6 Commits

Include renames

Author	SHA1	Message	Date
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	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	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	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	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