Commit Graph
4785 Commits
Author SHA1 Message Date
DottaandPaperclip e35b11db21 Integrate MCP write-boundary repair for real Pi plan qualification
Co-Authored-By: Paperclip <noreply@paperclip.ing>

* codex/runner-copilot-acp:
  Preserve MCP tool display identity in native ACP events
2026-09-28 16:37:51 -05:00
DottaandPaperclip c5a34cce65 test(runner): retain Pi v3 paid behavior and projection evidence
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:36:55 -05:00
DottaandPaperclip 204b056ba7 Carry the shared MCP identity repair through the provider stack
Co-Authored-By: Paperclip <noreply@paperclip.ing>

* codex/runner-cursor-acp:
  Preserve MCP tool display identity in native ACP events
2026-09-28 16:36:04 -05:00
DottaandPaperclip d2e271338b Integrate shared ACP MCP display identity repair
Co-Authored-By: Paperclip <noreply@paperclip.ing>

* codex/runner-rich-acp:
  Preserve MCP tool display identity in native ACP events
2026-09-28 16:36:04 -05:00
DottaandPaperclip 5aa02662b3 Preserve MCP tool display identity in native ACP events
Parse ACP MCP namespace and tool names consistently with the TypeScript projection so persisted plan writes anchor to their actual tool boundary. Keep authority and raw argument handling unchanged.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:34:34 -05:00
DottaandPaperclip 7ab4636970 Integrate all three ACP providers through the shared verified registry
Retain each native builder, profile installer, extension adapter and image-content input. Update the pack dispatch test now that Pi is installed alongside Cursor and Copilot. Combined ACP tests pass 616 cases; actual distribution/wrapper package checks pass 34 cases.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:32:10 -05:00
DottaandPaperclip a55422a48d Integrate Cursor prerequisite without losing Copilot registrations
Combine both pinned native builders, isolated profile installers, capabilities, extension adapters and complete Daytona content inputs. Verify dispatch remains isolated between the two native installation factories.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:26:55 -05:00
DottaandPaperclip 3525dce1ad Integrate final shared profile contracts and verification fixes
Preserve the independently verified Cursor dependency lock while accepting the prerequisite profile-v3 parser and portable fixture corrections.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:23:48 -05:00
DottaandPaperclip 915adc4d33 Keep real Git streaming stress coverage portable on macOS
Retain forty thousand files and four filename lanes above 32 MiB while fitting the macOS path limit. Allow 300 seconds for real filesystem staging/deletion on macOS and retain the 180-second bound elsewhere.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:22:19 -05:00
DottaandPaperclip 9cd42f6df9 Record Pi v3 immutable pack and timely startup proof
Retain version 2 paid/runtime evidence separately. Record complete closure reproduction, 95 focused tests, 25 package checks, 16 native Rust tests and zero-prompt launch results.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:16:34 -05:00
DottaandPaperclip 7710736ca3 Retain Pi denial proof and failed file qualification accounting
Preserve the original version 2 source, missing file oracle and terminal receipt, and aggregate billing attribution across the delayed charge.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:13:23 -05:00
DottaandPaperclip 96a9725f34 test(runner): retain isolated Linux Copilot image initialization proof
Record exact image, pack and executable digests with no credentials, network, fixture requests or model prompts. Keep Daytona Product qualification pending.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:11:55 -05:00
DottaandPaperclip ee0836203f Refresh reviewed Daytona workspace resolution pin
Record the independently reproduced resolved lock digest after the integrated mainline dependency changes. Candidate image builds continue to supply their own verified lock digest.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:11:34 -05:00
DottaandPaperclip 06cf356a8b Preserve Pi validation failures and structured Bash output
Bump the immutable Pi profile to version 3 and reject prior warm snapshots. Bound and redact authenticated MCP validation errors while retaining failure status; preserve standard ACP tool values alongside terminal metadata.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:10:15 -05:00
DottaandPaperclip a88056eee9 Stabilize feedback route mocks during serialized validation
Keep the route service factories bound to hoisted test doubles and assert exact calls while preserving both company-boundary 404 checks.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:09:38 -05:00
DottaandPaperclip f676c9d2c8 docs(runner): record offline Cursor Linux image verification
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:06:05 -05:00
DottaandPaperclip aec56e2365 Admit versioned ACP profile snapshots for the Pi error contract
Allow profile version 3 without changing existing provider identities. Reject unsupported and malformed versions, and retain exact runtime identity verification.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:02:36 -05:00
DottaandPaperclip e405de788a test(runner): bind Copilot denial oracle to exact native write target
Reject unrelated edits and command mentions, normalize the private workspace path, and replay retained paid evidence offline without another prompt.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:02:12 -05:00
DottaandPaperclip e8dee462e2 Admit versioned ACP profile snapshots for the Pi error contract
Allow profile version 3 without changing existing provider identities. Reject unsupported and malformed versions, and retain exact runtime identity verification.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 16:01:36 -05:00
DottaandPaperclip 87c7fdaca7 test(runner): retain Copilot plan and restart qualification evidence
Preserve the separate question marker failure and unknown provider USD alongside successful plan approval and controller recovery. Keep the candidate pending.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:59:48 -05:00
DottaandPaperclip 72f8887709 docs(runner): record Cursor native EOF lifecycle limit
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:57:45 -05:00
DottaandPaperclip e450bc4346 test(runner): retain Cursor native denial and billing evidence
Preserve the original grader failure and assess the same captured turn through exact tool-call correlation without another prompt.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:55:37 -05:00
DottaandPaperclip cb63ccd1d0 test(runner): add bounded native Cursor denial qualification
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:51:38 -05:00
DottaandPaperclip 19ca0f558d fix(runner): tighten Copilot discovery evidence and cleanup
Reject auto as exact model evidence, release native leases on early workspace failure, and reject pending metadata requests immediately when the provider exits or sends malformed output. Extend early cleanup to the real-service probe.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:49:16 -05:00
DottaandPaperclip b371ca7a32 test(runner): retain Copilot probe spawn failure evidence
Handle a missing child PID and broken stdin during early launch failure, retaining the no-prompt failed result and cleanup proof.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:46:55 -05:00
DottaandPaperclip 829686b0c8 Record successful serialized Cursor question restart recovery
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:46:51 -05:00
DottaandPaperclip 06e3bae33b Retain Pi local hello pass and model admission proof
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:44:14 -05:00
DottaandPaperclip c06fc5fccc docs(runner): retain real Copilot denial and settlement proof
Record native permission ID0, denial without filesystem effects, detached async command completion before terminal, process cleanup and externally reconciled unknown credit granularity.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:43:20 -05:00
DottaandPaperclip d35b83074a Retain native Cursor question availability qualification failure
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:41:32 -05:00
DottaandPaperclip 47eed960b3 test(runner): add bounded Copilot real-service risk probes
Prepare isolated single-turn denial and detached-command oracles with exact native option identities, marker timing, explicit model admission and process cleanup. Credential-free tests do not claim live qualification.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:39:29 -05:00
DottaandPaperclip 697e20562e docs(runner): retain final Copilot packaging checkpoint
Record exact merged source, repeated dependency lock resolution, matched immutable daemon, and credential-free native registry proof separately from live qualification.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:35:42 -05:00
DottaandPaperclip d9321659d4 Refresh Cursor packaged launch proof after shared integration
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:19:19 -05:00
DottaandPaperclip 25fb1b5b31 Pin final Cursor lock graph and reconcile bounded product usage
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:33 -05:00
DottaandPaperclip 8aa867b64d docs(runner): retain Copilot file pass and question failure
Record actual GitHub billing attribution, unpriced receipts, answered question continuation with failed exact marker, and pre-provider plan infrastructure failure. Candidate qualification stays pending.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 2663e4af7c docs(runner): retain Copilot Product proof and accounting defect
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 986af2854d Retain first real Copilot semantic qualification evidence
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 08cabb1f2e test(runner): retain authenticated Copilot model discovery
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip a989354a5e Refresh Copilot package proof through final launch-boundary fixes
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip a72d9b8073 Refresh Copilot proof after credential-boundary review
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 38fd2ede0a Close Copilot probe resources on failure and retain redaction context
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 7343bfffd1 Refresh Copilot pack evidence after foundation integration
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip f36adb3edb Document Copilot tool diff and location preservation gaps
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip f61f17e8f8 Retain Copilot packaged launch evidence and complete capability gaps
Record the exact verified provider pack, native initialize metadata, zero-spend offline probe attempts, and missing-credential preflight. Explicitly account for unused terminal authentication, image/context inputs, session management and SSE capabilities.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 9136678ef0 Reject missing Copilot credentials before provider admission
Use only the explicitly sanitized COPILOT_GITHUB_TOKEN binding and preserve typed authentication diagnostics. Exercise missing-key cleanup and subsequent explicit credential admission, and make the packaged initialize smoke hermetic with a metadata-only loopback fixture.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 6f7e2d20d9 Audit Copilot provider packs through verified offline launch
Hash the exact Copilot builder and materializer into Daytona image identity, and add a credential-free initialize smoke that exercises the packaged installation registry and native snapshot launch.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 4fc5dbd4ec Connect Copilot candidate installation, events, diagnostics and pack registries
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 2b19bd22be Build Copilot packs from verified immutable native archives
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 5a7bf05d0c Resolve Copilot assets through verified runner package authority
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip 969944b38e Bind Copilot launches to pinned build-owned native assets
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00
DottaandPaperclip fe3b7e6fb8 Project Copilot native events into attributed runner activity
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-28 15:17:09 -05:00