32 Commits

Include renames

Author	SHA1	Message	Date
DottaandPaperclip	dd777f4b73	feat(dot): complete onboarding and expand governed Runner capabilities (#15414) ... ## Thinking Path > - Paperclip manages AI agents, their work, and their permissions. > - Paperclip Runner supplies the same admitted tool authority to each provider. > - The Dot provider in #15402 needs reliable onboarding and useful agent capabilities. > - An idle Dot could not start work, assign a human, read skills, or produce a workspace artifact. > - Pairing also relied on a second configuration save before ordinary admission could work. > - This pull request adds governed idle admission and shared Runner tools, and completes pairing atomically. > - Operators can test Dot with fresh data while keeping normal company, approval, budget, and run ownership checks. ## Linked Issues or Issue Description **Subsystem affected** Paperclip Runner, dedicated Dot MCP access, OAuth onboarding, experimental settings, and empty worktree startup. This PR builds on merged provider PR #15402. It reuses the merged MCP gateway from #14846 and assistant connection work from #14933 and #15380. **Problem or motivation** An idle Dot could see assignments but could not act on a conversation request until someone created a task first. Its Runner catalog could not assign tasks to humans or read pinned skills and workspace files. First-time OAuth discovery and pairing also needed browser fixes, and a completed pairing did not persist its binding reference on the agent. **Proposed solution** Keep Dot within the existing Runner. Admit a visible agent-authored intake task for idle requests. Add people, human assignment, cross-task, skill, and optional sandbox workspace tools through shared authority. Relay assigned app calls through the configured MCP gateway. Add lease renewal and follow-up references. Save pairing and its configuration revision atomically. Show prerequisites and provide a complete copy prompt. **Roadmap alignment** This extends the experimental provider in #15402. It uses the existing governed gateway, task model, skills, artifact path, and native Runner. It adds no separate execution subsystem. ## What Changed - Add a standalone OpenAI Dot agent choice with an independent experimental opt-in. It works with the general Runner option off. Require Assistant connections (MCP), authenticated sign-in, and public HTTPS for pairing. - Use Dot’s own option for company package import. Allow an unpaired Dot configuration to save after external billing acknowledgement; task admission still requires pairing. Prepare the shared dev binary for Dot-only opt-in. - Label saved Dot agents as OpenAI Dot. Use prerequisite-check copy in setup and runtime configuration. - Route Dot creation directly to pairing after explicit external billing acknowledgement. Hide local CLI, model, and harness setup for Dot. Preserve the shared Runner implementation and canonical API type. Other Runner providers still require their general opt-in. - Add an empty worktree option with fresh signing keys and no production data copy. - Fix public-client OAuth negotiation, discovery compatibility, and optional separate browser authorization origin. - Add one-use pairing consent preview, clear copied setup instructions, and atomic binding persistence and cleanup. - Add idle request admission with stable request IDs and normal scheduling, permissions, budgets, and task ownership. - Add identity and people discovery, human task assignment and reassignment, and authorized cross-task comments and documents. - Read assigned skill files from pinned manifests. Relay assigned app calls through the merged gateway without exposing credentials. - Add an off-by-default workspace bridge. Constrain paths and writes. Run commands in a deny-by-default OS sandbox with no network or injected credentials. Reserve mutations before effects and never blindly repeat uncertain work. - Add rolling lease renewal, task pagination, bounded operation limits, and deduplicated follow-up references without comment bodies in webhooks. - Add an off-by-default attachment reading setting. Restrict reads to files on the current assigned task. Verify size and hash, cache bounded verified copies per run, paginate text or binary bytes, and recheck live authority before returning. - Keep file grants operator-owned. Reject agent self-grants across configuration routes. Preserve attachment consent in create/import forms. Close generic API file bypasses while retaining current-run response snapshots and permitted uploads. - Keep provider limits explicit. Do not inherit a Dot binding, attachment permission, or workspace permission when hiring another agent. - Include the required Markdown format in cross-task document writes and validate the API title limit. Verify real creation and revision persistence. - Restrict command execution to Linux bubblewrap with descendant containment. macOS retains workspace file tools and artifact publishing, while refusing command calls. Explain the platform limit in setup. - Exclude Paperclip instance state from workspace files, uploads, artifact publication, and sandbox commands. Protect nested directories and case variants. Fail closed when the directory protection scan exceeds 4,096 directories. - Add static UI compression for slow public tunnels. Document setup, the complete tool inventory, and qualification limits. ## Verification - Merge preparation on `00ca2c75b` integrates merged base #15402 and master `fc6304dfe`. The ancestry commit preserves the reviewed follow-up source tree. The subsequent security fix excludes instance state from file tools, uploads, artifact publication, and sandbox commands. It preserves private task authorization and task monitors. It regenerates the combined tool catalog, seeded catalog digest, and protocol manifest. Workspace typecheck, full build, and UI token gates pass. All sixteen real Dot broker cases and 93 company import cases pass after the review fixes and creator-attribution test correction. The exported human-assignment catalog and Unicode page boundaries are also fixed. All ten catalog tests and nine workspace/skill bridge tests pass. All 35 workspace bridge and authority tests passed after the instance-state fix, including real macOS commands in that intermediate version. The subsequent document and descendant-containment fixes pass 44 focused tests across bridge, authority, and setup UI, with six Linux command cases skipped on macOS. Real cross-task documents pass the route validator and persist two revisions. macOS refuses command execution and does not advertise the tool. Full workspace typecheck and build, changed server/UI typechecks, and token gates pass again on the final commit. Greptile rates final head 00ca2c75b 5/5 and its completed check concludes success; all review threads are resolved. All 58 current-head checks are complete: 54 passed and 4 intentionally skipped. This includes full tests, typecheck, build, Runner, browser E2E, release verification, and Canary Dry Run. The older full local root attempt finished with 16,602 passes, 93 skips, and ten failures across two suites: it began before source edits and retained earlier imported implementations while loading later tests. Both suites pass a clean final-head rerun (25 passed, six Linux-only command cases skipped on macOS). This mixed-source full attempt is not a final-head full-suite pass; use the fresh CI evidence below. - Full workspace typecheck and build pass for the standalone Dot change on head `392d54f80`. UI token gates are clean. The full workspace typecheck passed before the final importer UI edit; the changed UI typecheck, build, and token gates pass again on the final commit. The server build passes for its unchanged final source. - Standalone selection, creation, settings, harness visibility, inventory, and runtime admission checks pass. OAuth onboarding and the real Rust/PostgreSQL broker suite pass 27 cases with the general Runner option disabled. Dot and MCP revocation still block pairing; other Runner providers remain disabled. Create, hire, conversion, and inherited-hire route regressions pass 68 cases. The runtime selection suite passes 20 cases. The setup UI suite passes 50 cases. Company import and dev binary checks pass 97 cases. Import UI checks pass 29 cases, including Dot-only selection, preservation of imported Dot agents, generic Runner fallback, canonical configuration serialization, and required billing acknowledgement. A read of the synthetic instance reports the native binary required with Dot enabled, the general rollout disabled, and no persisted native work. - The latest attachment, operator-consent, generic API file-guard, and bridge checks pass 80 tests. Cache and native lifecycle checks pass 550 tests; create/import builders pass 45 tests; attachment setup UI checks pass 16 tests. The real Rust/PostgreSQL Dot broker suite passes 15 cases. - Earlier authority, human assignment, pinned skill, confinement, cancellation, inheritance, onboarding, replay, OpenAPI, and gateway regressions pass their focused rechecks. Workspace writes reject concurrent stale hashes. - In the live empty test-drive, turn the general Runner option off and leave Dot and MCP on. Add agent shows a separate OpenAI Dot choice. Create rejects missing billing acknowledgement, saves the canonical Dot configuration, and opens pairing. The existing paired Dot remains ready and passes its prerequisite checks. No new plugin pairing was needed for this UI change. The final browser import preview keeps a Dot source agent as OpenAI Dot, falls back a generic Runner agent while its switch is off, and offers Dot independently. - Real Dot completed OAuth, signed MCP Events readiness, and an event-only assigned document task in an empty synthetic instance. Pairing saved its binding without a second configuration save. - Real Dot verified human assignment, cross-task comments and documents, pinned skill reading, sandbox commands, lease renewal, follow-up input, and a downloaded artifact whose bytes and hash matched its receipt. An idle conversation request created an intake, created a task for its human owner, continued after a definite missing-file read error, and finalized Done with exit code 0. - After operator approval, real Dot read a synthetic assigned-task attachment and wrote its file-only random proof into an agent-authored document. Its first test required accepting review because the existing document tool removed the final newline. - On head `2626c8f9b`, real Dot read a 13,849-byte synthetic attachment in two pages, used `expectedSha256` on page two, saved exactly its final random marker, verified readback, and finalized Done with exit code 0. A direct inbox check was required for this attachment qualification; it does not claim event-only delivery. - Previous head `392d54f80` passes all 55 checks (53 passed, two intentionally skipped), including the full test, typecheck, build, native Runner, browser, and release verification gates. Greptile rates this head 5/5; all review threads are resolved. - Head `2626c8f9b` passed all 56 checks: 54 passed and two intentionally skipped. This includes full typecheck, build, native Runner, server tests, serialized suites, browser E2E, and Canary Dry Run. The unchanged Cursor managed-runtime test exceeded its five-second deadline on the first attempt; its focused local suite passed all eight cases, and the single CI rerun plus dependent verify gate passed. - A prior full local serial test attempt reported 19 failures (16,141 passed, 88 skipped) and stopped before later wrapper groups. It began before the final source edits. Every failed suite has a passing fresh recheck; the macOS snapshot stress case passes alone in 227 seconds. The previous head `000fb9261` passed all 56 CI checks. PRs leave `pnpm-lock.yaml` unchanged; CI and the refresh bot own dependency resolution. ## Risks - Dot remains off by default. Its own opt-in does not enable other Runner providers. It still requires the MCP option; disabling Dot blocks new work while keeping existing recovery and saved bindings. - Dot requires a stable public HTTPS origin. Its base provider in #15402 is merged. Temporary tunnels are useful for testing but are not permanent deployments. - Idle intake creates a visible agent-authored task. It does not fabricate a human message or bypass ordinary admission. - Workspace commands require Linux bubblewrap with a private PID namespace; deployment qualification is still needed. macOS file tools and artifact publishing remain available, but commands are disabled because sandbox-exec does not contain detached descendants. There is no unrestricted fallback. Command protection fails closed above 4,096 workspace directories. The historical macOS command walkthrough does not qualify the current Linux implementation. - Provider model choice, token usage, cost, native thread control, and global external stopping remain unavailable. Known Paperclip budget gates still apply. - The workspace bridge and attachment reader are separate opt-in settings. Reading assigned task files sends their contents to OpenAI. Revocation prevents future reads but cannot withdraw bytes already sent. Files are read on request; automatic inbound attachment staging remains disabled. - An existing event registration can retain earlier instructions that prohibit extra tasks. Dot asked for permission before a second intake after the final event-only bootstrap; that extra no-nudge continuation is not live-qualified under that earlier registration. The later attachment qualification submitted normally through the composer. The revised onboarding prompt describes the new idle entry point, and its protocol polling path is tested. - OpenAI event delivery can be delayed; a webhook acknowledgement is not proof that Dot has begun work. - A running Dot can retain an old plugin catalog after tool refresh. Refresh and actual tool exposure must be checked before using new top-level actions. - Hosted and remote controller modes are not qualified. ## Model Used OpenAI Codex, based on GPT-6. The exact deployment ID and context window size are not exposed in this session. Capabilities used: reasoning, repository editing, code execution, test inspection, and browser control. ## 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 linked existing issues or described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass (focused suites and all fresh failure rechecks pass; the earlier full attempt is disclosed 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>	2026-10-07 19:44:17 -05:00
DottaandPaperclip	8cfedd7df8	fix(runner): restore task monitors and durable timed waits (#15446) ... ## Thinking Path > - Paperclip manages AI agents and their task execution. > - Agents need a durable way to return to work after a delayed check. > - The issue monitor scheduler already provides a one-shot wake for an assignee. > - Native runners reject generic execution-policy writes and had no bound monitor tool. > - Scheduling alone is insufficient because native completion also needs to accept a timed wait. > - This pull request adds an authorized monitor tool and connects it to completion and the existing scheduler. > - An agent can now schedule its next check, end the run, and resume on the same task. ## Linked Issues or Issue Description **What happened?** A native runner could not set its own task monitor. `call_api` correctly rejected execution-policy writes, while `schedule_wake` had no production binding. `paperclip_finish` also rejected monitor waits. **Expected behavior** A standard native run can set a one-shot monitor on its current task or another accessible task assigned to the same agent. After a confirmed schedule on the current task, it can yield. The scheduler later delivers `issue_monitor_due`. **Steps to reproduce** 1. Start a standard native task. 2. Ask the agent to check the task again later and end its current run. 3. Inspect available tools and try the generic issue execution-policy update. 4. Observe the missing native tool and the lifecycle-write denial. Related PRs: #14680 concerns monitor notes in the shared wake prompt. #11919 changes attempt-limit scope. This PR adds native scheduling and completion authority and retains the existing cumulative attempt bounds. It does not depend on either PR. ## What Changed - Add provider-neutral `set_task_monitor` with a default current-task target, future timestamp, required notes, existing bounds, and explicit clearing. - Check company, task visibility, ownership, runtime permissions, work mode, and active-run authority. Preserve review-only restrictions. Reject the reserved server-owned quota-recovery name before saving or accepting a native wait. - Commit the monitor, audit event, and retry receipt together. Retry receipts survive a successor run without re-arming cleared or consumed timers. - Permit `paperclip_finish` to yield to a persisted monitor. Recheck ownership and the schedule when committing final disposition. Release execution without an immediate continuation. - Preserve due monitors during native execution. Fence wake admission and consumption against replacement, clearing, reassignment, and completion. Preserve unrelated review policy. - Expose scheduled and consumed monitor instructions in task context. Update provider schemas, Rust validation, generated contracts, and execution documentation. - Add an opt-in live Codex smoke script with isolated data and explicit run/session/runner/process evidence. ## Verification - Repository `pnpm -r typecheck` and `pnpm build` passed after rebase. Server typecheck passed again after review fixes. All CI test shards pass on `3def77b1b`, including runner TypeScript/Rust, server, serialized server, workspace, and browser tests. All CI gates are green, including the canary dry run. Greptile is 5/5 on the same commit with zero unresolved threads. - The local monolithic `pnpm test:run`, started before the rebase, was interrupted after current-head CI test coverage passed. It is not counted as a standalone full-suite pass; the focused local regression suites passed. - Targeted server tests cover scheduling, replacement, clearing, policy preservation, cumulative bounds, cross-run retries, permissions, provider-neutral discovery, review restrictions, completion authority, and scheduler/finalizer races. - Runner contract/catalog/semantic tests and Rust terminal-tool tests cover the new operation and monitor completion. - Live Codex test passed twice (latest live run on `e0bcd63e6`) in a temporary database and workspace, with a 300,000 ms warm window. First run `67bd7709-c089-4d4a-9d2b-0d6b618a34b0` yielded at `2026-10-07T13:15:03.274Z`. Second run `97c323f9-595a-4cc5-a007-db5a2fbb937c` started at `13:15:30.952Z`, received `issue_monitor_due`, and completed the same task. Exactly one monitor wake was recorded. - Both live runs used native session `7b1dd753-1c9b-4e7a-b22f-a125dbc3748c`, runner `e90d9a1b-3502-4ee3-b15e-edc024c555d4`, provider session `01a11680-6d01-70c0-9a55-db7246ed66c3`, and PID `64218` with the same process start time. This proves warm reuse for that local Codex test, not only successful scheduling. - Reproduce the paid live test with `node --import ./server/node_modules/tsx/dist/loader.mjs server/scripts/smoke-native-task-monitor.ts --run`, with the installed Codex binary on `PATH` and a valid local login. ## Risks - The scheduler now defers monitor dispatch while the task has an active native run. A stuck run still depends on the existing recovery lifecycle. - Idempotency uses the existing run ledger; no table or migration is added. - Other providers share the tested tool and completion contracts. Only Codex received a live model test. - Existing `call_api` lifecycle restrictions remain enforced. Monitor waits do not bypass task blockers, reviews, or approvals. ## Model Used OpenAI Codex, GPT-6 family, with tool use, code execution, and TypeScript/Rust editing. The session does not expose the exact deployed model ID or context-window size. ## 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>	2026-10-07 08:41:24 -05:00
DottaandPaperclip	faa8e452c7	fix(tasks): stop repeated reminders for historical questions (#15392) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Task questions remain saved so a person can answer them later. > - The composer moves an old question into history after a newer human message. > - Native completion still treated every pending question as a required response. > - This caused agents to demand an old answer after the person moved work forward. > - This pull request shares the historical-question rule across context and task execution. > - Agents can finish verified work while the original question remains answerable. ## Linked Issues or Issue Description Refs #15229, Refs #14613, Refs #13130. **What happened?** An agent repeatedly asked a person to answer a question that had moved into feed history. Completion feedback explicitly told the agent to request a response. The saved pending row also blocked task completion. **Expected behavior** A question before newer human direction remains answerable in the feed. Its pending state alone must not require another reminder or stop completed work. A new input blocker, an approval, or a configured review stage must keep its gate. **Steps to reproduce** 1. Let a task agent create an ordinary question. 2. Dismiss the question and send a newer task message. 3. Let the agent finish the requested work and submit its completion report. 4. Observe a demand to answer the old question and a retained completion gate. ## What Changed - Add one company-scoped predicate for historical questions. Only later human comments count. Exclude agent attribution, run attribution, system notices, and untrusted source data. - Apply the predicate to completion feedback, native waits, finalization, commit validation, retry validation, blocked routing, and successful-run handoff. - Include question classification and guidance in heartbeat context and both native task-context tools. Add the guidance to fresh and resumed task prompts. - Replace automatic reminders for current ordinary questions with instructions to assess the real blocker, continue independent work, and withdraw obsolete questions through the existing API. - Preserve historical question rows during completion while cancelling their live native source runs through the existing post-commit and recovery paths. Let an authorized human answer them after completion without reopening work or creating a response wake. Preserve cancellation, current-input, approval, permission, credential, connection, and review gates. Add no dismissal storage or migration. - Document the rule in the execution contract and agent skill. Refresh generated capability source anchors. Add database-backed status, context, attribution, and governance regression tests. ## Verification - `pnpm build` passed. The server rebuild also passed after the lifecycle fix. Generated capability contract and inventory checks passed after the agent documentation update. - `pnpm -r typecheck` passed. Final `pnpm --filter @paperclipai/server exec tsc --noEmit` also passed after the last test additions. - Lifecycle and interaction regressions passed: 224 tests in 3 suites. Context and prompt tests also passed. Final historical-question cases passed (33 tests), native cancellation/recovery cases passed (6 tests), and the existing interaction/confirmation suites passed (72 tests). The full local `pnpm test:run` was attempted and stopped after more than two hours with unrelated fixture/hook timeout failures; it did not pass. All 52 successful GitHub checks are green on the latest commit, including the complete test matrix; no checks are pending or failing. Greptile is 5/5 and both review threads are resolved. - Regression cases cover the old-question/new-human-message sequence, final task status, answering after completion with no wake, live-run cancellation and crash recovery, current input blockers, both task-context tools, API context, timestamp precision, attribution boundaries, and protected gates. ## Risks - A later human task message makes an earlier ordinary question historical even if its input is still missing. The agent must identify the current blocker and ask only for information that still prevents work. - Browser dismissal remains a local preference. Dismissal without a later human message is not recorded by this change. - No schema change or data migration. Completion retains ordinary historical questions; cancellation still expires them. A completed task accepts historical answers only from an authorized human and creates no response-delivery outbox row. Governed requests retain their gates. ## Model Used OpenAI Codex, GPT-6, with repository editing, code execution, and browser diagnostics. The exact deployment model ID and context-window size are not exposed in this session. ## 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>	2026-10-06 20:33:13 -05:00
DottaandPaperclip	b508a05c43	feat: add internal agent complaints and suggestions (#15367) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents use legacy skills or native runner tools to work on tasks. > - Those agents can encounter friction that does not belong in the task thread. > - A complaint should preserve the raw reaction. A suggestion should describe an improvement. > - This pull request adds attributed local storage and both submission paths. > - Agents can submit feedback once and continue their primary work. ## Linked Issues or Issue Description **Subsystem affected** Server, database, shared contracts, runtime skills, and native runner tools. **Problem or motivation** Agents have no default internal channel for incidental complaints and suggestions. Sending this feedback through task comments adds noise and can alter task workflows. **Proposed solution** Store free-form feedback in the current instance database. Derive agent, run, company, and task attribution from active authority. Provide default legacy skills and provider-neutral native actions. Keep the instructions close to Warp's MIT-licensed originals. **Alternatives considered** Task comments and external Slack delivery add unwanted side effects. Mandatory suggestion fields and short editorial limits would discard useful feedback. This release has no listing API, UI, read tool, automatic triage, or external forwarding. **Roadmap alignment** This is a maintainer-requested addition to the existing runtime skills and runner tool paths. It does not duplicate a listed roadmap milestone. Searches for complaint tooling, suggestion-box, and agent commentary found no overlapping public PR or issue. ## What Changed - Add the company-scoped `agent_commentary` table, shared validation, and idempotent migration `0310`. - Add one transactional service and the agent-only POST route. Validate active authority before writes or replay. Redact known credentials. Commit a content-free audit with each new record. - Add `submit_complaint` and `submit_suggestion` to standard, ask, and planning modes. Keep review, revocation, and completion restrictions. Store replay identity on the commentary row. - Mount `complain` and `suggestion-box` by default for legacy agents. Bundle a dependency-free Node.js stdin helper in the operational skill and allow its POST through the sandbox bridge. - Preserve Warp's complaint voice and suggestion guidance, with attribution and local transport adaptations. Keep source attribution and MIT notices in each skill's LICENSE, outside runtime instructions. - Document custom-runtime HTTP use and database inspection. Add real-database tests and a repeatable live Codex smoke for local and Daytona execution. - Pin the lagging-source migration fixture before the identity-repair migration so later migrations preserve its regression coverage. ## Verification - Personally ran real Codex submissions in all four environments on 2026-10-06. Local runs passed at 20:35 UTC. Daytona native passed at 20:31 UTC; Daytona legacy passed at 20:33 UTC. Each stored exactly two rows with company, agent, run, and task attribution, wrote the continuation marker, exited zero, created no task comments, and left task status unchanged. Each recorded two content-free activity entries. - Daytona used production provider hooks, real remote execution and file transfer, the legacy queue callback bridge, and native private WebSocket ingress. The current Linux runner was built from `abf47b595`, staged, and verified against controller contracts. Both sandboxes were confirmed deleted. This is a focused feedback transport smoke; it does not claim full Runner E2E catalog or browser qualification. - The immutable base image and Linux binary digest are recorded in [the verification documentation](https://github.com/paperclipai/paperclip/blob/codex/agent-commentary/doc/agent-commentary.md#verification). The smoke script can save content-free JSON evidence. No credentials or feedback bodies are in these reports. | Environment | Runner | Complaint row | Suggestion row | | --- | --- | --- | --- | | local | legacy Codex | `59413a00-1de2-4bb1-bcc6-9c4b54c64aa6` | `3db2364d-3e15-4f47-846f-875d3902999d` | | local | native Codex | `5da22b5f-41df-4de5-8ba0-d9345ab01267` | `2d5abe17-dd41-403c-a5ee-4729f2d58921` | | daytona | legacy Codex | `27c9d0aa-8477-409f-9da0-e8ffa48dee50` | `209681c9-d1e9-4ce1-999e-48fa07692389` | | daytona | native Codex | `6eb001bb-4bcf-43f7-8717-f662f53dc7c3` | `77c383d8-a997-49e5-a33e-25c70e15c0b2` | - Run the local check with `node cli/node_modules/tsx/dist/cli.mjs server/scripts/verify-agent-commentary-live.ts`. The documentation gives the Daytona invocation. Both use disposable instance databases and normal Codex provider usage. - Repository `pnpm -r typecheck` and `pnpm build` passed after the test extension. The build includes runner generation, contracts, and replay checks. The smoke scripts also passed a separate TypeScript check. The lagging-source migration regression passed. All equivalent current-head Vitest CI shards passed. The local monolithic `pnpm test:run` invocation was stopped after CI supplied that coverage; it did not complete locally. - Focused tests cover company isolation, spoofing, revoked credentials, stale ownership, post-finish rejection, concurrent replay, conflicting keys, atomic rollback, and deletion through existing services. Boundary tests cover empty text, Unicode, text beyond 8,000 characters, and the 524,288-character ceiling without truncation. Mounting tests cover Codex, Claude, and sandbox staging. Helper tests cover standalone Node execution, stdin, invalid UTF-8, redirects, HTTP failure, and its deadline. Privacy and bridge tests cover successful and rejected requests. - Instructions were compared with Warp's originals. MIT notices and source credits live only in LICENSE files. Native tools preserve truthful disclosure when asked, without routine announcements. - [Full CI](https://github.com/paperclipai/paperclip/actions/runs/37508559190) and Greptile 5/5 passed on the earlier feature commit `5209c3501`. The later head found the migration-fixture assumption fixed in this update. On `8a4965164`, all 55 check contexts passed after one browser shard rerun. Its initial reviewer signoff failure also passed an isolated local browser run (1 test). Greptile scored that head 5/5 and identified one smoke cleanup gap. `6ecbafb0b` fixes failed-acquisition cleanup with four passing tests and a passing smoke-script typecheck. Fresh CI is pending for this final test-only fix. No commentary production code changed during verification. ## Risks - Feedback is internally attributed. It is not anonymous. Existing redaction removes known credentials, but agents must still omit sensitive content. Normal provider transcripts can include their submitted arguments. - Default skill availability changes for existing legacy agents. Runtime policy filtering still applies. The helper uses the existing Node.js runtime with no extra dependencies; custom runtimes can call the HTTP endpoint. - Feedback is removed with its run, agent, or company. Task deletion clears only the issue pointer. Normal database backups include the table. - The migration is additive and has no backfill. Writes serialize on the active run for replay consistency. No server suggestion quota is imposed. ## Model Used OpenAI `gpt-6-astra` through Codex, with `xhigh` reasoning effort and a reported 258,400-token context window. Capabilities used: repository inspection, code execution, and live runtime verification. No subagents were used. ## 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>	2026-10-06 16:14:06 -05:00
DottaandPaperclip	e34abee670	feat(mcp): connect assistants to a team with user OAuth (#14846) ... ## Thinking Path > - Paperclip gives teams durable tasks, agent execution, budgets, and approvals. > - People also use assistants in Codex, Claude, and other MCP clients. > - Those assistants need a scoped connection that preserves the person’s permissions and attribution. > - Delegating a task must not turn the assistant into the assigned agent. > - This PR adds opt-in user OAuth, ten first-party tools, browser consent, and workflow packages. > - Paid product evals verify the resulting tasks, documents, attribution, retries, and access boundaries. > - The team keeps working after the assistant conversation ends. ## Linked Issues or Issue Description **Problem or motivation** A person cannot connect an external assistant to an existing team through browser consent and safely delegate durable work as themselves. **Proposed solution** Expose an opt-in `/mcp/paperclip` endpoint with individually described first-party operations. Bind every connection to a person, client, company, resource, and scopes. Reuse domain authorization and scheduling. Package shared team-review, delegation, and follow-up workflows for OpenAI/Codex and Claude. **Alternatives considered** Related PRs #9393 and #12549 cover earlier remote MCP and board-operator approaches. This change uses user OAuth and a bounded public catalog. It does not expose a generic executor, operator administration, static shared board credentials, or external agent execution. Registry listing work in #9851 is a separate distribution step. **Roadmap alignment** This maintainer-requested implementation extends the governed MCP gateway, activity attribution, durable work products, and hosted deployment direction in `ROADMAP.md`. It implements the first release of the saved design plan; external agent participation and granted third-party tools remain later releases. ## What Changed - Add MCP 2.0 discovery and task status/comment/document Events on the same authenticated endpoint. Persist subscriptions and delivery receipts, verify HTTPS callbacks, sign Standard Webhooks, encrypt callback material, recheck permissions/Cloud membership, and bound retries/expiry. Older MCP clients keep their existing tools. - Add discovery, dynamic client registration, S256 PKCE, resource validation, rotating refresh tokens, revocation, and company consent. Store credentials as hashes and recheck membership at execution. - Add tools for connection identity, agents/projects, task search/read/create, human comments, documents/deliverables, and pending-approval links. Preserve current domain permissions and scheduling. - Add durable mutation receipts across reconnects. Matching retries replay results; uncertain outcomes keep the same request ID and require inspection. - Add consent and connection-management pages, OAuth log redaction, shared plugin workflows, and separate OpenAI/Codex and Claude package outputs. - Add eight paid Product E2E cases across three models, independent durable-state grading, usage evidence, cleanup, and report integration. Add task-document guidance and regenerate the runner capability inventories. - Add migrations 0301 and 0302, the dated implementation plan, result notes, and direct-client setup instructions in `doc/public-mcp.md`. ## Verification - Merge integration `e180b1948`: resolved conflicts with current master, preserved both eval registries, regenerated capability catalogs, and regenerated migrations as 0301/0302 while keeping the original replay-safe SQL byte-identical. Local migration safety/snapshot tests (26), MCP/OAuth tests (38), redaction/OpenAPI tests (71), and eval catalog/grading tests (198) pass. Token and capability gates pass. Full recursive typecheck passed. Fresh Greptile review is 5/5 with no unresolved findings. CI is green on this exact head (55 successes, two intentional skips, one neutral result): one unchanged Cursor sandbox test timed out at 10 seconds, then passed locally in 856 ms. A single retry of that failed shard and the aggregate workflow passed. Merge remains blocked on the repository code-owner approval rule. Earlier checks passed at `6aa0962d4fb715f2190bb7bb22efacab2e58495d`: 55 successes, two intentional skips and one neutral result. [The earlier CI run](https://github.com/paperclipai/paperclip/actions/runs/36901592350) includes all test shards, browser tests, typecheck, build and canary dry run. Greptile was 5/5 on that commit with no unresolved review threads. GitHub still requires code-owner review under the repository merge rules; passing checks do not bypass that approval. Paid source fingerprints remain separate below and in the dated result note. - Paid Events qualification passes **3/3**: GPT-5.4 Mini, Claude Haiku 4.5 and Claude Sonnet 4.6. Each uses a real public HTTPS callback, signature verification and report retrieval in a fresh conversation. A final Mini regression passes after the quota/status fixes. All evidence validates. Bounded tunnel startup retries occur before provider calls and remain visible; failed earlier attempts retain their original grades. - The earlier complete seven-case matrix passes **21/21**, with a separate **3/3** delegation regression. Two preceding matrices also passed 21/21 each. A complete 24-cell matrix including Events has not been run. [The dated results](doc/plans/2026-10-01-public-mcp-paid-eval-results.md) retain exact source fingerprints, failures, model IDs and partial costs. - Node 24: repository-wide `pnpm -r typecheck` and `pnpm build` pass after merging master. Server typecheck passes after the final quota/status changes. Eval typecheck and all 892 eval-support tests pass. - All 33 real MCP/OAuth tests pass. The preceding combined MCP, redaction, private-address and DNS-rebinding run passed 129 tests; two later MCP regressions cover quota reuse and unchanged-status suppression. All 28 adjacent issue-tree/stale-lock route tests pass. CI then found a null checkout result in the existing concurrent-workspace path; logging now uses optional status access. All 12 closed-workspace tests and all 33 MCP tests pass after that correction. The exact-start event calibration exposed a timestamp gap; scanning now includes the subscription start, with all 33 MCP tests and server typecheck passing. These two narrow corrections follow the paid regression. - A real Core → Cloud → Core authority round trip passes OAuth, MCP 2.0 subscription/delivery, current membership loss, unsubscribe, legacy SDK tools, refresh and revocation. Its callback transport is a fixture with independent HMAC verification. The paid Events campaigns separately prove public HTTPS delivery. - Earlier component qualification passed UI 7,117 tests, CLI 502, shared 832, skills catalog 20, database 160 and OpenAPI 10. Token gates, module boundaries, migration order and plugin regeneration passed. CI covers general/serialized suites, eight browser shards, runner checks, typecheck, build and canary dry run. - **Local full-suite limitation:** the earlier monolithic run was not clean. It encountered overlapping schema rebuilding, Mac database shared-memory limits and isolated CLI/fixture failures. Targeted reruns passed. The existing >32 MiB Git filename stress test still hit its 300-second Mac timeout. The additional serialized sweep stopped after 62 passing suites once CI passed. Original failures and partial logs remain; this PR does not claim a wholly green local monolithic run. - Local Codex CLI and Claude Code OAuth login and MCP SDK interoperability were verified. Public-store installation, actual ChatGPT Work Cloud Events UI, staging HTTPS client behavior and hosted newcomer provisioning remain release gates. Enablement is moving to **Settings → Experimental → Assistant connections (MCP)** in the stacked follow-up [#14933](https://github.com/paperclipai/paperclip/pull/14933). Merge both for the intended setup experience. This foundation branch alone still uses `PAPERCLIP_PUBLIC_MCP_ENABLED=true`. After deployment, set `PAPERCLIP_PUBLIC_URL` to the authenticated instance's HTTPS origin, and connect to `/mcp/paperclip`. Select a team and allow writes in browser consent. Configure an available agent and budget, then delegate and retrieve results later. For Events, rescan the deployed plugin catalog in ChatGPT Work Cloud; the host supplies its webhook credentials when the user asks to watch a task. See [the setup runbook](doc/public-mcp.md). ## Risks - Events are at-least-once and may arrive out of order. No replay cursor is advertised. Clients must refresh finite subscriptions, read current state and avoid comment feedback loops. Callback material uses the instance secrets master key; hosted subscriptions require the updated Cloud broker and are bounded to five minutes/the access proof expiry. - ChatGPT Work Cloud/dot event UI, plugin rescan and a hosted staging subscription remain deployment gates. Local signed-webhook and paid model evidence does not claim those surfaces have been exercised. - Disabled by default. Merging adds schema and opt-in code; it does not deploy a public endpoint, publish a store listing, create a team, or start paid agents. - Migrations 0301 and 0302 are additive and idempotent. Their SQL is unchanged from the earlier preview numbers, so hash-aware upgrade reconciliation preserves prior staging applications. Normal instance upgrades must apply it before enabling MCP. - Task creation and comments can schedule paid agent work. Consent and tool descriptions disclose that effect. Revocation blocks future calls but does not undo delegated work. - Public deployments need edge rate limits and credential-safe logging. Internal dispatch is restricted to the closed catalog and carries a request-local verified actor. - Hosted onboarding requires the companion Cloud broker, encryption-key configuration, and tenant rollout. Self-hosted direct connections can use this PR alone. - Store acceptance and agent-mode participation are not claimed. Checked-in plugin endpoints are development defaults; rebuild packages for a real deployment before installation. ## Model Used OpenAI GPT-6 in Codex, with reasoning, tool use, and code execution. A more specific serving version and context-window size were not exposed by the session. Paid eval models: `gpt-5.4-mini-2026-03-17`, `claude-haiku-4-5-20251001`, and `claude-sonnet-4-6`. ## 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 (targeted/component checks; full local-run limitations are recorded 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>	2026-10-06 11:48:53 -05:00
DottaandPaperclip	16b7db35ff	Shorten planning skills and measure task decomposition (#15296) ... ## Thinking Path > - Paperclip manages work for AI agents. > - Planning guidance helps agents choose owners and dependencies. > - The runtime skill favors few tasks, but the catalog skill requires a child-task breakdown. > - Both add repeated process instructions that can distract from the requested outcome. > - This change keeps the ownership and dependency rules and removes the required matrix and repeated checklist. > - A bounded Product E2E comparison measures saved outcomes and task handoffs before qualification. ## Linked Issues or Issue Description Refs #11057. Related measurement work: #15218. **What existing behavior does this improve?** Planning and delegation through the runtime plan-to-tasks and bundled task-planning skills. **Current behavior** The two skills contain about 1,900 words and conflicting guidance on whether plans require child tasks. **Proposed behavior** Keep cohesive work with one owner. Split only for a real owner, parallel output, dependency, independent review, or follow-up lifecycle. Preserve existing authorization and planning mechanics. ## What Changed - Shorten both skills to about 400 words combined. Preserve their keys and installed-version behavior. - Remove the duplicate operational-skill pointer and regenerate affected source metadata. - Add twelve explicit Product E2E cells: four scenarios with current, short and disabled planning skills. - Use the current task composer and actual create-response ID; calibrate public skill APIs and browser creation without providers. - Eliminate an observed collision in chat-test company prefixes with a per-suite sequence. - Grade saved documents, exact author/run attribution, child count, prerequisite execution order, review boundaries and completion handoffs. - Retain current skill bytes and report source, selections, run accounting and failures. ## Verification - `pnpm test:e2e:runner:typecheck`: pass. - `pnpm test:e2e:runner:unit`: 1,287 Vitest tests and 128 Node checks pass. - `pnpm test:e2e:runner -- --list --suite plan-task-guidance`: twelve local Codex cells. - Archived current skills match master `72ff3a9f27e581a27acb49771e8658bbb0bbaa47` exactly. - Corrected fixture: three real public-API/database calibrations pass with zero provider runs; all 35 evaluator checks and Product E2E typecheck pass. - Setup campaign [37399550253](https://github.com/paperclipai/paperclip/actions/runs/37399550253) was canceled after source review found unsupported bundled edits and automatic core reinstallation. Its paid-cell step was skipped: zero provider runs, no behavioral grade. - The next setup [37401094799](https://github.com/paperclipai/paperclip/actions/runs/37401094799) failed before task creation on the old title-field selector: zero actual runs, original FAIL retained, cleanup passed. A real browser/API calibration of the new helper passes with paused non-provider agents and zero runs. - Full local typecheck/build pass. Full local tests retain one unchanged five-minute Git streaming timeout (also fails isolated), 9,591 passes and 5,796 skips. CI's chat failure was a proven random fixture-prefix collision; five affected cases pass after the test-only repair. - Paid behavior comparison and new-head CI/review remain pending. This PR remains a draft. ## Risks - The shorter text may change delegation decisions. Live outcomes are not yet qualified. - The initial comparison uses one profile and one attempt per cell. It cannot establish cross-model reliability or cost trends. - Disabled means unassigned company-owned copies; the company library remains discoverable. This does not qualify global removal, automatic accepted-plan wiring changes, or installed-copy migration. - Skill availability does not prove a model read or cognitively used it. - No provider/tool protocol, permission, timeout or runtime lifecycle behavior changes in production. ## Model Used OpenAI Codex (GPT-6), with repository inspection, code editing and tool use. The exact backend model ID and context-window size are not exposed in this session. The declared eval model is native Codex `gpt-5.6-sol`. ## 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 - [ ] 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>	2026-10-06 09:36:01 -05:00
DottaandPaperclip	a65ca09508	fix(runner): settle accepted results after shutdown failures (#15217) ... ## Thinking Path > - Paperclip manages AI agents and the tasks they perform. > - The native runner saves tool results and completion reports before it releases a session. > - Large project discovery responses can exceed the durable command limit. > - A shutdown failure can leave a saved answer waiting for workspace repair. > - Recovery reused the old assessment for a different status decision, which violated a database constraint. > - This pull request bounds discovery responses and lets recovery commit the saved result after workspace repair. > - The benefit is a task that reaches its correct final status without another provider turn. ## Linked Issues or Issue Description **What happened?** A native run can save its final answer, fail during shutdown, and leave the task In Progress after workspace repair succeeds. Reconciliation tries to reuse the failed-workspace assessment for a new decision. The one-decision-per-assessment constraint rejects the write. Replaying the old decision can also retain a fresh coordinator lease. Separately, retained session cleanup only recognizes the old `adapter_failed` label. The project-list tool returns full project records, including large descriptions and workspace configuration. A large response exceeds the runner's durable command limit. The settlement diagnostic previously recorded only a failure flag. **Expected behavior** Project discovery stays within the command limit. Recovery finishes the saved result after workspace repair, releases its lease, and preserves the original error for inspection. It does not repeat provider work or relax session ownership checks. **Steps to reproduce** 1. Return large project records from `list_projects` and observe an oversized semantic result. 2. Persist an accepted native completion result, then record a shutdown failure. 3. Finalize with a failed workspace, repeat that attempt, then record successful workspace repair. 4. Reconcile the run. Before this fix, the issue stays In Progress. **Paperclip version or commit** Reproduced on `a386a599983519eb1d399f8b770bfccdb2a74762`. **Deployment mode** Self-hosted server with Paperclip Runner. Related transport work: #12208 drains queued events; #12241 resumes interrupted semantic calls. This change addresses bounded project discovery and accepted-result finalization. ## What Changed - Read bounded project summary projections from the database and return at most 50 authorized summaries with a continuation cursor and explicit description truncation. Agent and run trust boundaries narrow the database candidates; project-specific policies still receive full authorization. Only visible projects determine continuations. The default project-list API remains unchanged. - Record bounded, content-free settlement failure causes for command limits, storage errors, and rejected dispatch. - Include workspace state in assessment identity. Preserve the initial assessment for interrupted finalization, and commit replacement assessment and decision references together. - Release the coordinator lease when an existing decision is replayed, without repeating its effects. - Clear stale errors when recovery succeeds and retain them in `recoveredExecutionFailure`. - Accept both current and legacy close-failure labels in the existing exact-state cleanup path. - Add regression tests and update the tool contracts and recovery documentation. ## Verification - Red: the new project paging, settlement diagnostic, current cleanup label, and repaired-workspace regressions failed on the original implementation. - Green: protocol/catalog/tool checks (117 tests), the full project-tool and finalizer suites (47 tests), cleanup ownership cases (70 tests), and cleanup sweep cases (4 tests) pass. Database-backed pagination covers large descriptions/configuration, complete enumeration, uppercase cursors, agent/run restrictions, project-policy scope contributions, and identical results/cursors when hidden projects are added. - The initial CI failures in interrupted Board waits, contended endpoint proof, and semantic schema validation were reproduced and fixed; all affected cases pass locally. - `pnpm -r typecheck` — passed. - `pnpm build` — passed. - `pnpm test:run` — started before the review corrections; it spanned several source revisions and was stopped after reporting old-behavior and timing failures. It is not claimed green. Fresh project and recovery suites pass; the recovery suite also passes all 25 cases with the broad runner’s isolated home/config. The Slack timing case passed in isolation. Latest-head CI is the authoritative complete test matrix. - Existing authorization suite — 66 tests passed. - Latest-head CI on `8e5763d915aa6f375bdab6601996899ea01496fc` — 55 checks passed, 4 intentionally skipped, no pending or failing checks. - Greptile — 5/5, zero unresolved threads on the same commit. - `git diff --check` — passed. ## Risks - `list_projects` now returns summaries. Callers must follow `nextCursor` and use the authorized project API for full records. Candidate narrowing is only an optimization: project policy and responsible-user authorization remain authoritative. - Assessment identity changes for workspace finalization. Existing evidence remains intact; no migration is needed. - Cleanup still requires matching identities, settled tool evidence, and verified process ownership. Unknown tool outcomes remain blocked from session reuse. ## Model Used OpenAI Codex, based on GPT-6, with reasoning, code execution, and GitHub tools. The exact serving model ID and context window are not exposed in this session. ## 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>	2026-10-05 10:31:11 -05:00
DottaandPaperclip	eb049aebf2	feat(skills): let agents update company skills safely (#15049) ... ## Thinking Path > - Paperclip is an open source control plane for AI-agent companies. > - Company skills give agents reusable work instructions. > - Skill Studio can edit skill files and save version history. > - Agents can create a skill, but they do not have a first-class update tool. > - An agent update needs a version check and safe retry behavior to prevent lost edits. > - This pull request adds `update_skill` through the existing company skill file API. > - The change keeps company policy, version history, and audit records in one path. ## Linked Issues or Issue Description **Subsystem affected** Cross-cutting: the server API, shared validation, and runner tool catalog. **Problem or motivation** An agent can create a company skill but cannot update its `SKILL.md` through a first-class tool. An unguarded retry can also create duplicate versions or overwrite a newer edit. **Proposed solution** Add `update_skill` with a required current version ID and a retry key. Route it through the existing skill file API. Reject stale versions and changed-input retries. Save the version and audit event together. **Alternatives considered** A separate write endpoint would duplicate the Skill Studio mutation path and policy checks. This PR reuses that path instead. **Roadmap alignment** This work extends Skills Manager and Skill Studio, which are listed in `ROADMAP.md`. **Additional context** The tool accepts a complete `SKILL.md`, not a partial patch. Callers must read the current version before they edit it. ## What Changed - Add optional version and retry fields to the existing skill file update contract. - Add a guarded API update with a stable retry receipt and attributed audit event. - Add `update_skill` to native and semantic runner tool catalogs, with mode and policy gates. - Add unit, integration, protocol, and semantic-tool regression coverage. - Document agent use and extend the OpenAPI request contract. ## Verification - Focused tests and direct server and runner TypeScript checks passed before this PR. - `git diff --check` passed after the rebase onto `master`. - CI passed on the latest PR head, including the full test matrix, typecheck, and build. Local full typecheck and build stopped because `cargo` is not installed. The local full test run ended without a verdict. - No dedicated end-to-end eval scenario was added or run. The protocol coverage and semantic-tool test cover the new action deterministically. - Reviewers can read a skill version, call `update_skill`, repeat the same key, then try a stale version and a changed-input key. Only the first edit must create a new version. ## Risks - File writes and database transactions must stay in sync when a write fails. The integration tests cover failed writes and retry behavior, but CI must verify them on the PR head. - Existing Skill Studio callers do not send the new optional coordination fields. Their request shape remains valid. ## Model Used - OpenAI Codex CLI assisted with this change. The runner did not expose the exact model ID or context window. The agent used code execution and repository 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; exact model ID and context window were not exposed) - [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 (focused tests; full suite is pending CI) - [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 (53 pass, 4 skip on the latest head) - [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>	2026-10-03 12:37:55 -05:00
DottaandPaperclip	b17019e14d	fix(agents): reduce default instructions and qualify stock harnesses (#14948) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Its adapters supply task context and access to Paperclip skills and tools. > - The default hire manual and shared prompts also repeat general work procedures. > - Those procedures overlap with stock provider instructions and the Paperclip skill. > - Existing E2E fixtures supply a QA manual, so they do not qualify the production default. > - This pull request reduces the generic instructions and adds real default-hire coverage. > - The benefit is less competing guidance, with inspectable evidence for preserved skills and task context. ## Linked Issues or Issue Description Refs: #14920. That merged change preserves native Codex base instructions. This PR covers the default manual, shared legacy prompts, operational skill guidance, and the narrowly approved ACP skill-discovery/session-environment repair for measured delivery and credential-persistence failures. **What existing behavior does this improve?** New non-CEO hires without a custom bundle and legacy task/chat startup and continuation prompts. **Current behavior** The shipped default manual contains 602 words. Generic task/chat prompts and ordinary resume deltas repeat work procedures already available through the harness and Paperclip skill. **Proposed behavior** The default manual contains only the eight-word company identity. Shared startup prompts retain identity and connection guidance. Ordinary resume deltas retain current work context without the generic execution contract. **Reason and benefit** Let the stock harness guide general work. Keep Paperclip-specific capabilities and independently test default hires, skills, ordered comments, and chat restart. **Breaking changes** New default hires receive less guidance. Existing saved manuals, explicit custom bundles, CEO templates, and specialized wake contracts retain their behavior. The obsolete includeExecutionContract option remains accepted for source compatibility. ## What Changed - Reduce the default hire manual to one sentence. - Reduce shared task/chat defaults and remove the generic ordinary-resume contract. - Keep connection guidance, auth, skills, custom prompts, and specialized wake context. - Add credential-free instruction-boundary gates and 26 explicit Product E2E cells across eight legacy/native profiles, including two focused Paperclip-storage cases. - Capture public hire receipts before providers run, then grade delivered prompts and independent task/chat outcomes. - Add an early legacy skill API recipe for saving a task document, checking the saved revision receipt and linking the document. Improve stock task/heartbeat skill-selection metadata and show a clickable Markdown UI-link example. Keep native tool completion separate. - Advertise bounded routing descriptions and exact successfully staged SKILL.md paths in legacy ACP Claude; keep full bodies on demand and preserve remote path rebasing. - Remove only the provider environment from copied persisted ACP session records, while loading current run credentials and preserving all other options/conversation state. - Regenerate both capability metadata inventories and reject stale manifests/inventories before provider admission. - Publish the original reduction and focused skill-repair comparisons, preserving all failures, automatic recovery, cost coverage and limitations. ## Verification **Behavioral qualification remains pending.** Original legacy ACP Claude loses the issue document only in the reduced cohort beneath an unchanged credential failure. A source-backed diagnosis finds that neither ordinary assignment reads the staged operational skill, while the runtime persists provider environment in session state. The new common repairs expose skill metadata/path and omit persisted env; strict document and credential guards stay intact. [Inspectable diagnosis and retained hashes](https://github.com/paperclipai/paperclip/blob/9f654db4541d3d002769c988f6e51fc0b08dadbd/doc/plans/2026-10-03-legacy-acp-claude-readiness.md). Current repair head `de0965984ff3edf611ae6d0e7ca5c7d5ae3947bb` incorporates master `569c7203aa24b95440682983ce7940ba1d4247bd` (merged #14961/#15007). All 222 affected adapter tests, adapter-utils/E2E typechecks, and final 96 variant/grader/retry calibrations pass. The frozen historical comparator is `c25697f4260b6f3adfea143c3ae9932e2f42986d`: 8,280 of 8,291 paths identical, exactly two production instruction paths plus nine declared unit expectations differ. The operational skill/discovery/environment repairs, selected model/profile/task/core grader/auth/permissions/retry policy are identical. Both actual launcher prepare→verify admissions pass with zero providers. [Immutable manifest and exact receipts](https://github.com/paperclipai/paperclip/blob/9f654db4541d3d002769c988f6e51fc0b08dadbd/doc/plans/2026-10-03-legacy-acp-claude-evidence/manifest.json). One original legacy ACP Claude cell per variant is authorized, with enforced single campaign attempts, 12-minute deadlines and company/agent 1,000-cent hard stops; every product recovery run/cost is counted. Actual live outcomes are pending. Current normal CI has one failed server shard and failed aggregate verify under diagnosis; other normal gates including typecheck/build/Rust/all eight browser shards pass. Fresh review completed successfully; the valid historical startup/resume masking finding was fixed with per-invocation task/chat checks and strict complete-snapshot capture, calibrated and resolved. Prior heads, failures and campaigns below remain historical evidence, not checks on this repair head. - Prior head `36aa4d81c49a1a8f6f04b1a068fae19aa901955f` is replayed on merged hiring master `862a5758ba0e88a33232c1f1fa645e85c38a3113`. All 52 current-head checks pass with two intentional Storybook skips, including repository typecheck/test/build and the browser shard. Fresh Greptile is 5/5 with zero unresolved review threads. Exact-head stock prerequisites pass 599 assertions (598 TypeScript + 1 Rust), all six gates and retained receipt verification, zero providers/source errors. Fingerprint `a7f5a22d860a88fe20cce213c6d5e0004788f32c8363930729aea4fd740ad16d`. Combined catalog/hiring calibrations pass 67 assertions, E2E typecheck and 26-cell stock discovery pass. Canonical contract/inventory checks and the later issue-derived reference calibration are retained; that reference-only follow-up is not live-qualified by earlier frozen runs. - Prior full repository typecheck/build passed. The complete local Vitest run executed 14,956 tests: 14,870 passed, 83 skipped, three timing failures. All three affected files passed unchanged narrow reruns; original failures remain retained. Current-head CI now passes the full general checks; the original local failures remain retained. - The original 24-pair default-manual/shared-prompt comparison has two new overall classic Claude/OpenCode document-delivery failures plus an additional legacy ACP Claude document loss beneath an unchanged credential-guard failure (not closed by later runs), two newly passing OpenCode ordered cases, seven unchanged failures and 13 unchanged passes. Equal 15/24 totals do not establish behavioral equivalence. [Complete original report](https://github.com/paperclipai/paperclip/blob/875f4c397d9e8c3f12f39dedd59abaf1eaf5236e/doc/plans/2026-10-02-stock-harness-live-comparison.md). - The skill-only repair holds the eight-word manual/shared prompts and merged #14920 fixed. All four matched profile configurations and 203 fixture/behavior files match. Candidate `abd0b628ca642c09a54a4edc56a5227402f6686e` varies only the two skill sources against baseline `bc83fe030234439ac51279502a28803958963e2e`. [Candidate workflow](https://github.com/paperclipai/paperclip/actions/runs/37060885547) and [baseline workflow](https://github.com/paperclipai/paperclip/actions/runs/37060888047) each pass 571 exact-source prerequisites before providers; all eight cells clean up successfully. Failed campaigns publish successfully and remain failed. - Repair pairs: Claude original Fail → Pass; Claude explicit Pass → Pass; both OpenCode cases Fail → Fail. Explicit OpenCode's handoff worsens beneath the unchanged failing UI-link grade: baseline gives a clickable API URL, candidate gives a code-formatted path without an anchor. The request's usable-link wording is narrower in the UI-only oracle. [Complete repair report and safe projection](https://github.com/paperclipai/paperclip/blob/875f4c397d9e8c3f12f39dedd59abaf1eaf5236e/doc/plans/2026-10-02-legacy-document-skill-repair.md). - The subsequent narrow stock metadata/link correction has two matched Pass → Pass cases, zero new machine failures/passes and no pending pairs. Both original-case handoff links remain deficient: candidate uses a wrong PAP prefix, baseline supplies a bare prefix-less slug path; the preserved original oracle only requires a durable document. Both explicit clickable UI-link cases pass revision/content/link grading. All four exact-source 587-check gates, single assignment runs and cleanup pass. This does not establish fix causality because baseline also succeeds. [Candidate workflow](https://github.com/paperclipai/paperclip/actions/runs/37069547401) freezes `fe9dc1e3c518825242ed889ab9c8352986f8c2ed`; [matched baseline](https://github.com/paperclipai/paperclip/actions/runs/37069552374) freezes `0d7ecfa96d72fba79b7f0a25052b42c0686c0488`. This is a skill-only comparison with reduced manuals/shared prompts held constant, not a repeat of the historical-manual comparison. Only original and clarified explicit classic OpenCode cases are selected, two per variant/four expected turns. 8,242 other tracked files and both profile hashes match; protected workflows admit each exact source before credentials. [Complete qualification report](https://github.com/paperclipai/paperclip/blob/74d0d3d945f4c52d0814b5a845ab5bd09f33cd6b/doc/plans/2026-10-02-opencode-skill-routing-link-qualification.md). Candidate original loads Paperclip/reference before saving publicly; baseline original loads it after writing locally, then saves publicly within the same assignment. Reported cost totals are $0.0107824490 candidate / $0.0107909015 baseline, with unmetered runtime. The later reference-only issue-derived link correction is provider-free calibrated and **not live-qualified** by these frozen runs; no further paid runs. - Retained tool calls show the repaired original OpenCode assignment loads only its assigned output skill before writing locally. Operational Paperclip is first loaded during automatic disposition recovery; its early recipe is visible then, but it never saves the missing document. Explicit candidate loads Paperclip and reads the new reference before saving successfully. All nine actual runs are counted. Reported LLM totals are $0.3802537209 baseline and $0.4918990161 candidate; local runtime is unmetered. - Initial setup, packaging, cancelled/missing-cell recovery, callback test and relative-output attempts remain retained. No completed provider failure was rerun. Frozen measurement branches are unchanged by later canonical metadata maintenance. - Run `pnpm test:e2e:runner:stock-harness`, `pnpm test:e2e:runner:unit`, and `pnpm test:e2e:runner:typecheck`. Select `stock-harness` explicitly for paid execution; it is excluded from `--all`. Prior-head integration: `36aa4d81c49a1a8f6f04b1a068fae19aa901955f` replays this PR on merged hiring #14985 (`862a5758ba0e88a33232c1f1fa645e85c38a3113`), preserving the four explicit custom-CEO-bundle checks, minimal generic manual boundary, and both suites. The combined fixture catalog and hiring calibrations pass 67 assertions; exact-head stock prerequisites pass 599 assertions (598 TypeScript + 1 Rust), all six gates and retained-receipt verification, zero providers/source errors, fingerprint `a7f5a22d860a88fe20cce213c6d5e0004788f32c8363930729aea4fd740ad16d`. E2E typecheck and 26-cell stock discovery pass. Fresh current-head CI passes all 52 checks with two intentional skips, and fresh Greptile is 5/5 with zero unresolved review threads. The prior source-plan browser failure is retained: a deterministic process fixture replayed its last `fixture:plan` command on `chat_task_completed`, writing revision 2 with identical body after the approval handoff. This was not paid provider execution. Rebased current-head CI passes the same assertion without an old-head retry or a change to that browser fixture. The merged hiring change was measured separately on immutable matched unions, with this reduced/shared/operational context and native completion guidance held constant. [Complete original two-profile report](https://github.com/paperclipai/paperclip/blob/f0512647656be78e48abd8c22a3078db8bf6bcd2/doc/plans/2026-10-02-hiring-template-live-comparison.md): [candidate](https://github.com/paperclipai/paperclip/actions/runs/37075466208) / [historical baseline](https://github.com/paperclipai/paperclip/actions/runs/37075469463), 705 provider-free prerequisites each. Both pairs are unchanged Fail → Fail on the exact-five count, with six core delivery checks passing all four cells; 28 actual successful runs include eight automatic completion wakes, zero retries, four successful cleanups. Source-read coverage is uncomparable, actual model charges unknown. Separately versioned provider-free accounting remains analytical work; original verdicts are preserved. This does not rerun or qualify the completed default-manual or native campaigns. ## Risks - Legacy ACP Claude's additional delivery loss is not closed by any later matched run and blocks the no-extra-failing-behavior merge criterion. Legacy document delivery may have relied on the prior manual/shared prompts. The early skill repair improves Claude in one trial; the later OpenCode pairs pass in both variants and cannot establish causality or robust recovery. Both original-case links remain deficient beneath the storage-only grade. The later issue-derived reference correction has only provider-free validation. Native finish/block descriptions must not be supplied to legacy agents. - The comparison holds merged native Codex fix #14920 constant; it cannot measure that fix's before/after task performance. - These bounded skill/context/chat workflows do not measure general coding quality. Unrepresented providers remain unqualified. - Saved manuals and old Codex sessions are not automatically migrated. Codex through ACP still has a separate base-instruction follow-up. ## Model Used OpenAI Codex, GPT-6 family as identified by this session. The exact deployment ID and context-window size are not exposed. The assistant used reasoning, repository tools, code execution, and delegated PR/eval work. ## 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 (relevant suites and all three unchanged narrow reruns pass; complete-run timing failures retained in Verification) - [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 on the new repair head (prior-head checks retained above) - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups on the new repair head - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-10-03 12:32:42 -05:00
DottaandPaperclip	d034ba7491	fix(interactions): derive question storage from canonical forms (#14946) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents request human input through durable issue interactions. > - A question form has a canonical presentation and a compatibility storage format. > - The creation API required agents to write both formats. > - Tool guidance told agents to split text and choice questions across those formats. > - This pull request accepts one complete canonical form and derives storage fields on the server. > - The benefit is a complete question card with stable answer and retry behavior. ## Linked Issues or Issue Description Related work: Refs #13630 and #14430. PR #13630 addresses the display of historical partial forms. This change fixes creation and keeps the check that rejects conflicting new forms. **What happened?** A question save supplied three compatibility questions and one canonical text question. The API correctly rejected the incomplete canonical form. The Runner's tool description encouraged this split. Sending only a complete canonical form also failed because the API required compatibility questions. **Expected behavior** An agent sends one complete `payload.questionSet` with every text and choice question. Paperclip derives `payload.questions` for storage and answer compatibility. Existing legacy requests remain valid. Explicitly conflicting dual forms remain invalid. **Steps to reproduce** 1. Call `paperclip_request_human_input` with `interactionKind: "questions"`. 2. Send `payload: { version: 1, questionSet: ... }` with a required text question and a required choice question. 3. The old API rejects the missing compatibility questions. With this change, it stores both questions and preserves the canonical form. 4. Retry with the same idempotency key. Confirm that only one interaction exists. 5. Submit both answers. Confirm that the normal resolver and continuation rules apply. **Paperclip version or commit** The branch is based on `cf8ad63c8`. The problem affects the native Runner and the interaction creation API. **Deployment mode** Server deployment with the native Paperclip Runner. Integration tests use the real interaction service and an embedded test database. ## What Changed - Add one shared canonical-to-storage projection. Reuse it for native harness question requests. - Accept canonical-only question creation at the shared validator and server boundary. - Export the input type and update the plugin SDK and its RPC contract. - Advertise a typed, complete question form in the live and scenario tool schemas. - Enforce canonical text and custom-answer constraints before ordinary or native resolution. Preserve harmless display whitespace. - Run regex matching in isolated workers with a deadline and resource limits. Both answer paths await the result before persistence. Saved native delivery uses the validated answer without taking another worker slot. - Update agent guidance and generated Runner contracts. - Test mixed forms, option-ID collisions, retries, answers, legacy requests, and conflicting forms. ## Verification - Interaction service, HTTP route, native bridge, and Runner authority suites: 221 tests passed after correcting an obsolete tool-description assertion. - Shared validator, plugin SDK, CLI, and UI compatibility suites: 67 tests passed. - Runner core tool-contract suite: 20 tests passed. AJV validates live and scenario schemas. - Final review regressions: 172 shared, service, native bridge, and authority tests passed. These cover text length, pattern, numeric limits, whitespace, custom option IDs, and historical pending cards. - Runner session suites: 67 tests passed. Published example tests: 4 tests passed. - Server typecheck and the shared/server builds passed after the compatibility fixes. - Final delivery verification: 35 response-delivery tests passed. The native delivery regression proves saved answers do not enter pattern workers; server typecheck and build passed. - Pattern security and answer-flow verification: 205 tests passed after repairing the child fixture loader. These cover pathological matching, event-loop responsiveness, worker concurrency, slot cleanup, HTTP routes, native delivery, and the full helper in a child process. - `pnpm -r typecheck` passed on the bounded-worker revision. - `pnpm build` passed on the bounded-worker revision. - All 55 GitHub checks passed on `fe457af`; four optional jobs were skipped. An unchanged Cursor adapter test timed out once in CI, passed locally, and passed on one failed-job rerun. - Reviewers can send the canonical-only mixed form above and verify that the saved interaction contains both canonical and compatibility questions. ## Risks - The creation API accepts a new input shape. Stored rows and answer contracts keep the existing shape. - The shared projection must preserve synthetic free-text option IDs. Collision and native round-trip tests cover this behavior. - Historical partial rows remain readable. New conflicting dual forms, including written-answer mismatches, remain rejected. - Existing pending cards retain the written-answer paths offered by their stored options. Canonical text constraints still apply. - Ordinary answers now enforce declared canonical constraints before persistence. Invalid answers leave the card pending. - Regex validation has a one-second deadline and a four-worker capacity limit. A complex pattern or capacity error leaves the card pending with a validation error. - No database migration or change to company authorization is required. ## Model Used - OpenAI GPT-6 through Codex. The session exposes the GPT-6 model family; its exact runtime model identifier and context window size are not exposed. Used reasoning, tool use, and code execution. ## 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>	2026-10-02 14:21:11 -05:00
DottaandPaperclip	018993140f	feat: let agents name prompt-only tasks (#14761) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Users create tasks with a title and a description. > - A required title adds work when the prompt already explains the request. > - An agent can name the task once it reads that request. > - This pull request accepts prompt-only tasks and starts them with a short prompt slice. > - A scoped title tool lets the assigned agent replace that slice early without changing execution state. > - A live browser eval checks the real agent call, saved title, audit entry, and preservation of user titles. ## Linked Issues or Issue Description **Subsystem affected** Cross-cutting: task creation, shared contracts, database, server, runner tools, and board UI. **Problem or motivation** Users must currently write a title before they can submit a detailed task prompt. The agent has enough context to write a useful title itself. **Proposed solution** Make the title optional when a description is present. Save the first 120 characters of the normalized prompt as a provisional title. Ask the assigned agent to call `set_task_title` early. Use an atomic provisional-title guard to preserve titles supplied or edited by users. Keep explicit titles supported. Related: #14543 and #14556 concern empty-title submission. This change intentionally enables that submission when a prompt is present, instead of requiring a title. ## What Changed - Add the `titleNeedsGeneration` field with an idempotent migration. Keep existing titles unchanged. - Add `PUT /api/issues/:id/title` and the native and legacy `set_task_title` tool. Enforce company access, active-run ownership, shared, bounded retry receipts across native/HTTP calls, and transactional audit logging. Refresh external-object links after commit, with the same feature gate and plugin detectors as ordinary title edits. - Add early naming guidance in Standard, Ask, and Plan task context. Preserve the description, status, and assignment. - Allow prompt-only root and child task creation, plus draft restoration in the New Task dialog. Keep user titles supported. - Add an opt-in Product E2E suite for prompt-only Standard and Ask tasks, plus an explicit-title control. It checks actual provider calls within the first five tools, persisted state, audit attribution, and the reloaded UI. - Preserve a closed vocabulary of API key maintenance phrases in declared prose while rejecting opaque credential suffixes. Add one bounded naming retry after wording is rejected, without treating the rejected call as a saved title. - Repair the native cleanup receipt check exposed during full verification: accept matching input digests, retain legacy input checks, and reject conflicting receipts. ## Verification - Live Product E2E on `f43478473800e3a46b85c5ee79677efdb15108e7`: **3/3 passed** with native Codex `gpt-5.4-mini`, first attempts only, automatic retries disabled. Standard and Ask each saved “Rotate expired API key” on their first tool call, with matching persisted state and a single same-run audit entry. The explicit-title control retained its user title with zero title writes. All three verified the reloaded browser UI. - Campaign: `local-2026-09-30T21-30-11-021Z`. Earlier failed campaigns are retained separately; they exposed credential-prose handling and prompted the naming recovery fix. No failed result was regraded or deleted. - Reproduce with `pnpm test:e2e:runner -- --id task-titles.runner-codex-mini.local.prompt-title-standard --id task-titles.runner-codex-mini.local.prompt-title-ask --id task-titles.runner-codex-mini.local.preserve-explicit-title --max-automatic-retries 0` and an authorized provider key. - Full `pnpm -r typecheck` and `pnpm build` passed on the latest commit. The runner build used the configured external eval source tree. - Product E2E unit suite: **61 files, 818 tests passed**; E2E typecheck and UI token gates passed. - Title API/native regressions cover prompt-only and explicit child creation, user edits, ownership/company isolation, external reference refresh, cross-surface retry replay, and the 64-key limit without receipt eviction. All passed. Prompt-context coverage: **44 tests passed**. - Rust credential regressions: **35 tests passed**, including benign maintenance qualifiers and opaque credential rejection in every declared prose field. Catalog/report reconciliation: **28 tests passed**. Native recovery: **560 tests passed**. - Broad local `pnpm test:run`: **14,555 tests passed** in the general server group; two suites failed to initialize embedded PostgreSQL and the existing 40,000-file Git streaming stress test exceeded its 300-second macOS timeout. All three suites then passed in isolation (**5 tests passed**) without code or timeout changes. The original full local command exited nonzero and is not being represented as a clean full run. - Latest-head GitHub checks are green: **53 passed, 4 skipped, zero failed or pending**, including all test shards and the canary packaging dry run. Greptile reviewed the same commit at **5/5**, with zero unresolved review threads. ## Risks - The additive database field must reach the server and UI together. The migration uses `IF NOT EXISTS` and defaults existing tasks to a final title. - Title generation depends on the assigned agent running. Tasks without a run keep their provisional title. - Live qualification covers the native Codex path in Standard and Ask modes. API/legacy and Plan behavior have deterministic coverage. - The credential-prose exception validates the entire suffix against a closed maintenance vocabulary. Unknown suffixes, assignments, quoted values, credential prefixes, and diagnostics retain strict checks. ## Model Used OpenAI Codex, based on GPT-6, with reasoning, tool use, and code execution. The exact deployment ID and context window are not exposed in this session. The live eval uses the native Codex `gpt-5.4-mini` profile. ## 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>	2026-09-30 16:48:24 -05:00
DottaandPaperclip	3c561642b4	fix(chat): resolve approvals and preserve unanswered questions (#14613) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents ask for decisions and optional details through cards in chat. > - A clear approval in a message can leave the matching card pending. > - An unanswered question can also block an unrelated later reply. > - Decisions need a saved source message, while optional questions need to remain answerable in history. > - This pull request records conversational decisions and lets users move on from questions and answer them later. ## Linked Issues or Issue Description **What happened?** Native Claude and Codex could act on approval in chat while the original approval card stayed pending. Pending question forms stayed above the composer, were absent from history, and could suppress later chat replies. A late native question answer could wait for a finished run to reconnect. **Expected behavior** The active agent records a clear approval or refusal against the exact card and user message. Ambiguous replies do not grant consent. Users can send another message without answering a question. The question remains pending in history and can be reopened and answered later. The saved answer reaches the agent. **Steps to reproduce** 1. Ask an agent to propose work with a confirmation card, then approve it in chat. 2. Check that the original card records that approval before work starts. 3. Ask an interactive question, send an unrelated message, and reload. 4. Open the unanswered question from history and submit an answer. Related work: #14408 added completion delivery. #14607 tests completion reporting turns. Neither records conversational answers on approval cards. ## What Changed - Add a confirmation endpoint backed by a user comment, with schema validation, OpenAPI discovery, and native Plan-mode access. Ask mode remains read-only. - Check company, active run, actor, current session, message provenance, revision, and resolver policy. Save the decision and audit in one transaction. Retries do not repeat effects. Emit resolution telemetry after commit. - Give fresh and resumed chat turns the actual pending confirmation identities. Teach agents to save clear conversational decisions before acting and to clarify ambiguity. - Keep unanswered Agent Chat questions as compact history entries. A newer user message closes the old form. Question cards never contribute to composer pending counts or navigation, including after dismissing a fresh form. The history card is the sole reminder; clicking it restores that exact form and draft. - Preserve Agent Chat questions when later messages or questions arrive. Historical ordinary inputs no longer gate later chat replies. Current-run requests, task execution, and governed approvals keep their gates. Remove the special acknowledgement-publication proof helpers that this rule replaces. - Route answers to finished native runs through durable fresh-wake delivery, with existing idempotency and source-question context. Settle late replies against contiguous completed conversation turns and freeze their history replay; failed, unhandled, and newly arriving messages remain actionable. - Add real-component Storybook scenarios, database and UI regressions, and a three-turn native Claude/Codex E2E case. Capture distinct, UI-ready screenshots and report the individual assertions. ## Verification - Focused decision/publication/UI regressions after merging master: 288 passed; subsequent UI draft, failed-send, and conversation checks: 199 passed. - Native question and durable delivery regressions: 106 passed, including all four terminal run states and exactly-once late delivery. Seven targeted regressions fail against the original implementation and pass with the fix. - Latest conversation/decision/native-delivery regressions after the master merge: 121 passed. Covers completed progress, missing or failed intervening turns, new messages during a late reply, stale sessions, and frozen retry/replay boundaries. Four new assertions fail before the ordering fix. - E2E support suite after the master merge: 792 passed. Negative controls reject expired cards, wrong questions/answers, stale or missing replies, unrelated clarification forms, and unexpected tasks. - The embedded-browser walkthrough caught one additional defect: dismissing a fresh question still showed a composer badge. Both Cancel and close-button regressions failed before the fix. The fix at `65f2ade12` passes 170 chat-thread tests and 792 E2E support tests. After merging master, 232 chat-thread/confirmation tests, server/UI typechecks, and token gates pass. The preview and two-provider live E2E pass at `e5512a206`; Greptile is 5/5 with zero unresolved threads at that commit. All 55 checks are now successful at `e5512a206` (four conditional checks skipped), including the aggregate verification gate and clean-install canary test. The first attempt was interrupted by simultaneous CI worker shutdowns; one failed-job rerun passed without code changes. - [Published Storybook](https://d1p6rlowie26tp.cloudfront.net/storybook/branches/codex~2Fchat-approval-resolution/?path=/story/chat-comments-agent-chat-unanswered-questions--moved-on): nine real-component scenarios. Manually exercised move on, reopen, preserve draft, answer later, answer one of multiple questions, and a custom mobile answer in the embedded browser. Retested fresh Cancel and close-button dismissal in the updated build, then reopened and submitted the preserved Green selection and inspected its answered receipt. Static preview has no live model/backend; its callbacks are fixture responses. - [First live campaign](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36714504406-1/) reproduced the late-answer completion-state defect on both providers despite correct saved answers and acknowledgements. It also exposed a valid imperative clarification rejected by the old oracle. Both issues are fixed with regression controls; this failing run is retained as evidence. - [Four-cell qualification](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36717804064-1/) passed 4/4 at `2bf8a1009`: unanswered-question return and ambiguous confirmation, each on native Claude and Codex. Inspected saved state, source-message decisions, visible cards, and agent replies. Both late-answer chats settled to waiting; no unrequested tasks were created. [Final branch rerun](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36719666238-1/) passed 2/2 at `142630720`: the same unanswered-question journey after merging master, plus an additional screenshot and browser assertion for the actual late-answer acknowledgement. - [Composer-reminder E2E](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36727006818-1/) passed 2/2 at `5b62c52d9`: native Claude and Codex, three turns each, with explicit no-badge assertions before and after reload. Inspected saved pending/answered state, both screenshots with a clear composer, and actual Blue acknowledgements; all five behavioral matchers passed per provider and neither created tasks. Cost coverage is partial; this is bounded workflow qualification. - [Fresh-dismissal E2E](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36742773318-1/) passed 2/2 at `e5512a206`: native Claude and Codex, including fresh Cancel, clear composer, reopen, unrelated message, reload, late Blue answer, and actual agent acknowledgement. All five behavioral matchers pass per provider. Inspected the fresh-dismissal screenshots and saved pending/answered identity; neither created tasks. Cost coverage is partial (4/6 runs). - Prior evidence remains available in [the earlier campaign](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36642252725-1/). Its early loading screenshot and overwritten final capture prompted the UI-ready, distinct screenshot fixes. ## Risks - The model interprets intent. The server verifies permission and provenance; it does not infer consent from text. Ambiguous and unrelated replies are not approvals. - Historical questions can accumulate. They remain visible, pending, and answerable; no automatic answer or expiry is invented. - The change to completion gates is scoped to Agent Chat and ordinary historical inputs. Current-turn and governed approvals retain their existing controls. - Live qualification is limited to the selected stories. Broader native onboarding finalization remains separate work. - No database migration. Telemetry adds no fields or values; the contract and README document the commit boundary. Privacy review was requested on the PR. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, repository tools, code execution, and browser-test orchestration. The exact model ID and context-window size are not exposed to this session. ## 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>	2026-09-30 11:46:46 -05:00
DottaandPaperclip	d30b03bd8c	test: add persistent E2E coverage for human blocker decisions (#14707) ... ## Thinking Path > - Paperclip manages work for AI agents. > - Agents use the coordination skill when work needs human authority or a scope decision. > - PR #14188 replaced automatic manager escalation with direct blocker handling. > - This behavior needs real browser, server, database, and provider tests. > - The test must verify saved human input, task ownership, and resumed work. > - This pull request adds six reusable Product E2E cases and improves the skill examples that they exercise. ## Linked Issues or Issue Description Refs #14188. The merged change needs repeatable behavior coverage. The new suite tests missing administrator access, missing hiring permission, and requester scope questions. Searches found no duplicate blocker-guidance suite. This extends the existing eval system described in ROADMAP.md. ## What Changed - Add the explicit-only `blocker-guidance` Product E2E suite. It has three local scenarios on legacy Codex and legacy Claude. - Use the production UI and public APIs to create work, save a human-only question or confirmation, answer it after reload, and resume the same task. - Check requester identity, ownership history, manager activity, hiring, saved answers, and completion. Keep direct text input as a separate UX result. - Save pending and final screenshots, API checkpoints, skill hashes, provider evidence, and billing data through the existing report pipeline. - Isolate the Claude fixture home. Verify the served skill bytes before dispatch so an old installed skill cannot silently replace the evaluated skill. - Improve the coordination and hiring skill examples. Include the human-only policy, requester address, wake behavior, and handling of authorized scope changes. - Grader v5 requires the exact approved public welcome note as a new worker comment. Browser input checks reject unwritable scope cards before clicking, and confirmation direction must be saved in the resolution before the worker wakes. - Add grader calibration and browser-input tests. Update the fixture guide and generated capability inventories. ## Verification - `pnpm build`: passed after rebasing onto current master. - `pnpm -r typecheck`: passed. - `pnpm test:e2e:runner:typecheck`: passed. - `pnpm test:e2e:runner:unit`: 742 tests passed. - `pnpm test:e2e:runner:browser-support blocker-input.spec.ts`: 10 tests passed. - `pnpm test:e2e:runner -- --list --suite blocker-guidance`: six cells found. - Capability inventory and generated-contract checks: passed. - `pnpm exec vitest run server/src/__tests__/hiring-operational-examples.test.ts`: four tests passed after synchronizing the generated API reference and section anchor. - Full general and serialized test suites: passed in CI on `6652cee74517039676bad6a720f213625d265acd`. The redundant local `pnpm test:run` was interrupted after complete CI coverage passed; it is not claimed as a completed local full-suite run. - Final GitHub checks: 54 passed, two optional Storybook checks skipped. The runtime-exposure startup test hit a 10-second readiness timeout once, passed a targeted local reproduction, and its CI shard passed the single retry without code changes. - Current-head Greptile: 5/5, clean check, zero unresolved threads. - Historical live measurement on September 29 at `4edc77ae2b95b10dd61426ce3f042bac00527ad9`: three independent six-cell runs scored 5/6, 6/6, and 6/6. Claude Sonnet 4.6 passed 9/9. Codex `gpt-5.6-sol` passed 8/9. These runs predate this rebase. - Version 5 changes the scope answer to an exact approved publication draft. The historical runs do not qualify that new requirement; the two-provider scope pilot at `49a1f4eab369948b9e3b34a6ce436489e875e4ec` passed Codex and failed Claude. Claude posted the correct salary-free sentence but omitted its required reference line from that comment, placing the reference in a separate completion message. The `public-welcome-note` check correctly failed. An earlier Claude database-startup failure was retained separately; its fresh-instance retry reached the model. This pilot is not a six-cell qualification. - The failed Codex scope case omitted `addresseeUserId`. The strict routing check remains. All 18 attempts had clean evidence manifests and passed cleanup. - To repeat with provider credentials: `pnpm test:e2e:runner -- --suite blocker-guidance --max-parallel 1`. This is a paid, opt-in suite and is excluded from `--all`. ## Risks - The live suite measures variable model behavior. The retained 17/18 historical result and the current 1/2 scope pilot are not all-pass qualifications. These paid cases are opt-in; their observed model failures remain visible independently of deterministic CI checks. - A separate generic task-replacement diagnostic still exposed a Claude refusal. The ordinary cases use specific business decisions. The diagnostic is not a standalone catalog case in this change. - Earlier measurements included an old installed Claude skill and test defects. Their grades remain retained and are not combined with the three final repetitions. - Skill examples can affect when agents ask for human input. Downstream permission checks still apply. - Native runners, Daytona, agent-requester routing, and real external connection authorization are outside this suite. - Raw provider traces and credentials remain private. No screenshots, raw reports, secrets, workflow changes, or lockfile changes are committed. ## Model Used OpenAI GPT-6 through Codex assisted with this change. The exact deployed variant and context window size are not exposed in this session. The assistant used reasoning, repository edits, tool use, and shell execution. The evaluated models were `gpt-5.6-sol` and `claude-sonnet-4-6`. ## 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>	2026-09-30 07:56:54 -05:00
DottaandPaperclip	2de43fc909	fix(issues): keep agent mentions as context and defer personal app authorization (#14577) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Each task has one assignee. Explicit assignment and review requests select who should act. > - An agent mention started another agent on a task it did not own. Native attachment staging then rejected that run. > - Allowing that run through startup could also let two agents work on the same task. > - Mentions should identify relevant context. They should not start work or forward comments to other tasks. > - A personal app installed on a shared agent must also wait until tool use to resolve the current user's grant. > - This pull request removes mention dispatch and keeps missing personal app credentials from blocking startup. ## Linked Issues or Issue Description **What happened?** A native agent mentioned on another agent's task failed with `paperclip_runner_attachment_staging_not_authorized`. The source task could already be complete. A nearby optional-app warning was a separate problem: personal app tools were excluded when their shared health state required attention. **Expected behavior** An agent mention is context only. It does not wake the agent, take ownership, or copy a comment onto another task. Normal feedback still reaches the assignee. Assignment and explicit review requests still dispatch work. An unavailable personal app does not block startup or produce a startup warning. Tool use requests the current user's authorization and never uses another user's grant. **Steps to reproduce** 1. Assign a task to agent A. Post a comment that mentions agent B, including a comment that closes A's task or references B's child task. 2. Confirm the comment retains its agent link and B receives no run or deferred wake. A can still receive normal feedback. 3. Install an active personal MCP connection on B. Give only Alice a grant and leave shared health at `error`. 4. Explicitly assign work to B for another user. Confirm it can finish without using the app. 5. Ask B to use the app. Confirm its tool call shows an inline connection request for the current user. Related work: Refs #11144. This change uses the existing execution-time personal grant resolution. ## What Changed - Remove mention dispatch from standalone comments and issue updates. Remove implicit forwarding of parent comments to a mentioned worker's child task. - Ignore new requests with the legacy mention wake reason before creating a run or deferred request. Preserve already accepted queue entries, which can combine assignments and feedback with a later mention. - Remove the native mention admission, staging, and finalization exceptions from this PR. Native task ownership checks remain intact. - Keep active, installed personal app tools available despite shared health errors. Remove optional-app startup warnings. Tool execution retains the current user's grant and policy checks. - Update agent instructions and product/API docs. Refresh generated capability source anchors. ## Verification - Red: comment-route regressions reproduced extra agent wakes and child comment forwarding. A separate regression proved that cancelling by the last coalesced reason could drop an accepted assignment. - Green: the targeted route, wake queue, heartbeat, workspace, responsible-user, MCP discovery, and HTTP gateway suites passed. The final queue and heartbeat rerun passed 104 tests, the restored queue adapter passed 56, and both comment-route suites passed 135. These include accepted assignment preservation, rejection of new mention requests, and normal assignee feedback. - `pnpm -r typecheck` and `pnpm build` passed locally. The full local `pnpm test:run` attempt was interrupted for review/CI fixes, so it is not claimed as a completed local pass. It exposed a cleanup timing race in the concurrent-mention assertion, now fixed and verified across 10 repetitions. CI also exposed an obsolete test waiting for the removed mention lookup; it was reproduced and fixed, then both comment suites passed. Final full-suite verification is through CI. - Final head `bd9ea4cb05a8f081c54e017760a8999f9ea6ef44`: 54 checks passed, 2 Storybook checks intentionally skipped; no pending or failing checks. Full CI includes general and serialized suites, all 8 browser shards, runner verification, typecheck, build, and canary dry run. Greptile is 5/5 on this exact commit, with no unresolved findings. - One unchanged Cursor adapter test hit its 10-second CI timeout. All 5 tests in that file passed locally; one retry of its CI shard passed all 674 tests (3 skipped). The aggregate verification gate then passed. No code or timeout was changed for that retry. - Live browser check: inserted a structured mention with the picker on a human-owned task. The saved link remained visible. Database checks found zero new runs and zero wake requests. - Live Codex runner check: explicitly assigned that task with the unavailable personal app attached. The run succeeded and committed completion without using the app or creating a connection card. - Live browser follow-up: asked the assignee to call PostHog and mentioned another enabled agent as context. Only the assignee ran. It succeeded and displayed the existing inline connection card. Only Alice's grant existed; the run belonged to a different user. - The HTTP regression covers tool discovery with no provider calls or connection cards, first use returning the current user's authorization request, and successful retry after that user's grant exists. - App checks use an isolated local fixture and a fake MCP provider. They do not use production app credentials. ## Risks - Intentional behavior change: workflows that used mentions to wake agents must use assignment, a bounded child task, or an explicit review request. - Already accepted queue entries retain their prior rules. An old entry can combine assignment or feedback with a later mention; its last reason cannot safely identify mention-only work. New mention requests create no run or deferred wake. - Personal apps with a shared health error remain discoverable. Actual tool use still requires the responsible user's grant and existing policy gates. - No database migration or public API schema change. ## Model Used - OpenAI GPT-6 through Codex, with reasoning, repository tools, code execution, and browser testing. The exact serving model ID and context-window size are not exposed in this session. - Live native-run verification used `gpt-6-astra` through the Codex provider. ## 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>	2026-09-29 12:49:01 -05:00
DottaandFry	3ca196b0a6	feat(agents): persist agent files across tasks without revision history (#14420) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - An agent needs personal files across tasks and sessions. > - AGENTS.md is one file in that directory. Supporting files need the same persistence. > - The Instructions Editor and agent runs must share one current directory. > - Concurrent runs should apply only the files they change. The last sync of the same file wins. > - This pull request uses existing file transport and removes temporary copies after sync. > - Old instruction-only sessions keep their restore contract. New saves do not create revision history. ## Linked Issues or Issue Description Refs #14325. This replaces its revision-oriented design with persistent agent files. Keep #14325 unmerged. Transport prerequisite #14416 merged first at `d172197117a14b80a1eb2d2835a0e7cce2679656`. This PR now targets master and remains below 100 changed files. Related work: #4513 and #8798 cover instruction tooling. This change handles run synchronization, cross-task personal files, browser editing, and old-session restoration. ## What Changed - Keep one current directory per company and agent. Point AGENT_HOME at a temporary working copy for each active run. Keep task files and provider HOME separate. - Restore text, binary files, and nested folders through workspace transport. Exclude remote agent files from task Git snapshots with a self-ignoring file inside the reserved runtime directory; never write through repository-controlled Git metadata. - Collect after the provider and child processes have stopped. Keep resumable conversation state. - Apply changed and deleted files under the agent lock. The last sync wins for the same file. Unrelated concurrent changes survive. - Remove temporary copies after successful sync, rejected sync, and staging failure. Register ownership before copying so restart recovery can remove interrupted preparation. Retry transient synchronization up to three times. Preserve the original remote lease reference until deletion succeeds; restart cleanup never acquires a replacement sandbox. Do not create captured directories or a conflict-review queue for new runs. - Keep browser editing, stale-draft protection, and streaming binary downloads. Keep the instruction entry and text editor limited to 1 MiB. - Keep historical agent-folder sync failures on their affected runs instead of repeating them above current saved instructions. Preserve legacy candidate review and current browser-save errors. Avoid duplicate quota warnings while retaining separate sync failures when they describe a different problem. - Require target-scoped caller grants for peer instruction access, while preserving self edits, responsible-user checks, and protected-change consent. - Treat full storage as a nonblocking run warning, never an agent pause or run-admission failure. Restore already-over-quota saved folders so ordinary agent cleanup can recover; warn on each run until cleanup. The run detail view shows the warning. - Allow 256 MiB per file, 2 GiB per directory, and 100,000 entries. Hash large files as streams. Check editor-save quotas with metadata instead of hashing unrelated files. - Preserve old native inputs, instruction-only copies, paths, digests, and pending legacy candidates. Adopt old revision heads once. New writes do not append history rows. - Add idempotent migration 0287 and verify upgrades from the preview tables and receipts. - Add nine interactive stories under **Agents / Persistent files**, including automatic incoming edits, stale browser drafts, and storage-limit diagnostics. ## Verification - Merge candidate: `4f5390107ec6ffd80a76d1d2e85530e66f21d079`, after merging current master and the landed transport prerequisite. Integration required no manual conflict resolution; the feature remains 99 changed files. Full workspace typecheck, production build, token gates, and 715 focused tests passed on this merge candidate. Fresh Greptile review is 5/5 with no unresolved findings. All 55 checks passed, with four conditional skips, including the build, typecheck, browser E2E, and canary dry run. A single retry recovered four jobs interrupted by runner shutdowns; no source changes were required. - Historical-warning UI fix: all 6,834 UI tests across 640 files passed, including regression coverage for three old failures, legacy preserved edits, and warnings scoped to the affected run. Full workspace typecheck, production build, Storybook build, and token gates passed. Browser-verified Storybook playtests passed for Historical Failures After Successful Save, Storage Limit, and Full Storage Run Warning. - Review follow-ups at `4e20c9fb2`: all 18 focused tests passed, including external Git directories, linked worktrees, symlinks, hardlinks, and distinct I/O failures alongside storage warnings. Server and UI typechecks, token gates, and the production build passed. - Storage warning regressions at `0724f3012`: all 33 directory tests and all five heartbeat-list tests passed, with no skips in their successful runs. They cover repeated runs while full, an already-over-quota saved folder, cleanup, warnings retained after unrelated save failures, and bounded warnings in large result JSON. Server typecheck passed after the final warning fixes. - Full workspace typecheck, production build, and token gates passed during this follow-up. Product E2E harness: 631 tests passed across 52 files; harness typecheck passed. Earlier native session/context and directory/legacy collection suites passed 537 tests; Runner unit/transport suites passed 329 tests. - **Real E2E at `0724f3012` (before this follow-up):** legacy local Codex and native Daytona Codex each passed six tasks, one server restart, seven independent assertions, and cleanup verification. Both prove browser-to-agent edits, agent-to-browser edits, nested/binary restoration, per-file last-sync-wins, a successful run after an oversized save rejection, and cleanup clearing the warning. - Native local Codex also passed the six-task quota flow before the final warning-retention fixes. That pass began at `918d1ed02` while the bounded-result warning fix was being edited, so it is not claimed as exact-final-head evidence. Its final-head rerun failed during embedded PostgreSQL bootstrap before any provider run: the macOS host had 87,365 of 87,381 SysV semaphores occupied. No unrelated services or kernel limits were changed. - The final-source report intentionally records **2/3 cells passed**, preserving the blocked native-local attempt: `tests/runner-e2e/results/agent-files-quota-final-20260928-report/`. Earlier failed attempts and provenance notes remain under `tests/runner-e2e/results/agent-files-quota-final-20260928-input/` and the original campaign directories. - Daytona used immutable image `ghcr.io/paperclipai/paperclip-daytona-runner@sha256:5643f0d801417cae3581833a1a3bc6715b325e028602738d2652c44cac5dc6bf` and its exact Linux runner binary. Controller source is `0724f3012`; image source is recorded separately. - Legacy-session compatibility and all three ACP Stop/resume browser regressions passed on the prior validated feature head `169fab46d5af21caa2269b4c1b29b69c933a6951`. They assert the same provider session is retained and interrupted writes are not replayed. Migration upgrade tests also passed earlier. - Nine interactive stories are under **Agents / Persistent files**, including **Full Storage Run Warning**. Its playtest and visual browser inspection passed; the warning states that runs continue and the editor remains available. - Prior-head checks on `4e20c9fb2`: 55 passed, two conditional jobs skipped, no failures or pending checks. All eight browser E2E shards and their aggregate passed. Fresh Greptile review is 5/5 with no findings; all review threads are resolved, the security scan passed, and GitHub reports no merge conflicts. - The broad local follow-up test run was interrupted after host semaphore exhaustion affected isolated PostgreSQL instances. It also encountered the existing macOS long-path fixture failure and two timeout failures. This is not a claim that the full local suite passed. Logs are retained; focused storage/warning tests passed. ## Risks - A later sync can overwrite an earlier edit to the same file, including a saved browser edit. There is no text merge or retained version. This is the intended last-sync-wins policy. - A save that exceeds a storage limit is rejected and its temporary copy is discarded. The run itself continues normally, and later runs restore the last saved files with a warning until cleanup. Transient sync failures get bounded retries. An I/O failure partway through a sync can leave some files updated; a failed receipt does not claim whole-folder success. - Larger folders increase copy time, network traffic, and temporary disk usage. Active runs still need working copies. Terminal runs do not accumulate archives. Operators must provision disk for agents and configured concurrency; these limits are not company-wide quotas. - A restored old native session remains instruction-only until a fresh session starts. Its original conflict fence and existing pending candidates remain compatible. - Provider processes close at the collection boundary. Conversation resume remains available, but warm process reuse is lost. - Backups must include the instance filesystem and database. External bundles keep their existing behavior until explicitly moved to managed storage. ## Model Used OpenAI Codex, GPT-6 family. The session does not expose a more specific model ID or context-window size. Reasoning, code execution, and browser tools assisted this change. Real provider E2E uses `gpt-5.6-sol`. ## 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: Fry (Paperclip) <noreply@paperclip.ing>	2026-09-29 08:25:56 -05:00
DottaandPaperclip	3447609d22	fix(runner): stream and page large API responses within capture budgets (#14301) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents use governed API tools to inspect task evidence. > - Large API results become saved assets with short previews. > - Reading an asset through the same tool used to create another asset, so the agent could not reach the rest of the evidence. > - The 10 MiB response cap also blocked useful large results. Removing all bounds allowed excessive disk use. > - This pull request streams responses up to 1 GiB and makes saved text readable in bounded pages. It adds durable run budgets and capture admission limits. > - Agents can inspect complete evidence while tool results, memory use, and capture work stay bounded. ## Linked Issues or Issue Description **What happened?** A large response became an asset. Reading that asset returned another asset and the same preview. Responses above 10 MiB failed before the agent could read any page. **Expected behavior** The agent can fetch a large response and read its saved text to EOF. Each page stays bounded. New snapshots have a generous finite limit and a durable run budget. Existing larger assets remain readable through byte ranges. **Steps to reproduce** 1. Call a GET operation that returns more than 10 MiB of text or JSON. 2. Before the fix, the tool returns `api_transport_failure`. 3. With this change, responses up to 1 GiB become streamed snapshots with artifact references. 4. Read `GET /api/assets/{assetId}/content` with `responseText: {offsetBytes: 0, limitBytes: 8192}`. Follow `nextOffsetBytes` until null. Related work: #14186 added the API fallback tools. #14218 bounded API discovery. ## What Changed - Add authenticated UTF-8 text windows to `call_api`, with byte offsets and total size. Keep each page at or below 24 KiB. - Stream new responses above 24 KiB through private temporary files into company-owned assets. Bound each capture to 1 GiB of decoded bytes. Reject oversized declared lengths before reading and count streamed bytes before writing. - Reserve capture budget in the run record before spilling. Allow 4 GiB per run. Settle successful captures to their actual size. Failed or interrupted captures retain their full 1 GiB reservation. Run restarts do not reset the budget. - Enforce a 20 GiB company snapshot quota with database reservations. Count legacy snapshots and unfinished storage work across runs and processes. Asset deletion frees quota. - Limit large captures to two per company and four per server process. Hold slots through storage upload and temporary-file cleanup. Use a 10-minute download deadline and 30-second connection/idle-read timeouts. - Return explicit size, budget, busy, and timeout errors. Preserve unknown outcomes for mutations whose response cannot be captured. - Read saved assets through authenticated storage ranges, with at most two extra bytes for UTF-8 and EOF handling. Unpaged reads return the existing asset and digest with a bounded preview. Reads create no copies and do not consume capture budget. - Keep existing assets above 1 GiB readable in pages. Use safe integer offsets and PostgreSQL `bigint` asset sizes. - Stream large S3 uploads through ordered multipart requests. Abort failed uploads and remove partial local files. - Revalidate run authority during downloads. Keep company authorization, GET-only text paging, redirect denial, and mutation replay receipts. - Document the separate 10 MiB upload limits. This PR does not raise memory-buffered attachment ingestion limits. Future large video uploads need streamed ingestion and storage quotas. ## Verification - Full workspace `pnpm -r typecheck` and `pnpm build` pass after rebasing on master. - Focused API and response tests: 1,761 pass. Cover declared and chunked oversize responses, incorrect Content-Length, exact-limit success, active-stream deadline, cancellation, cleanup, concurrency admission, and mutation outcome handling. - Real HTTP integration: 28 tests pass, including runnerd → PRP → authority → HTTP, a 12 MiB snapshot, final-page/EOF reads, cross-company denial, a persisted 3 GiB sparse asset, and large mutation receipt replay. - The HTTP suite verifies durable run-budget accounting, simultaneous runs competing for company quota, legacy snapshot accounting, deletion refunds, failed-storage reservations, cleaned-failure refunds, metadata-rollback cleanup refunds, preservation after a lost commit acknowledgement, and small/saved reads after capture-budget exhaustion. - A standalone proof streams exactly 1 GiB through the production capture helper, verifies the final bytes, and removes its temporary file. It uses repeated 256 KiB chunks and records a peak process RSS of 191 MiB. - Earlier storage verification covers exact S3 multipart boundaries, cleanup/abort failures, and a 17 MiB transfer through the real AWS SDK to a local HTTP S3 endpoint. No cloud S3 qualification was run for this follow-up. - The local full test run was interrupted for the company-quota changes. A later targeted run hit exhausted macOS shared-memory slots before tests started; two unattached PostgreSQL segments with dead owners were reclaimed before retrying. All 55 current-head checks pass at `aebb80ceeeee77d5a56b67bfffd835f2f846878c`, including the full CI test suite, typecheck, build, browser suites, security scan, and Greptile (5/5). There are no unresolved review threads. The combined rebased test catalog also passes (48 tests). - Earlier paging acceptance passed Daytona and separate staging at `7739879e9`. Those runs predate the streaming and budget changes. ## Risks - The 1 GiB response cap and 10-minute active-download deadline are intentional product limits. Larger live results must use endpoint pagination or a direct file workflow. Existing larger assets remain readable through bounded ranges. - A durable 20 GiB company snapshot quota counts stored runner-api assets and active/orphan reservations across runs and processes. The operator can set PAPERCLIP_RUNNER_API_COMPANY_CAPTURE_MAX_BYTES to a finite value of at least 1 GiB. Deleting snapshots frees capacity; possible orphan storage must be reconciled before releasing its reservation. - A failed capture uses its full reservation. A new large capture needs a full 1 GiB available, even if it later completes at a smaller size. Small reads and existing asset pages remain available. - Concurrency limits apply per server process. The run byte budget is shared through the database. - The `integer` to `bigint` migration rewrites asset metadata and takes an exclusive table lock. File bytes stay in storage. - A live endpoint is fetched once before returning its snapshot. Continue reading the saved artifact for stable pages. Mutations may commit before any size or transport error; inspect state before retrying. - Attachment uploads and native file handoffs still default to 10 MiB. Raising buffered ingestion paths to GiB sizes is separate work. ## Model Used OpenAI Codex, based on GPT-6, with code execution and repository tools. The runtime does not expose an exact serving model variant or context-window size. The earlier paging work also used browser testing and subagents. ## 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>	2026-09-28 10:36:32 -05:00
DottaandPaperclip	bacc0e6a98	docs: remove automatic agent escalation from coordination skill (#14188) ... ## Thinking Path > - Paperclip manages work for AI agents. > - The coordination skill tells agents how to handle blocked work. > - The skill directs blocked work to managers and other agents. > - Those agents may lack the same access or authority. > - These extra assignments delay the required human action. > - This pull request removes automatic escalation advice. > - Agents must identify the missing capability and use the correct approval or human-input path. ## Linked Issues or Issue Description **Issue type** Incorrect information. **Where is the issue?** The critical rules in `skills/paperclip/SKILL.md` and blocker guidance in `skills/paperclip/references/api-reference.md`. **What's wrong?** The skill tells agents to escalate through `chainOfCommand`, ask another agent for help, and avoid human help. A manager title does not grant permission to fix a connection or complete an administrator action. **Suggested fix** Remove blanket escalation and agent-first rules. Keep normal delegation when the recipient has a concrete capability for a bounded task. Use saved human-input interactions or existing connection and approval flows for human-only actions. Searches for open PRs with “escalation”, “chainOfCommand”, and “ask another agent” found no duplicate skill change. Recovery-routing PRs change server behavior, which is outside this change. ## What Changed - Remove the chain-of-command escalation rule and both repeated agent-first directives. - Replace manager handoffs in the API reference with direct blocker handling. - Keep reporting fields, normal delegation, approval gates, and the ban on bypassing permission denials. - Keep the ban on cancelling cross-team tasks. Request a decision instead of automatically assigning the task to a manager. ## Verification - Final head `1483e82cc3fe10a7c910230b3779635d6d54c162`: Greptile 5/5, no outstanding findings, all CI checks pass (optional Storybook jobs skipped). - Created a fresh worktree at `.worktrees/skill-blocker-guidance` from the current master commit. - Ran `git diff --check`: passed. - Ran Node assertions against both documents: passed. Removed directives are absent. Human-input and capability-based delegation guidance is present. - Checked that checkout conflict, approval, dependency, and normal delegation instructions remain. - Attempted `pnpm -r typecheck`, `pnpm test:run`, and `pnpm build`. None could run because this environment has no `pnpm` executable. - Refreshed both generated capability inventories and their derived contract after skill heading positions changed. Both generator and live-inventory checks pass. The eval and MCP baselines remain unchanged. - Ran `node --test packages/paperclip-runner/scripts/check-capability-inventory.test.mjs`: all four tests pass. - Ran `node packages/paperclip-runner/scripts/check-capability-inventory.mjs` and `node packages/paperclip-runner/scripts/generate-capability-contract.mjs --check`: both pass. - Added explicit requester routing for agent and human scope questions. Focused Node assertions pass. ## Risks - Agents can request human input earlier for actions that require human authority. - Existing runs or installed copies can keep old skill text until refreshed. - This change does not alter server recovery routing or permission checks. ## Model Used OpenAI Codex, with reasoning, tool use, and shell execution. The runtime does not expose a verifiable exact model ID or context window size. ## 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>	2026-09-28 08:37:26 -05:00
DottaandPaperclip	7944ed3d97	fix(runner): preserve hire runtime safety and first-activity timing (#13852) ... ## Thinking Path > - Paperclip is the open source control plane for companies of AI agents. > - Native runner agents need governed tools, durable runtime state, and useful execution evidence. > - A first activity trace waited 53.467 seconds even though tool activity took 6.274 seconds; provider input arrived before the server API call executed. > - Native agents also need a safe way to hire teammates without asking the model to rebuild runtime configuration. > - This pull request separates the observed ACP input-stream window from the actual server `tool.execute` span and adds a server-owned native hire contract. > - The benefit is clearer latency evidence and safer native teammates with existing approval, auth, and company boundaries preserved. ## Linked Issues or Issue Description Related Daytona provenance work is in [#13814](https://github.com/paperclipai/paperclip/pull/13814). No duplicate public PR was found for this combined timing and native-hire change. **What existing behavior does this improve?** Native runner agents can use governed tools and request hires. The server did not expose a safe native hire operation that reused the caller's validated runtime settings. First-activity traces also mixed provider input timing with server tool execution timing. **Current behavior** A native hire must construct a separate runner configuration. Full configuration copying could expose paths, instructions, secrets, or sessions. Timing evidence could make a provider or MCP identity join appear proven when the trace did not contain that join. **Proposed behavior** The native `hire_agent` operation accepts identity and persona inputs. The server sends `adapterType: "paperclip_runner"` with `inheritRuntimeFrom: "caller"`, then copies only validated provider, model, permission, lifecycle, and bounded execution settings. It inherits and validates the default environment, derives the managed AI binding through existing normalization, preserves approval and permissions, and creates fresh child instructions. Caller secrets, paths, prompts, and sessions are excluded. Provider events now include the optional boolean `inputUpdated`, with Rust forwarding support. Timing evidence separately records the ACP input-stream window and the actual server `tool.execute` activity. It does not claim a provider or MCP join without matching evidence. **Reason and benefit** Native agents can hire teammates that start with the caller's approved execution policy. Operators retain company boundaries, auth rules, approval gates, and requalification. Reviewers can distinguish provider streaming time from server API execution time when diagnosing first-activity delays. **Breaking changes** None for existing hires or tool calls. `inheritRuntimeFrom` is optional and only applies to same-company native agent callers. Conflicting explicit runtime settings are rejected. The provider event field is optional for existing producers. ## What Changed - Added the native `hire_agent` protocol action, catalog entry, API contract, and runner authority checks. - Added `inheritRuntimeFrom: "caller"` validation and a closed native runtime inheritance allowlist. - Preserved managed AI binding normalization, default-environment validation, approval snapshots, permissions, requalification, and fresh child instructions. - Added provider `inputUpdated` schema support and Rust forwarding. - Added first-activity and server tool timing evidence with conservative identity-join handling. - Added route, authority, provider-event, sidecar, API, catalog, and Rust-focused tests. - Kept private Honeycomb links, raw traces, and local result paths out of this description. ## Verification Focused checks passed: - 458 timing/session checks. - 61 native hire inheritance checks. - 20 hire authority checks. - 1,741 API checks. - 106 catalog checks. - 54 provider sidecar checks. - 12 Rust provider checks. Live R2 and R3 each passed 45 checks across 6 runs (361,135 ms for R2). R1 stopped at missing Docker image setup. The final trace is available at https://ui.honeycomb.io/paperclip/environments/test/datasets/paperclip/result/BiMypLNvmiB?tab=traces. Latest-head CI passed all required build, typecheck, Rust, static, Vitest, serialized-server, workspace, chat, and E2E jobs. The focused local checks listed above passed; the broad local suite was not run before the live evaluation, while CI provides the full repository verification. ## Risks - Timing fields describe separate observed windows. They do not prove a provider or MCP owner without a valid trace join. - The inheritance allowlist must stay synchronized with native runner configuration fields. - Approval snapshots include resolved safe inherited settings and should be reviewed when native configuration fields change. - The focused local suite is narrower than the full repository suite; latest-head CI covers the broader repository checks. > Roadmap review: `ROADMAP.md` places this work within Paperclip's bring-your-own-agent direction. It extends existing native runner hiring and observability behavior. ## Model Used OpenAI GPT-6 (exact serving model ID is not exposed), with extended reasoning and repository tool use; GPT-5.6 Luna assisted with focused implementation and verification work. ## 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 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>	2026-09-22 23:16:11 -05:00
DottaandPaperclip	0f5fafe16b	fix(runner): preserve task replies and warm process continuity (#13738) ... ## Thinking Path > - Paperclip lets people manage AI agents and their work. > - The Runner connects provider sessions to task state, replies, and delegated work. > - Full-stack tests found lost final replies, rejected helper calls that stopped the parent, and unnecessary process restarts. > - A completed child could also receive a new assignment wake that the scheduler then cancelled. > - This change fixes those boundaries and gives agents clearer teammate instructions. > - The tests retain strict completion and process-continuity requirements. ## Linked Issues or Issue Description **What happened?** A generated attachment comment could suppress an agent's final reply. A known Codex helper could stop its parent when it requested a Paperclip tool. Native Daytona processes restarted between turns because Paperclip minted an unused GitHub broker token. Reassigning a completed child queued a run that immediately cancelled. Revision instructions also allowed agents to do work assigned to a named teammate themselves. **Expected behavior** Keep the final reply. Reject helper tool requests without borrowing parent authority or stopping the parent. Keep an unconfigured sandbox process alive between turns. Treat assignment-only changes to completed tasks as metadata changes. Preserve explicit teammate assignments during revisions. **Steps to reproduce** Run the retained Runner E2E cases for file handoff, teammate reuse, Daytona warm continuity, and Legacy Claude interview/plan acceptance. The focused regression tests reproduce the reply, helper, process-lifetime, and assignment-wake defects without provider calls. **Paperclip version or commit** The live lifetime and completion campaign used `db3857807`. This PR replays the changes on master `c65fc9e3c`. See Verification for the limits of that evidence. **Deployment mode** Isolated local instances and native Runner sessions in Daytona sandboxes. Related work: #13546 handles a different queued-run issue after an issue-lock compare-and-set failure. This PR prevents the unnecessary assignment wake earlier. #13410 covers retained user services; this PR covers the provider process. No duplicate fix was found. ## What Changed - Exclude generated deliverable-binding comments from final-reply deduplication. Preserve the attachment and explicit user-facing replies. - Reject Paperclip tool and input requests from known Codex helper threads without terminating the parent. Keep unknown-thread rejection intact. - Explain how to hire or reuse a persistent teammate and preserve named delegation on revisions. Update generated protocol fixtures. - Use stable, token-free GitHub wrappers for unconfigured native sandboxes. Preserve credential isolation, configured-account rotation, and cleanup after partial staging failures. - Do not queue assignment-only wakes for done or cancelled tasks. Keep explicit reopening behavior. - Make warm-continuity fixtures create real review cards. Read the persisted final response selected by production presentation logic. Missing selected evidence still fails. ## Verification - Before rebase: 560 focused route, native-executor, and launcher tests passed. The new regressions were reproduced before their fixes. - Live E2E: Legacy Claude interview/plan acceptance passed 3/3 repetitions. Daytona warm continuity passed 2/3 full repetitions. Each successful run retained one process and provider session for all three turns. - The remaining Daytona repetition stopped after a same-URL browser reload left the page blank. Both completed turns retained the same process. Its failed verdict remains unchanged; this PR does not claim the blank-page cause is fixed. - Reports: https://pages.paperclip.ing/runner-e2e-lifetime-race-20260920/investigation.html and https://pages.paperclip.ing/runner-e2e-behavior-followups-20260919-results/investigation.html - Post-rebase `pnpm build` and `pnpm -r typecheck` passed. All 414 Runner E2E harness unit tests and its typecheck passed. Codex protocol tests: 88 passed, 2 ignored. - Latest-head CI: 55 successful checks and 2 intentional skips. Greptile: 5/5 with no review threads. The unchanged workspace exposure tests hit a fixed-port collision on the first CI attempt; their local suite passed (25 tests, 3 platform skips), and the CI shard passed on one retry. - The duplicate local `pnpm test:run` was stopped after the full hosted general and serialized test shards passed. It did not finish locally and is not counted as a local full-suite pass. ## Risks Configured GitHub accounts retain run-scoped credential rotation and can still restart warm processes. That limitation requires a separate design. Known provider helpers cannot use Paperclip coordination tools directly; they must return findings to the parent. The delegation prompt is an instruction, not an enforced guarantee; Codex Mini hiring/reuse failures remain open. No schema or workflow changes are included. ## Model Used OpenAI GPT-6 through Codex, with repository tools, code execution, and parallel coding agents. The exact deployment suffix and context-window size are not exposed in this session. ## 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 issues and shared reports) - [x] My branch name describes the change and contains no internal Paperclip ticket id or instance-derived details - [x] I have run focused tests locally and they pass; full hosted test shards also 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>	2026-09-21 08:56:35 -05:00
DottaandPaperclip	7bc03e0acd	feat(runner): default harnesses to full auto and support task reassignment (#13686) ... ## Thinking Path > - Paperclip lets people manage AI agents and their work. > - Agent Chat uses native runners to save plans and coordinate tasks. > - Provider defaults differed across harnesses and could stop unattended work at a second permission gate. > - Agents also lacked a dedicated tool to move existing work to another agent safely. > - This change defaults native providers to full automatic permission for provider tools and connected tools. > - A guarded reassignment tool preserves task identity, stops the previous run, and schedules the new owner once. > - Codex and Claude chat acceptance tests now use production permission defaults. ## Linked Issues or Issue Description **Subsystem affected** Native runner, ACPX Claude permission policy, task authority, and Agent Chat acceptance tests. **Problem or motivation** A user can authorize an agent to save a plan or create a task, but Claude's default provider gate can still stop that action. Reassignment needs a dedicated operation that preserves context and avoids concurrent owners or unintended recovery runs. **Proposed solution** Default Claude/ACPX to `approve-all`, OpenCode to `allow`, and Codex to `never`. Apply the defaults at configuration, execution, fresh-session, resume, driver, and proxy boundaries. Keep explicit permission settings and server-side company, claim, task-mode, and approval checks. Add `reassign_task` with version checks, durable idempotency, audited cancellation, and guarded successor scheduling. **Alternatives considered** A Paperclip-only allowlist still blocks provider tools and other connections during unattended work. Full automatic permission is the requested product default. Recreating a task discards its identity and history. Updating assignment without stopping the previous run can leave two agents working on the same task. **Roadmap alignment** This extends the existing planning, delegated work, governed tool access, and recovery features. It adds no new service or schema migration. Recent related tasks and open PRs were checked for duplicate work. **Additional context** Related: #13678 (Agent Chat tools and recovery), #13677 (remote runner startup). The stacked legacy-adapter companion is #13693. This also fixes the deployed-server artifact fallback needed to stage the current runner binary. ## What Changed - Default Claude/ACPX to `approve-all`, OpenCode to `allow`, and Codex to `never`, including missing settings at direct driver and proxy entry points. These defaults cover provider tools and connected tools. Preserve explicitly configured restrictive modes. - Include assigned approval reads using canonical side-effect classifications, so verifying a recorded approval does not trigger another provider gate. Paperclip approval decisions still enforce controller authority. - Carry the new permission mode through server configuration, execution contracts, recovery identity, TypeScript, and Rust. Keep `approve-paperclip` as an optional restricted mode, with exact SDK rules and closed unknown requests. It is not a default. - Add `reassign_task` to the semantic catalog, controller, mock authority, and generated contracts. - Guard reassignment with company authorization, expected owner and version, protected-state checks, and durable retry receipts. - Honor explicit backlog task creation atomically with the initial plan, without scheduling a wake. Preserve backlog holds regardless of dependency readiness. - Stop active work before changing ownership. Restore the prior owner through a guarded, idempotent wake if final handoff validation fails. Keep intentional reassignment stops out of failure recovery. Preserve backlog and blocked states without waking them early. - Add authorization, concurrency, replay, stop, and permission boundary regressions. Add Codex and Claude chat reassignment cases and run native chat cases with production defaults. - Clarify shared runner guidance: save plans and Paperclip documents directly with `write_document`; create and register a local file only when a downloadable file is requested. - Document provider defaults and the operator choices for existing agents. ## Verification - Current head `d82fbb0f03546d27cecf072250e4172e0b1ee662`: **55 checks passed**, with two intentional skips. [PR checks](https://github.com/paperclipai/paperclip/pull/13686/checks). - Greptile reviewed that exact head at **5/5**. The security reviewer acknowledged the intended full-auto default, and the acknowledged discussions are resolved. - Full workspace `pnpm -r typecheck` and `pnpm build` passed locally after rebasing onto current master. Targeted adapter/server, runner, API, default/resume, and heartbeat configuration tests passed. - **All six real-provider acceptance cases passed on their first attempt, with cleanup passing:** plan handoff, task reassignment, and backlog creation/status, each on native Claude and Codex. Evidence records Claude's effective `approve-all` mode. [Campaign and downloadable evidence](https://github.com/paperclipai/paperclip/actions/runs/35469926548). - The live campaign tested combined revision `a37881c824dcd7170380fc4b788732fc743e5da7`. The final PR heads add only a heartbeat test expectation correction; application code is unchanged from that live-tested revision. - The campaign's result-enforcement job passed. Its separate report publisher failed because the trusted workflow's `patchedDependencies` configuration differs from its frozen lockfile. All six results and screenshots remain available as GitHub artifacts. The overall manual workflow is red for this publishing failure. - Full-suite coverage is supplied by the passing CI partitions. The separate unsharded local run was stopped after the corresponding CI partitions passed; it is not counted as a completed local run. - Reassignment tests cover stale state, cross-company access, denied authority, cancellation failure, compensating wake, and idempotent retries. Backlog tests verify the original creation audit, saved plan, exact task count, and absence of task-bound runs. ## Risks - Agents with no explicit permission mode now receive full provider tool permission, including connected tools. This is a deliberate broad default. Existing explicit restrictive modes still apply. Controller authorization, company isolation, workspace boundaries, and Paperclip governance remain in force. - Reassignment crosses run cancellation and task ownership transactions. Durable stop intent, revalidation, audit receipts, and guarded queue dispatch cover interruptions and retries. - The new permission enum requires a current runner artifact. The remote artifact fallback uses the same resolved controller binary for upload and execution. - Live provider behavior remains subject to the selected model. Targeted live results do not qualify the full catalog. ## Model Used OpenAI Codex, based on GPT-6, with code execution and repository tools. The exact deployment model ID and context-window size are not exposed in this session. ## 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>	2026-09-19 16:49:18 -05:00
DottaandPaperclip	36dbb7ed1c	fix: harden agent chat runner tools and recovery (#13678) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agent Chat turns discussion into plans, tasks, reviews, and hires. > - These workflows need reliable tool results and task context on the native runner. > - Live Claude and Codex tests exposed lost retry requests, invalid project inputs, and a child startup crash. > - Recovery also exposed a misleading retry action and missing child task context. > - This pull request fixes those paths and adds regression coverage. > - Agents can continue the original request and operators can inspect a stopped run. ## Linked Issues or Issue Description **What happened?** A failed Agent Chat retry could lose the user's question. Project creation accepted unsupported icons in its tool schema. Codex could stop when a helper's MCP startup event arrived before its thread lineage. A stopped task offered Retry even when the server required execution reconciliation. Resumed agents could miss existing delegated tasks. Hiring and review instructions did not describe the native runner's available tools and source requirements. **Expected behavior** Retries retain the selected request. Tool schemas match the API. Child startup information does not gain authority over the parent or stop it. Recovery actions match the server's requirements. Task context exposes existing child work. Handoffs contain the material the assignee needs. **Steps to reproduce** 1. Enable experimental Agent Chat in an isolated development instance. 2. Configure native Codex and ACPX Claude agents on Paperclip Runner. 3. Ask for a plan, revise it, approve task creation, and request a hire and status report. 4. Retry a failed chat turn and check that it answers the original request. 5. Start a Codex helper before its thread lineage arrives. 6. Resume a delegated task and inspect its existing children and saved output. **Paperclip version or commit** The live failures were found at `f2c5e54dc`. This branch is rebased onto `86b7ee992`. **Deployment mode** Isolated local development instance with native Codex and ACPX Claude. No database migration or default permission change. Related work: Refs #13284 for Agent Chat. Refs #13438 for the server-side API receipt fix, which this branch preserves. The transport also accepts the earlier HTTP receipt format. Refs #13655 for the current Codex continuation and helper lineage handling, which this branch also preserves. ## What Changed - Preserve failed Agent Chat wake-comment IDs and session generation from the authorized source run. Reject pre-reset retries. - Wrap API receipts with the correct semantic call identity. Test current and earlier receipt formats through real HTTP and runnerd. - Classify early child MCP startup notifications as information. Keep foreign completion and result events rejected. - Constrain project icons on both tool surfaces and regenerate the protocol contracts. - Include bounded, company-scoped visible direct child tasks in task context. Filter hidden tasks before applying the limit. - Replace the rejected Retry action with Inspect run for native continuation reconciliation. - Update hiring, review handoff, status reporting, and development guidance. ## Verification - Live tests covered Claude and Codex questions, plan revisions, approval, task creation, hiring, status, chat reset, failures, and recovery. - The recovered task produced its saved checklist and example. A later follow-up read the existing child tasks and document without creating more work. - Full build, repository type checks, token gates, 142 focused tests, 188 runner TypeScript tests, and the Rust notification/descendant regressions passed after rebase. The separate local full-suite run was stopped after the complete CI suite passed. - Review fixes passed the updated route, tool-authority, and icon regression tests plus server type checking. - Required commands: `pnpm build`, `pnpm -r typecheck`, `PAPERCLIP_IN_WORKTREE=false pnpm test:run`, and `pnpm check:token-gates`. - At `4ce8047b0`, all 55 applicable GitHub checks pass (two Storybook checks are intentionally skipped), including the complete general/serialized test matrix, runner tests, browser tests, build, type checks, Docker checks, and canary dry run. - Fresh Greptile review is 5/5 on `4ce8047b0`; all three findings were fixed with regressions and there are no unresolved review threads. - Two initial CI service-startup timeouts passed unchanged in local reproductions and in the latest CI run. ## Risks - The new event classification is limited to MCP startup information. It does not authorize foreign task completion, results, or tool requests. - Task context returns at most 100 direct child tasks and reports truncation. It excludes hidden tasks and other companies. This improves delegation context but does not enforce semantic duplicate detection. - Native reconciliation still requires an operator to inspect and record prior outcomes. The new link does not replace the recovery API. - API tools remain opt-in. Claude permission choices remain explicit. No default permission, schema, or workflow changes. ## Model Used OpenAI GPT-6 in Codex, with reasoning, repository editing, code execution, API tools, and browser testing. The exact deployment identifier and context-window size are not exposed in this session. Live acceptance agents used OpenAI `gpt-5.6-sol` and Anthropic `claude-sonnet-4-6`. ## 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>	2026-09-19 09:11:04 -05:00
DottaandPaperclip	43acbcc398	fix(runner): preserve sessions and complete question and approval continuations (#13655) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native runner connects task state to provider sessions. > - Follow-up turns must retain provider memory and carry new user direction. > - Lost session IDs caused repeated context and extra input tokens. > - Native question answers and approval races could leave valid work blocked. > - This pull request repairs those paths and adds regression coverage. > - Agents can continue accepted work without repeating the conversation or losing the user's answer. ## Linked Issues or Issue Description Refs #13574. That merged PR shortened continuation prompts and moved question instructions into tool documentation. This change preserves sessions and fixes failures exposed by broader testing. Related runtime work: #13408 and #13410. **What happened?** Native follow-up turns could lose the provider session ID. Completion guidance could replace the original task with its latest comment. Claude native questions could remain pending after the user answered. Approval during a running tool call could suspend the run before the tool response arrived. Onboarding and chat handoff instructions also caused repeated planning or missing plan documents. **Expected behavior** Reuse a valid provider session. Send only new events when that session already has the history. Preserve the task requirements and apply later user direction. Store the question answer and deliver it to the waiting run. Finish governed tool responses before suspending. Execute the accepted plan without asking for the same approval again. **Steps to reproduce** Run the continuation, local-session-integrity, first-task, and agent-chat suites with native Codex and Claude. Include provider-question-bridge, accept-while-running, and plan-handoff. **Paperclip version or commit** This branch is based on master d54b75011. The active full catalog run tests 4e75881db. Later review fixes have separate regression coverage. **Deployment mode** Isolated local instances and Daytona sandboxes in the existing Runner full-stack E2E harness. ## What Changed - Retain provider session identity across turns and late usage snapshots. Send new continuation events on session reuse, with full context available for a fresh session. - Preserve task requirements and later direction in completion guidance. Return the current contract revision after a stale completion submission. - Bridge native Claude questions to saved Paperclip cards. Submit answers through the saved card and resume the same run. - Delay governed suspension until tool results settle. Add a deterministic test barrier for approval during an active run. - Clarify free-text question examples, explicit onboarding plans, and execution of accepted chat plans. - Fix continuation readiness, verified output evidence, and declared screenshot collection. - Qualify the legacy Claude test CLI at 2.1.277. The old 2.1.19 CLI did not discover mounted skills. Update the existing workflow pin and isolated launcher together. - Refresh the Daytona image lockfile integrity pin after reviewing master patch updates. - Carry continuation mode as runtime metadata instead of inferring it from user-visible text. Install the test Claude CLI without lifecycle scripts. ## Verification - Targeted paid verification: 20/20 cases passed across local-environment campaigns before the rebase. [Report](https://pages.paperclip.ing/runner-e2e-seven-fixes-35397904249/). - Harness checks: 379 unit tests passed; harness typecheck passed. - Latest-head PR checks: 55 passed, two intentionally skipped. Greptile is 5/5; the security scan passes. - Review regressions: 350 executor tests and 204 session/driver tests passed. A script-free Claude install was verified with the actual CLI. - Full catalog, including the explicit-only everyday suite: [run 35417932353](https://github.com/paperclipai/paperclip/actions/runs/35417932353). Completed: **164/205 passed; 41 failed**. [Full dashboard and failure investigation](https://pages.paperclip.ing/runner-e2e-full-catalog-35417932353/). Includes 204 case artifacts and one pre-case GitHub authorization timeout; missing evidence is not scored as a pass. The full run tested `4e75881db`; Final-head metadata/CLI smoke cases both passed. In the separate [six infrastructure retries](https://github.com/paperclipai/paperclip/actions/runs/35419769343), the GitHub timeout case passed and all five Docker preflight failures repeated. [Follow-up dashboard](https://pages.paperclip.ing/runner-e2e-full-catalog-35417932353/follow-up/). - Full local typecheck and build passed on the rebased branch. The full local unit run completed with 657 passing files, two test timeouts and one suite setup timeout. All three affected files passed when rerun in isolation (84 tests). The first full local run was not clean. - Focused regression coverage includes the live question bridge, same-run response delivery, UI routing, stale revisions, approval overlap, and session reuse. ## Full-catalog follow-ups - Test infrastructure: 14 Claude everyday cells probe an absent host CLI; six cells failed pre-task GitHub/Docker qualification (GitHub passes on retry; all five Docker cases repeat; the workflow preflight allowlist omits their case IDs); five ACPX Codex cells cannot create sandbox namespaces. - Runtime: four OpenCode completion-criteria mismatches masked by shutdown errors, one service-approval suspension failure; three Daytona recovery failures encounter existing skill files; one duplicate completion wake. - Confirmed test defects: question pagination and a noncanonical plan document key. - Product/behavior: mismatched visible/required question sets, an attachment instead of the requested task document, one lone-option onboarding question, early completion instead of review, and a Codex Mini completion-schema failure. - The report job itself fails on trusted master’s stale patch/lock configuration. The linked report is rebuilt with the shared renderer from original cell results and public fixture screenshots; it excludes private snapshots, logs and traces. These are investigated follow-ups, not silently regraded passes. First-task passed 51/52. The PR checks are green independently of the broader catalog’s behavioral/infrastructure failures. ## Risks - Session reuse depends on a valid provider identity and context coverage. Fresh-session fallback and reset tests cover this boundary. - Native question delivery spans saved interaction state and a live provider run. Tests cover duplicate events, closed runs, and same-run answers. - Provider behavior varies. The full paid catalog may expose failures beyond these targeted fixes; those results will be reported without relaxing valid approval or output checks. - The legacy Claude version update is limited to test infrastructure. No database migration is included. ## Model Used OpenAI Codex, GPT-6 family, with repository inspection, code execution, and browser/E2E tools. The exact runtime model identifier and context-window size are not exposed in this session. ## 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 (targeted checks and all three timeout-file reruns pass; full-run timeout caveat 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>	2026-09-19 07:42:57 -05:00
DottaandPaperclip	e26d787928	Shorten continuation prompts and verify question tool guidance (#13574) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents must continue tasks using user answers without losing earlier requirements or approval gates. > - The wake prompt mixed human decisions with prior tool evidence and repeated detailed question instructions. > - Those instructions belong with the question tool, with a short routing hint in the wake. > - The Runner evals need to prove that answers, approvals, and completed work survive later turns. > - This PR shortens the prompts, separates authenticated answers, and adds continuation tests with useful screenshots. ## Linked Issues or Issue Description Refs #13517. This is a follow-up to the merged onboarding skill and Runner E2E work. Related #13539 covers responses received while a run is active; this PR preserves its cases and adds continuation coverage. Existing continuation/recovery and question PRs were searched; none covers this prompt/documentation and eval change. **What existing behavior does this improve?** The instructions sent when an agent continues a task, the native human-input tool documentation, and the evidence captured by Runner full-stack E2E. **Current behavior** The wake repeats a long question-tool guide. Human answers appear alongside untrusted prior results. Screenshot capture can finish at DOM load while the task still shows a spinner, even when backend behavior checks pass. **Proposed behavior** Keep earlier requirements unless the user changes them. Treat clarification as distinct from approval. Give authenticated human responses a scoped field. Keep tool and agent results as evidence. Put detailed question behavior in the tool descriptor and retain one routing sentence in the native wake. Wait for the correct task and loaded conversation before taking screenshots. **Reason and benefit** Reduce repeated prompt text and make authority boundaries clear. Test that real question cards, later answers, approval gates, and completed child tasks still work. Make screenshots useful for human review. ## What Changed - Shorten shared continuation instructions for legacy and native runners. Separate authenticated user responses from tool results and agent summaries. - Remove the detailed question guide from native wake prompts. Keep its behavior in the canonical `request_human_input` descriptor and existing payload schema. Regenerate semantic contracts and fixture hashes. - Add five continuation cases across four local profiles. Add a dedicated choice-then-text case for native Codex and native Claude. All 22 cells join the shared full E2E campaign. - Cover revised scope, clarification without approval, hostile instructions in a handoff file, and reuse of a completed child after restart. Keep production instructions and fixed user facts. - Capture continuation screenshots only when the intended task and conversation have rendered. Add provider-free browser regressions for loaders and wrong-task capture. - Preserve current master’s extra tool and onboarding cases. The default campaign now contains 166 cells; 35 manual everyday cells remain separate. ## Verification - `pnpm -r typecheck`: passed after replay on current master. - `pnpm test:e2e:runner:unit`: 340 passed. Harness typecheck passed. - `PAPERCLIP_PLAYWRIGHT_CHANNEL=chrome pnpm test:e2e:runner:browser-support`: 4 passed. These tests failed against immediate screenshot capture and passed after the fix. - Focused continuation and native-input tests: 36 passed locally. The tool-authority suite could not initialize embedded PostgreSQL locally, including one isolated retry; its 17 assertions did not run locally. The full remote server shards passed on this PR commit. - `pnpm build`: passed after replay on current master. `pnpm test:run` was attempted locally but hit the same embedded PostgreSQL initialization failure; the remaining local run was stopped after complete remote CI passed. This is not claimed as a full local test pass. - [Full PR CI](https://github.com/paperclipai/paperclip/actions/runs/35232755685): passed on `6a22128c14f4552d0613a6d9a25955db4a1ed02f`. All server/chat/workspace/serialized shards, browser shards, Runner checks, typecheck, build, canary and policy checks passed. The isolated native Runner build and security checks also passed: 57 successful checks, with two expected Storybook skips. - Greptile reviewed the exact PR head at 5/5, with no findings or unresolved review threads. The PR has no merge conflicts. - [Live question-docs report](https://pages.paperclip.ing/runner-e2e-question-docs-35227647794/): 3/3 passed at source `83dd132f2` before replay on master. Native Codex and Claude each asked a choice, waited, asked a text question, and saved both answers. Claude also passed a completed-child restart case. All three native turns are checked for absence of the old question block. - [Earlier continuation report](https://pages.paperclip.ing/runner-e2e-continuation-35154943615/): all five continuation cases passed on native Claude. The report retains campaign and revision provenance and separately shows two unresolved onboarding behavior failures. - [Before/after prompt report](https://pages.paperclip.ing/runner-prompt-comparison-20260917/): full text, current recorded Claude inputs, and reproducible reference-token counts. The controlled wake comparison removes 401 reference tokens; the net counted input reduction is 339 after charging the larger tool description. These are text-size estimates, not measured billing savings. ## Risks - Prompt wording affects model behavior. Live results cover the stated cases, not every provider or conversation. Legacy profiles are registered but were not rerun for this change. - The optional continuation field changes prompt data only; there is no database migration or new production API. - Authenticated answer projection excludes generated summaries and agent-resolved interactions. It preserves the answer’s question or approval scope. - The screenshot guard can expose UI loading failures that earlier runs hid. Backend grading alone no longer makes those captures valid. - The two prior onboarding failures remain separate product issues: work before acceptance and a missing saved plan. This PR does not claim the entire onboarding suite passes. ## Model Used OpenAI Codex, GPT-6, with reasoning, repository tools, code execution, and browser verification. The exact deployed model identifier and context-window size are not exposed in this session. ## 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 — targeted tests above; the full local database-startup limit is documented - [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>	2026-09-17 09:32:54 -05:00
DottaandPaperclip	11921075a4	Add first-task onboarding skill and Runner E2E coverage (#13517) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The first task helps a new user define and approve useful work. > - That workflow needs reusable instructions and tests against the production experience. > - Native Codex and Claude must load the assigned skill, including after resume. > - Maintainers need recorded conversations and precise failed checks to judge regressions. > - This pull request adds the first-task skill and a suite in the shared Runner E2E harness. > - It keeps behavior results separate from informational quality scores and incomplete recordings. ## Linked Issues or Issue Description **What existing behavior does this improve?** The first onboarding task and the Runner E2E report used to review it. **Current behavior** Onboarding embeds its policy in a hidden brief. Native Codex drops the skill-instructions setting at the Rust boundary. The shared E2E harness has no onboarding suite or full conversation view. **Proposed behavior** Assign and invoke `/first-task` for the onboarding task. Send selected Codex skills as structured protocol inputs. Run twelve scenarios across legacy Codex, legacy Claude, native Codex, and native ACPX Claude. Include all 48 cells in full campaigns. Show recorded chat, question and approval cards, exact checks, instructions, and billing in the shared dashboard. **Reason and benefit** Measure the real onboarding experience before changing prompts. Distinguish infrastructure failures, behavior failures, and unexercised journey steps. **Breaking changes** No database migration or production API change. First-task instructions now live in an assigned skill. The user-edited persona is preserved; the skill includes the maintainer-approved proposal-mode mapping and saved-plan requirement. Related: #11043 is earlier onboarding work. #13422 already fixes native Claude model pinning, context delivery, and read permissions on master; this branch includes those fixes through its base. The new Claude recovery test supplements them. ## What Changed - Extract and assign the first-task skill while retaining the production greeting and opening question. - Carry the Codex skill-instructions flag through thread start and resume. Resolve explicit task skill references only against assigned skills and send native skill inputs. - Invoke an unambiguously selected assigned skill through Claude ACPX’s native slash-command parser on initial and resumed turns, retaining the entire task/wake envelope as its argument. Do not carry that invocation into ordinary tasks. - Restore the saved single-task proposal modes: confirmation card, or saved plan with revision-targeted checkbox approval. Explicit plan requests also require a saved plan. - Add first-response and complete-journey cases with fixed user facts, acceptance checkpoints, durable outcome checks, and accounting for child runs. - Fail the eval when choice questions have fewer than two real options. Recognize planning documents without treating them as completed work. - Add optional, bounded quality judging as explicit post-processing. - Render full conversations and static interaction cards in the shared report. Conversations start folded. Show original and regraded results and incomplete journeys distinctly. - Keep credential-persistence scanning outside the first-task behavioral suite; retain public evidence redaction. - Refresh generated capability references after the API-reference edits. - Correct shared native question guidance and tool schemas: choices need at least two meaningful options; open-ended questions use canonical text fields with the required compatibility payload. Verify both formats through real tool-authority persistence. - Disable announcements automatically for every isolated Runner E2E process and label the gallery environment/provider/target explicitly. - Remove CI races in the GitHub connection browser test and native session recovery test by waiting for the actual async work before asserting its results. ## Verification - `pnpm exec vitest run server/src/services/onboarding-first-task-assets.test.ts server/src/__tests__/issue-onboarding-first-task-routes.test.ts`: 19 passed. - `pnpm --dir packages/paperclip-runner exec vitest run src/drivers/acpx/runtime-host.test.ts src/drivers/acpx/native-skill-prompt.test.ts src/cli/acpx-runtime-sidecar.test.ts`: 70 passed. Native command forwarding and the 1 MiB input boundary both failed before their fixes and passed afterward. Coverage includes changed skills on reopen, approval context, and an ordinary subsequent task. - Runner E2E unit suite: 306 passed. Harness typecheck passed. The 64 first-task fixture and grader tests also pass. - Full repository typecheck and build passed locally. Server typecheck and Runner build passed again after the native-command change. - Full GitHub Actions CI passed on `23e56447b`: all server/workspace/browser shards, Runner verification, typecheck/release registry, build, canary, policy, and Docker checks. Greptile reviewed this exact head at 5/5 with no unresolved threads. The earlier broad local run had database startup/timing failures that passed isolated retries; the complete remote suite is green. - Merge verification against current master: 312 harness tests and 13 native recovery tests passed. Regenerated semantic contracts and fixture hashes pass their consistency check. Full local typecheck and build also passed on the stacked queue branch. After merging the latest master and preserving the GitHub setup timing regression in the split browser suite, both focused GitHub browser tests passed. Three CI timing/startup flakes passed local verification and one remote retry; all latest-head checks are green. - Real pinned Claude SDK and Claude ACP JSON-RPC probes against a local mock API confirmed that `/skill-name` expands the assigned skill body before the model request and retains the task arguments. A prose mention does not. The probes made no paid model calls. The ACP probe used the current first-task skill body and retained the wake arguments. - [Full 48-case campaign and report](https://pages.paperclip.ing/runner-e2e-first-task-35053063880/): 44 passed after three interrupted Codex cases completed in targeted reruns. Original results, regrades, and all 51 executions remain in the report provenance. - [Claude campaign after the shared-question fix](https://pages.paperclip.ing/runner-e2e-first-task-claude-35099525201/): 10/12 passed with zero single-option failures. All 12 recorded the current assigned skill and corrected guidance. The failures exposed skipped skill invocation and a missing saved plan. This PR adds native command invocation and explicit saved-plan instructions; the subsequent report below still shows behavior failures. - [Fresh 12-case Claude report](https://pages.paperclip.ing/runner-e2e-first-task-claude-35102737804/) at `78452129e`: 10/12 pass after correcting two false proposal-matcher failures. The recordings said “Here is the task I will create and run/complete” in approval cards; the old matcher missed that word order. Regression tests failed before the fix and pass after it. Original results and offline regrade provenance remain linked. No agent rerun was needed. Zero single-option-question failures; two behavior failures remain: direct work before acceptance on a plain first message, and an explicit plan request without a saved plan. Neither check was relaxed. The follow-up `82087ac7e` fixes command-prefix size accounting; `94aefb1f3` fixes only that proposal matcher. - Report browser checks confirm folded conversations, rendered cards, explicit Local/Daytona labels, and no page errors. The published-object audit scanned 1,306 text files across 2,154 objects with no credential-format findings or prohibited files. Image pixels and unknown token formats are outside that scan. ## Risks - Model behavior is nondeterministic. One campaign is evidence, not a guarantee. The two remaining Claude behavior failures are visible in the report and require further product work; this PR does not claim all onboarding scenarios pass. - The suite checks persisted Paperclip effects. It cannot prove the absence of arbitrary external effects. - Historical recordings can miss later journey steps. These remain incomplete, never passes. - Native profiles switch runtime after the production onboarding wizard because it does not yet expose a native option. - Quality scores are informational and cannot override behavioral failures. ## Model Used OpenAI Codex, GPT-6, with reasoning, repository tools, and code execution. The exact deployed model identifier and context-window size are not exposed in this session. ## 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>	2026-09-16 14:24:32 -05:00
DottaandPaperclip	9fd2e50310	feat: create company skills from runner tasks (#13538) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The Runner gives agents tools to change company resources. > - Users need agents to save reusable skills during a task. > - A saved skill needs a visible result that users can inspect and edit. > - This pull request adds `create_skill` and a task feed card linked to Skill Studio. > - Users can open the saved skill from the task and edit the same resource. ## Linked Issues or Issue Description **Subsystem affected** Runner tools, company skill storage, task feed, and Skill Studio. **Problem or motivation** The Runner has no dedicated tool to create a company skill. A user cannot follow a creation result from the task feed to the saved skill. **Proposed solution** Add a company-scoped `create_skill` tool. Save the skill with the existing company policy. Add one creation card to the task. Open a named sidebar tab from that card. Let the user open the same skill in Skill Studio. **Alternatives considered** An agent can write a local file, but that file is not a company skill. A second document copy in the task would become stale after a Studio edit. The sidebar therefore reads the saved skill directly. **Roadmap alignment** This extends the shipped Skills Manager, Skill Studio, and Skills Store milestone. The maintainer requested and approved this scope. Search found no duplicate `create_skill` PR or issue. Related UI validation work: #8715. This PR does not change that validation display. ## What Changed - Add the real Runner tool, its contract, and its mock implementation. - Validate the complete SKILL.md and derive company, task, agent, and run identity from authentication. - Apply the existing company skill policy. Do not assign the skill to an agent. - Make keyed retries return one skill and one creation event. Reject conflicting retries. - Make concurrent file creation safe. Never replace an existing published skill during creation. - Add a creation card, a named sidebar tab, and an Open in Skill Studio action. - Show saved Studio edits when the user returns to the task. - Add storage, policy, mode, retry, UI, and Product E2E tests. Document the tool. - Fix deleted-name reuse, onboarding panel persistence, immediate feed refresh, and mock validation parity from review. - Serialize Studio file edits and renames with skill deletion and recreation. Reject stale editor requests before they can change a replacement skill. - Generate the standalone mock parser and validator from the production contract. Use portable UUIDs so the browser scenario bundle builds. ## Verification - All latest-head PR checks pass on `145dd76a5`, including all server shards, browser E2E, Runner verification, build, typecheck, and release dry run. Greptile: 5/5 with no open findings. An interrupted CI runner was retried successfully. - `pnpm -r typecheck`: passed. - `pnpm build`: passed. - `pnpm check:token-gates`: passed. - Review regressions: 73 storage tests, 6 real API tests, 63 UI tests, and 61 semantic runtime tests passed. Parser synchronization passed. - CI exposed existing fire-and-forget Sentry test races. Reproduced the resumption race locally, then synchronized the related sweep and finalizer assertions on the actual report; all 27 tests across the three affected files pass. - Runner scenario browser build and strict content-security-policy check: passed. - Runner suite: 2,012 tests passed; 10 skipped. - `pnpm test:run`: the general-server batch had 12,416 passes and two failures. The old tool-count assertion was fixed; all 16 authority tests then passed. The chat webhook test had a socket error; it passed four isolated reruns. - Both workspace test groups passed. The isolated route suites completed. Two socket failures in the initial route batches passed on individual reruns; all remaining 61 files passed. - Product E2E `create-skill-studio`: passed with local Codex and local ACPX Claude. - Manual browser test: submit a task, observe the real tool call and creation card, open the sidebar, edit in Studio, save, and return. The task reached Done. The saved second revision and sidebar tab survived a server restart. - The new companion headless Runner Eval passed. Companion coverage PR: https://github.com/paperclipai/paperclip-evals/pull/23. Daytona was not run because no immutable runner image was configured. ## Risks - Database writes and local file writes cannot share one transaction. Recovery accepts only an exact file-for-file retry after a database rollback. Conflicting files remain untouched. - The sidebar displays the current skill. The feed card remains the historical creation receipt. - No database migration, dependency, or workflow change is included. - Remote Daytona behavior still needs a run with a configured immutable image. ## Model Used OpenAI GPT-6 (`gpt-6-astra`) handled design, integration, review, and browser verification. OpenAI `gpt-5.6-luna` assisted with bounded implementation and eval work. Both used code execution and tool access. The host did not expose the context window size. ## 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>	2026-09-16 13:01:58 -05:00
DottaandPaperclip	78ce96a48b	fix(runner): restore native Claude context and read permissions (#13422) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native runner supplies each agent with instructions, assigned skills, and tools. > - Native Claude lost its skill snapshot before provider launch. It also changed exact model IDs to aliases. > - The read permission mode denied ordinary Paperclip reads because this runner has no interactive approval handler. > - This pull request restores the missing context and permits only assigned tools that Paperclip defines as reads. > - Other requests that need approval stop with a clear action for the operator. They do not retry automatically. > - Agents can complete read tasks. Users can see why a restricted task stopped. ## Linked Issues or Issue Description **What happened?** Native Claude could not find assigned skills. The ACP layer could replace an exact model ID with an alias and then fail identity verification. The default `approve-reads` mode denied Paperclip read tools. A denied write showed a generic transport failure. The tool descriptions also called live operations “mock” operations. The completion prompt said to call a completion tool once, although the protocol can reject a claim and require a corrected call. **Expected behavior** Load assigned skills before launch. Keep the selected model ID. Allow assigned Paperclip reads. Stop an operation that needs approval with clear instructions when no approval handler exists. **Steps to reproduce** 1. Configure a native Paperclip Runner agent with ACPX Claude and an exact model ID. 2. Assign a skill and ask the agent to use it. 3. Select the read permission mode and ask the agent to read task context and list documents. 4. Ask the agent to write a document. Check the task state and recovery message. **Paperclip version or commit** Reproduced from `d351e08deee1b49d3467a950d1a3f01131943441`. **Deployment mode** Local native runner with real Claude, Rust runnerd, the Paperclip server, and embedded PostgreSQL. Related: #13196 fixed remote skill staging in the legacy `claude_local` adapter. The native runner uses a separate path, which this pull request fixes. ## What Changed - Carry the runtime context through Rust and the ACPX sidecar. Load assigned Claude skills after the provider lifetime lease is held. Refresh the files on each open. - Write the exact requested model ID into the isolated Claude settings. - Grant exact MCP permissions for the intersection of assigned tools and Paperclip's read catalog. Provider hints cannot grant access. Existing task-control permissions stay in place. - Stop requests that need an unavailable approval handler. Preserve the typed error through the server. Show “Approval required” on the task and require operator action without automatic retry. - Label the setting “Allow Paperclip reads.” Remove “mock” from live tool descriptions and regenerate the contracts. - Change one completion-prompt sentence to require one accepted result. Add regression tests and update the runner documentation. ## Verification - Red/green regression tests cover read admission, unavailable approval handling, server recovery, and the task error message. - A real Claude read trial failed before the fix and completed after it: [red trace](https://www.braintrust.dev/app/Paperclip/object?object_type=project_logs&object_id=fda74078-b00d-495a-90d3-ea1be019d71b&id=95e6a326e24437f1), [green trace](https://www.braintrust.dev/app/Paperclip/object?object_type=project_logs&object_id=fda74078-b00d-495a-90d3-ea1be019d71b&id=85a1f347db5604d1). - Full browser tests used real Claude and the production tool authority. Reads completed. A write stopped with “Approval required.” No document was created and no automatic retry was scheduled. All nine checks passed: [events and screenshots](https://www.braintrust.dev/app/Paperclip/object?object_type=project_logs&object_id=fda74078-b00d-495a-90d3-ea1be019d71b&id=1c4ff10be0d779cc). - A separate full browser test assigned a skill, invoked it, and completed with a marker absent from the task prompt: [skill evidence](https://www.braintrust.dev/app/Paperclip/object?object_type=project_logs&object_id=fda74078-b00d-495a-90d3-ea1be019d71b&id=ba5fbcb29a60be52). - Post-rebase checks passed: 128 targeted runner tests, 46 Rust tests, 27 sidecar/protocol contract tests, `pnpm -r typecheck`, and `pnpm build`. The server/UI red-green checks and `pnpm check:token-gates` also passed. The full suite passed in CI, including all general and serialized test shards, all three browser shards, and runner `check:all`. The duplicate unsharded local full-suite run was stopped after CI passed. Braintrust links require project access. The traces contain provider/runner events and app outcomes. They do not contain raw model HTTP requests. ## Risks - `approve-reads` now allows assigned Paperclip reads. Other operations that need approval stop the turn. Users must review the operation and change permissions before retrying. - The Claude settings depend on the pinned ACP and SDK behavior. Automated tests and real Claude trials cover this boundary. - The native Codex path is unchanged. The ACPX Codex fallback shares the clearer approval failure handling. - Local execution was tested end to end. Remote execution was not run. This change has no database migration. ## Model Used OpenAI GPT-6 through Codex. The agent used reasoning, code execution, and browser tools. The exact deployment ID and context-window size were not exposed in the session. Live acceptance tests used `claude-sonnet-5`. ## 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>	2026-09-14 10:56:24 -05:00
DottaandPaperclip	7e6d512597	fix(onboarding): make chief-of-staff hiring reliable (#13317) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The first agent helps the board define work and hire other agents. > - That agent can have the general role while its instructions require hiring skills. > - Missing skills and blocked schema discovery make valid requests fail. > - Repeated confirmation and invalid waiting guidance can turn these failures into extra runs. > - This PR supplies the required skills, opens read-only schema discovery, and corrects the guidance. > - The agent can complete an authorized hire while company approval and duplicate checks still apply. ## Linked Issues or Issue Description Refs #13068 — the first-task onboarding flow that this change repairs. Refs #12029 — related drift between the sandbox allowlist and bundled hiring guidance. This PR adds schema access; it does not replace the earlier hiring-route fix. **What happened?** A general-role onboarding chief received hiring instructions without the core hiring skills. Sandbox requests to the documented OpenAPI endpoint failed. The agent then guessed question and hire payloads. The persona required new confirmation after validation errors and described waiting states that agents cannot set. **Expected behavior** A direct request authorizes the requested hire. The chief asks only for material missing details, uses valid API payloads, and completes the task. Formal company approval gates still apply. A saved human-input card gives the task a valid waiting state. **Steps to reproduce** 1. Create an onboarding chief with role `general` through the board. 2. Ask it to hire a friendly robot with a supplied name and responsibilities. 3. Check its assigned skills, schema requests, question cards, hire requests, and final task state. **Paperclip version or commit** Reproduced on the first-task onboarding implementation after #13068. The live local verification used this branch at `112f44610`. **Deployment mode** The original failure used a hosted sandbox with legacy Codex ACP. Live verification used an isolated local instance and real `codex_local` execution. Queue and HTTP/2 transport access is covered by automated tests. ## What Changed - Give board-created onboarding chiefs the existing core skills regardless of role. Preserve explicit skill version pins, including aliases. Keep ordinary general-agent defaults and authorization checks. - Allow exactly `GET /api/openapi.json` through both sandbox bridge transports. - Publish validator-tested question, free-text, hire, and waiting examples. Regenerate the runner API reference and capability inventory. - Clarify direct authorization, material ambiguity, and correction of confirmed pre-creation validation failures. Preserve uncertain-outcome reconciliation, duplicate protection, and company approval gates. - Align disposition instructions with agent permissions and the saved human-input waiting path. ## Verification - After rebasing onto current `master`: 69 targeted server tests, 110 queue/HTTP2 bridge tests, and 4 capability inventory tests passed. These cover core skill defaults, version pins, actor restrictions, schema access, published examples, hire validation, idempotency, and approval gates. Waiting recovery tests and live question flows also passed before the rebase. - `pnpm -r typecheck` and `pnpm build` passed again after the rebase. Frozen dependency installation and both generated capability checks passed. - Ran the full `pnpm test:run` suite. The initial run had 14 failed server files due to local database resource limits, a missing built test fixture, and socket failures. All 14 files passed after fixture repair and isolated retries. UI, CLI, workspace packages, database tests, and all 145 serialized server files passed. - Real one-request hiring replay: one hire, one successful run, task done in 2m16s. No repeated approval or recovery escalation. - Real two-turn browser conversation: start with an unspecified hire, then supply a name and friendly robot responsibilities. One clarification card, one hire, two successful runs, task done in 3m27s of execution. No failed writes, confirmation cards, or recovery actions. - Assigned the hired robot a welcome-message task through the browser. It produced a warm message under 100 words and finished in one successful 66-second run, with no questions or recovery actions. - The two-turn flow still asked an optional preferences question and gave a technical final reply. These are remaining presentation limits. - Greptile: 5/5 on `b71f83ba2`, with zero unresolved review threads. Fixed its generator finding and passed 1,655 published-example/runtime API tests plus server typecheck. All latest-head CI checks are green (32 passed; 2 unrelated Storybook checks skipped). The signoff-policy browser test initially timed out while waiting for an approver run. Its shard passed on one rerun without code changes. [CI run](https://github.com/paperclipai/paperclip/actions/runs/34698211049). ## Risks - Onboarding chiefs receive more default skills. Ordinary general agents retain existing defaults, and explicit versions take precedence. - Prompt guidance can affect model behavior. The live replays are examples, not a guarantee that every model follows the guidance. - Retry guidance applies only when validation confirms that nothing was created. Uncertain outcomes still require checking existing agents. - No database migration or new public endpoint. Existing company boundaries, approval gates, and bounded recovery remain in force. ## Model Used OpenAI Codex, model `gpt-6-astra`, with reasoning, tool use, code editing, and live browser verification. The exact context-window size is not exposed in this session. ## 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>	2026-09-12 12:59:42 -05:00
DottaandPaperclip	ab15aff390	feat: add experimental persistent agent chat (#13284) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Conversations must use the same tasks, controls, and execution history. > - Users need an ongoing chat with an agent without managing task properties. > - Agents should clarify and plan work, then hand execution to assigned project tasks. > - This pull request combines the reviewed Agent Chat stack for one squash merge. > - The benefit is persistent conversation with normal task governance and shared UI. ## Linked Issues or Issue Description **Subsystem affected** Task lifecycle, agent runtime tools, shared task UI, and browser/paid runner tests. **Problem or motivation** Users need one persistent conversation with each agent. A separate chat store or renderer would duplicate task behavior and bypass existing controls. **Proposed solution** Use a task-backed chat per company, user, and agent. Reuse the task composer and transcript. Clarify and plan in chat, then create assigned project tasks with the relevant plan. Keep Agent Chat behind its own disabled-by-default experimental setting. **Roadmap alignment** This implements the task-backed direction in [CEO Chat](https://github.com/paperclipai/paperclip/blob/master/ROADMAP.md#-ceo-chat). Related proposals: #2504 and #9693. Related request: #7981. The maintainer requested one squash merge of the complete stack. Consolidates the reviewed runtime [#13281](https://github.com/paperclipai/paperclip/pull/13281), backend [#13282](https://github.com/paperclipai/paperclip/pull/13282), and UI [#13283](https://github.com/paperclipai/paperclip/pull/13283) layers with this PR's E2E coverage. All four layers passed CI and received Greptile 5/5 before consolidation. This PR targets master and includes the complete feature. ## What Changed - Add personal canonical chat tasks with ordinary company visibility, immutable identity, idempotent first sends, and an idle waiting state. - Process `/new` in queue order. Preserve history, release a chat pause, and fence old provider context and delayed writes. - Keep chat lifecycle rules across recovery, finalization, assignment, task lists, and rollups. - Support research and plan revision in chat. Hand plans to ordinary assigned project tasks before execution starts. Reject new chat subtasks. - Add repository-aware project creation and discovery tools, including multiple repository IDs and GitHub URLs, authorization, idempotency, and durable project-created cards. - Reuse task UI components for chat, with starred/recent agent navigation and a separate `enableAgentChat` experimental flag. - Add deterministic browser tests and 24 paid chat cells across four Codex/Claude profiles, with validated reports and screenshots. - Integrate current master recovery, controller lease, queued-message, and task UI changes. Gate chat interruption and deferred promotion on ownership/feature policy. Guarantee lease renewal and active controls are stopped even if teardown fails. - Preserve master's migration 0273 and generate chat migration 0274 with idempotent replay for development databases. ## Verification - Prior exact heads of all four PRs passed Linux CI, including build, typecheck, general/serialized tests, and browser E2E. Each had Greptile 5/5 and no unresolved findings. - Integrated local verification passed: full repository typecheck and production build, Storybook build, token gates, 340 focused UI tests, all 20 deterministic chat browser tests, two migration replay tests, 88 focused chat/queue/native/controller tests, and provider/session regressions including real lease expiry. These include the three lifecycle regressions for the final admission/teardown fixes; server typecheck also passes. Current head `1268eda16cc2af892055917e7292f068820be135` has Greptile 5/5 with no unresolved findings and passing security scans. All final-head CI gates passed: build, full Runner verification, typecheck/release registry, canary, all general/serialized test shards, and all browser E2E shards ([CI run](https://github.com/paperclipai/paperclip/actions/runs/34696739927)). Local PostgreSQL startup contention required serialized retries; skipped fixtures do not count as passing coverage. - The earlier paid campaign passed all 24 chat cells and retained 32 screenshots: [report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-34648511170-1/index.html?report=agent-chat#suite-agent-chat). It tested `abacbdfd2f660709ec37312cdb758284c8399d04`; it is prior evidence, not a paid run of this integrated head. - Manual check: enable Agent Chat in Experimental settings, open an agent, clarify and revise a plan, then hand off to an assigned project task. Stop a reply, send `/new`, and verify fresh context with retained history. Disable the setting and verify agent shortcuts/new chat turns are blocked. ## Risks - Queue/session integration can affect retries and delayed writes. Tests cover ownership, cancellation, reset boundaries, idle recovery, and ordinary task behavior. - Migration 0274 adds conversation fields and constraints. Replay is idempotent and preserves existing development chat history. - This combines the previously reviewed stack at the maintainer's request. Agent Chat remains off by default and is separate from Conference Room. ## Model Used OpenAI Codex, GPT-6 Astra (`gpt-6-astra`), with reasoning, code execution, browser tools, and parallel review. The exact context-window size is not exposed in this session. Codex and Claude also ran as test subjects in the linked paid campaign. ## 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>	2026-09-12 08:56:04 -05:00
DottaandPaperclip	889947c238	feat: add experimental native chat connectors (#13038) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - People also ask agents for work in their existing chat tools. > - Each external conversation needs one task and a current authorized source. > - Retries, Stop, and provider failures must not duplicate work or expose private data. > - The first chat PR establishes the opt-in provider and data contracts. > - This PR adds experimental channel integration and its durable control plane. > - Users can request work from connected channels and inspect delivery in Paperclip. ## Linked Issues or Issue Description Refs #13100 and #13092. This is the second of exactly two chat PRs. Foundation #13100 is merged and changed 143 files. Runner prerequisite #13092 is also merged. This PR changes 400 files against master, below the 500-file review limit. It contains no wireframe images or HTML galleries. ## What Changed - Add native Slack, GitHub, Microsoft Teams, Telegram, and Discord chat connections. Keep chat disabled unless the operator enables experimental chat connectors. Preserve the production GitHub tool connection and its normal setup path. - Bind each provider bot identity to one immutable Paperclip agent. Bind each admitted external conversation to one task. Paperclip owns tasks, runs, permissions, and audit records. - Add durable admission, per-conversation queues, questions, task controls, progress, final replies, images, files, and delivery receipts. Board comments remain internal unless explicitly sent to the channel. - Check current identity, provider reach, resource access, credentials, runtime generation, and exact source before provider effects. Keep private responses private. Never send raw reasoning, private logs, credentials, or tool arguments. - Hold uncertain sends for explicit audited resolution. Make Board Send-to-channel atomic and idempotent. Keep reconnect and setup credentials in Paperclip secret storage. - Preserve current native-runner authority across retries, lost acknowledgements, and recovery. Keep immutable input and completion contracts separate from newer user input. Receipt reconciliation cannot launch a provider. - Reconcile chat close/new ordering and provider-effect lock order. Audit resource access changes in the same transaction. Submit only the selected resource from each UI toggle so stale pages cannot undo unrelated access changes. - Drain Codex stdout before certifying process exit. Bound the drain with the existing shutdown grace. Preserve observed terminal authority without treating an undrained process as successful or reusable. - Incorporate master `018ca5da` with its ACP Stop, mobile task layout, runner packaging, and official lock changes. Preserve dedicated chat-answer continuations in both directions when ordinary queued comments are adopted after Stop. - Fence late adapter readiness behind an earlier Stop for the same run. Preserve verified cleanup for registered adapters. Handle single Stop, agent pause, duplicate Stops, and failure release without creating a false cancellation receipt. - Incorporate master's `6dd48cad4` wake-queue extraction. Preserve exact failed-chat retry authorization and lineage, retired question-source suppression, and the block on generic recovery that would discard the admitted source. Fresh deferred input retains its separate promotion path. - Incorporate master `2a05b5ed3` and its queue-admission extraction, simplified transaction ports, and separate runner CI job. Preserve exact durable receipts, actor separation, and dedicated-answer isolation through the new module. A failed receipt insert rolls back the accompanying deferred-wake merge. ## Verification Current head: `afe19299d06253cb628eb398e91d1200ea9f412a`, incorporating master `2a05b5ed3457ea33efd6895520447d1d97fe98d8`. The conflicts are resolved. This successor fixes two test-harness boundaries exposed by CI: per-case route-module preparation and actual durable-save completion before intentional runner termination. Production code and all existing test/turn deadlines are unchanged. [Exact-head Greptile review](https://github.com/paperclipai/paperclip/pull/13038#issuecomment-5587250594) is **5/5**, completed September 10 at 13:20:55 UTC, with no actionable findings or open review threads. [Fresh exact-head CI](https://github.com/paperclipai/paperclip/actions/runs/34481724341) passes **all 24 jobs**, including Build and both required aggregates. Normal exact-head guarded merge was attempted and rejected by the remaining branch approval policy: CODEOWNER review is required and no human approval is present. Normal **squash auto-merge is enabled** as of September 10 at 13:36:26 UTC. Requested CODEOWNERS have been notified; no approval bypass or self-approval was used. Earlier-head results below remain historical evidence, not qualification of this successor. - Final exact-head Linux evidence: 995/995 chat integration cases; 36/36 agent-skills routes; 35/35 runner live-session cases, including real process kill/resume; 1948 runner Vitest cases with three existing benchmark/platform guards; 870/870 API-authority cases; and 104 browser cases with four existing optional skips. Rust, conformance/replay, full repository build, typecheck, canary, all server/workspace shards, and both required aggregates pass with normal CI concurrency. Earlier failed attempts remain recorded below. - Latest test-only qualification: 141/141 route/permissions/authentication cases pass in separate cold forks, with plain server types and independent review clear. The real-runner suite passes 35/35, with plain runner types and independent review clear. A controlled premature-save acknowledgement fails as expected; matching ownership/effect/process evidence, rejected saves, real turn outcome, test abort, and pre-kill liveness are covered. No local reproduction of the original CI scheduling failure is claimed. The preceding [CI run](https://github.com/paperclipai/paperclip/actions/runs/34479680858) passes 21/24 jobs, including all 995 Linux chat cases and browser aggregate (104 passed, four existing optional skips); only Build, the skills serialized shard, and the required verification aggregate fail. Its exact-head Greptile review was 5/5. Both failed job logs are retained. - Final fixture qualification: all eight focused Discord cases and all 995 chat integration cases pass. The exact modal statement/PID is observed before taking the real connection lock; the test then proves its actual blocking relationship before mutation. Original SQL execution, provider behavior, negative assertions, and 1s/15s timeouts remain unchanged. Independent review is clear and test/production hashes remain frozen. The preceding [CI attempt](https://github.com/paperclipai/paperclip/actions/runs/34477184777) passed 22 jobs, including Build/runner, typecheck, canary, all other test shards, and browser aggregate (104 passed, four existing optional skips); the two fixture failures and failed verification aggregate remain recorded, not relabeled as a pass. - Current queue-module composition: 308/308 recovery/batching/queue/Stop tests; 995/995 full chat integration; 89/89 module tests, including real PostgreSQL receipt-insert rollback; 24/24 workflow/module-boundary tests; plain server and UI types. All four actual local process/ACP browser paths pass in 1.4 minutes. Fresh databases, no skips or retries, stable reviewed source hashes. The initial boundary failure is retained; its no-op service wrapper was removed without changing recovery context or weakening the check. An exploratory standalone test-directory typecheck fails because its new upstream transformation config is not a standalone typechecking project; standard CI/build does not invoke it, and no configuration was weakened to suppress those diagnostics. - The preceding head `e02a63d462ce5d47433b0aeb632bb6fd20aab1ba` passed [all 24 CI jobs](https://github.com/paperclipai/paperclip/actions/runs/34436462958) and exact-head Greptile review at 5/5. Required CODEOWNER review prevented its normal merge before master advanced again. - Final extracted-module composition: 307/307 recovery, batching, queue and Stop-control tests; 995/995 full chat integration; 49/49 module tests including eight PostgreSQL adapter cases; and 19/19 issue-update tests. Plain server types pass. All four actual local process/ACP browser paths pass in 1.3 minutes. Fresh databases, no skips or retries in these cohorts, frozen source hashes, and independent review clear. - The preceding head `3e4e1c1c` passes [all PR CI jobs](https://github.com/paperclipai/paperclip/actions/runs/34415826820), including Build and required `ci / verify` and `ci / e2e`. Both the original Rust failure and the previously load-sensitive lineage fixture pass with unchanged Linux concurrency. Master advanced afterward and required this reconciliation. - Final master composition: 448/448 focused UI tests, 186/186 adapter tests, 24/24 queue/control tests, and 11/11 packaging tests. Plain UI, server, shared, and adapter types pass. Token gates and diff checks pass. Independent server and UI reviews are clear. - Stop-registration regression: both real-service cases fail against exact `a95` source and pass with the fix. The full corrected recovery/control suite passes 265/265. Duplicate-owner and failed-Stop controls also pass. Plain server types pass. The readiness barrier prevents provider startup without adding an acknowledgment to an already terminal run. - Final qualification strengthens terminal-field equality and repeats both affected cases successfully on a fresh database. All four actual local process/ACP browser paths pass again in 1.3 minutes, without skips or retries. The final screenshot shows Cancelled, a paused subtree, retained input, and no error toast. - Two new actual-service regressions fail before the merge fix. They prove that queued-comment adoption could consume a dedicated chat answer or add unrelated input to that answer. The fixed four-case cohort passes, including ordinary upstream continuation and adapter Stop controls. Full recovery passes 257/257. All four actual local process/ACP Stop browser flows pass in 1.4 minutes, without skips or retries, on a fresh database. - The unchanged runner artifact was qualified with 171/171 transport tests, 870/870 API-authority tests, conformance 1/1, and replay 11/11. Six controlled reader tests prove the exit/drain repair. Its local serial Rust workspace passed 546 top-level cases plus two invoked helpers; the later passing Linux CI supplies default-concurrency evidence. - Prior exact-source full chat integration passes 995/995. Settings regressions cover concurrent stale pages, 501 destinations, pending state, rejected updates, and explicit retry. These deterministic tests do not prove live provider behavior. - Retained failed attempts and their causes are in the [qualification log](https://github.com/paperclipai/paperclip/blob/afe19299d06253cb628eb398e91d1200ea9f412a/doc/plans/chat-adapters/2026-09-08-chat-queue-and-webhook-repair.md). The first merge adapter run timed out while macOS slept for 290 seconds. Its unchanged repeat passed with a temporary sleep guard. No assertion, deadline, or CI gate was weakened. Review commands include `pnpm --filter @paperclipai/server exec vitest run src/__tests__/heartbeat-process-recovery.test.ts src/__tests__/issue-queued-comments-routes.test.ts` and `pnpm exec playwright test --config tests/e2e/playwright.config.ts tests/e2e/acp-stop-continuation.spec.ts`. Database suites require fresh disposable databases. See the [browser runbook](https://github.com/paperclipai/paperclip/blob/afe19299d06253cb628eb398e91d1200ea9f412a/doc/plans/chat-adapters/2026-09-04-chat-adapters-browser-e2e-runbook.md) for provider setup and separate live acceptance steps. ## Risks - This remains experimental. Deterministic tests and bounded live evidence do not establish every provider feature, tenant, permission layout, or media shape. Teams work-tenant qualification is still open. - Failed and uncertain provider effects remain visible and can require operator action. A transport receipt does not prove recipient visibility. - Native controller and runner artifacts must remain compatible. Preserve lease ownership, terminal authority, source binding, and quarantine during future changes. - Access and audit rows commit together, but activity notifications remain best-effort. This is not a new durable event outbox. - The PR operation does not deploy a live server, replace its runner, or change provider permissions. Remaining live qualification is documented in the [temporary handoff](https://github.com/paperclipai/paperclip/blob/afe19299d06253cb628eb398e91d1200ea9f412a/doc/plans/chat-adapters/2026-09-08-open-qualification-followups.md). ## Model Used OpenAI Codex assisted with implementation, tool execution, testing, and review. The work records `gpt-6-astra` assistance. The environment does not report a context-window size. No private reasoning traces are included. ## 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>	2026-09-10 10:06:45 -05:00
DottaandPaperclip	5bddff0920	feat(runner): add guarded API search and call fallback (#13003) ... ## Thinking Path > - Paperclip manages AI agents and their work. > - The new runner gives agents dedicated tools for common tasks. > - Some API operations and parameters have no dedicated tool. > - Agents need a controlled way to find and use those operations. > - This pull request adds API search and calls through the real server routes. > - Existing tools remain the preferred path. The new tools are disabled by default. > - Paired tests measure correctness, tool choice, cost and time. ## Linked Issues or Issue Description **Subsystem affected** Paperclip Runner contracts, production tool authority and the server API catalog. **Problem or motivation** The runner cannot use much of the API described by the old Paperclip skill. A generic HTTP client would also let agents bypass runner control rules. **Proposed solution** Add `search_api` and `call_api`. Resolve calls from the mounted API catalog. Use server-held, run-bound credentials. Preserve route checks and runner lifecycle rules. Keep the tools disabled until an operator enables selected companies. **Alternatives considered** A dedicated tool for every endpoint would add a large initial prompt. An unrestricted HTTP tool would weaken authorization and replay controls. **Roadmap alignment** This extends the native runner tooling. The repository owner requested this design and implementation. The roadmap and related open PRs were checked. No duplicate API escape-hatch PR was found. ## What Changed - Register two compact fallback tools in canonical contracts and provider projections. - Build deterministic API discovery from OpenAPI, mounted experimental routes and the old skill reference. - Execute bounded JSON, text, file and download requests through authenticated HTTP routes. - Recheck active runs, company access and work modes. Block runner lifecycle, scheduling, credential and approval bypasses. Keep routine annotation collaboration available. - Retain mutation receipts. Report uncertain outcomes without blindly repeating writes. - Add a company rollout gate and a durable eval worker with complete cost accounting checks. - Record child-task creation in the activity log with the agent and run. - Add contract, authorization, file, replay and real runnerd/PRP/HTTP tests. - Document rollout gates and paid coverage limits. The companion eval repository retains immutable attempts and reports. ## Verification - Final app commit `da58370524c3626a744eec20164397c5fb6ba9ef`: all 32 checks passed; the unrelated Storybook visual check was skipped. Greptile 5/5; no unresolved review threads. - Full Linux build and recursive typecheck passed. Repository tests were run by project and serialized shard; all 143 serialized server suites passed. - Runner TypeScript: 1,599 passed, two skipped. Rust release: 451 passing test reports. Conformance and replay parity passed. The required API check passed 837 tests, including runnerd → PRP → authority → real HTTP. - Bindings cannot enable API tools without the explicit deployment flag. Unit and real-authority tests prove the default-off boundary. - The standalone API check builds and stages its own binary. It passed after existing staged and debug binaries were removed from the test container. - UI and CLI tests passed. Initial environment failures (missing jq, Docker overlay file identity, and parallel linker memory pressure) and focused passing reruns are retained. The macOS full runner suite has platform-specific failures; Linux is the qualified full-check platform. - Eval harness: 27 tests passed; existing CI discovery ran 86 tests with two unrelated skips. Credential export rejection is tested against the actual report command. - Luna and OpenRouter Sonnet each passed 60 common-workflow runs: ten workflows, three repetitions per arm, zero unnecessary API fallback. - Sonnet passed 11 selected capability/contract cases after fixes. Gemini passed three smoke cases. DeepSeek exceeded the 120-second limit and remains unqualified. - Luna's two cost flags received focused follow-up. The original flags and a later n=1 latency flag remain visible. Sonnet had no cost or latency increase above 20%. - The catalog contains 785 entries; 58 were exercised across all stages. Most operation probes remain unrun and some need additional fixtures. Authored probes do not establish successful coverage. - Total conservative accounted cost: $9.875960. Active paid-campaign time: 88.16/90 minutes. No missing accounting. Later security and harness fixes have provider-free verification; no paid validation is claimed for those revisions. - Inspect the [qualification report](https://github.com/paperclipai/paperclip-evals/blob/codex/seach-call-api-tools/evals/runner-api-tools/reports/2026-09-07-production/READINESS.md) and [verification record](https://github.com/paperclipai/paperclip-evals/blob/codex/seach-call-api-tools/evals/runner-api-tools/reports/2026-09-07-production/verification.json). ## Risks - This is a broad authenticated API surface. Keep the default-off gate until an operator selects initial rollout companies. - Paid coverage is incomplete. Small regression samples do not prove all workflows are unchanged. - A timeout or server failure can follow a committed mutation. The result reports an unknown outcome and requires state inspection. - The new definitions add prompt tokens. The report retains cost flags and cache variation. - No database migration is required. - Repository rules require code-owner approval before merge. Technical CI and automated review are complete. ## Model Used OpenAI Codex based on GPT-6 assisted with code, tests and review. The exact serving model ID and context window are not exposed in this session. It used reasoning, tool calls and code execution. Eval models: `gpt-5.6-luna` with low reasoning, `openrouter/anthropic/claude-sonnet-5`, `openrouter/google/gemini-3.8-flash`, and `openrouter/deepseek/deepseek-v4-flash-0731`. Attempts retain runtime versions, model identity, usage and source provenance. ## 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>	2026-09-07 14:14:43 -05:00
Dotta	560e7e48b5	feat(runner): add SDK and developer tooling (#12608) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The runner package already provides the production protocol and execution spine. > - Contributors still need stable SDK surfaces, deterministic test tools, and local inspection tools. > - Those surfaces share generated contracts and must change as one package boundary. > - This pull request adds the package-local SDK, labs, examples, and drift checks. > - The benefit is a reviewable developer platform that does not change application execution selection. ## Linked Issues or Issue Description **Subsystem affected** `packages/paperclip-runner` — runner SDK, conformance tools, and developer tooling. **Problem or motivation** The production runner spine is present, but package consumers cannot build deterministic integrations, inspect sessions, or verify provider-neutral behavior through supported surfaces. **Proposed solution** Add browser, React, standalone, live-session, scenario, conformance, and evaluation surfaces. Add generated contract inventories and package-local verification scripts. Keep production application routing unchanged. **Alternatives considered** We considered splitting each generated catalog, SDK surface, and demo into separate pull requests. Those changes share exports, fixtures, and drift gates. Splitting them would create intermediate package states that do not build. **Roadmap alignment** No overlapping item appears in `ROADMAP.md`. This work extends the runner package that is already on `master`. ## What Changed - Add browser, React, standalone, live-session, and issue-thread SDK surfaces. - Add deterministic mock control-plane, scenario, conformance, replay, and evaluation tools. - Add bounded Codex, OpenCode, and ACPX development transports and fixtures. - Keep deferred managed-provider execution fail-closed. Persisted compatibility data remains readable. - Add generated capability inventories with their source files and drift checks. - Add examples, package documentation, browser checks, and clean-consumer checks. - Preserve the reviewed protocol bounds, replay compatibility aliases, process environment isolation, and semantic redaction limits. - Update the ACPX package patch that the existing workspace patch registry already tracks. - Do not change `pnpm-lock.yaml`, repository workflows, server runtime selection, or the application UI. ## Verification GitHub Actions is the verification authority for this pull request. The repository CI, package TypeScript and Rust checks, package tests, generated-output drift checks, browser checks, security scans, and Greptile review must pass on the exact head. Local test suites were not run because this series uses parallel GitHub Actions for verification. ## Risks This is a large greenfield package change. The main risks are public export drift, generated-output drift, and optional React consumer compatibility. Package boundary checks, clean-consumer checks, and browser tests cover those risks. Production adapter selection and server execution are outside this pull request. ## Stack 1. **This PR:** runner SDK and developer tooling. 2. [Codex production server integration](https://github.com/paperclipai/paperclip/pull/12616). 3. [Provider-neutral task-thread UI](https://github.com/paperclipai/paperclip/pull/12617). ## Model Used OpenAI Codex, GPT-5, high-reasoning mode, with tool use and code execution. ## 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 following the feature request template - [x] I have not referenced internal/instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal Paperclip ticket id - [ ] 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 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	2026-08-31 21:33:11 -05:00
DottaandPaperclip	23048f1219	Add canonical semantic action catalog to Paperclip Runner (#12121) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Paperclip Runner now has a durable PRP transport and a Codex provider bridge. > - Codex must use stable, provider-neutral action contracts before Paperclip can grant run-scoped tool access. > - A catalog must describe actions without granting permission to discover or invoke them. > - Generated inventory must stay synchronized with its TypeScript source. > - This pull request adds the canonical Codex-spine semantic action catalog inside the runner package. > - The benefit is a small review unit for schemas and inventory before authorization and dispatch land. ## Linked Issues or Issue Description **Subsystem affected** Cross-cutting. This pull request extends private runner infrastructure in `packages/paperclip-runner`. **Problem or motivation** The Codex provider bridge has no canonical description of the Paperclip actions that a later authorization layer can project into a run. Independent operation lists can drift in names, claims, task modes, effects, and input bounds. **Proposed solution** Add one immutable v1 catalog for the first 27 Codex-spine actions. Give each action a stable identifier, placement, effect, required claims, supported task modes, and JSON Schema input and output contracts. Generate a deterministic JSON inventory from that source and fail package checks on drift. **Alternatives considered** The combined runner branch contains larger live and scenario catalogs with authorization, bindings, labs, and other providers. That change is too large for this review unit. A generic API escape hatch would also bypass the operation-level boundary, so this catalog excludes it. **Roadmap alignment** This work supports the governed tool access direction in `ROADMAP.md`. It does not add a tool gateway, application binding, server endpoint, or production authorization decision. **Additional context** Refs #12111 and #11962. Pull request #12111 was squash-merged first. This branch starts at the resulting `master` commit. Its delta is 10 files. ## What Changed - Added 27 versioned, provider-neutral semantic action declarations for the Codex spine. - Added bounded JSON Schema input contracts and normalized operation receipt output contracts. - Added placement, effect, claim, mode, and role metadata. - Added a deeply frozen public catalog and an operation lookup helper. - Added a deterministic checked-in JSON inventory and generation commands. - Added a byte-for-byte drift gate to the package build. - Added AJV schema compilation, mutation-bound, forged-field, immutability, inventory, and non-executable-boundary tests. - Exported only the catalog types and declarations from the existing package root. - Documented that catalog membership does not grant discovery, authorization, dispatch, or application binding. - Kept server code, UI code, other providers, scenario-only actions, labs, generic API access, authorization, dispatch, and receipts processing out of this pull request. ## Verification - `pnpm --filter @paperclipai/paperclip-runner check:all` passes. - TypeScript protocol tests pass: 8 Node tests and 49 Vitest tests. - All package Rust tests and conformance and replay parity checks pass. - `pnpm --filter @paperclipai/paperclip-runner check:semantic-action-catalog` passes. - `pnpm -r typecheck` passes. - `pnpm build` passes. - `pnpm check:token-gates` passes. - Prettier and `git diff --check` pass for the changed source and documentation files. - The generated catalog matches its source byte for byte. - The secret scan is clean. - The delta against `master` is 10 files. `pnpm-lock.yaml` is unchanged. - `pnpm test:run` completed locally with 4,692 passing tests, 19 skipped tests, and 24 failures in 8 unchanged server test files. The failures reproduce the established local macOS path-alias, listener, and workspace-runtime baseline. No changed-file test failed. Linux CI remains the repository handoff authority. - The full Linux PR workflow passes, including the aggregate `verify` gate. - Snyk, Socket, Superagent security, and supply-chain checks pass. - Greptile is 5/5 with no actionable comments, recommendations, or follow-ups. - Storybook visual regression skipped by design because this pull request changes no UI file. - Browser and migration tests are not applicable because this pull request changes no server, UI, database, or migration file. ## Risks Production behavior is unchanged because no consumer projects this catalog into a provider run. The main risks are contract drift, unbounded mutation input, forged scope fields, accidental executable authority, and generated inventory drift. Closed input schemas, explicit bounds, a frozen catalog, tests, and the byte drift gate cover these risks. The later authorization layer must still bind every action to the active run and company before discovery or invocation. I checked `ROADMAP.md`. This change is private contract infrastructure for the governed tool access direction. It does not duplicate a shipped or public product surface. ## Model Used OpenAI Codex with GPT-5 was used. The exact serving model ID and context size were not exposed. The model used high reasoning, repository tools, GitHub tools, and local code execution. ## 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 - [ ] 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>	2026-08-24 16:26:21 -05:00