Validate columns × (rows + scrollback) against a 1,000,000-cell xterm working-buffer budget, including every resize with the selected scrollback. Document the budget in the advertised MCP input and process-capture guide; never clamp caller dimensions.
Validation: default/exact-boundary schema cases, prelaunch MCP rejection, compiled CLI capture, terminal rendering, normalization, cancellation, and lifecycle checks pass on macOS. This is resource admission, not a measured serializer throughput improvement; Linux-only and real deep-analysis providers were not exercised.
BREAKING CHANGE: process scenarios whose initial or resized terminal exceeds 1,000,000 combined visible-plus-scrollback cells are now rejected before launch.
Guide task-centered recovery from observed client, registration, PATH and
provider blockers. Install the recovery reference, document exact JavaScript
module selectors, and require clarification before searching for an unnamed
app. Validate public setup in isolated Codex accounts and preserve failed
or unrecognized tool outcomes in the existing evaluator.
Refs: #1587
BREAKING CHANGE: Optional verify:agent reports now use schemaVersion 4.
Consumers must accept expectedFirstTool: null and targetClarificationPassed
for missing-target scenarios. Production CLI/MCP contracts are unchanged.
* feat(native): admit bounded MIPS ELF analysis through Ghidra
Retain MIPS ELF identity and interpretation through Evidence and snapshots.
Keep provider admission bounded to ELF32 ET_EXEC o32 MIPS32r2, without
implicitly widening Hopper, IDA or Windows P0 coverage. Add source-owned
fixtures and an optional real-provider verifier; real Ghidra verification
remains pending in this contribution environment.
Refs #718
* fix(ghidra): bound MIPS floating-point mode admission
Reject explicit EF_MIPS_FP64 and EF_MIPS_NAN2008 declarations until their
semantics have a real-provider verification lane. Add PSP PRX/Allegrex,
o64/EABI and floating-point-mode refusal regressions. Document that the
header gate is not a full .MIPS.abiflags check and advance the profile lane
identity to invalidate older interpretation bindings.
Validation: 24 standalone checks against the transpiled production profile
module passed; the two new flag cases failed before this change. Clang 17
and LLD compiled the source-owned fixture for both endian targets. The
complete Vitest/typecheck suite and real Ghidra verification remain pending.
Refs morluto/rea#718; PSP support remains follow-up morluto/rea#1330.
* fix(native): validate MIPS ABI records before Ghidra admission
Read bounded ELF32 PT_MIPS_ABIFLAGS and SHT_MIPS_ABIFLAGS records through
the already-open target handle. Preserve declared ABI fields, reject
conflicting/duplicate/truncated records, and keep missing records unknown.
Wire inspection into target resolution before provider selection. Require
compatible declarations for the deliberately narrow Ghidra lane and bind
all ABI fields into profile identity (v3) for snapshot invalidation.
Clang 17 produced eight source-owned fixtures spanning both byte orders
and FPXX/FP32/FP64/soft-float modes with identical ELF header flags. The
new reader and policy distinguish them. 24 focused regression test bodies
passed after TypeScript transpilation using node:test in place of Vitest;
strict isolated TypeScript checking of the reader and target/result types
passed. These are limited checks, not full Vitest/project typechecking or
real-Ghidra verification, which remain pending.
Advances morluto/rea#718. PSP/Allegrex remains morluto/rea#1330 follow-up.
* fix(native): repair MIPS integration boundaries and test resolver behavior
Keep ELF targets out of Hopper Mach-O preparation and scope existing PE fixture types correctly. Move ABI tests into the filesystem boundary lane, use shared cleanup, add resolver regressions, apply the pinned formatter, and register the real MIPS verifier through the existing package-command pattern. Validated with repository-pinned Node/npm, check:ci, actual focused Vitest, discovery and docs:check. Real Ghidra conformance remains pending.
* fix(test): honor caller-selected JDK in real MIPS verification
* test(native): strengthen MIPS Ghidra conformance
Cross-check the source-owned fixture with bounded GNU readelf inspection, compare production ELF/ABI interpretation and independent symbol addresses, and verify effective Ghidra language/compiler identity through existing public operations. Add a source-owned fixed-encoding probe for immediate and conditional branch checks plus global/string byte assertions.
Add 16 assertion/producer-boundary regression cases without widening production admission, changing provider contracts, or introducing proprietary dependencies. Local focused suite: 99 passed, one existing root-permission test skipped. Typecheck, lint/module boundaries, formatting and 700-file discovery pass; full hosted checks and real Ghidra verification remain pending for this checkpoint.
* fix(ghidra): preserve native-tool architecture checks after MIPS integration
The conflict-free upstream merge failed TypeScript compilation because includes on the union of MIPS-only and other architecture arrays requires never. Use equality-based membership without casts or changing accepted native hosts. Extend the existing native-decompiler rejection table with a MIPS executable at a Linux x64 tool path; retain upstream FAT and unknown-header behavior. Hosted verification follows this commit; no success is claimed yet.
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* feat(apktool): decode Android resource tables through a caller-supplied launcher
Add an Apktool family with two operations over the caller's apktool
launcher (REA_APKTOOL_COMMAND, absolute, or apktool on PATH):
- inspect_apktool_client: resolved launcher, selection source, and
version; decodes nothing.
- decode_android_resources: apktool d --no-src in a provider-owned
workspace that is removed before the result returns. Projects the
decoded AndroidManifest.xml (bounded at 512 KiB), apktool.yml version
and SDK facts exactly as printed, string resources verbatim (default or
one locale, bounded at 2000 entries, nested-markup entries counted as
unparsed), available string locales, and the decoded file count with a
hard cap. The target APK is digested with SHA-256 before decoding so
Evidence binds the observation to the exact input.
Smali production is skipped by design: Java-source recovery belongs to
the JADX family. Workspace cleanup happens before results return; an
unremovable workspace is named in the limitations instead of abandoned.
Verified against apktool 2.7.0-dirty (Debian packaging) on Linux with
OpenJDK 25 against a signed aapt2-built probe APK with two resource
locales: launcher version, on-disk digest agreement, metadata projection,
manifest package agreement, and both string tables (default and de).
Parser goldens come from the same decode. READMEs carry the new
'Android resources' row in every supported language.
* fix(apktool): own snapshots and bound decoded resource reads
* docs(apktool): describe owned resources and bounded projection
---------
Co-authored-by: REA Contributor <contributor@rea.tools>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
* feat(jeb): add JEB engine provider over its MCP interface
Add a bring-your-own JEB provider that serves project, unit, and
decompilation inspection from a caller-started JEB client speaking MCP
(streamable HTTP, selected with REA_JEB_MCP_URL). Expose four provider-neutral
operations through shared CLI/MCP workflows: inspect_jeb_client,
open_jeb_project, list_jeb_units, and decompile_jeb_item, each returning
Evidence with engine identity, endpoint, and preserved refusal reasons.
The adapter keeps JEB's envelope semantics: success fields are parsed
format-aware at the boundary, message-only refusals become unsupported-target
errors with the engine's own reason, transport failures become availability
failures with recovery guidance, and unit pagination derives coverage from the
engine's 100-item page cap. Explicit unknowns (implicitly selected unit,
omitted filters) are reported instead of guessed.
Verified against a real JEB 5.48.0 licensed build serving jeb-mcp-server 1.3.0
headless: client inspection, unit listing, and method decompilation were
exercised through the CLI, MCP boundary, and scripts/verify-jeb.mjs.
JEB 5.48.0 headless instances do not advertise open_project; the refusal is
preserved and documented.
* fix(jeb): verify against a real signed APK and fix CLI option surface
Verify the provider against a locally built, v1/v2/v3-signed probe APK
(binary manifest, classes.dex with a launcher activity) on JEB 5.48.0: the
full unit tree (apk, manifest, three certificate units, dex bytecode,
decompiler), wildcard-filtered and paginated unit listing with derived
coverage, parent-restricted listing, and launcher-activity method
decompilation through both CLI and MCP, including dexdec's inline
constant folding of the probe's obfuscated tag.
Move list-jeb-units filter/pagination and decompile-jeb-item unit selection
from positional arguments to options; the MCP schemas are unchanged.
* fix(jeb): preserve engine refusals through the real MCP boundary
Testing against the published Signal 8.30.3 universal APK exposed a boundary
bug the scripted provider tests missed: decodeJebToolResult raised a protocol
error for isError results before the provider could map JEB's
{success:false, message} envelope, so real engine refusals surfaced as
unreadable output instead of the engine's own reason. Decode refusal
envelopes like any structured result and let the provider preserve the
reason; cover the decoder directly, including contentless and unparseable
results.
Signal verification: full 109 MB R8/Kotlin/Compose APK with four signature
schemes and native arm64 ELF units parsed; MainActivity.onCreate and R8
synthetic lambdas decompiled through CLI and MCP; paginated, filtered, and
parent-restricted unit listing; refusal path confirmed on the live engine.
* docs(jeb): record Flutter Gallery verification on the real-engine lane
Verify the provider against the official Flutter Gallery 2.9.2 release APK
(112 MB): per-ABI libapp.so Dart AOT snapshot images analyzed as native code
with 75k methods on arm64, snapshot internals and wrapper methods decompiled
through both CLI and MCP with explicit unit selection, decoded manifest, and
filtered native-library unit discovery. Note that JEB 5.48.0 headless does
not expose the dedicated Dart snapshot processor or run_script; both remain
GUI-only engine surfaces.
* docs(jeb): translate the README JEB row for every supported language
The JEB row was inserted in English across all translated READMEs; each now
carries its own label, capability summary, requirements, and guide link
following that language's Android-row conventions.
* fix(jeb): enforce local endpoints and preserve cancellation
* fix(jeb): refuse redirects across the local MCP boundary
---------
Co-authored-by: REA Contributor <contributor@rea.tools>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
* fix(javascript): accept the Wakaru 1.x release line and verify 1.14.0
Exact --version equality rejected every Wakaru build except 1.13.0, and
strict report schemas rejected any added field, so each upstream release
broke recovery until REA re-pinned. Wakaru now documents that --version,
--json and provenance.json change only by addition within a major version.
Admit ^1.13.0 with the verified/compatible split used for Binwalk and
Unblob, report the observed version instead of the pinned constant, and
add a limitation for unverified releases. Parse reports with loose
objects and keep the reported module status as a string; path, identity,
range and file-set checks stay exact.
Move the audited pin, submodule, CI binary and verifier to 1.14.0, and
document where to get the binary from the refusal message.
* fix(javascript): project known Wakaru warning fields
---------
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
* fix(electron): resolve pages served from inside app.asar
Packaged Electron applications load their renderer pages from file URLs
inside app.asar. The host filesystem cannot stat those paths, so
list_electron_targets excluded every such page as unsupported_url and
inspect_electron_page could not select it.
Resolve these URLs the way Electron's file protocol does: the first .asar
path component that is a regular file is the archive, and the remainder
must name a regular file in its header. Directories, links, and missing
members stay rejected. Parsed headers are cached by archive identity.
* fix(artifacts): extract and explain rewritten ASAR unpacked companions
Packaging tools commonly sign or strip .asar.unpacked native binaries after
writing the archive header, so their declared hashes no longer match.
analyze_javascript_application already accepts integrity_policy, but
extract_artifact did not, and inspect_artifact and extract_artifact still
told callers to "get a fresh copy", which cannot help for a shipped app.
- Accept integrity_policy on extract_artifact (MCP and CLI). The default
still fails closed; record-and-continue writes the observed bytes and
returns the extracted files' integrity_contradictions records.
- Name the unpacked entry and the post-packaging cause in integrity
failures, and point every operation that accepts integrity_policy at
record-and-continue.
- Report an active unpacked entry whose companion file is absent as
unavailable with its logical path instead of a format failure.
- Share one integrity_policy schema across the inventory, extraction, and
JavaScript application inputs.
* fix(electron): bound ASAR headers before allocation
---------
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
* feat(adb): acquire installed APK sets from connected Android devices
Add a read-only ADB device-acquisition family over the caller's adb binary:
inspect_adb_client, list_adb_devices, inspect_adb_device, list_adb_packages,
and pull_adb_package, exposed through the CLI and MCP with shared admission,
Evidence provenance (binary, version, serial, transport), and fixed argv
vectors that never reach a shell.
pull_adb_package acquires the complete split set reported by pm path into a
package-named directory that must not exist, digesting every file with
SHA-256 and keeping per-file failure reasons and partial coverage. Device
kind is reported as an inference with its basis; getprop whitelisting keeps
build identity bounded. REA installs nothing and never manages devices or
emulators; the first device query may start the caller's local adb server,
recorded when observed.
Verified against adb 34.0.5 on Linux with an Android 14 (API 34) x86_64
emulator: full 224-package inventory, a real two-APK split set pulled with
byte-exact digests, and a 73.9 MB system-package pull. npm run verify:adb
records the lane; parser goldens come from the same device. READMEs carry
the new row in every supported language.
* feat(adb): complete the adb surface with observation, transfer, and lifecycle tools
Extend the ADB family from five to twenty-four operations, all through
fixed adb argument vectors with no shell exposure:
Observation: read_adb_logcat (bounded dump, count/buffer/pid), inspect_adb_package
(dumpsys package projection), list_adb_processes (ps -A), list_adb_directory
(ls -la with kinds and symlink targets), list_adb_features (hex GL versions),
list_adb_services (AIDL slash-suffixed names), inspect_adb_display (wm size and
density), inspect_adb_window (focus declarations), read_adb_setting (device-side
nulls reported as such), capture_adb_screen (exec-out screencap with PNG
dimensions), collect_adb_bugreport (digested device archive).
Transfer and search: pull_adb_file and push_adb_file (device-side sha256sum
verification, explicit overwrite authority), resolve_adb_packages (substring
package search with exact-match flag — the find step of an easy get).
Lifecycle for dynamic analysis, each declaring mutatesTarget:
install_adb_package and uninstall_adb_package preserving the device's
Success/Failure verdict, start_adb_app (resolve-activity then am start -W),
start_adb_activity (typed extras as --es/--ez/--ei/--el/--ef), and stop_adb_app
(am force-stop).
Verified end-to-end against adb 34.0.5 on Linux with an Android 14 (API 34)
x86_64 emulator: 287 services, 92 features, split-set pulls with byte-exact
digests, verified push/pull roundtrip, sized screen capture, and the full
install → resolve → start → observe-in-ps → force-stop → uninstall lifecycle.
Fixed a v-mode regex incompatibility in the settings key pattern and added
argument descriptions required by the CLI catalog audit.
* fix(adb): quote remote shell operands and protect captured output
* test(adb): cover bugreport destinations containing spaces
---------
Co-authored-by: REA Contributor <contributor@rea.tools>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
inspect_binary_layout accepts the same optional detail input as
analyze_javascript_application. The default complete delivery is
unchanged; detail "summary" retains the complete layout Evidence in the
session and returns its inspect_analysis_view summary, whose
parent_evidence_id selects sections, symbols, mitigations or linkage
later. Both tools share one detail schema and output projection.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
analyze_javascript_application returns the complete application graph
inline, which repeats tens of kilobytes even for a few source lines and
exceeds the default 10 MiB MCP frame for a 300-function source file.
The new optional detail input keeps complete delivery by default. With
detail "summary" the server records the complete analysis Evidence in
the session and returns its inspect_analysis_view summary, whose
parent_evidence_id lets callers page modules, select items, or pass the
retained reference to application workflows. A server without Evidence
retention refuses summary detail with capability_unavailable rather
than returning a summary whose analysis cannot be reached.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Hosts forward every tool's input schema to the model on each request.
Seventeen tools advertised a canonical example that embedded a complete
producer Evidence record, up to 22 KB each, accounting for 116 KB of the
450 KB of advertised input schemas.
Advertised examples now show an embedded Evidence record as its exact
retained-evidence reference when the canonical input accepts one, and
omit an example that can only carry inline Evidence. Canonical contract
examples, their executable tests, and validation are unchanged.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
- CONTRIBUTING: CLI logs go to stderr, not stdout. `createLogger` writes every
mode to fd 2 so protocol and `--json` stdout stay parseable.
- Get started: Ghidra supports Linux arm64 (`GhidraInstallation` maps
`linux.arm64`), as installation.md already states.
- Browser guide: drop the caption claiming the hosted request path carries a
`/rea/` prefix. The guide now targets rea.tools, where the example is served
at `/examples/notes-web/`, as the evidence table above it shows.
- JavaScript workflows: six CLI commands accept inline JSON or a JSON file,
not five; `inspect-analysis-view` was added after the sentence was written.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
Inventory gave nested members a ZIP or ASAR family from their path
suffix. Byte classification replaced it only for ZIP magic, so text named
`.apk` or `.asar` stayed a container, and encrypted entries and symlinks
kept the suffix guess. A filesystem `.asar` without an ASAR header failed
the whole inventory as a malformed archive.
Nested ZIP families now follow ZIP magic and ASAR follows its header
pickle, shared with root classification. An unread member named like a
container has an unknown format and a limitation naming the suffix. ASAR
expansion requires the header.
The Android projection adds a limitation when no root AndroidManifest.xml
was observed, and its rejection names the observed root format.
Fixes#1491
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Retain one pending intermediate observation and drop stale live status before terminal cleanup. Preserve monotonic counts and final delivery while an observer is slow or rejects an update.
Verify the send rate at its controlled-clock owner and lifecycle notification density at the CLI/MCP boundary, where receive timestamps include buffering and scheduling.
Long captures emitted only a final result, so a quiet child looked idle.
Pass the shared rate-limited progress reporter through the capture lifecycle
and report the observed phase, elapsed time, and collected-unit counts.
CLI writes those lines to stderr; MCP forwards them only when the client
supplied a progress token. Final Evidence on stdout keeps its shape.
* refactor(setup): resolve skill destinations per client
* fix(setup): honor active client configuration and skill roots
* fix(setup): validate effective client scopes and Gemini trust
* fix(setup): treat empty OpenCode overrides as unset
An empty OPENCODE_CONFIG_DIR now stays on the XDG directory, and doctor
and setup inspect global OpenCode files when a custom directory is absent.
Uninstall reports one status per client so a missing earlier layer does
not hide a removed registration.
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* feat(mcp): add compact input schema profile for size-capped providers
Moonshot's function-calling API rejects a request while any single tool
parameters schema exceeds its literal serialized size cap, so clients
such as kimi-cli fail every request while the default catalog is
attached (#1484).
Add an opt-in REA_MCP_INPUT_SCHEMA_PROFILE=compact server presentation.
Each advertised input schema is rendered within a 13,312-byte budget,
measured to sit below the observed provider cap: annotation prose
(nested descriptions, examples, defaults, titles) is dropped, repeated
annotation-free subschemas are shared through schema-local $defs/$ref
references the provider validates without expansion, and the three
structurally oversized schemas are advertised in a documented reduced
form. The canonical catalog, tool set, output schemas, and server-side
canonical validation are unchanged; the default full profile is
byte-identical to today's advertisement.
Boundary tests pin every compact schema to the budget, keep them valid
JSON Schema that still accepts every canonical example, hold reduced
presentations at three or fewer, and verify canonical rejection still
guards a permissive advertisement. Verified against the real Moonshot
API through kimi-cli: prompts succeed with the compact catalog attached
where the default catalog fails every request with 400.
* fix(mcp): preserve compact schemas through Kimi conversion
---------
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
Keep caller-selected replacement text literal with a callback, preserving
empty-search positions instead of changing their split/join behavior.
Commit the replacement interpretation for captures using custom patterns so
legacy records cannot report this producer correction as a target change.
BREAKING CHANGE: Captures with custom normalization patterns use
literal-replacements-v1 and cannot be compared with legacy unversioned
pattern captures. Capture both sides with the same replacement semantics;
legacy captures remain readable and captures without patterns are unaffected.
inspect_analysis_view is the recovery path when an analyze_function
dossier exceeds the MCP response budget, but its native facets covered
only procedure, pseudocode, assembly, callers/callees, references, and
value flow. Basic blocks, comments, unresolved calls, referenced strings
and names, and the native API record could not be read from retained
Evidence at all; basic blocks grow with the function just like assembly.
These are now facets: collections page by rows, and native_api is a
singleton. A dossier without an unresolved_calls record reports "not
recorded" rather than the value-flow failure reason.
Refs #1247 and #1065.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat(setup): add native Pi client support
* fix(setup): isolate invalid Pi agent directory overrides
Keep malformed Pi path evidence on its client entry so unrelated selected clients can complete setup and doctor. Preserve explicit Pi rejection and block filesystem operations rather than falling back to another directory.
* fix(setup): parse Pi configuration as strict JSON
Pi's installed MCP loader reads mcp.json with a bare JSON.parse and no
BOM tolerance, so comments, trailing commas, a BOM, or an empty existing
file yield loader errors and no servers. Parsing the Pi dialect with
objectSchema.parse(JSON.parse(text)) before the shared empty/JSONC
shortcut rejects those files at every mutation boundary instead of
reporting configured registrations Pi cannot load. A missing file still
initializes a fresh strict-JSON document, other dialects keep their
JSONC/BOM/empty tolerance, and malformed files are never rewritten.
---------
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
* feat: add Hermes as a supported MCP client
Hermes Agent reads stdio MCP servers from `mcp_servers.<name>` in
`config.yaml`. REA had no Hermes client, so setup could not register it and
Hermes users had to wire the server up by hand.
- SupportedClients: add the `hermes` format and client definition, resolving
the config path from HERMES_HOME, else the platform default that Hermes's own
resolver uses (LOCALAPPDATA/hermes on Windows, ~/.hermes elsewhere), including
HERMES_DATA_DIR_SUFFIX.
- ClientConfigurationDocument: parse and serialize Hermes YAML, upserting the
rea entry into the parsed document so user comments and unrelated settings are
preserved; emit `enabled: true` since Hermes connects entries unless disabled.
- ClientRegistrationStatus: forward the Hermes location variables so status
checks resolve the same path as setup.
- Tests: cover path resolution on both platforms and the register/read/uninstall
round trip, and clear the Hermes location variables between tests.
- delilah 🌸
* docs: document the Hermes client and its config path
- delilah 🌸
* refactor(setup): resolve skill destinations per client
* fix(setup): install Hermes skills in the active profile
* fix(setup): identify each client skill action uniquely
---------
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
ZIP member names are case-sensitive. Inventory was folding them with a
filesystem case rule, so shrunk APKs never became evidence for the Android
application graph. Logical registration now keeps both spellings and records
an English Unicode case-folding limitation. Extraction fails only when the
destination directory already holds the other spelling.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Rendered frames padded every visible row with trailing spaces to the
terminal width. Blank rows cost a full row each and every frame repeats
them, so the padding made up 14-39% of capture Evidence (2 KB of sparse
output produced 228 KB). The padding carried no information: columns is
recorded and serialized_state keeps the exact terminal state.
Lines are now trimmed after normalization, so line.padEnd(columns)
restores the previous value. The comparison contract commits
rendered_line_format so older padded captures do not compare as the
same contract.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Ysopwnable
morluto
Jay-Alexander Elliot
Quentin Limo
Pionxzh
Thang Luu
曾亮
Kaoru0822
Joseph Demarest
Fazmin Nizam
Cursor Agent
Peter
Haythem Sellami
Kaoru0822
Richard A Steenbergen
zayd / cold
易良