morluto/rea
1
0
Fork 0
mirror of https://github.com/morluto/rea.git synced 2026-11-05 06:45:22 +00:00
Code Issues 1.3k Projects Packages Wiki Activity

[PR #5470] [MERGED] fix(mcp): guide agents through tool error recovery #6932

New issue
Closed
opened 2026-11-01 21:44:09 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-11-01 21:44:09 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/morluto/rea/pull/5470
Author: @gensokyo-dev
Created: 10/20/2026
Status: ✅ Merged
Merged: 10/20/2026
Merged by: @gensokyo-dev

Base: main ← Head: feat/5431-tool-recovery-errors

📝 Commits (6)

  • 4df946a fix(mcp): add agent recovery guidance to tool errors
  • 6a43bc9 test(mcp): assert structured adb input recovery
  • bade159 test(mcp): assert structured depth validation recovery
  • 12c5dc5 test(mcp): assert bounded browser input recovery
  • 4a9af96 chore: merge main and preserve MCP recovery envelopes
  • 8d048ad fix(mcp): preserve validation diagnostics within wire budgets

📊 Changes

20 files changed (+1007 additions, -66 deletions)

View changed files

📝 docs/error-contract.schema.json (+540 -0)
📝 docs/mcp-contracts.md (+18 -1)
📝 docs/user-visible-errors.csv (+2 -2)
📝 src/contracts/errorSchemas.ts (+4 -1)
📝 src/domain/analysisErrorPresentation.ts (+10 -1)
📝 src/domain/analysisErrorProjection.test.ts (+46 -0)
📝 src/domain/analysisErrorProjection.ts (+21 -0)
➕ src/domain/analysisErrorRecovery.ts (+36 -0)
📝 src/server/EvidenceMcpServer.test.ts (+90 -16)
📝 src/server/EvidenceMcpServer.ts (+122 -22)
📝 tests/acceptance/applications/javascriptAnalysisLimits.test.ts (+12 -1)
📝 tests/boundary/cli/browserInputDiagnostics.test.ts (+7 -1)
📝 tests/boundary/filesystem/processCliFileInput.test.ts (+8 -1)
📝 tests/boundary/mcp/adbMcp.test.ts (+21 -4)
📝 tests/boundary/mcp/browserMcp.test.ts (+10 -0)
📝 tests/boundary/mcp/browserScenarioInputDiagnosticsMcp.test.ts (+8 -1)
📝 tests/boundary/mcp/ghidraInventoryMcp.test.ts (+9 -3)
📝 tests/boundary/mcp/largeBytePattern.test.ts (+11 -7)
📝 tests/boundary/mcp/sessionMcp.test.ts (+20 -4)
📝 tests/boundary/mcp/webBundleContainmentMcp.test.ts (+12 -1)

📄 Description

Summary

Fixes #5431. Wrong MCP argument types currently produce raw SDK text, unknown tool names lack discovery guidance, and generic timeouts do not explain which deadline to adjust. This change adds compact, typed recovery guidance shared by CLI/MCP and normalizes SDK input errors at the MCP delivery boundary.

Problem and expected behavior

For example, inspect_wasm_artifact({path:42}) now returns canonical invalid_request with recovery: {kind:"inspect_input_contract", operation:"inspect_wasm_artifact"} and directs the caller to the advertised input schema or tools/list before correcting the request. Timeout errors identify the server/provider deadline and recommend inspecting state before retrying. Increasing the MCP client deadline is appropriate only when that client ended the call first.

Change and scope

  • Add optional inspect_input_contract / inspect_timeout_state recovery metadata to the existing error projection and JSON Schema.
  • Normalize SDK argument errors according to the actual wire budget, preserving complete rejected-field diagnostics when they fit. Retain original Evidence before shortening a response that overflows after wrapping/escaping, and preserve protocol metadata and target-content markers.
  • Direct unknown-tool callers to tools/list; preserve JSON-RPC -32602.

Contract and boundary impact

  • Semantic owner: domain error projection/presentation; transport owns SDK-boundary normalization.
  • Contribution scope: ordinary usability fix within existing contracts; additional provider/authority decision not applicable.
  • CLI/MCP: additive optional recovery metadata; bounded SDK validation errors now use canonical JSON.
  • Provider/platform: provider-specific remediation remains authoritative.
  • Evidence: retained oversized originals and provenance remain available.
  • Target selection, execution authority, and cleanup: unchanged.
  • Generated output: authored docs/error-contract.schema.json regenerated; no package or installation changes.

Expected effects:

  • Documentation or usability only; no target interaction.

Evidence and regression coverage

The baseline returned raw SDK text for a wrong inspect_wasm_artifact argument. Regression tests cover canonical validation errors, unknown tools, oversized retention, provenance markers, protocol envelopes, CLI/MCP equivalence, deep JSON input, and real JavaScript/browser-bundle timeouts.

  • Observed, derived, and inferred claims remain distinguishable.
  • Artifact identity, source provenance, and failed attempts remain preserved.
  • Unsupported, incomplete, unavailable, or uncertain outcomes remain visible.

Validation performed

  • Full GitHub CI on earlier 12c5dc553: run 39420774558 passed, including six portable shards, Apple/browser, native, SQLite and other selected environment lanes. Latest main c374c2fe7 was integrated; final 8d048ad34 was squash-merged as e50a271c7. Their complete file trees are identical. Final PR CI run 39432049829 passed build/docs; its source tests passed 12,273 tests with only the three reproduced main-baseline path assertions failing. Static checks failed on the reproduced main-baseline duplicate threshold. The compiled suite was not green: one failed shard cancelled four peers. Four legacy recovery-text assertions introduced by the main update are corrected in follow-up #5536, with all five CLI tests passing locally. Remaining observed compiled failures were reproduced on the pre-change baseline below.
  • Latest local typecheck/lint, format and docs passed. Domain/server source tests: 63 passed. Four compiled MCP suites: 13 passed. Earlier focused ADB/session/browser suites: 22 passed. Coverage includes complete >5,000-character diagnostics at a 16 KiB wire budget and retained quote-expansion overflow on legacy/modern protocols. Architecture guards and knip passed before the main integration.
  • Real JavaScript timeout acceptance: 6 tests passed; elapsed 40.33s, peak process RSS approximately 552 MiB. Large input/stdio input diagnostics passed, peak RSS approximately 1.23 GiB. Repository-wide static checks peaked near 4.76 GiB RSS without OOM.
  • Codex CLI with temporary REA MCP configuration completed actual recovery: a 1ms small-app timeout led to a session-state check and successful bounded analysis in three MCP calls; a wrong input_path type led to correction and successful analysis in two calls. Application coverage was complete; semantic unknowns remained explicit. The second task used 128,076 input tokens (89,984 cached) and 632 output tokens, 39.67s wall / 12.46s CPU, maximum individual-process RSS 440 MiB. Concurrent process-family peak was not sampled; no before/after or statistical efficiency improvement is claimed.
  • Additional real-package acceptance used Commander 14.0.3 (252 KiB), Codex CLI 0.161.0 / gpt-6.1-sol, Node 24.18.0 and only the analysis/session MCP tools. A forced 1ms timeout led to a session-state check and successful 30s retry in three calls, preserving the actual max_heap_mb:128 and summary view while lowering semantic limits. The tool reported 12 relevant files, 10 parsed JS files and 108 findings; application/semantic coverage remained explicitly partial, with 452 retained unknowns. Timeout/full/summary Evidence references survived. Whole-agent usage: 241,221 input tokens (189,440 cached), 985 output tokens, 56.52s wall / 15.57s CPU, maximum individual-process RSS 659 MiB; concurrent process-family peak was not sampled. This is a recovery success, not a token-efficiency improvement claim.
  • Independent Codex CLI review identified lost diagnostics; the producing boundary was fixed and a second review reported no actionable regressions. Both related GitHub review comments are addressed.
  • Known main-baseline CI failures: duplicate detection is 3.5279% on c374c2fe7, versus 3.5255% on this change (both exceed 3.5%); three cliJsonPaths.test.ts message assertions reproduce unchanged on the baseline. A further compiled comparison reproduced the same five failures before and after this change: TypeScript application graph, two EVM cancellation-warning cases, malformed Protobuf trailer deadline and Electron path-message wording. The isolated baseline run passed 51 tests and failed those five, with two named skips. A separate worker cancellation assertion failed once in CI and passed in the focused baseline run; it is outside changed execution code. These unrelated failures are recorded rather than changing their owning code in this PR.
  • Complete local MCP suite was stopped after 15 minutes and is not claimed as passing; the completed GitHub suite provides broader verification. BYO Hopper/Ghidra/IDA runtime qualification was unavailable. Unknown-tool server guidance was checked through direct stdio because Codex rejects invented bindings before dispatch.

Compatibility, safety, and release

Recovery is optional. Clients that depended on SDK prose should parse the documented canonical error instead. Recovery fields do not echo input arguments or embed the tool catalog; bounded SDK diagnostic text can include validation values. Raw oversized diagnostics retain the existing Evidence access path. No new provider, execution, injection, mutation, or protection-recovery capability is added.

Author readiness

Human owner: @gensokyo-dev

Recorded at the human owner's explicit instruction and authorization in the task conversation; implementation review and executed validation were performed by Codex.

  • I reviewed the final diff and relevant existing code, understand the change and its edge cases, and take responsibility for the complete PR, including AI-assisted work.
  • I checked the evidence above, confirmed it supports the current change, and recorded meaningful validation gaps.
  • I declare this PR ready for initial maintainer review.

Before merge

  • This PR addresses a concrete problem or an agreed enhancement.
  • Material scope and authority questions are resolved, and any required maintainer scope decision covers the final diff.
  • The PR has one focused outcome and the title follows type(scope): outcome.
  • Related issue is linked, or the reason for not linking one is stated above.
  • Tests cover changed observable behavior and meaningful failure paths.
  • Owning docs, contracts, and generated metadata are updated where needed.
  • User-visible CLI/MCP changes include representative output.
  • I checked the final diff for secrets, unrelated cleanup, and unsupported claims.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/morluto/rea/pull/5470 **Author:** [@gensokyo-dev](https://github.com/gensokyo-dev) **Created:** 10/20/2026 **Status:** ✅ Merged **Merged:** 10/20/2026 **Merged by:** [@gensokyo-dev](https://github.com/gensokyo-dev) **Base:** `main` ← **Head:** `feat/5431-tool-recovery-errors` --- ### 📝 Commits (6) - [`4df946a`](https://github.com/morluto/rea/commit/4df946afbc9d8a59e56cebb9e9ca84284ea6f090) fix(mcp): add agent recovery guidance to tool errors - [`6a43bc9`](https://github.com/morluto/rea/commit/6a43bc907494c017823583e20e25c900a8f63dbe) test(mcp): assert structured adb input recovery - [`bade159`](https://github.com/morluto/rea/commit/bade1599cbd45aa0a1c936d9ee77f30c4fc87e44) test(mcp): assert structured depth validation recovery - [`12c5dc5`](https://github.com/morluto/rea/commit/12c5dc553f00778ab472f8d080c8b949d678abf6) test(mcp): assert bounded browser input recovery - [`4a9af96`](https://github.com/morluto/rea/commit/4a9af968c33f9566407a8d65b6e8e1aa0fcf563b) chore: merge main and preserve MCP recovery envelopes - [`8d048ad`](https://github.com/morluto/rea/commit/8d048ad34ed9ef0abd38cac64bb12d52cc07d960) fix(mcp): preserve validation diagnostics within wire budgets ### 📊 Changes **20 files changed** (+1007 additions, -66 deletions) <details> <summary>View changed files</summary> 📝 `docs/error-contract.schema.json` (+540 -0) 📝 `docs/mcp-contracts.md` (+18 -1) 📝 `docs/user-visible-errors.csv` (+2 -2) 📝 `src/contracts/errorSchemas.ts` (+4 -1) 📝 `src/domain/analysisErrorPresentation.ts` (+10 -1) 📝 `src/domain/analysisErrorProjection.test.ts` (+46 -0) 📝 `src/domain/analysisErrorProjection.ts` (+21 -0) ➕ `src/domain/analysisErrorRecovery.ts` (+36 -0) 📝 `src/server/EvidenceMcpServer.test.ts` (+90 -16) 📝 `src/server/EvidenceMcpServer.ts` (+122 -22) 📝 `tests/acceptance/applications/javascriptAnalysisLimits.test.ts` (+12 -1) 📝 `tests/boundary/cli/browserInputDiagnostics.test.ts` (+7 -1) 📝 `tests/boundary/filesystem/processCliFileInput.test.ts` (+8 -1) 📝 `tests/boundary/mcp/adbMcp.test.ts` (+21 -4) 📝 `tests/boundary/mcp/browserMcp.test.ts` (+10 -0) 📝 `tests/boundary/mcp/browserScenarioInputDiagnosticsMcp.test.ts` (+8 -1) 📝 `tests/boundary/mcp/ghidraInventoryMcp.test.ts` (+9 -3) 📝 `tests/boundary/mcp/largeBytePattern.test.ts` (+11 -7) 📝 `tests/boundary/mcp/sessionMcp.test.ts` (+20 -4) 📝 `tests/boundary/mcp/webBundleContainmentMcp.test.ts` (+12 -1) </details> ### 📄 Description ## Summary Fixes #5431. Wrong MCP argument types currently produce raw SDK text, unknown tool names lack discovery guidance, and generic timeouts do not explain which deadline to adjust. This change adds compact, typed recovery guidance shared by CLI/MCP and normalizes SDK input errors at the MCP delivery boundary. ## Problem and expected behavior For example, `inspect_wasm_artifact({path:42})` now returns canonical `invalid_request` with `recovery: {kind:"inspect_input_contract", operation:"inspect_wasm_artifact"}` and directs the caller to the advertised input schema or `tools/list` before correcting the request. Timeout errors identify the server/provider deadline and recommend inspecting state before retrying. Increasing the MCP client deadline is appropriate only when that client ended the call first. ## Change and scope - Add optional `inspect_input_contract` / `inspect_timeout_state` recovery metadata to the existing error projection and JSON Schema. - Normalize SDK argument errors according to the actual wire budget, preserving complete rejected-field diagnostics when they fit. Retain original Evidence before shortening a response that overflows after wrapping/escaping, and preserve protocol metadata and target-content markers. - Direct unknown-tool callers to `tools/list`; preserve JSON-RPC `-32602`. ## Contract and boundary impact - Semantic owner: domain error projection/presentation; transport owns SDK-boundary normalization. - Contribution scope: ordinary usability fix within existing contracts; additional provider/authority decision not applicable. - CLI/MCP: additive optional recovery metadata; bounded SDK validation errors now use canonical JSON. - Provider/platform: provider-specific remediation remains authoritative. - Evidence: retained oversized originals and provenance remain available. - Target selection, execution authority, and cleanup: unchanged. - Generated output: authored `docs/error-contract.schema.json` regenerated; no package or installation changes. Expected effects: - [x] Documentation or usability only; no target interaction. ## Evidence and regression coverage The baseline returned raw SDK text for a wrong `inspect_wasm_artifact` argument. Regression tests cover canonical validation errors, unknown tools, oversized retention, provenance markers, protocol envelopes, CLI/MCP equivalence, deep JSON input, and real JavaScript/browser-bundle timeouts. - [x] Observed, derived, and inferred claims remain distinguishable. - [x] Artifact identity, source provenance, and failed attempts remain preserved. - [x] Unsupported, incomplete, unavailable, or uncertain outcomes remain visible. ## Validation performed - Full GitHub CI on earlier `12c5dc553`: [run 39420774558](https://github.com/morluto/rea/actions/runs/39420774558) passed, including six portable shards, Apple/browser, native, SQLite and other selected environment lanes. Latest main `c374c2fe7` was integrated; final `8d048ad34` was squash-merged as `e50a271c7`. Their complete file trees are identical. Final [PR CI run 39432049829](https://github.com/morluto/rea/actions/runs/39432049829) passed build/docs; its source tests passed 12,273 tests with only the three reproduced main-baseline path assertions failing. Static checks failed on the reproduced main-baseline duplicate threshold. The compiled suite was not green: one failed shard cancelled four peers. Four legacy recovery-text assertions introduced by the main update are corrected in [follow-up #5536](https://github.com/morluto/rea/pull/5536), with all five CLI tests passing locally. Remaining observed compiled failures were reproduced on the pre-change baseline below. - Latest local typecheck/lint, format and docs passed. Domain/server source tests: 63 passed. Four compiled MCP suites: 13 passed. Earlier focused ADB/session/browser suites: 22 passed. Coverage includes complete >5,000-character diagnostics at a 16 KiB wire budget and retained quote-expansion overflow on legacy/modern protocols. Architecture guards and knip passed before the main integration. - Real JavaScript timeout acceptance: 6 tests passed; elapsed 40.33s, peak process RSS approximately 552 MiB. Large input/stdio input diagnostics passed, peak RSS approximately 1.23 GiB. Repository-wide static checks peaked near 4.76 GiB RSS without OOM. - Codex CLI with temporary REA MCP configuration completed actual recovery: a 1ms small-app timeout led to a session-state check and successful bounded analysis in three MCP calls; a wrong `input_path` type led to correction and successful analysis in two calls. Application coverage was complete; semantic unknowns remained explicit. The second task used 128,076 input tokens (89,984 cached) and 632 output tokens, 39.67s wall / 12.46s CPU, maximum individual-process RSS 440 MiB. Concurrent process-family peak was not sampled; no before/after or statistical efficiency improvement is claimed. - Additional real-package acceptance used Commander 14.0.3 (252 KiB), Codex CLI 0.161.0 / `gpt-6.1-sol`, Node 24.18.0 and only the analysis/session MCP tools. A forced 1ms timeout led to a session-state check and successful 30s retry in three calls, preserving the actual `max_heap_mb:128` and summary view while lowering semantic limits. The tool reported 12 relevant files, 10 parsed JS files and 108 findings; application/semantic coverage remained explicitly partial, with 452 retained unknowns. Timeout/full/summary Evidence references survived. Whole-agent usage: 241,221 input tokens (189,440 cached), 985 output tokens, 56.52s wall / 15.57s CPU, maximum individual-process RSS 659 MiB; concurrent process-family peak was not sampled. This is a recovery success, not a token-efficiency improvement claim. - Independent Codex CLI review identified lost diagnostics; the producing boundary was fixed and a second review reported no actionable regressions. Both related GitHub review comments are addressed. - Known main-baseline CI failures: duplicate detection is 3.5279% on `c374c2fe7`, versus 3.5255% on this change (both exceed 3.5%); three `cliJsonPaths.test.ts` message assertions reproduce unchanged on the baseline. A further compiled comparison reproduced the same five failures before and after this change: TypeScript application graph, two EVM cancellation-warning cases, malformed Protobuf trailer deadline and Electron path-message wording. The isolated baseline run passed 51 tests and failed those five, with two named skips. A separate worker cancellation assertion failed once in CI and passed in the focused baseline run; it is outside changed execution code. These unrelated failures are recorded rather than changing their owning code in this PR. - Complete local MCP suite was stopped after 15 minutes and is not claimed as passing; the completed GitHub suite provides broader verification. BYO Hopper/Ghidra/IDA runtime qualification was unavailable. Unknown-tool server guidance was checked through direct stdio because Codex rejects invented bindings before dispatch. ## Compatibility, safety, and release Recovery is optional. Clients that depended on SDK prose should parse the documented canonical error instead. Recovery fields do not echo input arguments or embed the tool catalog; bounded SDK diagnostic text can include validation values. Raw oversized diagnostics retain the existing Evidence access path. No new provider, execution, injection, mutation, or protection-recovery capability is added. ## Author readiness Human owner: @gensokyo-dev Recorded at the human owner's explicit instruction and authorization in the task conversation; implementation review and executed validation were performed by Codex. - [x] I reviewed the final diff and relevant existing code, understand the change and its edge cases, and take responsibility for the complete PR, including AI-assisted work. - [x] I checked the evidence above, confirmed it supports the current change, and recorded meaningful validation gaps. - [x] I declare this PR ready for initial maintainer review. ## Before merge - [x] This PR addresses a concrete problem or an agreed enhancement. - [x] Material scope and authority questions are resolved, and any required maintainer scope decision covers the final diff. - [x] The PR has one focused outcome and the title follows `type(scope): outcome`. - [x] Related issue is linked, or the reason for not linking one is stated above. - [x] Tests cover changed observable behavior and meaningful failure paths. - [x] Owning docs, contracts, and generated metadata are updated where needed. - [x] User-visible CLI/MCP changes include representative output. - [x] I checked the final diff for secrets, unrelated cleanup, and unsupported claims. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
bsakaguchi 2026-11-01 21:44:09 +00:00
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
codex/procedure-reference-stacked
release-please--branches--main--components--rea-agents
release-please--branches--main--components--rea-agents--release-notes
codex/kuna-independent-retry
codex/byte-search-overlay-coverage
codex/open-failure-target-receipt
codex/kuna-xref-evidence
codex/ghidra-ambiguous-procedure-recovery
codex/function-source-bundle
codex/trace-function-integration-prototype
codex/snapshot-source-closure
codex/recorded-evidence-array-pages
codex/evidence-recovery-redesign
codex/trace-feature-address-scope
codex/call-discovery-scope
codex/ghidra-literal-candidate-evidence
codex/decompile-directory-independent-retry
codex/retry-provenance-base
codex/value-flow-capability-experiment
codex/ghidra-containing-instruction
cursor/readme-discord-button-ef9f
dependabot/github_actions/actions/setup-node-7.1.0
dependabot/github_actions/actions/upload-artifact-7.0.2
dependabot/npm_and_yarn/npm-minor-and-patch-d8d97ce6df
codex/kuna-1989
fix/8559-native-ui-fixture-ownership
fix/8555-go-verifier-mcp-ownership
codex/provider-capability-recovery
fix/8642-rizin-target-stdin
codex/ghidra-memory-effect-scope
codex/ghidra-annotation-entry-selector
codex/ghidra-readonly-recovery
codex/ghidra-regex-verifier-recovery
codex/evidence-discovery-view-guidance
fix/8545-bulk-append-overflow
fix/8428-navigation-refusal-alternatives
codex/address-context-recovery
codex/matching-member-limitations
codex/unknown-scope-contract
codex/evidence-view-guidance
feat/8373-native-trace-views
codex/ghidra-snapshot-verifier-binding
codex/elf-export-visibility
codex/evidence-view-recovery
codex/native-reference-cli-help
codex/provider-candidate-observation-scope
codex/kuna-session-verification
codex/ghidra-switch-lifetime-guidance
codex/pseudocode-paging-discovery
codex/clarify-evidence-view-support
codex/kuna-xrefs-selector-recovery
codex/context-capacity-recovery
codex/evidence-closure-large-links
codex/same-function-evidence-identity
codex/ghidra-verifier-inspected-jdk
codex/audit-guided-workflows
codex/crash-prompt-retained-dossiers
codex/analysis-view-error-recovery
codex/kuna-verifier-target-selection
codex/ghidra-selected-project-call-coverage
codex/docs-native-analysis-scope
codex/ghidra-java-socket-boundary
codex/ghidra-retained-snapshot-verifier
codex/ghidra-search-inventory-facts
fix/8284-zero-argument-parameter-bindings
fix/8198-ui-action-handler-offset
fix/8257-elf-entry-label-identity
fix/8304-deferred-output-schema-projection
fix/8277-call-path-computed-target-uncertainty
fix/pr-8089-conflicts
fix/ci-static-duplicate-export
dependabot/npm_and_yarn/lint-staged-17.6.0
dependabot/github_actions/actions/download-artifact-8.0.2
dependabot/npm_and_yarn/write-file-atomic-8.0.0
dependabot/npm_and_yarn/canonicalize-5.1.0
dependabot/github_actions/actions/cache/restore-6.1.0
dependabot/npm_and_yarn/toon-format/toon-4.4.0
dependabot/github_actions/actions/deploy-pages-5.0.1
codex/review-fixes-pr-2403
codex/review-fixes-pr-2400
codex/process-terminal-width
codex/test-brittleness-cleanup
verify/7167-browser-connect-macos
fix/7167-browser-connect
feat/native-matching-allowance-setting
feat/browser-scenario-dry-run
test/managed-caller-parameters-20261024
codex/parser-fortythird-boundaries
fix/6926-pinvoke-platform-decorations-20261023
fix/6889-har-body-encoding-20261023
fix/6888-sqlite-schema-budget-20261023
fix/dependency-security-gates-6708
cursor/evidence-overwrite-rebase-b4ac
feat/4057-verify-native-exports
fix/windows-acl-observer-overhead-20261022
cursor/erlang-beam-restack-4476
cursor/pe-certificate-review-bf32
fix/6116-javascript-application-fs-errors
fix/6061-unmapped-runtime-script-unknown
feat/browser-scenario-summary
fix/pe-certificates
codex/verify-3407
cursor/rebase-5699
cursor/rebase-5352
cursor/rebase-5600
cursor/fix-cli-schema-omission-10a8
codex/audit-hopper-shutdown-reasons-20261021
fix/demangle-swift-omitted-record
fix/nib-boolean-value-types
cursor/cancellation-partial-observation-a5ac
fix/ib-object-limit-reasons
fix/electron-fuse-limit-advice
fix/kuna-doctor-dangling-cache
fix/fixed-budget-refusal-advice
fix/js-ipc-listener-dedup
fix/js-return-member-provenance
fix/dmg-integrity-retry-advice
fix/ida-doctor-readiness
fix/kuna-version-probe-output-drain
fix/legacy-swift-runtime-name-matching
fix/dylib-lazy-load-commands
fix/browser-scenario-startup-cancel
fix/swift-nested-punycode-classification
fix/compare-unselected-scopes
fix/objc-method-budget-coverage
fix/dmg-mounted-root-observations
audit/ci-tests-20261019-round2
release/6.7.0
fix/wabt-cleanup-retry-resolution
fix/electron-fuse-elf-pe-architecture
fix/native-plist-descriptor-ownership
fix/kuna-caller-cleanup-ownership
experiment/atomic-codemode-20261016
review/first-contributor-3776
fix/call-resolution-full-read-cycles
fix/member-mutation-selection-repeat
experiment/atomic-re-tools-20261015
perf/member-mutation-lazy-origins
perf/static-network-mutation-index
fix/hopper-startup-lifecycle
audit/3050-windows-proof-20261015
feat/windows-window-capture-2183
audit/3049-windows-proof-20261015
audit/3735-macos-fixtures-20261015
fix/batch-decompile-null-pseudocode
fix/kuna-inventory-honors-jobs
experiment/browser-codemode-tool-design-20261015
fix/hopper-clean-runtime-argv
codex/review-2049-27f1b367
review-fixes/pr-2787-routing
fix/3360-scoped-this-emitters
fix/3367-replaced-global-effects
fix/3838-compact-any-value-items
test/hopper-download-probe-20261015
codex/windows-runtime-creation-red-green-20261015
codex/windows-readonly-root-red-green-20261015
codex/windows-root-share-red-green-20261015
codex/exp-1685-win-mcp-startup
codex/bug-sweep-20261015
investigate/2190-windows-package-phases
investigate/3543-macos-cli-deadline
perf/3281-reverse-tools-feedback-quality
fix/3406-hopper-doctor-fixture
fix/3341-wrapper-require-test-context
fix/3301-owned-uninstall-fixtures
fix/3164-compiler-input-ownership
fix/pcap-cleanup-stdout-newline-20261014
perf/interface-builder-summary
codex/review-fixes-pr-1977
fix/ghidra-effective-jvm-platform
fix/docs-turkish-rust-link-20261013
fix/main-maintenance-ci-20261010
fix/recover-binary-session-process-effects
codex/review-fixes-pr-2457
codex/ci-required-cancellation-gate
fix/main-format-baseline-20261013
fix/setup-preserve-entry-fields
cursor/restore-main-checks-1ffc
fix/ghidra-bridge-hashmap-import
codex/shared-ci-jadx-json-default-20261013
codex/shared-ci-ghidra-test-groups-20261013
codex/shared-ci-java-fixture-format-20261013
codex/fix-intrinsic-invocation-boundaries
test/release-preflight-reusable-jobs
test/js-parameter-provenance-expectation
fix/linux-hopper-verification-current
test/2419-ghidra-elf-probe-size
followup/pr-1544-native-ida
codex/fold-pr-2230-contribution
docs/readme-responsible-use
fix/issue-2064
fix/issue-2050
fix/issue-2053
fix/issue-1968
fix/issue-1945
experiment/codemode-bridge-20261011
fix/tool-effects-negative-wording-1904-20261012
fix/1842-electron-interop-provenance
feat/recover-javascript-multi-input
refactor/website-i18n-prep
fix/nativeaot-pe-virtual-extent
fix/browser-verifier-ci-hang
fix/pe-resources-input-selection
docs/beginner-friendly-guides
docs/beginner-setup-guide
fix/javascript-analysis-worker-1563
fix/1649-ghidra-duplicate-names
fix/javascript-export-keys-integration-1369
test/maintenance-boundary-contracts-20261011
review/javascript-export-keys-1369
review/process-live-progress-1483
test/javascript-1495-growth-ratio
fix/ci-escape-timing
docs/normalized-terminal-geometry-1450
release/6.3.0
archive/release-6.3.0-pr1381
release/6.2.0
fix/electron-preload-dynamic-override
fix/javascript-self-referential-bundler-edges
release/6.1.0
cursor/grok-client-cherry-pick-0b56
feat/signature-posture
feat/dyld-shared-cache
feat/artifact-integrity-policy
feat/pkg-inventory
release/6.0.0
chore/sync-release-5.0.0
release/5.0.0
cursor/cloud-agent-node-787e
fix/javascript-xhr-open-endpoints
review/pr-711-realpath-fallback-wording
cleanup/replay-confinement
codex/test-suite-performance
codex/issue-foundations
codex/address-open-issues-2026-07-20
agent/javascript-vite-rollup-esbuild-adapters
agent/process-cleanup
agent/triage-integration
agent/unknown-commands-registry
feat/mcp-identity-metadata
morlvps/issue_cleanup
codex/installer-redesign
morl/roadmap-investigation-core
morl/roadmap-investigation-docs
release-please--branches--main--components--rea
rea-agents-6.8.0
rea-agents-6.7.0
rea-agents-6.6.0
experiment/atomic-codemode-wait-runtime-20261016
rea-agents-6.5.0
rea-agents-6.4.0
rea-agents-6.3.0
rea-agents-6.2.0
rea-agents-6.1.0
rea-agents-6.0.0
rea-agents-5.0.0
rea-agents-4.1.0
rea-agents-4.0.1
rea-agents-4.0.0
rea-agents-3.2.1
rea-agents-3.2.0
rea-agents-3.1.0
rea-agents-3.0.0
rea-agents-2.7.0
rea-agents-2.6.0
rea-agents-2.5.1
rea-agents-2.5.0
rea-agents-2.4.0
rea-agents-2.3.0
rea-agents-2.2.0
rea-agents-2.1.0
rea-agents-2.0.0
rea-agents-1.7.0
rea-agents-1.6.0
rea-agents-1.5.0
rea-agents-1.4.0
rea-agents-1.3.0
rea-agents-1.2.0
rea-agents-1.1.0
rea-agents-1.0.0
rea-agents-0.5.0
rea-agents-0.4.0
rea-agents-0.3.0
rea-0.2.1
rea-0.2.0
Labels
Clear labels   
area: bridge

   
area: bridge

   
area: build

   
area: build

   
area: build

   
area: cli

   
area: domain

   
area: evidence

   
area: mcp

   
area: native

   
area: providers

   
area: runtime

   
area: server

   
area: setup

   
area: tests

   
bug

   
design

   
documentation

   
enhancement

   
enhancement

   
enhancement

   
experiment

   
help wanted

   
i18n

   
invalid

   
P0: critical

   
P1: high

   
P2: medium

   
P2: medium

   
P2: medium

   
P3: low

   
performance

   
provider-request

   
pull-request
Mirrored from GitHub Pull Request

  
question

   
roadmap

   
triage
No labels
area: bridge
area: bridge
area: build
area: build
area: build
area: cli
area: domain
area: evidence
area: mcp
area: native
area: providers
area: runtime
area: server
area: setup
area: tests
bug
design
documentation
enhancement
enhancement
enhancement
experiment
help wanted
i18n
invalid
P0: critical
P1: high
P2: medium
P2: medium
P2: medium
P3: low
performance
provider-request
pull-request
question
roadmap
triage
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
morluto/rea#6932
No description provided.