mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-23 17:33:51 +02:00
DottaandPaperclip
92b238137b
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Apps and AI Connections store credentials and govern access to agent runtimes. > - Users need a supported saved-token connection and config values that survive save and reopen. > - The release must preserve saved-token access and task lifecycle guarantees. > - This pull request will connect Copilot through the normal Apps and AI Connections path. > - The benefit is a reviewable part of the Copilot production release. ## Linked Issues or Issue Description Refs #15701 and #15703. Supersedes setup work in #15562. Base: #15703. Next: #15706. ## What Changed - Require configuration update authority before Copilot credential-bearing model discovery; default to the saved environment and preserve explicit selection for editors. - Keep Copilot discovery passive during reconnect reconciliation; refresh on explicit opening, account/environment changes and reconnect. - Add GitHub AI token connections with encrypted storage, ownership, grants and audit logging. - Keep repository access separate from Copilot runtime authentication. - Probe the selected environment without sending a model prompt and preserve authenticated model selection through save/reopen. - Keep fresh execution admission consistent with normal Copilot setup; persist task model choices without changing provider or permission policy. - Refresh authenticated models after reconnecting the same saved Copilot account, including recovery from a previous authentication error. - Apply the additive provider-default constraint migration through the normal generated migration workflow. ## Verification Runtime #15701 is merged at `d855e550ad8d2a267312983f26457aabf5393c3a`. History #15703 is merged at `df80616d98119cbf5abd40549794d9980a5fabf6`. Remaining source [`42bcbd61299655f7e37aabe6bb5f19bba770ad1d`](https://github.com/paperclipai/paperclip/commit/42bcbd61299655f7e37aabe6bb5f19bba770ad1d) contains the four-file authorization repair. The remaining PR trees preserve six nonoverlapping files from the newer public mainline managed-settings fix and the CI-owned lockfile. No unrelated provider is enabled. The security finding is repaired: existing-agent discovery requires `agent_config:update` before connection selection or token resolution. The saved environment is the default. Authorized editors can select a prospective environment. Both denied board-viewer and agent-reader regressions fail on the original source. All49 route tests and server typecheck pass with the fix. Denied requests perform no connection selection, credential resolution or probe. Current-head security scans pass on both remaining PRs; the repaired thread is resolved. Copilot CLI1.0.88 and profile47 retain digest `sha256:55044aa235e88b3fe36ec8a556ee1e3382590870aab907e4462ef7d64af49cea`. The [qualification record](https://github.com/paperclipai/paperclip/blob/42bcbd61299655f7e37aabe6bb5f19bba770ad1d/doc/plans/2026-10-20-copilot-qualification-v47.json) reports20/20 Product cells,154 assertions and7/7 protocol cases,46 assertions against frozen normal installed source `c2616370800f5f6df45246b0890ba35a7cd2faab`. The exact qualification model is `gpt-5.6-luna`. Every passing Product case confirms cleanup. Original failures remain recorded; automatic behavior retries are disabled. The route-only authorization repair changes no bound runtime/profile bytes and does not relabel the frozen campaign. The ordinary installed remote journey passed saved-token selection, model discovery, normal UI save/reopen, metadata-only Test, completed task, accepted receipt and exact19-byte browser download. An open model catalog caused no additional discovery requests during117seconds. Actual installed runtime smokes passed on macOS ARM64, macOS x64 under Rosetta and native Linux x64 on Daytona. Raw token browser entry was not exercised; encrypted connection creation used the normal API. The first Daytona file attempt timed out during delayed semantic dispatch; its precise stalled layer remains unresolved. Independent ordinary remote delivery and the other19 Product cells passed before one instrumented recheck passed8/8 with unchanged source,prompt,assertions and deadlines. No causal latency repair is claimed. Before the authorization repair, all four final PR heads passed required verify/E2E and fresh Greptile5/5 reviews with zero unresolved threads. Current-head CI/review is running for the two repaired heads. Local focused checks retain129 connection,59 runner,72 shared-eval and88 recovery/workspace passes, plus migration safety and token gates. The additive Copilot migration is361; released master history is preserved. [Cloud normal-package run39414239704](https://github.com/paperclipai/paperclip/actions/runs/39414239704) builds the pre-security source4f3f. All four native producers and Linux package assembly pass; the final clean installed consumers are finishing. All18 retained archives match their hashes;37,863 regular files contain zero selected credentials. That package does not contain the later route repair. The actual final published package must include it and pass the local/Daytona live canaries. The frozen Daytona image remains published and independently verified. No separate full-image scan is claimed. Docker builds run in the cloud. **Remaining:** current-head CI/review, setup and qualification merges, final publication, and ordinary local/Daytona canaries against the actual shipped package. The user explicitly authorizes the maintainer review override; CI remains a merge gate. No production deployment is claimed. Provider USD remains unknown and GitHub-attributed. ## Risks Bad credentials, missing entitlement, runtime installation and unavailable models must remain distinct failures. A connection must not adopt ambient credentials. The constraint migration changes accepted provider values, with no credential-storage migration. Current-master NewAgent fixture extraction is retained. Copilot cases use that shared support and test both passive discovery and explicit reconnect under the same setup lifecycle. The onboarding retry regression shares the component suite’s saved-connection, authenticated-model, draft, agent-list, hire and render lifecycle fixtures. Keeping it beside the existing onboarding failures makes adoption versus duplicate hire observable under the same lifecycle; this is the concrete cohesion reason for the existing large test file. ## Model Used OpenAI Codex, based on GPT-6. The exact serving model ID and context window are not exposed in this task. Used for code changes, review and tool-assisted verification. ## 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 - [ ] All Paperclip CI gates are green - [ ] 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>
73 lines
4.6 KiB
Markdown
73 lines
4.6 KiB
Markdown
# GitHub Copilot runtime connection
|
|
|
|
GitHub Copilot uses a saved GitHub token and the packaged Copilot CLI **1.0.88**.
|
|
Runtime profile **v47** passed the local and Daytona qualification campaign.
|
|
The [qualification record](../plans/2026-10-20-copilot-qualification-v47.json)
|
|
identifies the tested build, retained failures, and remaining release gates.
|
|
|
|
On first setup, choose **GitHub Copilot** when creating your first agent. In an
|
|
existing organization, open **Connectors → GitHub → Connect Copilot**. Create a
|
|
fine-grained personal access token owned by your personal GitHub account and
|
|
add the **Copilot Requests** account permission. Organization-owned tokens and
|
|
classic personal tokens are unsupported for this setup. Follow
|
|
[GitHub's authentication instructions](https://docs.github.com/en/copilot/how-tos/copilot-cli/set-up-copilot-cli/authenticate-copilot-cli).
|
|
|
|
Save the token as a personal or shared AI connection and select the execution
|
|
environment. Paperclip uses its encrypted credential store, grants, access
|
|
checks, reconnect/revocation, and activity logging. GitHub repository/MCP access
|
|
uses its separate connection and grants. Copilot execution receives only the
|
|
selected runtime token as `COPILOT_GITHUB_TOKEN`; ambient GitHub credentials
|
|
are not adopted.
|
|
|
|
Connection verification runs the pinned packaged runtime in the selected
|
|
environment with a private temporary home. It initializes a session, discovers
|
|
models, and confirms an explicitly selected model when testing an agent. It
|
|
sends no model prompt. Authentication, entitlement/policy, installation, and
|
|
unavailable-model errors are reported separately. Remote verification releases
|
|
its owned login lease and does not fall back to the controller host.
|
|
|
|
In an agent's **Harness / Runtime** settings, select **Paperclip Runner**,
|
|
**ACP agents**, **GitHub Copilot**, and a model from authenticated discovery.
|
|
Saving and reopening retain `provider: acpx`, `acpxAgent: copilot`, and that exact
|
|
model. Auto/default and unavailable models are rejected. The qualification
|
|
model is `gpt-5.6-luna`, subject to current authenticated availability. Reconnecting
|
|
the same saved account refreshes its discovered models and clears the old selection.
|
|
|
|
Normal package installation materializes the pinned runtime for macOS ARM64,
|
|
macOS x64, and Linux x64. Keep installation scripts enabled. No qualification
|
|
environment override or ambient GitHub login is required. **Test configuration**
|
|
verifies the saved connection and exact model without sending a prompt.
|
|
|
|
For Daytona, install the first-party Daytona provider and configure an execution
|
|
environment with its saved API key and the matching release image. Environment
|
|
assignment currently uses Paperclip's existing **Enable Environments** instance
|
|
setting. Select that environment for connection verification and agent execution;
|
|
successful local verification alone does not establish remote readiness. The
|
|
admitted daemon and provider assets must belong to the same verified build.
|
|
|
|
Core workflows use Paperclip's semantic questions, plans, and completion tools.
|
|
Permission cards identify actual targets. Denied writes have no effects; Stop
|
|
cancels unanswered permissions and refuses late answers. Provider death must
|
|
expire stale input without replay. Detached work, native steering, native plan
|
|
mode, and additional native event presentation are outside this release.
|
|
Unsupported native blocking callbacks fail explicitly.
|
|
|
|
Usage is attributed to **GitHub**. Provider credits and model multipliers are
|
|
supplemental notices, not USD billing receipts. USD cost remains unknown when
|
|
GitHub supplies no invoice value; included credits are not recorded as measured
|
|
zero-dollar usage. Session-scoped notices cannot establish task completion,
|
|
artifacts, or charges.
|
|
|
|
Model discovery uses the selected environment and can create a short-lived Daytona sandbox. Copilot model choices refresh when opening a task selector, changing an account or environment, reconnecting, or explicitly refreshing. Background live-data reconciliation does not repeat this probe.
|
|
|
|
The qualification record retains one Daytona tool-dispatch timeout whose exact
|
|
cause is unresolved. Its unchanged instrumented recheck passed after independent
|
|
ordinary remote delivery and the other19 Product cases passed. No timeout or
|
|
completion check was weakened. Qualification does not establish deployment: use
|
|
the release record to verify the shipped package and canary.
|
|
|
|
Discovering models for an existing agent requires permission to update that
|
|
agent configuration. The probe uses the saved environment unless an authorized
|
|
editor selects another environment. Read-only configuration access does not
|
|
resolve the token or start a discovery probe.
|