mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-28 12:04:41 +01:00
DottaandPaperclip
7a8df30953
## Thinking Path
> - Paperclip lets people manage AI agents for work.
> - Paperclip Runner must preserve each agent's model and thinking
effort.
> - The Grok migration in #17922 passes explicit effort to native
Runner.
> - The pinned Grok 1.0.13 CLI reports native session metadata instead
of standard ACP config options.
> - The standard effort guard rejects that valid session before the
first prompt.
> - This pull request binds model and effort on Grok session open and
verifies the native reply.
> - Restored sessions keep the selected effort instead of reverting to
Grok's default.
## Linked Issues or Issue Description
Related: https://github.com/paperclipai/paperclip/pull/17922
**What happened?**
A migrated Grok 4.7 agent with High effort fails at native session.open
before it can run a tool. Grok 1.0.13 has no standard configOptions
response and rejects session/set_config_option. Its native session
metadata supports the requested model and effort. A cold load also
resets effort to High unless the request supplies it again. The upgrade
banner also calls Grok “Codex”.
**Expected behavior**
The native session must acknowledge the selected model and effort before
a prompt. A cold restore must preserve both values. The upgrade banner
must describe the selected harness accurately.
**Steps to reproduce**
1. Upgrade a Grok agent to Paperclip Runner with explicit High effort.
2. Assign a bounded shell task. The pre-fix native session fails during
admission.
3. For the restore case, create a Low native session, close the process,
and load it without effort metadata. The pinned CLI reports High.
**Paperclip version or commit**
Observed at f60ac29cf1 with Grok 1.0.13.
**Deployment mode**
Cloud, with the board operator interface.
## What Changed
- Project the bound model and effort into native Grok session/new,
session/load, and session/resume metadata before transport writes and
observation.
- Require a correlated native acknowledgement with the exact model,
effort, and session identity. Reject conflicting metadata, selection
drift, stale connections, and prompts before admission.
- Connect lazy restored handles through read-only native session
inspection. Keep the existing process ownership and launch snapshot
checks.
- Replace Grok's unsupported standard config setter. Keep the existing
Claude effort path.
- Add behavioral guard cases and a real ACPX client fixture for fresh
and cold Low/High sessions. The fixture resets effort on restore if
metadata is absent, as the pinned CLI does.
- Publish Copilot profile v69 because its source identity includes the
shared runtime adapter. Preserve published v66/v67/v68 bytes and the
reviewed Grok v67 candidate as history. Keep old profiles closed for
launch.
- Explain the native protocol in the Grok Runner guide and use
provider-independent upgrade banner text.
## Verification
- Three native create/load/resume cases failed before the repair. The
pre-fix guard rejected the native metadata reply.
- Seven affected Runner test files: 234 tests passed after the master
merge. These include native Grok admission, the real ACPX transport
fixture, runtime ownership, Claude effort, and profile history.
- The review follow-up extends the same Low/High fixture through a
complete first turn after cold restore. It checks the repeated native
load, original session id, actual response event, and completed turn.
All 127 tests in the three affected Grok/adapter files passed again;
Runner typecheck and source identity checks also passed.
- All 167 existing agent form tests passed. Token gates and diff checks
passed.
- Workspace typecheck passed. Final Runner typecheck and generated
profile checks passed.
- Production `pnpm build` passed, including after the master conflict
resolution. Runner typecheck, profile history checks, and the 234
affected tests passed on the merged source. All 55 Rust ACPX library
tests also passed on the merged source.
- Real pinned Grok 1.0.13 metadata probes reproduced the unsupported
standard setter and native create/load/resume behavior. No model prompt
was sent. An earlier actual ACPX runtime probe passed fresh and cold
Low/High metadata checks. A repeat with an explicitly isolated HOME
failed authentication before session creation, so it does not count as
final live acceptance. The deterministic transport fixture is green; a
deployed shell task remains required.
- `pnpm test:run` did not complete locally. Embedded Postgres failed
during bootstrap after five attempts. This is the same local fixture
limitation recorded for #17922. Fresh PR CI must pass before merge.
- After deployment, retry the original bounded shell task with the saved
Grok 4.7/High configuration. Verify actual tool output, a successful
run, and Done state after reload.
- Final commit `810d84fd19728e7d798989582f26b05f69166db2`: all CI gates
passed. Greptile and the formal Paperclip review both reached 5/5. No
unresolved review threads remain.
## Risks
- This depends on the pinned Grok 1.0.13 native metadata format. Missing
or conflicting replies stop admission instead of silently changing
effort.
- Cold restores must make one read-only native inspection call before
admission. The existing handshake timeout and process ownership checks
still apply.
- The shared adapter changes Copilot's source identity. The new current
profile includes the final source hashes; the prior profile remains
decodable but cannot launch.
- This does not change the Grok CLI version, account selection, search
policy, dependency patch, or lockfile.
## Model Used
OpenAI Codex, GPT-6. The exact serving model ID and context window are
not exposed in this session. The agent used reasoning, code editing,
shell tools, and browser tools.
## 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 tests locally and they pass
- [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>
@paperclipai/ui
Published static assets for the Paperclip board UI.
What gets published
The npm package contains the production build under dist/. It does not ship the UI source tree or workspace-only dependencies.
Storybook
Storybook config, stories, and fixtures live under ui/storybook/.
pnpm --filter @paperclipai/ui storybook
pnpm --filter @paperclipai/ui build-storybook
Typical use
Install the package, then serve or copy the built files from node_modules/@paperclipai/ui/dist.
Editor dependency identity
Keep the root and workspace overrides for @codemirror/state,
@codemirror/view, and @lezer/common aligned. CodeMirror requires shared
extension identity, while Lezer parsers and syntax highlighters require shared
NodeProp IDs. Multiple Lezer copies can crash code-block highlighting with
tags is not iterable. src/lib/codemirror-single-instance.test.ts checks the
installed dependency graph and highlights sample code through the editor's real
language dependencies. GitHub Actions owns regeneration of pnpm-lock.yaml.