknown files and model-visible rollout content remain blocking findings. - Deterministic checks establish saved state, output structure, required brief facts and access. They do not score all prose quality. Initial samples also require human inspection. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, code execution, browser and repository tools. The precise model revision and context window are not exposed to this session. Live eval agents used `gpt-5.6-sol`; that is the evaluated model, not a claim about the authoring model. ## 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 searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run local tests; focused suites pass and the interrupted full-run failures are documented above - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
112 lines
5.1 KiB
YAML
112 lines
5.1 KiB
YAML
# yaml-language-server: $schema=./catalog.schema.json
|
|
# Planning scenarios; not registered executions or evidence of a pass.
|
|
schema_version: 1
|
|
feature: projects
|
|
status: planned
|
|
scenarios:
|
|
- id: projects.create-project
|
|
capabilities:
|
|
- projects/lifecycle
|
|
context: >-
|
|
No Launch project exists; the CEO can create projects in the active company.
|
|
query: >-
|
|
Create a project called Launch for the new website.
|
|
expected_outcome: >-
|
|
One company-scoped project is saved with the requested identity and a usable link. The
|
|
agent checks for an existing intended project before duplicating it on retry. Creation
|
|
alone is not described as a ready repository, running task or deployed website.
|
|
- id: projects.archive-project
|
|
capabilities:
|
|
- projects/lifecycle
|
|
context: >-
|
|
Launch is complete and the actor may change its project lifecycle through the supported
|
|
API.
|
|
query: >-
|
|
Archive the Launch project but keep its history.
|
|
expected_outcome: >-
|
|
The project receives the supported archived state and remains reachable through its
|
|
historical context. Existing tasks, files and audit attribution remain intact. The
|
|
response reports the actual saved state and does not delete resources or confuse hiding a
|
|
project with cancelling unfinished execution.
|
|
- id: projects.project-work
|
|
capabilities:
|
|
- projects/task-context
|
|
- tasks/create
|
|
context: >-
|
|
Launch exists alongside another project with similarly named tasks.
|
|
query: >-
|
|
What is left in Launch, and create a task for Morgan to fix the mobile layout there.
|
|
expected_outcome: >-
|
|
The agent summarizes Launch's visible unfinished tasks and creates the requested
|
|
mobile-layout task in that exact project. It checks for an already matching request to
|
|
avoid accidental duplication and links both the relevant work and new task. Other projects
|
|
remain unchanged.
|
|
- id: projects.add-repository
|
|
capabilities:
|
|
- projects/repositories
|
|
- workspaces/provisioning
|
|
context: >-
|
|
A new project is requested with an authorized synthetic Git repository; initial repository
|
|
selection is supported.
|
|
query: >-
|
|
Create Launch using the acorn/site repository.
|
|
expected_outcome: >-
|
|
The project records the intended repository through the supported creation path and any
|
|
checkout preparation reports its real state. The agent distinguishes repository metadata
|
|
from a usable checkout, uses the current authorized connection and does not insert
|
|
operator filesystem paths or credentials into project settings.
|
|
- id: projects.replace-repository
|
|
capabilities:
|
|
- projects/repositories
|
|
context: >-
|
|
Launch already has a repository; replacing its repository selection requires board
|
|
authority.
|
|
query: >-
|
|
Switch Launch from acorn/site-old to acorn/site-new.
|
|
expected_outcome: >-
|
|
The agent identifies the existing and requested repositories and directs the authorized
|
|
human to the replacement control. It explains the effect on future work without claiming
|
|
existing active workspaces have already moved. No ordinary agent mutation bypasses the
|
|
board-only replacement path.
|
|
- id: projects.project-defaults
|
|
capabilities:
|
|
- projects/defaults
|
|
- goals/alignment
|
|
context: >-
|
|
The CEO may edit project instructions and goal associations; budget and environment fields
|
|
retain their separate permission rules.
|
|
query: >-
|
|
Make new Launch work follow our accessibility checklist and tie it to the growth goal.
|
|
expected_outcome: >-
|
|
The permitted project defaults and goal association persist, and new task context reflects
|
|
them. Chat distinguishes defaults for future work from changes to active tasks. If another
|
|
requested setting has a separate human gate, that field remains unchanged and the required
|
|
step is stated.
|
|
- id: projects.private-project
|
|
capabilities:
|
|
- projects/privacy
|
|
- tasks/privacy
|
|
context: >-
|
|
The person has a responsible-user identity; the CEO may create a private project but
|
|
cannot broaden an existing project's audience.
|
|
query: >-
|
|
Create a private project for the acquisition research.
|
|
expected_outcome: >-
|
|
The new project is private with ownership derived from the authorized person and correct
|
|
access for the acting agent. Its tasks inherit the appropriate restrictions. Company-wide
|
|
search and unrelated agents cannot discover its protected contents, and chat returns only
|
|
authorized links.
|
|
- id: projects.share-project
|
|
capabilities:
|
|
- projects/privacy
|
|
context: >-
|
|
Acquisition research is private; audience changes require its authorized human owner or
|
|
administrator.
|
|
query: >-
|
|
Let Riley see the acquisition project.
|
|
expected_outcome: >-
|
|
The agent identifies Riley and the supported project sharing step for the human owner. It
|
|
does not change the project to public to approximate a one-person grant. After the real
|
|
action, project access changes as intended while separately protected tasks retain their
|
|
own privacy rules.
|