[GH-ISSUE #7155] MCP tools/list is 3.16 MB - outputSchema is 74.5% of it` #4290

New issue

Open

opened 2026-10-31 00:48:33 +00:00 by bsakaguchi · 6 comments

bsakaguchi commented 2026-10-31 00:48:33 +00:00

Owner

Copy link

Originally created by @joneminiss on GitHub (Oct 25, 2026).
Original GitHub issue: https://github.com/morluto/rea/issues/7155

Summary

tools/list returns 207 tools / 3,158,352 bytes. Clients that keep the catalog in every request (Claude Code, Cline, Roo, Codex, Cursor, DeepSeek Harness) then spend ~215,000 tokens every turn regardless of the prompt. On 200k-context models REA eats the entire budget before the first user message; on 128k it will not load at all.

Measured on rea-agents@6.7.0, Windows 11 x64, Node 24.22.1, Ghidra 12.1.4, rea mcp over stdio, protocolVersion: 2024-11-05.

Byte composition

Component	Bytes	Share
outputSchema	2,353,893	74.5%
inputSchema	667,641	21.1%
description	92,265	2.9%
annotations	18,534	0.6%
title	4,078	0.1%

Three quarters of the payload is outputSchema.

Largest tools

Tool	Total	output	input
compare_web_captures	181,042	14,248	165,694
inspect_analysis_view	170,393	137,985	25,282
compare_application_versions	62,206	31,285	30,271
capture_browser_scenario	58,724	36,152	21,352
reconcile_javascript_runtime	46,395	30,167	15,489

Top 10 tools = 727,403 bytes = 23.0%.

Cross-tool duplication

Hashing every inputSchema sub-object over 800 bytes:

• 38 fragments appear in more than one tool
• Redundant bytes: 1,083,810 (34% of the catalog)
• One 6,941-byte fragment x 23 tools = 152,702 redundant bytes
• One 7,249-byte fragment x 18 tools = 123,233 redundant bytes

"evidence_id" appears 542 times because the Evidence envelope is inlined everywhere instead of referenced.

Suggestions, by impact per effort

1. Make outputSchema opt-in (-74.5%). A model cannot use an output schema before calling the tool, and most clients do not render it. Omit by default behind --full-schemas, or publish once out of band and $ref it.

2. Let the server filter its own list. Today a client wanting 20 tools must wrap the server:

rea mcp --tools binary_session,analyze_function,xrefs
rea mcp --tool-groups binary,android
rea mcp --tools-file ./rea-tools.json

3. Factor out the Evidence envelope (-34%). One canonical $defs.Evidence + $defs.Location, $ref from each tool. Standard JSON Schema. Removes over 1 MB.

4. Group the compare_* / project_* families. compare_web_captures is 181 KB because it inlines the whole inspect_web_page input shape twice. Use a single compare(kind, left, right), or accept evidence_id instead of inline Evidence. You already return evidence_id from every call, so accept it back.

5. Add rea mcp --tier minimal|standard|full. minimal (~15 core tools) should land under ~50 KB.

6. Add rea mcp --print-schema-stats. You already have --token-count; let users see this before wiring it in.

Workaround I used

A stdio proxy filtering tools/list by allow-list, passing tools/call through. 207 -> 29 tools took the catalog from ~215k tokens to ~6.1k with no capability loss. I then found the CLI covers the same ground and dropped MCP entirely (206 commands, zero resident tools).

That works, but every downstream user should not have to write it.

Reproduce

{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"probe","version":"1"}}}
{"jsonrpc":"2.0","method":"notifications/initialized"}
{"jsonrpc":"2.0","id":2,"method":"tools/list"}

Measure JSON.stringify(response.result.tools).length.

---

Happy to PR any of these. $defs factoring (#3) and the --tools allow-list (#2) both look self-contained. Thanks for REA: the CLI surface is excellent and the Evidence model is good design, only the wire format at tools/list needs trimming.

Originally created by @joneminiss on GitHub (Oct 25, 2026). Original GitHub issue: https://github.com/morluto/rea/issues/7155 ## Summary `tools/list` returns **207 tools / 3,158,352 bytes**. Clients that keep the catalog in every request (Claude Code, Cline, Roo, Codex, Cursor, DeepSeek Harness) then spend ~**215,000 tokens every turn** regardless of the prompt. On 200k-context models REA eats the entire budget before the first user message; on 128k it will not load at all. Measured on `rea-agents@6.7.0`, Windows 11 x64, Node 24.22.1, Ghidra 12.1.4, `rea mcp` over stdio, `protocolVersion: 2024-11-05`. ## Byte composition | Component | Bytes | Share | |---|---:|---:| | `outputSchema` | 2,353,893 | **74.5%** | | `inputSchema` | 667,641 | 21.1% | | `description` | 92,265 | 2.9% | | `annotations` | 18,534 | 0.6% | | `title` | 4,078 | 0.1% | Three quarters of the payload is `outputSchema`. ## Largest tools | Tool | Total | output | input | |---|---:|---:|---:| | `compare_web_captures` | 181,042 | 14,248 | 165,694 | | `inspect_analysis_view` | 170,393 | 137,985 | 25,282 | | `compare_application_versions` | 62,206 | 31,285 | 30,271 | | `capture_browser_scenario` | 58,724 | 36,152 | 21,352 | | `reconcile_javascript_runtime` | 46,395 | 30,167 | 15,489 | Top 10 tools = 727,403 bytes = **23.0%**. ## Cross-tool duplication Hashing every `inputSchema` sub-object over 800 bytes: - **38 fragments** appear in more than one tool - Redundant bytes: **1,083,810** (34% of the catalog) - One 6,941-byte fragment x 23 tools = 152,702 redundant bytes - One 7,249-byte fragment x 18 tools = 123,233 redundant bytes `"evidence_id"` appears **542 times** because the Evidence envelope is inlined everywhere instead of referenced. ## Suggestions, by impact per effort **1. Make `outputSchema` opt-in (-74.5%).** A model cannot use an output schema before calling the tool, and most clients do not render it. Omit by default behind `--full-schemas`, or publish once out of band and `$ref` it. **2. Let the server filter its own list.** Today a client wanting 20 tools must wrap the server: ``` rea mcp --tools binary_session,analyze_function,xrefs rea mcp --tool-groups binary,android rea mcp --tools-file ./rea-tools.json ``` **3. Factor out the Evidence envelope (-34%).** One canonical `$defs.Evidence` + `$defs.Location`, `$ref` from each tool. Standard JSON Schema. Removes over 1 MB. **4. Group the `compare_*` / `project_*` families.** `compare_web_captures` is 181 KB because it inlines the whole `inspect_web_page` input shape twice. Use a single `compare(kind, left, right)`, or accept `evidence_id` instead of inline Evidence. You already return `evidence_id` from every call, so accept it back. **5. Add `rea mcp --tier minimal|standard|full`.** `minimal` (~15 core tools) should land under ~50 KB. **6. Add `rea mcp --print-schema-stats`.** You already have `--token-count`; let users see this before wiring it in. ## Workaround I used A stdio proxy filtering `tools/list` by allow-list, passing `tools/call` through. 207 -> 29 tools took the catalog from ~215k tokens to **~6.1k** with no capability loss. I then found the CLI covers the same ground and dropped MCP entirely (206 commands, zero resident tools). That works, but every downstream user should not have to write it. ## Reproduce ```json {"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"probe","version":"1"}}} {"jsonrpc":"2.0","method":"notifications/initialized"} {"jsonrpc":"2.0","id":2,"method":"tools/list"} ``` Measure `JSON.stringify(response.result.tools).length`. --- Happy to PR any of these. `$defs` factoring (#3) and the `--tools` allow-list (#2) both look self-contained. Thanks for REA: the CLI surface is excellent and the Evidence model is good design, only the wire format at `tools/list` needs trimming.

bsakaguchi commented 2026-10-31 00:48:34 +00:00

Author

Owner

Copy link

@Navneet14-cmd commented on GitHub (Oct 25, 2026):

I’d like to take #2. Proposal: rea mcp --tools a,b,c and --tool-groups , default behavior unchanged. Unknown tool names fail at startup with a clear error, and tools/call for a filtered-out tool returns the standard unknown-tool error. Happy to adjust names or semantics before I start. I’ll leave #3 for a separate PR if you want it.

<!-- gh-comment-id:6400862778 --> @Navneet14-cmd commented on GitHub (Oct 25, 2026): I’d like to take #2. Proposal: rea mcp --tools a,b,c and --tool-groups <names>, default behavior unchanged. Unknown tool names fail at startup with a clear error, and tools/call for a filtered-out tool returns the standard unknown-tool error. Happy to adjust names or semantics before I start. I’ll leave #3 for a separate PR if you want it.

bsakaguchi commented 2026-10-31 00:48:34 +00:00

Author

Owner

Copy link

@definitelynotchirag commented on GitHub (Oct 25, 2026):

Two of these already exist, in case you missed them on 6.7.0. REA_MCP_OUTPUT_SCHEMA_PROFILE=off in the server env drops every outputSchema from tools/list, which is your suggestion 1. REA_MCP_INPUT_SCHEMA_PROFILE=compact trims the inputs. Both are in docs/client-configuration.md. Your suggestion 2 is close to the open PR #3026, which filters the advertised list by family.

One thing to be aware of from the other direction: #7154 tags every tool with its family in _meta, which adds about 14 KB to the list (0.3 to 0.4% depending on profile). That's the vocabulary a --tool-groups flag could key on, so it should help here rather than hurt, but it is a few more bytes.

<!-- gh-comment-id:6400912063 --> @definitelynotchirag commented on GitHub (Oct 25, 2026): Two of these already exist, in case you missed them on 6.7.0. `REA_MCP_OUTPUT_SCHEMA_PROFILE=off` in the server env drops every outputSchema from tools/list, which is your suggestion 1. `REA_MCP_INPUT_SCHEMA_PROFILE=compact` trims the inputs. Both are in docs/client-configuration.md. Your suggestion 2 is close to the open PR #3026, which filters the advertised list by family. One thing to be aware of from the other direction: #7154 tags every tool with its family in `_meta`, which adds about 14 KB to the list (0.3 to 0.4% depending on profile). That's the vocabulary a `--tool-groups` flag could key on, so it should help here rather than hurt, but it is a few more bytes.

bsakaguchi commented 2026-10-31 00:48:34 +00:00

Author

Owner

Copy link

@ashishgit4 commented on GitHub (Oct 25, 2026):

/assign

<!-- gh-comment-id:6401157198 --> @ashishgit4 commented on GitHub (Oct 25, 2026): /assign

bsakaguchi commented 2026-10-31 00:48:35 +00:00

Author

Owner

Copy link

@XinwangTao commented on GitHub (Oct 25, 2026):

The 3.16 MB catalog is brutal for 128k-context models — outputSchema alone eating 74.5% makes the case for making it opt-in very strong. On top of that, the cross-tool duplication data (1 MB+ redundant, evidence_id inlined 542 times) suggests switching to shared schema references (JSON Schema $defs/$ref or equivalent) would cut payload size dramatically without losing information. Definitely a bug worth prioritizing.

<!-- gh-comment-id:6401942891 --> @XinwangTao commented on GitHub (Oct 25, 2026): The 3.16 MB catalog is brutal for 128k-context models — outputSchema alone eating 74.5% makes the case for making it opt-in very strong. On top of that, the cross-tool duplication data (1 MB+ redundant, `evidence_id` inlined 542 times) suggests switching to shared schema references (JSON Schema `$defs`/`$ref` or equivalent) would cut payload size dramatically without losing information. Definitely a bug worth prioritizing.

bsakaguchi referenced this issue 2026-10-31 01:12:20 +00:00

[PR #4290] [MERGED] fix(native): report PE input byte budgets as file-size limits #6161

bsakaguchi referenced this issue 2026-10-31 01:14:07 +00:00

[PR #4757] [MERGED] fix(javascript): report oversized recovery inputs as file-size limits #6391

bsakaguchi commented 2026-11-01 21:11:10 +00:00

Author

Owner

Copy link

@morluto commented on GitHub (Oct 31, 2026):

Current native-investigation catalog capture

A fresh stdio MCP SDK tools/list capture on REA b43c329df779708e43ae297f498a844e45d9c923 (server and contract source unchanged at checked main 23de10bb2849cdce8ddbe70504aa7cc57de75a98) returned these exact serialized SDK result sizes. Estimated tokens use tiktoken 0.12.0 o200k_base over the entire serialized result; they are not measured host prompt usage.

Configuration	Tools	Serialized bytes	Estimated tokens
Default	233	3,907,046	1,037,315
Compact output schema	233	572,979	123,924
Output schema off	233	316,026	68,097
session,direct,enhanced,application and compact output	100	234,338	49,880

In the default response, inspect_analysis_view alone occupied 594,287 bytes including a 578,094-byte output schema; batch_decompile occupied 21,486 bytes including 20,564 output-schema bytes. The compact output profile widens advertised schemas, while the scoped profile omits other tools; those are real contract/capability tradeoffs, not cost-free equivalent catalogs. The SDK received the complete payloads successfully here; no client line limit, autonomous tool-selection outcome, per-turn prompt cost, or analysis latency was measured. Host behavior determines which fields, if any, enter a model prompt. This refreshes the earlier capture at the newer source baseline rather than establishing a performance regression from a matched before/after workload.

<!-- gh-comment-id:6544466553 --> @morluto commented on GitHub (Oct 31, 2026): ### Current native-investigation catalog capture A fresh stdio MCP SDK `tools/list` capture on REA `b43c329df779708e43ae297f498a844e45d9c923` (server and contract source unchanged at checked main `23de10bb2849cdce8ddbe70504aa7cc57de75a98`) returned these exact serialized SDK result sizes. Estimated tokens use `tiktoken` 0.12.0 `o200k_base` over the entire serialized result; they are **not** measured host prompt usage. | Configuration | Tools | Serialized bytes | Estimated tokens | | --- | ---: | ---: | ---: | | Default | 233 | 3,907,046 | 1,037,315 | | Compact output schema | 233 | 572,979 | 123,924 | | Output schema off | 233 | 316,026 | 68,097 | | `session,direct,enhanced,application` and compact output | 100 | 234,338 | 49,880 | In the default response, `inspect_analysis_view` alone occupied 594,287 bytes including a 578,094-byte output schema; `batch_decompile` occupied 21,486 bytes including 20,564 output-schema bytes. The compact output profile widens advertised schemas, while the scoped profile omits other tools; those are real contract/capability tradeoffs, not cost-free equivalent catalogs. The SDK received the complete payloads successfully here; no client line limit, autonomous tool-selection outcome, per-turn prompt cost, or analysis latency was measured. Host behavior determines which fields, if any, enter a model prompt. This refreshes the earlier capture at the newer source baseline rather than establishing a performance regression from a matched before/after workload.

bsakaguchi commented 2026-11-04 04:56:16 +00:00

Author

Owner

Copy link

@XinwangTao commented on GitHub (Nov 4, 2026):

morluto 这份 capture 把问题的重心讲清楚了：scoped + compact output 组合已经能把 233 个工具压到 100 个 / ~50K tokens，但默认配置仍然是全量 1M+ tokens。结合 #5861 的「compact 存在但默认关闭」和 #7654 的「文档遗漏该选项」，核心矛盾其实是「可用配置没有成为默认路径」。#8388 的发现性设计是对的——建议同时考虑：1) setup/首次启动引导中默认勾选 compact 或按场景生成 scoped profile；2) 让默认 tools/list 至少应用 compact output schema（把 3.9MB 降到 573KB，客户端仍然拿到全部工具，只是省掉绝大多数 outputSchema）。这样对 128K 模型的可用性提升立竿见影，且不牺牲能力声明的完整性。

<!-- gh-comment-id:6622361369 --> @XinwangTao commented on GitHub (Nov 4, 2026): morluto 这份 capture 把问题的重心讲清楚了：scoped + compact output 组合已经能把 233 个工具压到 100 个 / ~50K tokens，但默认配置仍然是全量 1M+ tokens。结合 #5861 的「compact 存在但默认关闭」和 #7654 的「文档遗漏该选项」，核心矛盾其实是「可用配置没有成为默认路径」。#8388 的发现性设计是对的——建议同时考虑：1) setup/首次启动引导中默认勾选 compact 或按场景生成 scoped profile；2) 让默认 tools/list 至少应用 compact output schema（把 3.9MB 降到 573KB，客户端仍然拿到全部工具，只是省掉绝大多数 outputSchema）。这样对 128K 模型的可用性提升立竿见影，且不牺牲能力声明的完整性。

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

Subscribe

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#4290

No description provided.