Commit Graph
219 Commits
Author SHA1 Message Date
morluto 514df0918c fix(analysis-view): preserve inline Evidence error paths
Project authenticated inline Evidence failures at source.evidence while retaining their reasons and messages. Supply the matching request root to input issue projection so nested values remain identifiable.

Validation: both service entrypoints and SDK MCP integrity regressions, advertised-schema consumer suite, check:fast and architecture guards. No real-provider verification.
2026-10-11 03:36:35 +08:00
morluto a97bd5ed29 fix(ci): share provider workflows to restore static gates 2026-10-10 23:15:02 +08:00
96fd98cce0 feat(apktool): decode Android resource tables through a caller-supplied launcher (#1556)
* 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>
2026-10-10 23:04:12 +08:00
749e58772a feat(jeb): add JEB engine provider over its MCP interface (#1536)
* 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>
2026-10-10 23:03:27 +08:00
4d8d76b253 fix(electron): support packaged app.asar pages and rewritten unpacked companions (#1400)
* 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>
2026-10-10 23:01:54 +08:00
fef6f73064 feat(adb): complete ADB device support for Android reverse engineering (#1552)
* 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>
2026-10-10 23:01:24 +08:00
5156ba44c5 feat(native): return a retained summary view of binary layouts on request (#1570)
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>
2026-10-10 07:57:42 -07:00
c19e15a2b3 feat(javascript): return a retained summary view on request (#1568)
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>
2026-10-10 07:37:37 -07:00
a53689c55d fix(mcp): stop advertising complete Evidence in input examples (#1560)
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>
2026-10-10 07:10:38 -07:00
24d9337649 fix(native): preserve compact reference provenance (#1438)
Co-authored-by: N0zoM1z0 <161784452+N0zoM1z0@users.noreply.github.com>
2026-10-10 21:39:28 +08:00
b6ad1f2c3d feat(mcp): compact input schema profile for size-capped providers (kimi-cli/Moonshot) (#1514)
* 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>
2026-10-10 16:58:43 +08:00
9defed9725 perf(mcp): stop advertising placeholder input descriptions (#1479)
Input schema presentation gave every undescribed property a generic
"Value for <name>." sentence. That only restates the property name, yet
it covered 1,958 properties: 70 KB of the 522 KB of advertised input
schemas that clients load into model context. Authored descriptions,
referenced descriptions, and the name-pattern sentences that add meaning
(maximums, digests, paths, Evidence IDs) remain; other properties now
advertise no description.

The schema validity test now rejects placeholder descriptions instead of
requiring a description on every property.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 00:32:29 -07:00
YsopwnableandGitHub ea92328775 fix(mcp): validate doctor probe against its discovered output contract (#1461)
Validate the target-free probe against the named definition discovered from the complete production catalog. Preserve initialized server and inventory observations when the SDK rejects the probe, and retain the schema failure reason, absolute deadline and owned-child cleanup.

The negative stdio replay regression fails on original main and passes the fix; actual production-boundary fault injection confirms rejection. Nine doctor/help tests, serial full static checks and real small-target CLI/MCP parity pass. Successful doctor reports remain byte-identical. No performance or model-token reduction is claimed.

Closes #1454. Refs #1065, #723, #1433.
2026-10-10 14:33:57 +08:00
YsopwnableandGitHub dc5af6d68f perf(mcp): reuse output validators across catalog refreshes (#1433)
Advertise content- and dialect-bound identities for self-contained output schemas so the SDK can reuse unchanged Ajv validators after complete tools/list refreshes. Preserve explicit IDs and relative reference bases.

Verify changed schemas, availability transitions, reconnects, numeric and selector constraints, explicit IDs, relative references, and advertised dialects through the pinned SDK boundaries.

Refs #1065, #723
2026-10-10 12:49:09 +08:00
a9ee2360fd feat(native): inspect oversized retained function dossiers via bounded views
Add caller-selected native dossier facets with preserved Evidence identity, provenance, unknowns and transport recovery.

Refs #1247 and #1065.

Co-authored-by: jhuang-tw <77732008+jhuang-tw@users.noreply.github.com>
Co-authored-by: N0zoM1z0 <161784452+N0zoM1z0@users.noreply.github.com>
2026-10-10 12:18:50 +08:00
YsopwnableandGitHub 8550913cda fix(javascript)!: stop copying literals into semantic metadata (#1407)
Commit literal values with canonical JSON SHA-256 in semantic role keys
and use a type label for strings. Preserve complete values, provenance and
literal queries while avoiding two payload copies in each string node.

Verify real compiled CLI/default stdio MCP, typed union seeds, empty
strings and trace continuation with a large source-owned fixture.

Refs #723

BREAKING CHANGE: Newly produced semantic literal node IDs use
value-sha256 role keys, and string labels read "string literal". Read exact
values from properties.value and obtain node IDs from the selected parent
graph. Previously stored Evidence and its original IDs remain valid.
2026-10-09 20:00:53 -07:00
39dabd0608 fix(mcp): advertise object roots for union input schemas (#1373)
* fix(mcp): advertise object roots for union input schemas

Anthropic tool input schemas reject anyOf, oneOf, and allOf at the root.
Since 63bf9140 removed root flattening, compare_web_captures,
inspect_web_page, inspect_electron_page, and
project_managed_application_graph advertised root unions: Claude Desktop
disabled compare_web_captures and Claude Code exposed the tools without
parameters.

Present a root union of plain-reference object branches as one strict
object with the union of properties, shared required fields, a
minProperties bound, and a description of the accepted input groups. The
canonical Zod union still validates every call, so mixed input groups are
rejected before the handler runs. Branches whose reference siblings cannot
be merged keep their root alternatives.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* test(browser): keep comparison input boundary within lint limits

Express advertised and runtime expectations as one case table so the
boundary test stays under the 150-line function limit.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(mcp): preserve input group dependencies in object schemas

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 07:03:12 +08:00
355a292198 fix(javascript): preserve uncertainty after references escape to calls (#1292)
* fix(javascript): preserve uncertainty after references escape to calls

* fix(javascript): track iterator root escapes and preserve static captures

* fix(javascript): scope comparison unknowns to their evidence

* fix(javascript): track parameter origins at function body entry

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 06:53:42 +08:00
You WishandGitHub 1c0cc8a675 fix(snapshot): preserve complete investigation revision histories (#1354)
Select residual unknown histories as complete units and retain referenced registry mutation Evidence regardless of the active target at edit time. Prune incompatible dependency histories atomically instead of retaining stale dispositions.

Verify public MCP save/read/reopen for verified, withdrawn, and out-of-scope resolutions, and document target scope rules.
2026-10-10 06:39:29 +08:00
morluto 4bcea1aa76 fix(javascript): retain array identity after length mutations
Keep unknown element coverage on arrays whose length may have changed, preserving intrinsic length presence and subsequent slot mutations through semantic graph and export-return consumers.
2026-10-10 06:20:28 +08:00
morluto 392f1f3107 refactor: consolidate boundary semantics and prune redundant tests
Share parser modes and collision-free composite keys, enforce architecture guards, and consolidate redundant unit assertions into filesystem, CLI, MCP, and producer-backed workflows. Preserve concurrent upstream boundary fixes and exclude legacy Objective-C class-name bookkeeping labels.

Validation: source/composition suites (3358 passing), focused canonical digest and MCP checks, typecheck/lint, Knip, formatting, architecture guards, and real Foundation archive and Apple legacy simulator CLI/MCP verification. No real Hopper, Ghidra, or IDA verification claim.
2026-10-10 05:56:01 +08:00
morluto 614fb7681e fix(evidence): order canonical projections independently of locale 2026-10-10 05:13:53 +08:00
morluto 70bad53847 fix(native): distinguish symbol definitions from metadata 2026-10-10 05:13:53 +08:00
morluto 7ad353fa8b fix(native): retain LLDB cleanup ownership through client close 2026-10-10 04:35:03 +08:00
morluto 0bfb6e00ab test(filesystem): bound FIFO regressions at consumers 2026-10-10 04:23:03 +08:00
morluto 7829b1aeef fix(filesystem): reject unstable artifact targets 2026-10-10 04:14:54 +08:00
morluto f62b44971d fix(mcp): advertise primitive semantic literal seeds 2026-10-10 03:52:35 +08:00
morluto 218c13160e fix: report malformed application evidence as input errors 2026-10-10 03:52:35 +08:00
morluto a4ba8aecd5 fix(contracts)!: require observed provider output metadata
Reject omitted segment bounds, procedure classification and body facts, unresolved-call observations, dossier facets, and Ghidra parameter flow metadata. Providers emit explicit nulls for unsupported facets. Verify those unknowns in the real Hopper workflow.

BREAKING CHANGE: Provider analysis outputs must explicitly supply metadata previously repaired with defaults; unsupported nullable facets must be reported as null.
2026-10-10 03:52:13 +08:00
morluto e3bbb9ac45 refactor(javascript)!: share semantic evidence at fact construction
Intern shared provenance in a graph-scoped context registry while retaining exact locations on every fact. Semantic traces carry their referenced context subset, and portable graph validation rejects stale or dangling commitments.

BREAKING CHANGE: Semantic graph facts now store evidence context IDs and locations. Graph and semantic trace results require an inline evidence_contexts table.
2026-10-10 03:52:13 +08:00
morluto 7915ee5178 feat(javascript): record Electron integrity mismatches 2026-10-10 02:49:46 +08:00
3f59a84bd1 fix(contracts): advertise NUL with a portable hex escape
Use the equivalent hex NUL spelling in named public contracts while preserving current path and reserved-name validation. Verify converted JSON Schema and real stdio catalog consumers.

Closes #1329

Co-authored-by: Yi-111-a <97448247+Yi-111-a@users.noreply.github.com>
2026-10-10 01:54:42 +08:00
You WishandGitHub 5f16124a31 fix(files): reject nonregular capture and JSON inputs
Verify selected files through a nonblocking opened handle before reading. Preserve regular-file symlinks and return actionable CLI/MCP diagnostics without publishing output.

Co-authored-by: YouWish <29498139+Y0UW1SH@users.noreply.github.com>
2026-10-10 01:49:54 +08:00
morluto d83cbd2abf test: share snapshot replay and managed graph fixtures 2026-10-10 00:35:17 +08:00
morluto e11f4d371a fix(mcp): admit composed analysis through result bookkeeping 2026-10-10 00:35:17 +08:00
morluto e64678e8f9 fix(mcp): retry failed shutdown resources and retain failure reasons 2026-10-10 00:35:17 +08:00
morluto 24673aaae4 test(mcp): remove arbitrary schema inventory thresholds 2026-10-09 23:35:19 +08:00
morluto 3283a45d09 refactor(captures)!: require canonical producer metadata
Require process retention accounting, browser network transaction identity, and all web comparison dimensions. Remove obsolete omission repairs and derive completeness from the owning producer facts.

BREAKING CHANGE: Historical captures without current producer accounting or transaction identity, and web diffs missing accessibility or storage dimensions, are rejected.
2026-10-09 23:35:19 +08:00
Kaoru0822andGitHub 1f099a6fc0 Merge pull request #1299 from morluto/fix/schema-patterns-without-lookaround
fix(mcp): advertise input patterns without look-around
2026-10-09 07:58:51 -07:00
Kaoru0822andClaude Opus 5.5 a8701eaf48 fix(mcp): advertise input patterns without look-around
trace_dylib_resolution roots and capture_process_scenario environment
names still advertised negative look-ahead patterns. RE2 and Rust schema
validators reject look-around, so a client using one refuses the whole
tools request, as #1282 reported for the NUL escape. Spell both
constraints as equivalent look-around-free patterns and assert that no
advertised pattern uses look-around or backreferences.

Closes #1282

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 14:49:22 +00:00
morluto ad59531a96 refactor: remove forwarding exports and redundant aliases 2026-10-09 22:46:09 +08:00
morluto 5f749c2096 fix(mcp): only recommend exporting retained evidence 2026-10-09 22:46:09 +08:00
Kaoru0822andClaude Opus 5.5 7b51121f7c fix(mcp): measure tool errors against their text-only delivery
Since #1277 an error result reaches the client without structuredContent,
but toErrorToolResult and the transport recovery still budgeted it as
structured JSON plus escaped text. An error whose text fit between about
half and all of the response budget was replaced by resource_constraint,
and without Evidence retention the original diagnostic was lost.

Count only the escaped text for errors. The boundary, process-global and
real Ghidra large-result probes now use diagnostics that exceed the
text-only budget.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 14:03:12 +00:00
YsopwnableandGitHub 7e96f25f8b fix(mcp): deliver typed errors without invalid structured output (#1277)
* fix(mcp): deliver tool errors within advertised schema contracts

Retain complete typed JSON error content while omitting non-conforming
structured errors at the public transport boundary. Recover oversized
diagnostics into Evidence before removing their private structured carrier.
Update schema-validated client readers and cover actual stdio delivery.

Closes #1261

Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* test(mcp): read typed errors in canonical Evidence regressions

* test(mcp): validate public error diagnostics in acceptance workflows
2026-10-09 13:54:32 +00:00
morluto d6d1cd2485 test: remove duplicate workflow examples and self assertions 2026-10-09 21:01:53 +08:00
morluto b71a591a60 test: consolidate redundant assertions into boundary workflows
Remove getter, enum, cloned-projection, cache-identity, and obsolete profile assertions along with the shadow JSON Schema engine and dead test-only APIs. Retain producer, filesystem, SDK, lifecycle, integrity, and malformed-format coverage.

Document the priority of real end-to-end workflows, boundary integration, and producer goldens.
2026-10-09 20:26:46 +08:00
morluto 475a0f84da fix(javascript)!: preserve property paths and uncertain slot presence
Use one explicit object/array slot model and JSON-pointer property identity across mutation analysis, return projection, and semantic graphs. Require observed presence for discriminants and resolve writes only through retained object or array receivers.

BREAKING CHANGE: projected return fields require explicit presence and semantic object operations carry full property paths.
2026-10-09 20:18:52 +08:00
morluto 63bf91405c refactor!: enforce canonical evidence and provider boundaries
Deliver complete Evidence directly through MCP with required nullable analysis profiles and immutable per-server delivery settings. Bind selected environments at construction and require typed cleanup outcomes with retained retry ownership.

Remove test-only routing, duplicate session and snapshot metadata, producer-field repairs, and ambiguous provider arguments. Separate artifact byte identity from occurrence classification and retain typed source-map and partial native facts across CLI, MCP, and verifier consumers.

BREAKING CHANGE: obsolete Evidence envelopes, session aliases, incomplete snapshots, and missing normalized producer facts are no longer accepted.
2026-10-09 20:18:52 +08:00
morluto abc4f47683 build: separate runtime artifacts and supervise command ownership 2026-10-09 20:11:17 +08:00
N0zoM1z0 933fcb33c1 test(native): assert batch identity in production registration 2026-10-09 19:27:27 +08:00