mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-24 18:19:05 +02:00
codex/runner-permission-context-integration
4
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 DottaandPaperclip
|
992f720262 |
fix: make runner task context ownership explicit (#13753)
<!-- Write all pull request text in Simplified Technical English (ASD-STE100). --> ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Task descriptions, comments, continuation data, skills, and execution rules enter several agent adapters. > - The same source can be rendered by more than one automatic input carrier. > - Failed resumes can also rebuild input from stale or compact context. > - This pull request gives each Paperclip-owned source one delivery owner and preserves the required transport boundaries. > - It adds deterministic adapter, interaction, runner, and browser tests for these boundaries. > - The benefit is more predictable context delivery with explicit evidence for later live qualification. ## Linked Issues or Issue Description Related: #13144 removes a duplicate environment payload and bounds wake lists. Related: #11360 addresses Hermes resume behavior. This pull request preserves compatible active-session formats while repairing context ownership and stale question creation. **What happened?** Task descriptions and comments could enter more than one automatic context block. Native transports could wrap a complete model input in a second task envelope. Some legacy and gateway adapters could omit the owned assignment on ordinary tasks or rebuild a failed resume with stale compact context. A continuation could also request a question after newer human comments had arrived. **Expected behavior** Each task or comment source has one automatic model-facing owner. Distinct comment IDs and repeated wording remain distinct. Fresh fallback attempts rebuild the required full context. A question request is rejected when newer queued human direction makes it stale. Harness access policy remains owned by execution configuration. **Steps to reproduce** 1. Build a task with a description and current comments. 2. Capture the actual adapter or runner input. 3. Compare source ownership and task-envelope nesting. 4. Queue a human comment before a continuation requests a question. 5. Trigger a failed resume and inspect the fresh retry input. 6. Run the focused adapter, interaction, runner, and browser checks. ## What Changed - Add shared prompt-section selection at the provider-attempt boundary. - Deliver owned assignment context through native, legacy CLI, ACP, gateway, cloud, Pi, Kimi, Grok, Gemini, OpenCode, Cursor, OpenClaw, and Hermes paths. - Rebuild full or compact context after resume recovery changes the attempt. Add native and Claude ACP tests of actual recovery requests. - Preserve custom templates, loaded instruction files, execution policies, and older active-session formats. - Record continuation source metadata and reject stale question creation under the issue-row lock. - Add explicit Product E2E context-integrity profiles, prerequisite gates, credential-isolation checks, and report fixtures. - Bypass service-worker forwarding for same-origin Vite development modules. A real Chromium test fails with resource exhaustion before the repair and passes after it. Production asset caching keeps its existing policy. - Add browser diagnostics and service-worker module-loading regressions. - Add an explicit zero-retry eval option. The default retry behavior remains unchanged. Each campaign records its effective policy. - Remove the model-facing working-directory sentence from four prompt builders. Existing workspace, sandbox, permission, and custom-template configuration remains unchanged. - Align the everyday workflow assertion with the current 47-entry catalog. Compared with current upstream master, the branch carries the context-ownership implementation and its tests, the explicit context-integrity catalog and evidence harness, and the focused browser regression checks. ## Verification **Merge assessment:** focused regression evidence supports merge. This is not full completion of the original broad qualification matrix. The maintainer has authorized merge after fresh verification of the master integration. - Current head: `bbd52f82114eabf09bc7b1a7e97d54a5b43bbc00`. This integrates current master `2f585ef26a1814fa209715242d1ca791b63e4c4e`. All 14 conflicts are resolved. Cancellation checks, workspace finalization, native Grok support, and both sets of tests are retained. - Current-head Greptile: **5/5**, with no blocking findings. The review names this exact commit. All **59 reported checks are terminal: 55 successful, 4 skipped, zero pending or failing**. This includes the full root general and serialized suites, separate runner checks, typecheck, build, canary, browser E2E, Docker, and security checks. The successful legacy security status is included in that total. - After integration: workspace typecheck and full build passed. Separate runner checks passed: **2,160 TypeScript tests (10 skipped), 582 Rust tests, and 39 preparation checks**. Other passing checks include 621 Product E2E harness units, 376 focused shared/adapter tests, 160 real-database/API tests, 86 Hermes tests, 18 browser-support checks, and Product E2E typechecking. The complete root suite passed in CI. The duplicate local monolithic root run was stopped after that CI result; it is not counted as a completed local pass. - New native recovery coverage retains full assignment, completion contract, and explicit skill selection after safe replacement, for old and prepared input formats. Full native session test file: **136/136 passed**. - New Claude ACP coverage captures actual fresh, resumed, and missing-session fallback requests. It verifies one assignment copy, comment order, identical text under distinct comment IDs, and full fallback context. Full file: **33/33 passed**. Both affected TypeScript checks passed. - Existing deterministic tests cover source revisions, approval and trust boundaries, completion validation, custom templates, compatible sessions, standalone driver wrapping, and maintained adapter transport requests. - Provider-free browser support: **17/17 passed** after the master merge. Service-worker unit tests: **33/33 passed**. The module-overload regression failed before the repair and passed after it in real Chromium. ### Fresh live comparisons The new batch ran exactly four Product E2E attempts. **All four passed on the first attempt; no retries.** Each has six terminal matchers plus the existing browser lifecycle and invariant checks. | Exact case ID | Control | Candidate | |---|---|---| | `core-compatibility.runner-codex.local.plan-revise-accept` | Passed | Passed | | `local-session-integrity.runner-acpx-claude.local.structured-question-restart-resume` | Passed | Passed | The plan case checks a revised canonical plan and revision-bound approval before completion. The question case restarts the server before submitting the answer, then verifies the continuation completes. Control source is `dfa4e1bda8d50a1a01746603251a9128dbe9d0d6`. Candidate source is `79fcdb5dece501d28064ea9da306603881b46f0c`. They use identical frozen definitions and provider versions: Codex `0.156.0` with `gpt-5.6-sol`; ACPX `0.13.1` / Claude ACP `0.73.0` with `claude-sonnet-5`. The September 24 head added master browser recovery and test-only changes. The September 28 head also integrates newer master changes, including cancellation, workspace finalization, and native Grok. These are frozen-source live results, not exact-head live runs. The candidate received one description copy where the control initially received three. The submitted initial plan envelopes were 7,969 versus 19,097 characters. Question envelopes were 7,592 versus 18,919. These are structural measurements, not whole-provider token or dollar savings. ### Earlier evidence and failed attempts - The preceding fresh batch has four effective passing pairs: OpenCode comment continuation and assigned skill, native Codex comment continuation, and native Claude comment continuation. It retains **11 attempts: eight passed and three failed**. - Original failures remain recorded: missing local PostgreSQL library links before task creation; host-sleep cleanup after task/page checks passed; and a Claude **control** session-open rejection before a model turn. Setup was repaired identically on both worktrees. The permitted unchanged infrastructure retries passed. The underlying Claude provider startup error was not retained and remains unknown. - Older R2 retains **17 passes and one failure** across 18 attempts, including eight both-pass native/legacy Codex/Claude pairs. Its OpenCode blank-page failure led to the service-worker repair. R2 is historical evidence: master changed the native fixed prompt and removed duplicate wake environment data afterward. - The September 24 CI run initially failed one unrelated preview readiness test (`ECONNREFUSED` on its local fixture). Its test and production code match master. Isolated local verification passed **28 tests, 3 skipped**. One unchanged CI retry passed the full shard: **831 passed, 1 skipped**, including all **31 preview-exposure tests**. The aggregate CI gate passed afterward. The precise startup cause remains unknown; a port race is a hypothesis, not a proved cause. ### Limits The original wider profile/workflow matrix, repeated trials, and remote Daytona qualification are incomplete. These results support a focused merge recommendation, not statistical equivalence or universal harness qualification. Some usage receipts are missing in both variants, so no token or dollar savings are claimed. The $500 ceiling was preserved using conservative allowances; failed attempts and unknown charges remain in the ledger. Reproduce the focused additions with `pnpm exec vitest run packages/adapters/claude-local/src/server/acp.test.ts` and `pnpm --filter @paperclipai/paperclip-runner exec vitest run src/native-session-runtime.test.ts`. Full checks use `pnpm -r typecheck`, `pnpm test:run`, `pnpm build`, and the separate runner checks. Paid evals require the frozen definitions, profiles, and credentials; do not use `--all` as a substitute for the selected cases. ## Risks - Context placement changes can affect model behavior. Deterministic checks cover the selected paths, but live qualification remains incomplete. - The stale-question guard can reject a request when queued human comments arrived during the run. This is intended. - New stored inputs and model envelopes retain compatibility readers for older active sessions. - Custom templates may intentionally repeat content. - Removing a model-facing working-directory sentence does not change filesystem, command, sandbox, or permission configuration. - The worker bypass applies only to same-origin development module paths. Cache-policy tests preserve private-response handling and production asset caching. Mounted HTTP fixture changes remain test-only. - This PR does not claim measured token savings or statistical equivalence across every harness. ## Model Used OpenAI Codex, exact model gpt-6-astra, with repository tools and code execution. Bounded supporting work used gpt-5.6-luna and gpt-6-luna. The serving context-window size is not exposed in this task. ## 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 described the issue in-PR using the required issue fields - [x] I have not referenced internal/instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal ticket id - [x] I have run the focused local checks and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect these changes - [x] I have considered and documented risks above - [x] All current-head Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups for the current head - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
cbc5132e6c |
fix(adapters): expose a verified provider stop before workspace restoration (#14311)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agent adapters own local or remote provider processes. > - Run cleanup must know when the final provider process has stopped. > - A remote timeout or a lost transport does not prove that the provider stopped. > - Retried provider invocations also make an earlier stop signal stale. > - This pull request adds a verified final-invocation stop callback before workspace restoration. > - The dependent instruction revision change uses that boundary to preserve private instruction edits safely. ## Linked Issues or Issue Description **What happened?** Adapter completion did not expose a reliable point between provider shutdown and workspace restoration. Cleanup could lose provider-written files, or treat a remote timeout as proof that a process stopped. **Expected behavior** Cleanup runs once after the final provider invocation has a verified stop receipt and before workspace restoration. An incomplete remote command keeps collection pending. **Steps to reproduce** 1. Run a remote provider that returns a timeout without a numeric exit code. 2. Let the adapter return or retry the provider. 3. Attempt to collect provider-written files during cleanup. The adapter has no verified final-process boundary to use. This is the prerequisite for the stacked canonical instruction revision pull request. It has no database or UI dependency. Related #13291 verifies remote termination for later recovery; this change exposes the earlier adapter-owned stop boundary before workspace restoration. The scopes do not duplicate each other. ## What Changed - Add a stop callback to adapter execution context and a final-invocation fence. - Confirm local child closure and complete remote exit receipts. Reject remote timeouts, missing exits, transport failures, and SSH exit 255 as stop proof. - Invoke collection once before workspace restoration in eight CLI adapters and at the confirmed ACP stop boundary. - Preserve the stop observation when a later log flush fails. - Run bridge and workspace cleanup in `finally` even when collection rejects. ACP records a safe error without exposing a raw filesystem path. Grok keeps collection errors separate from workspace restore failures and preserves completed provider results when both cleanup steps fail. - Correct the existing Cursor test shell fixture so bounded remote file reads run against real fixture files. ## Verification - Three stop-boundary regressions failed before the callback implementation and passed after it. - Independent prerequisite branch: 377 tests passed across 24 adapter, process-target, and ACP suites. Two added collector-rejection tests failed before the cleanup fix and passed after it. - A third regression reproduced Grok misclassifying a collection failure as failed workspace restoration. Two additional cases covered completed and failed provider turns when collection and restore both fail. The Grok and restore-classifier suites passed 48 tests. - All nine affected package typechecks and affected package builds passed; Grok checks passed again after its classification fix. - Integrated instruction branch: native local, legacy local, and native Daytona each passed three browser tasks with exact persisted bytes, fresh-task readback, history/restore, and explicit conflict resolution. Unchanged warm Daytona passed three turns. Legacy Codex passed all five checks again after the exception-safe cleanup fix. - Alternate staging passed the same three-task native Daytona flow: exact stopped-run save, independent downloaded readback, browser history/restore, and explicit resolution of a real concurrent edit. The deployed source was `14c3d810c9e05625121b3d27767aea9317b03125`, which covers the initial adapter callback. Later Grok cleanup failures are qualified by the adapter tests above. - The final combined native Daytona flow passed again on deployed `2bedd0f23bf4698b1f8b818f6796900647030427`: three fresh tasks proved ordinary instruction edits, independent readback, History/Restore, concurrent board conflict, and explicit candidate resolution. This native staging flow does not claim to exercise the Grok adapter. ## Risks - An unverified remote stop intentionally does not trigger collection. A later controller with verified stop evidence must recover it or report the copy unavailable. - The callback is optional. Callers that do not register it retain their existing behavior. - The callback runs before workspace restoration and can delay cleanup if its caller does not bound its own work. The dependent instruction collector uses bounded reads and retries. A rejected callback still permits bridge and workspace cleanup; it cannot claim an instruction save. ## Model Used OpenAI Codex, GPT-6, with tool use and code execution. The runtime does not expose the exact deployment variant or context-window size. Multiple Codex agents implemented and verified the change. ## 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> |
||
|
Devin FoleyandPaperclip
|
0fe39a2d5c |
fix(cursor-local): resolve sandbox agent installs from cursor bin (#5686)
> _Stacked on top of #5685 (Harden remote sandbox runtime). Diff against master includes commits from earlier PRs in the stack — review focuses on the new commit only._ ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The cursor-local adapter wraps the Cursor Agent CLI so a Paperclip workflow can drive it inside a sandbox > - When the adapter runs in a remote sandbox, the Cursor Agent CLI installs under `$HOME/.local/bin/cursor-agent` (or wherever `$XDG_BIN_HOME` points), not on the global PATH > - The existing post-install resolution assumed `cursor-agent` would resolve via the sandbox's login shell PATH after `npm install -g`, which fails on sandboxes where the install lands in a user-prefixed directory that isn't on PATH at probe time > - This pull request resolves the agent CLI from the cursor binary's own directory (`dirname "$(command -v cursor)"`) so the install probe and execute path agree on a real binary location > - The benefit is that cursor-local works correctly on any sandbox provider where `npm install` lands in a user-prefixed directory ## What Changed - `packages/adapters/cursor-local/src/server/remote-command.ts`: resolve the cursor-agent binary from the cursor bin directory after install, instead of relying on PATH. - `packages/adapters/cursor-local/src/server/test.ts`: corresponding probe tweak. - `packages/adapters/cursor-local/src/server/test.test.ts` (new) + `remote-command.test.ts`: focused coverage that exercises the install + resolve path against a sandbox runner that places the binary in a user-prefixed directory. ## Verification - `pnpm exec vitest run --no-coverage packages/adapters/cursor-local/src/server/test.test.ts packages/adapters/cursor-local/src/server/remote-command.test.ts packages/adapters/cursor-local/src/server/execute.test.ts` All passing locally. ## Risks - Local cursor-local runs are unaffected — the resolution change only kicks in for the sandbox install path. - Low risk; isolated to one adapter. ## Model Used - Provider: Anthropic - Model: Claude Opus 4.7 (1M context) - Capabilities used: tool use (Read/Edit/Bash), no code execution beyond local repo commands ## 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 - [ ] If this change affects the UI, I have included before/after screenshots — N/A, no UI change - [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> |
||
|
Devin Foley
|
4269545b19 |
Stabilize Cursor sandbox runtime resolution (#5446)
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The Cursor adapter spawns the Cursor CLI against local, SSH, and sandbox execution targets; on a fresh sandbox lease, it has to resolve where Cursor was installed > - The previous resolver only looked for `~/.local/bin/cursor-agent` even though the official installer (and the adapter's own `SANDBOX_INSTALL_COMMAND`) sometimes lays the binary down as `~/.local/bin/agent`, so a sandbox where the install ran successfully would still fail to find the CLI > - This pull request lets the resolver accept either basename and lets the caller pass an optional `remoteSystemHomeDirHint` so a probe doesn't pay the cost of a remote `printf $HOME` round-trip when the home directory is already known > - The benefit is sandboxed Cursor runs find the binary that the install actually produced, and runtime probes are cheaper when the home dir is already resolved ## What Changed - `packages/adapters/cursor-local/src/server/remote-command.ts`: accept either `agent` or `cursor-agent` as the preferred basename; new optional `remoteSystemHomeDirHint` short-circuits the home-dir probe - `packages/adapters/cursor-local/src/server/execute.ts`: thread the home-dir hint through, prefer the resolved binary path, and shift the effective execution cwd to the per-run managed subdirectory once the runtime is prepared - New `remote-command.test.ts` and `execute.test.ts` cover both basenames, the hint short-circuit, and the cwd shift - `packages/adapters/cursor-local/src/index.ts`: update doc string to reflect the broader resolution - `execute.remote.test.ts` updated to expect the managed-subdirectory cwd shape introduced by the cwd shift ## Verification - `pnpm vitest run --no-coverage --project @paperclipai/adapter-cursor-local` — 6/6 passing - `pnpm typecheck` clean - Manual: a fresh sandbox lease with `npm install -g …`-installed Cursor (binary lands as `~/.local/bin/agent`) now runs cleanly through the adapter ## Risks Low. Resolver is strictly broader (matches a superset of paths); existing setups with `~/.local/bin/cursor-agent` continue to work. The home-dir hint is opt-in; callers that don't pass it get the existing probe behavior. Cursor's effective execution cwd now matches the rest of the adapters (per-run managed subdirectory) — sessions previously rooted at the workspace root will land in the new subdirectory. ## Model Used Claude Opus 4.7 (1M context) ## 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 — new tests cover both basenames + hint short-circuit + cwd shift - [x] If this change affects the UI, I have included before/after screenshots — N/A (no UI) - [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 --- > **Stacked PR.** Sits on top of #5445 (which sits on #5444). Cumulative diff against `master` includes both of those PRs' content; the files touched by *this* PR's commit are listed under "What Changed" above. Will rebase onto `master` and force-push once the prerequisite PRs merge. |