mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-11 14:10:50 +02:00
codex/plugin-task-execution
9
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 DottaandPaperclip
|
caf120105c |
test: prepare neutral native connection guidance evals (#15407)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents need to discover connections, obtain consent, and continue from saved decisions. > - We want to reduce repeated instructions only when measured behavior supports the change. > - The existing decline tasks tell the model not to retry. One provider-decline check can pass without an explanation or an observed service counter. > - This PR adds neutral tasks and stricter saved-evidence checks before any connection instruction reduction. > - Production instructions remain unchanged. The new cells are configured, not live-qualified. ## Linked Issues or Issue Description Refs #15218. Refs #15389. **What existing behavior does this improve?** The Product E2E connection workflow evaluation and its instruction measurement provenance. **Current behavior** Some decline prompts supply the policy they intend to test. The provider-decline workflow does not require a saved post-decision explanation. Its old no-call check can use a missing fixture counter as zero. OpenCode has no connection cases in the original Everyday matrix. **Proposed behavior** Add an explicit-only suite with five connection stories on native Codex, ACPX Claude, and OpenCode. Require an explanation attributed by exact run ID after a saved decline. Observe the provider fixture counter. Preserve the original cases and grades. ## What Changed - Add fifteen configured cells with one attempt, twelve-minute deadlines, and verified 1,000-cent company and agent budget stops. - Remove procedure hints from the three new decline prompts. Keep a user-permitted explanation fallback and the existing positive controls. - Require saved decline state, one decision, unchanged connections, observed zero service calls where applicable, and a post-decision explanation from a successful run on the same task. - Add negative grader calibration and test the actual fixture budget payloads. Exclude the suite from default and generic selection. - Extend the existing full-catalog measurement source manifest with connection descriptions and schemas. Add an audit of fixed text, tool descriptions, returned instructions, and unqualified behavior. - Rebase on master `a6306ba606eb87c89b9ef0344e9fe8e0025580f9` and preserve its new Cursor suites. No production, credential, workflow, or lockfile change. ## Verification - Before rebase: Product E2E support passed 1,424 TypeScript tests and 128 Node checks. Six catalog measurement tests, repository typecheck/build, Product E2E typecheck, and exact fifteen-cell discovery passed. - The full pre-rebase repository test run was stopped when master advanced. Its partial result is not a pass. - After rebase and the review correction: repository build/typecheck, Product E2E typecheck, 1,799 TypeScript support tests (one skipped), 128 Node checks, six measurement tests, and exact fifteen-cell discovery pass. The duplicate local full-suite run was stopped incomplete after about 20 minutes once complete CI passed; no local full-suite pass is claimed. - Review found that the initial grader read `runId` instead of public `createdByRunId`. A regression calibration reproduced both rejection of valid public comments and acceptance of the wrong alias. The fix uses the actual field and binds the evidence type to the shared `IssueComment` contract. A subsequent type-only import path correction passes Product E2E typecheck. - Final source `0de306b9664bfbdebb6709ddb54c95152740d1ad` passes [complete CI](https://github.com/paperclipai/paperclip/actions/runs/37560250545): 51 successful checks and two intentional Storybook skips, plus separate Snyk success. Fresh Greptile review is 5/5 with the single review thread resolved and no new findings. The PR is clean and mergeable. - Local commands: `pnpm build`, `pnpm -r typecheck`, `pnpm test:e2e:runner:unit`, `pnpm test:e2e:runner:typecheck`, and `pnpm test:e2e:runner -- --list --suite native-connection-guidance`. The measurement uses `PAPERCLIP_NATIVE_PROCEDURE_MEASUREMENT=/tmp/connection-measurement.json pnpm exec vitest run --project @paperclipai/server server/src/__tests__/native-procedure-measurement.test.ts`. Validation used pinned pnpm 9.15.4. - No paid provider campaign was started. There is no baseline/candidate behavior result for these new cells. - The audit records 654 UTF-8 bytes of fixed connection guidance. A clean capture at `a04b8c6a452315625014888335d45670a2094fb6` confirms 41 supplied tools, 53,341 normalized bytes at start/resume, 50,949 at compact continuation, and a 48,195-byte authenticated OpenCode MCP catalog. These are byte counts, not tokens, bills, vendor-private prompt sizes, or savings from this PR. ## Risks - This is eval preparation. Passing support tests do not establish live model behavior or qualify an instruction reduction. - The explanation oracle checks attributed saved output. It does not prove cognition or arbitrary prose truthfulness. One saved interaction also does not prove the absence of repeated idempotent tool calls. - Successful new authentication and tool refresh, existing-connection agent grants, independent work while waiting, explicit retry after decline, and blocking when mandatory work remains still need separate coverage. - Notion setup decline does not execute a real Notion service. Positive service approval uses an already installed deterministic service; it does not qualify new connection creation. - The original historical failures remain unchanged. Future comparisons must freeze source, fixture, model, input, and grading controls and retain every actual attempt. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, repository tools, and code execution. The exact serving model ID and context-window size were not exposed in this session; they are not inferred. No model provider was invoked by the eval suite in this PR preparation. ## 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> |
||
|
DottaandPaperclip
|
72ff3a9f27 |
Measure native tool context and expand bounded workflow evals (#15218)
## Thinking Path > - Paperclip manages persistent agents and their assigned work. > - Agents receive both fixed instructions and tool definitions. > - Moving a procedure into a tool description still adds model context. > - We need to measure the complete delivered catalog and test real outcomes. > - The tested reductions saved little space and introduced failing outcomes. > - This PR keeps measurement, bounded eval coverage and the original evidence. > - Production prompts, tools and runtime behavior stay unchanged. ## Linked Issues or Issue Description Refs: #15151, #14961, #14948, #14985. This adds the measurement and eval coverage needed to assess further native instruction changes. The attempted hiring and dependency reduction failed qualification and is excluded from the final diff. ## What Changed - Measure the actual standard-mode tool authority, including all 39 tools and their input schemas. Capture scripted native start, resume and continuation payloads and the OpenCode MCP declaration list. - Add OpenCode to the two explicit-only local hiring/reuse and delegation/feedback stories. Preserve the original task requests and independent oracles. - Apply one attempt per selected story and explicit company and lead-agent budget stops. - Select managed hiring credentials from the requested profile, including OpenRouter. - Run the existing Node test files under Node instead of collecting them as Vitest suites. - Retain sanitized comparison reports, original failed grades, source hashes and evidence gaps. ## Verification Final source: `2e7cef78eef7cdfe02265e0dcb03e855b8e50bd8`. Local verification passes: - Full repository `pnpm -r typecheck` and `pnpm build`. - Eval-support unit tests: 1,252 Vitest checks and 128 Node checks. - Eval TypeScript check and six final-source measurement tests. All 36 normalized components across nine scripted deliveries and the OpenCode MCP catalog match the baseline exactly; the complete standing projection is 49,200 bytes. Fresh review of this exact head is [5/5 with no remaining findings](https://github.com/paperclipai/paperclip/pull/15218#issuecomment-5996723170); all three review threads are resolved. [Final-head CI](https://github.com/paperclipai/paperclip/actions/runs/37354539126) passes all 47 jobs, including repository typecheck, build, tests, runner checks, browser shards and the canary check. One initial annotation-test timeout is retained in attempt 1; its seven-test suite passed locally, and the affected CI lane passed on one targeted retry. No source or paid eval rerun was needed. Both ready-transition security scans passed with zero annotations. The PR is out of draft and conflict-free. GitHub still requires code-owner approval for the `package.json` test-script change; its requested reviewers are already set. A byte-for-byte comparison against master context `a65ca0950834a85bb93bcc4b4042ecacdebfef53` confirms no production changes under `packages/` or production `server/` paths. The only server addition is a measurement test. No new paid rerun is needed to compare unchanged production bytes. This does not claim that existing product defects have been fixed. The rejected corrected experiment had baseline **5 PASS / 1 FAIL** and candidate **3 PASS / 3 FAIL**, including **two newly failing pairs**. The later readiness experiment had candidate **3 PASS / 3 FAIL** and baseline **3 PASS / 2 FAIL / one setup cell without a behavioral grade**. Its five comparable pairs had two new failures, two new passes and one unchanged pass. The missing baseline Codex cell never reached its provider step because Docker setup timed out. The observed missing behaviors include parent continuation, waiting for the latest child revision, revised ZIP delivery and OpenCode credential persistence. Those failures remain failures. Source review and passing CI do not regrade them. The original reduction saved 460 bytes; its first repair saved only 125 bytes, and the larger unqualified runtime repair increased the full projection. None of those production changes is shipped here. Read the [report](https://github.com/paperclipai/paperclip/blob/2e7cef78eef7cdfe02265e0dcb03e855b8e50bd8/doc/plans/2026-10-05-native-procedure-guidance.md) and its linked sanitized receipts for exact sources, original campaign links, pair-level results and evidence limitations. ## Risks - Full-catalog bytes are not model tokens, invoices, private vendor prompts, lazy-loading behavior or truncation proof. - The two stories are explicit-only and do not prove general coding quality or arbitrary resume behavior. Single trials do not establish causation or performance trends. - The retained OpenCode candidate credential guard failed. Cleanup removed the original provider database, so the precise persistence mechanism remains unknown. The guard is unchanged. - ACPX provider-execution IDs lack proven host-call mapping. No extra-work or feedback-consumption claim is inferred by matching names, order or counts. - PostgreSQL cannot start locally while the host's shared-memory slots are exhausted. Hosted CI must supply the full database checks; the full local database suite is not claimed green. ## Model Used OpenAI Codex, based on GPT-6, with repository tools and code execution. The exact deployment model ID and context-window limit 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> |
||
|
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> |
||
|
DottaandPaperclip
|
862a5758ba |
fix(agents): reduce hiring templates to role descriptions (#14985)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - New agents receive role instructions from onboarding, the hiring skill, or a team package. > - These sources repeat harness procedures and impose generic work policies. > - They can crowd out the task and the harness instructions. > - This pull request reduces those sources to short role descriptions. > - It preserves configuration, skills, authentication, reporting lines, and approval controls. > - The benefit is less repeated instruction text with explicit coverage for the default hiring path. ## Linked Issues or Issue Description Refs #3307. The CEO template can impose a fixed delegation route instead of letting the agent choose how to fulfill the request. This change removes that route. It does not implement autonomous goal selection. Related work: #14920 preserves stock Codex base instructions. #14948 reduces the generic manual and shared runtime prompts. #14961 improves native completion-tool descriptions. This PR is separate from those changes. ## What Changed - Select only the short CEO `AGENTS.md` for new default CEO bundles. Keep the three former companion files as compatibility assets. - Reduce the first-agent chief-of-staff prompt and coder, QA, UX, and security role examples. - Reduce seven bundled team role bodies. Preserve their role, reporting, and skill metadata. Regenerate the catalog. - Make hiring examples optional. Replace the long generic role manual with short role drafting guidance. Preserve explicit requester instructions. - Add configuration and import coverage for native and legacy managed bundles, custom instructions, first-agent rendering, and catalog contents. - Add an explicit-only hiring eval that starts from the production CEO default and checks one coder hire, independently computed JSON output, saved instructions, and worker reuse. - Include the full prompt comparison and a separate three-request drafting simulation. Neither is a live provider comparison. Prompt differences: [before and after](doc/plans/2026-10-02-hiring-template-prompt-diff.md). The CEO default falls from 1,897 to 20 words. The coder example falls from 652 to 18 words. Word counts describe instruction size, not outcome quality or billing. ## Verification - PASS: 99 focused server tests and eight shipped-catalog tests. - PASS: catalog generation and validation for four shipped teams. - PASS: hiring skill validation. - PASS: `pnpm -r typecheck`. - PASS: `pnpm build`. - INCOMPLETE: the full local `pnpm test:run` was stopped before rebase. Its original log is retained. This is not a completed full-suite pass. The full current-head GitHub CI workflow passed: https://github.com/paperclipai/paperclip/actions/runs/37073372419. - PASS: `pnpm test:e2e:runner:typecheck` and `pnpm test:e2e:runner:unit` (63 files / 843 tests). - PASS: discovery for the two new hiring cells, 50 existing everyday cells, and the full 438-cell catalog. - PASS after rebase: 99 server tests, 11 catalog tests, 62 selected E2E support tests, and the E2E typecheck. - PASS: all current-head PR checks at `57dcee147ed0b2d2e3cc657cd9e50fb16bf9ec25`: 51 successful check runs, two intentional Storybook skips, and successful Snyk status. Fresh Greptile is 5/5 with zero unresolved threads. - PENDING follow-up: matched live hiring runs on frozen integration refs. No live outcome-quality or non-regression result is claimed from the configuration checks or this merge. The new suite has two local native cells: Codex and ACPX Claude. It expects five provider turns per cell. It compares source-derived bundles, so the historical long templates remain admissible. Missing successful source-read receipts make a pair uncomparable. They do not establish a behavior regression or equivalence. ## Risks - New default roles have fewer prescribed procedures. Live checks must determine whether a removed instruction was needed for an outcome. - Existing custom and saved bundles keep their contents. The retained companion assets avoid a source-file compatibility break. - Specialized Summarizer, Reflection Coach, and Wiki Maintainer prompts remain unchanged. Their product contracts need separate review. - The generic non-CEO fallback reduction is in #14948. This PR alone does not provide its eight-word fallback. - Configuration tests and drafting simulations do not establish live outcome quality. QA, UX, security, and chief-of-staff hiring behavior remain outside the new two-cell comparison. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used OpenAI Codex, based on GPT-6, with reasoning, code editing, shell tools, and delegated verification. The runtime does not expose the exact deployment 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> |
||
|
DottaandPaperclip
|
24beb00575 |
feat(runner): add rich ACP transport and durable interaction foundation (#14430)
Add shared rich ACP transport, durable questions and permissions, verified provider packaging, and bounded activity and plan presentation. Keep Cursor, Copilot, and Pi pending their separate provider qualification. Persist interaction settlement before publication, fence failed writes until fresh recovery, and preserve owned-process cleanup. Incorporate reviewed mainline integration with extended harness coverage. Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
9d19f98b50 |
fix: harden native chat recovery and add coordination evals (#13741)
## Thinking Path > - Paperclip helps people manage AI agents and their work. > - Agent chat uses native runner sessions to plan, delegate, and track that work. > - A user can press Stop while the native session is still starting. > - The server can acknowledge that Stop without dispatching it, then let the session submit a turn. > - This leaves chat recovery waiting for an execution that the user expected to stop. > - This PR waits for the startup handle, dispatches cancellation, and prevents a late startup from submitting a turn. > - New full-stack evals check the resulting records and outputs across Claude and Codex. > - Those evals also exposed missing ACPX readiness fields, unbounded polling, and an old-run identity check that rejected valid warm handoffs. ## Linked Issues or Issue Description **What happened?** Stop during native startup could record an acknowledged cancellation with `dispatched: false`. The provider could then begin work. A subsequent `/new` stayed queued. A remote Claude follow-up also exhausted the command journal while probing warm-session readiness: ACPX never returned the readiness fields required by the shared transport. Once readiness worked, attachment incorrectly compared the next run descriptor against the old run ID. The 25 ms polling loop could issue 4,800 commands during its two-minute wait, beyond the 500-command bound. The existing chat eval treated lifecycle logs as proof of an active provider turn, so it did not distinguish startup cancellation from active-turn cancellation. **Expected behavior** A Stop during startup must reach the pending session. A late session must not submit a prompt after Stop. Recovery must retain control when startup exceeds the bounded wait. Chat evals must check saved task state, document contents, worker identity, account binding, and duplicate effects. **Steps to reproduce** 1. Start a native Claude or Codex chat turn. 2. Press Stop after process startup is requested but before the provider turn starts. 3. Send `/new`, then send a fresh message. 4. On the affected base, cancellation can be acknowledged without dispatch and the reset stays queued. **Paperclip version or commit** The live Claude baseline reproduced this on `29d6b3509`. The branch also includes master commit `0f5fafe16`. Related work: #13678, #13686, #13693, #13291, #13738. A separate runner reliability branch also contains a startup-wait fix. Its overlap must be reconciled before merging; this branch additionally prevents prompt submission after a late startup. ## What Changed - Wait for a pending native startup before acknowledging a run-scoped Stop. Preserve the existing recovery error when that wait expires. - Keep a Stop guard on startup. Cancel a late handle before it can submit a provider turn. - Add regression tests for normal handle publication and publication after the Stop deadline. - Back off blocked warm-attachment probes. Keep the fast two-snapshot barrier, fail closed, and record changed blockers. - Add red/green tests for delayed readiness, persistent blockers, alternating readiness, and readiness near the deadline. - Publish ACPX readiness and blockers. Preserve the old authority’s event acknowledgement barrier; only settled sessions can proceed to attachment. - Bind warm ACPX descriptors to the validated next authority while retaining old-run event correlation until activation. Preserve session identity and provider profile checks. - Exercise two consecutive run rotations through a qualified fake sidecar, verifying checkpointing, provider identity, pre-activation rejection, and new-run work admission. - Separate startup and active-turn cancellation checkpoints in the browser eval. - Add 18 explicit native chat eval cells: 12 local and 6 Daytona cells across Claude and Codex. - Cover hiring and reuse through managed AI accounts, source-based review, current blocked-task status, request replay after a lost HTTP acknowledgement, server restart continuity, and Stop/reset continuity. - Use ordinary production agent instructions. Enable API tools only for the two coordination cases that need them. - Calibrate the matchers with invalid records and outputs. Require remembered context after restart and a structured status snapshot that distinguishes the current blocker from history and task status from active execution. Compare the public issue mutation contract and relationships during read-only reporting. Preserve before/after source records in failed eval evidence. - Fix the lost-ack browser harness and verify it against a real HTTP server. Check the chat composer after restart instead of waiting for an unrelated document lifecycle event. - Document the scope and limits of each case. ## Verification - The startup regression failed on the unfixed executor and passed after the fix. - `pnpm test:e2e:runner:typecheck` passed. - `pnpm test:e2e:runner:unit` passed: 424 tests in 37 files. - `pnpm exec vitest run server/src/services/native-runtime/native-session-executor.test.ts` passed: 385 tests. - [Baseline live campaign](https://github.com/paperclipai/paperclip/actions/runs/35608208868): Claude Stop reproduced the bug. Codex Stop and Claude hire/reuse passed. Codex delegation was blocked by provider capacity. - [Eval-only startup campaign](https://github.com/paperclipai/paperclip/actions/runs/35609479786): both providers failed as expected. Both persisted `dispatched: false` and left `/new` queued. - [First fixed campaign](https://github.com/paperclipai/paperclip/actions/runs/35610533706) on `c9e95797d`: 10/18 cells passed. Startup Stop passed for both providers. Failed cases exposed eval harness defects and remote continuity failures. All attempts remain available. - [Original workflows and stronger memory checks](https://github.com/paperclipai/paperclip/actions/runs/35611896649) on `c04324fab`: 9/12 passed. Reassignment, local restart memory, and startup Stop passed for both providers; Codex remote restart passed. Claude remote restart exposed the missing readiness contract. Two Codex planning cells hit provider capacity. - [Unchanged-model retry](https://github.com/paperclipai/paperclip/actions/runs/35613854548): Codex planning and backlog creation both passed. - [18-cell campaign with ACPX readiness](https://github.com/paperclipai/paperclip/actions/runs/35614586963) on `6a98ef743`: 16/18 passed, including all local/remote Stop and committed-send cases. Claude remote continuity exposed the next-authority check, now fixed. Codex hiring produced its checklist, but the runner redacted the requested marker after it appeared as “Tracking token: …”. That content-redaction policy is unchanged and remains an explicit limitation. - [Structured status grading](https://github.com/paperclipai/paperclip/actions/runs/35614954725) on `50448c228`: both providers passed on their first attempt, including cleanup. - [Complete read-only state grading](https://github.com/paperclipai/paperclip/actions/runs/35616089011) on `551e13892`: both providers passed. - [Final ACPX handoff and hiring retry](https://github.com/paperclipai/paperclip/actions/runs/35617045456) on `cbd637587`: all three Claude Daytona cases passed (restart continuity, active Stop/reset, and lost-ack replay). Codex hiring reproduced the content-redaction failure: the saved checklist contained `Tracking token: [REDACTED]` instead of the required business marker. All four cases completed cleanup successfully. [Published report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35617045456-1/). The only subsequent commit adds the qualified-sidecar integration test; production code is identical to this live proof. - `pnpm test:e2e:runner:browser-support` passed: 5 browser tests without paid models. - Runner TypeScript typecheck passed. All 5 warm-readiness tests pass; two failed with the prior fixed-rate loop, and the late-readiness test failed before the pacing correction. - ACPX readiness and warm-identity regressions each failed before their fixes. All 292 runner-core Rust library tests passed. The qualified-sidecar integration test passes. Rust formatting is checked. - Status-grader regressions for misleading historical mentions and previously unchecked mutations each failed before tightening the oracle and pass now. - [Latest-head CI](https://github.com/paperclipai/paperclip/actions/runs/35617522307) passed on `a4093c8f1`: full build, type checks, test partitions, browser E2E, and native runner checks. Two unrelated tests initially failed (Sentry fixture release attribution and local-service fixture readiness); both passed locally together (35 passed, 5 optional SDK tests skipped) and on the failed-job retry. No changes were made to those tests. - Greptile reviewed `a4093c8f1` at 5/5; both earlier findings are fixed and all review threads are resolved. - The paid live suite is not fully green: the reproducible content-redaction case remains red. This is separate from the passing PR merge checks. No production content-redaction, prompt, model, or completion-policy change is included. - Managed-account hiring and review cases explicitly enable API tools; these do not qualify default new-user onboarding. ## Risks - Stop can wait up to 30 seconds for startup, then use the existing pending-recovery path. This does not prove that remote cleanup has finished. - Blocked warm readiness adds up to 750 ms between later probes with the two-minute remote budget, or about 32 ms with the default five-second budget. Ready sessions retain the short second barrier. - Paid evals can fail because of provider capacity or agent decisions. Each failure needs evidence-based classification. - The HTTP request replay case checks comment idempotency and duplicate effects. It does not prove replay safety for an ambiguous provider tool call. - The new suite is opt-in. It does not increase the default paid campaign. - No production prompts or model selection change. Review-handoff behavior and content-redaction policy remain separate product decisions. The latter can remove harmless business content that looks like credential syntax; the failing attempt is retained. ## Model Used OpenAI Codex, GPT-6, with repository tools and code execution. The exact deployment model ID and context window are not exposed in this task. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have 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> |
||
|
|
cceeb0aa66 |
test(runner): add everyday workflow evaluation harness (#13474)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native runner must support project work, delegation, hiring, and service access. > - Browser tests exposed lost connection access, rejected helper events, and stalled recovery. > - Some eval failures also came from incorrect fixtures and decision controls. > - This pull request fixes those paths and adds eight everyday workflow stories. > - The tests retain observed failures and verify delivered files independently. > - The benefit is repeatable evidence for common user tasks and their remaining gaps. ## Linked Issues or Issue Description Related work: #13404 contains earlier workflow fixes. #13300 and #13470 changed the CI contracts used by the harness security tests. Merged companion: [paperclip-evals#22](https://github.com/paperclipai/paperclip-evals/pull/22). **What happened?** Native ACPX sessions did not receive the assigned connection gateway. Codex helper events could arrive before their spawn receipt and fail thread validation. A parent continuation could take a shared workspace before its child retried. A failed native continuation could leave the task status without a clear recovery blocker. The eval harness also confused tool approvals with new connection requests and could reject a valid delegated download. **Expected behavior** Keep assigned gateway access and its approval checks. Verify helper lineage before accepting helper progress. Let a waiting child proceed before automatic parent recovery. Preserve a failed task's recovery ownership. Grade the actual requested workflow and its delivered files. **Steps to reproduce** Run the everyday workflow suite with the native Codex and Claude profiles. Exercise service approval, connection refusal, delegated project work, and teammate reuse. The commands and case requirements are in `tests/runner-e2e/EVERYDAY-WORKFLOWS.md`. Use `pnpm test:runner-recovery` for controlled crash and replacement cases. ## What Changed - Pass the scoped connection gateway binding through the native ACPX host and sidecar. - Recognize Codex helper lineage from parent metadata and spawn receipts. Verify early helper events with `thread/read`. Keep helper events separate from root completion authority. - Guide agents to use persistent hiring, child tasks, dependency records, and a blocked handoff while waiting for a child. - Defer automatic parent recovery while a child has an active execution path in the same shared workspace. Allow parent recovery when the child needs review. - Record Blocked status and recovery evidence when a failed native continuation needs reconciliation, including existing active or escalated incidents. Preserve their owner and retry budget. - Add eight browser-driven workflow cases. Use real decision controls, explicit child feedback delivery, managed hiring credentials, and independent ZIP checks inside a bounded Docker sandbox. Verify sandbox availability before task creation. Record screenshot SHA-256 at capture. - Keep runner crash probes in controlled recovery tests. Preserve the original failure when cleanup also fails. - Display missing accounting and replay revisions as unavailable. Align harness security assertions with the approved CI changes. - Make the channel-rejection browser fixture bind its file after the send captures its payload. This prevents live refresh from removing the file before the simulated race. ## Verification - Full workspace `pnpm -r typecheck` passed after merging current master. - Runner E2E typecheck passed. Harness unit tests passed: 216/216. - Wake-queue database tests passed: 55/55. The two added existing-incident tests failed before the fix and pass after it. - Docker artifact calibration passed: 12/12. Host-file and host-loopback isolation tests failed before the fix and pass after it. Read-only delivery and output limits are also verified. - Full `pnpm build` passed. Targeted recovery tests passed: 83/83. - The channel-rejection browser test passed five consecutive runs after fixing the fixture race found in CI. - Local general-server (12,351 tests), UI (6,250), CLI (485), and workspace package groups passed. The monolithic run stopped at an unchanged lock-heartbeat fixture race; the isolated workspace group passed on rerun (shared: 747/747). A separate local serialized run passed 97 files before two socket errors in the unchanged issue-list route suite; that suite passed 15/15 on isolated rerun. These local full commands did not finish uninterrupted; the complete CI matrix below covers the remaining suites. - Final head `0fb293733fe307be7e6667ae8f1364077d0c6455`: **34 successful checks, 2 expected skips**, including every server/workspace shard, browser shard, native runner verification, build, and typecheck. [Final CI run](https://github.com/paperclipai/paperclip/actions/runs/34989136700). - Greptile reviewed this exact head at **5/5**; all review threads are resolved. Both Superagent security checks are successful. - ACPX credential-boundary tests passed: 118/118. Superagent accepted the runner/sidecar versus provider-environment trace and cleared its finding. - The latest paid local campaign on source `f6a2fdf7ac2af859826a2ae627ff4125a5478529` passed 22/24 cases: Sol 8/8, Claude 7/8, Mini 7/8. These results predate the merge with current master. - The two remaining failures are in `hire-reuse`: Claude exceeded the attempt deadline during final review; Mini made invalid deliverable tool calls and remained Blocked. - Six Daytona cases were not run because the matching immutable runner image was unavailable. This PR does not claim new remote model results. ## Risks The changes affect connection admission, helper identity, and recovery scheduling. Assigned gateway grants and user approval still govern service calls. The workspace admission gate still exists; the broader folder-sync design is separate work. Provider behavior can still cause the two recorded hiring failures. No database migration is required. Paid cases are opt-in and have bounded attempt deadlines. Project stories now require Docker and the documented pinned Python image on the harness host. ## Model Used OpenAI `gpt-6-astra` performed implementation, diagnosis, and substantive review. OpenAI `gpt-5.6-luna` assisted with verification, PR preparation, and review tracking. Both used repository tools and code execution. Context-window sizes were not recorded. ## 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 (focused checks and isolated reruns; full-run limitations are documented 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: OpenAI GPT-5.6 Luna <noreply@openai.com> Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
Dotta
|
1dceee9a4e |
fix(runner): persist warm Daytona workspaces (#12901)
## Thinking Path > - Paperclip manages AI agent work and the execution state for each task. > - Remote agents run in sandbox environments such as Daytona. > - Daytona keeps files while a sandbox is stopped, but deletion removes those files. > - Runner Codex did not copy successful remote workspace changes back to the host workspace. > - A warm sandbox could therefore hide data loss until Daytona replaced or deleted the sandbox. > - This pull request makes the host workspace durable after every successful turn and keeps verified reusable sandboxes warm. > - The benefit is reliable multi-turn work across warm reuse, restart, stop, and sandbox replacement. ## Linked Issues or Issue Description **What happened?** A successful native Codex turn in Daytona could leave workspace changes only in the remote sandbox. A later warm turn appeared to work because it reused that filesystem. A replacement sandbox could start from stale host data and lose the successful changes. **Expected behavior** Paperclip must merge each successful remote turn into the authoritative host workspace before it completes the run. A verified warm lease may reuse its remote files. A replacement lease must reconstruct the exact durable workspace seed. **Steps to reproduce** 1. Run Codex in a reusable Daytona environment. 2. Write a file during one successful turn. 3. Replace the Daytona sandbox before the next turn. 4. Observe that the next turn can start without the prior file on the unpatched code. Related remote workspace foundation: #10070. ## What Changed - Added explicit `host_current`, `durable_seed`, and `adopt_remote` workspace preparation modes. - Added atomic, versioned native workspace descriptors and seed archives under `PAPERCLIP_HOME`. - Added real native sandbox export and three-way host merge before terminal result completion. - Added workspace-only recovery after a proposed result. Recovery does not submit another provider turn or consume the provider retry budget. - Added fail-closed handling when a sandbox with unexported changes is gone. - Kept healthy reusable Daytona sandboxes started for legacy Codex and Runner Codex. - Kept the Runner Codex process and provider session across verified warm turns. - Added the paid `daytona-warm-continuity` browser suite. It contains exactly the legacy Codex and Runner Codex cells. Each cell performs three measured turns. - Documented `pnpm test:e2e:runner -- --suite daytona-warm-continuity`. No package script was added. - Added no database migration. The metadata format is backward compatible and idempotent. ## Verification - `pnpm typecheck` - `pnpm test:e2e:runner:unit` — 114 passed - Native workspace, finalizer, session, and environment tests — 232 passed - Daytona provider tests — 150 passed - Workspace staging and merge tests — 98 passed - Runner transport tests — 63 passed - Legacy Codex restore tests — 5 passed - Rust format and compile checks pass through root typecheck - The paid Daytona suite was not run locally because the required Daytona, OpenAI, and immutable image credentials are not present. ## Risks - The main risk is an incorrect workspace identity or merge after a crash. Durable descriptors bind the run, workspace, lease, provider lease, local root, remote root, and baseline digest. Ambiguous evidence fails closed. - The host merge may conflict with concurrent host edits. The existing three-way merge and exclusion rules handle this case and surface failures. - A deleted sandbox cannot recover unexported bytes. Paperclip now blocks with `workspace_sync_out_unrecoverable` instead of reporting success or rerunning the provider. - There is no database migration. Descriptor writes and recovery are atomic and idempotent. ## Model Used OpenAI Codex with GPT-5. The run used agentic reasoning, repository inspection, code execution, test execution, Git, and GitHub CLI tools. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge |
||
|
Dotta
|
5716fe907e |
test(runner): add full-stack acceptance and eval gates (#12700)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The runner subsystem executes agent work across local and managed provider backends. > - The lower pull requests restore the task runtime, provider backends, and managed-provider control plane. > - The restored system needs repeatable full-stack checks before it can ship safely. > - Paid live checks also need clear access, cost, and secret controls. > - This pull request adds acceptance, live evaluation, chaos, and release gates for the restored runner stack. > - The benefit is measurable runner parity with safer release decisions. ## Linked Issues or Issue Description **Subsystem affected** Cross-cutting. This change covers runner tests, release workflows, server contracts, and evaluation tools. **Problem or motivation** The runner stack did not have one complete acceptance surface for native Codex, ACPX, Claude Managed, and AWS AgentCore. Release checks could miss provider drift, task-view regressions, cost-policy errors, and destructive cleanup errors. **Proposed solution** Add a 57-cell full-stack catalog, a Daytona image, and opt-in paid workflows. Add live evaluation, chaos, cost-limit, redaction, and release contract checks. Add AWS AgentCore infrastructure and guarded provisioning tools. Keep the native runner experimental flag off by default. **Alternatives considered** We considered manual smoke tests only. They do not give repeatable evidence and they do not protect release branches. We also considered one large pull request. The stacked pull requests keep each review below the Greptile file limit. **Roadmap alignment** This work supports the shipped Cloud / Sandbox agents milestone and the shipped Agent evals & feedback milestone in `ROADMAP.md`. Related stack: - #12699 adds managed provider backends and lifecycle support. - #12691 adds qualified OpenCode and ACPX provider backends. - #12685 restores task runtime rendering and steering. ## What Changed - Add the runner full-stack harness with 57 catalog cells and 60 unit tests. - Add a Daytona runner image with digest-pinned base images and base-aware image-content checks. - Add guarded live evaluation and chaos workflows with a fixed 40-execution matrix; live and full-stack paid schedules now run only on Sundays or by manual dispatch. - Add in-flight reported-usage cost stops, post-turn cost caps, exact-threshold failure classification, secret redaction, retry classification, and actor authorization. - Reattach stream and hard-budget listeners before restart-recovery continuations so restored paid sessions cannot bypass in-flight interruption. - Preserve OpenCode usage and cost across tool-loop messages and turns while exposing an explicit current-run delta to durable accounting. - Keep PNG/WebM evidence in access-controlled artifacts only, reject SVG, and publish only pruned inert structured per-attempt evidence. - Add AWS AgentCore infrastructure, provisioning checks, and smoke tools; reject unsafe model identifiers, require exact stack ownership markers, and make failed-stack replacement explicit. - Add evaluation-session contracts and capability reports. - Add release workflow checks for immutable action pins, frozen dependency installs, exact weekly cron shape, paid-run guards, provider-secret isolation, and chaos test paths. - Reauthorize the original and triggering numeric actor IDs as the first step of every provider-secret job, including partial reruns, before checkout or provider access. - Give each full-stack matrix cell only its matching provider credential, expose Daytona only to Daytona cells, and disable shared dependency caches anywhere paid credentials or OIDC write access are present. - Protect the legacy manual E2E workflow with the same default-branch, allowlist, environment, and per-job authorization boundary. - Rotate live-eval candidates by week and retain 120 days of compatible history so the seven-week trend window remains viable. - Restore the root runner-acceptance commands and reconcile reported snapshots, raw receipts, and terminal usage without double counting or losing late usage. - Mark ACPX token deltas exact only when every budget field is present, keep cumulative cost/request authority separate, reject non-USD cost labeling, and include thought tokens in output-token budgets. - Keep `enableNativeRunner` off by default. The acceptance harness enables it only in its isolated test instance. ## Verification Passed locally: - `pnpm --filter @paperclipai/paperclip-runner typecheck` - `pnpm test:runner-acceptance:typecheck` - `pnpm test:runner-acceptance` (19 tests) - focused OpenCode proxy, driver, runnerd transport, live-session, and turn-stream tests (106 tests) - `pnpm --filter @paperclipai/paperclip-runner exec vitest run src/live/clean-room-server.test.ts` (22 tests) - `pnpm test:e2e:runner:typecheck` - `pnpm test:e2e:runner:unit` (62 tests) - `node --test scripts/__tests__/release-verify-workflow.test.mjs` - `pnpm --filter @paperclipai/paperclip-runner test:runner-workflow-evals` (22 tests) - `pnpm -r typecheck` - `pnpm build` - `node --test packages/paperclip-runner/scripts/aws-agentcore-provisioning.test.mjs` (6 tests) - `git diff --check` - `cargo test --manifest-path packages/paperclip-runner/runner/Cargo.toml -p paperclip-runner-core --lib --locked` (161 tests) - focused ACPX provider-event tests (10 tests) - The rebased PR changes 92 files. `pnpm-lock.yaml` is unchanged. I did not run paid live provider jobs or provision AWS resources. Those checks need credentials and can create cost. ## Risks The paid workflows can create provider cost. They require an allowlisted original and triggering actor, the protected `runner-e2e-paid` environment, explicit opt-in variables, and cost limits. The four provider credentials exist only in that master-only environment, which requires allowlisted reviewer approval and disables administrator bypass; repository and organization Actions scopes contain no copies. Provider usage arrives after a billable request, so the live guard cannot prevent one request from crossing a threshold. It interrupts immediately on the first reported threshold hit and permits no continuation. Visual evidence can contain secrets rendered as pixels. PNG/WebM remain only in access-controlled workflow artifacts; SVG and per-attempt XML are excluded, and S3/Pages receive a pruned structured dashboard. The AWS scripts can create cloud resources. They use explicit commands, least-privilege roles, KMS encryption, saved nonsecret metadata, and explicit teardown. This pull request does not enable the experimental native runner for existing instances. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used OpenAI Codex with GPT-5. The model used extended reasoning, tool use, code execution, and parallel 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 |