Commit Graph
237 Commits
Author SHA1 Message Date
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
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
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 006b295f1d refactor(javascript): parse runtime evidence into one verified owner 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 449d57075e refactor(javascript)!: remove obsolete scope truncation statistic
BREAKING CHANGE: remove the never-incremented truncated_scopes statistic from JavaScript application analysis results and schemas.
2026-10-10 02:49:46 +08:00
morluto 7915ee5178 feat(javascript): record Electron integrity mismatches 2026-10-10 02:49:46 +08:00
morluto f7cf4c890d fix(cli): classify oversized JSON inputs 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
morluto 765e809e36 refactor: use canonical implementations and types directly
Remove forwarding wrappers and shadow aliases, migrate callers and verification scripts to their owners, and share one exhaustive semantic resource-bound projection.
2026-10-09 23:35:19 +08:00
morluto ad59531a96 refactor: remove forwarding exports and redundant aliases 2026-10-09 22:46:09 +08:00
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 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
N0zoM1z0 bfaa5a6c2c fix(native): distinguish batch selectors from resolved entries 2026-10-09 19:09:30 +08:00
45e3edc17f feat(javascript): report observed export property presence (#1160)
* feat(javascript): report observed export property presence

Extend compare_javascript_export_shapes so each retained return variant
lists observed property names and each change reports presence independently
of value resolution. Complete parent coverage classifies one-sided names as
added or removed even when static values stay unknown.

Fixes #725

* test(javascript): match unknown export-shape values by availability

Nested availability objects include a reason when values stay unresolved.
Assert availability through objectContaining so presence-only added and
removed rows still verify unknown values.

* fix(javascript): preserve uncertain export property presence and locations

* fix(javascript): normalize presence and preserve local property coverage

* fix(javascript): require present discriminants for return pairing

* fix(javascript): normalize retained shapes before comparison

* refactor(javascript): share return projection with executable examples

* fix(javascript): localize uncertainty for missing mutated slots

* fix(javascript): bind advertised export examples to exact artifacts

* fix(javascript): keep uncertain property flow as candidates

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-09 18:30:31 +08:00
N0zoM1z0 0e779533a9 fix(snapshot): report query workflow and Evidence counts separately 2026-10-09 18:13:50 +08:00
YsopwnableandGitHub aa5750c263 fix(mcp): emit portable Unicode NUL patterns (#1230)
Preserve NUL rejection while avoiding the short escape rejected by strict
schema consumers. Guard the entire advertised input/output catalog and all
three JavaScript regexp modes.

Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)
2026-10-09 17:18:17 +08:00
felipeatpandGitHub f0da05f67f fix: emit v-mode-compatible patterns for tool schemas (#1220)
* fix: emit v-mode-compatible patterns for tool schemas

Character classes in emitted patterns carried unescaped '-', '/' and '['. Annex-B and u-mode accept them, so REA's own Zod validation (u) and every u-based validator never saw a defect, but v-mode rejects ClassSetSyntaxCharacters and Ruby rejects [^s[]]. With 6.1.0 tools/list, 117 pattern fields across 11 tools were rejected under v.

The characters are escaped as \x2d, \x2f, \x5b and \x5d rather than \-/\//\[, because oxlint --fix removes an escaped '-' inside a character class as a useless escape, so an escape-only change does not survive the pre-commit hook. \x2d-style escapes are valid under Annex B, u and v, are matched identically, and are not useless-escape candidates.

22 pattern literals in 18 files are touched; no other token changes.

* fix: replace the Zod offset pattern and guard the advertised catalog

The offset datetime site projected Zod's offset class as [ +- ], which no escape in this repository's sources can reach, so evaluate_reconstruction_coverage stayed unreachable for exactly the clients this change targets. It now uses offsetDateTimeSchema in src/domain/offsetDateTime.ts: the same accepted set with the offset class escaped as [ +\x2d ].

Adds tests/boundary/mcp/advertisedPatternsVMode.test.ts, which performs the real tools/list projection, traverses every advertised input and output schema, compiles each pattern under v, and asserts the inventory it walked so a silent traversal collapse fails instead of passing vacuously.
2026-10-09 16:20:57 +08:00
6935dc7fe1 fix(ghidra): classify modern Swift manglings in swift type analysis (#1208)
* fix(ghidra): classify modern Swift manglings in swift type analysis

Categorize modern Swift 4.2+ manglings ($s, _$s) instead of dropping them
in analyze_swift_types. The classifier only accepted the legacy _Tt marker,
so procedure names reported by current providers produced an empty inventory.
Legacy _Tt families and behavior are unchanged. Fixes #1187.

* fix(swift): retain provider aliases and category unknowns

---------

Co-authored-by: Saim Shafique <sx4imm@gmail.com>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-09 16:10:55 +08:00
db675f1d52 feat(mcp): select views of retained analysis results (#1180)
Add explicit summary, facet, item and paged views of retained analysis Evidence without repeating analysis. Preserve captured observations, graph validation, artifact identity, coverage and complete default results.

Fixes #1050

Verified with focused source, CLI, pinned-SDK schema and MCP tests, serial static checks, and one complete native Windows Notion ASAR workflow. Real Hopper/Ghidra verification was not performed for this provider-independent projection change.

Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
2026-10-09 12:45:48 +08:00
YsopwnableandGitHub e1afbc1914 perf(mcp): reuse input schemas without losing caller guidance (#1162) 2026-10-09 11:38:07 +08:00
YsopwnableandGitHub 441813c070 perf(mcp): share repeated output schema definitions 2026-10-09 08:46:59 +08:00
morluto 44fd18305f fix(capture): retain Electron observations and HAR resource failures 2026-10-09 06:49:02 +08:00
morluto 70e8a8f860 fix(contracts): preserve local inputs and comparison uncertainty 2026-10-09 06:49:02 +08:00
morluto 82626c4499 fix(hopper): bind file mappings to verified source bytes
Read source digests, FAT tables and embedded headers from one opened source stream before translating native offsets. Preserve native mapping observations through changed, missing, nonregular and access-denied source failures; keep filesystem work outside the Hopper API thread.

Exercise source drift, relocated slices, missing files, permissions and recovery through real Hopper CLI/MCP verification for thin, FAT32 and FAT64 inputs.
2026-10-09 06:13:41 +08:00
morluto f201b04fbb fix(hopper)!: isolate regex matching from the native API thread
BREAKING CHANGE: Hopper regex mode uses ECMAScript Unicode syntax instead of Python re. Matching runs in a cancellable worker with a five-second deadline; literal mode keeps Unicode casefold matching.
2026-10-09 05:12:36 +08:00
morluto 246170238e fix(hopper): preserve partial native call and string evidence 2026-10-09 05:12:36 +08:00
morluto 7d7b3f961a fix(hopper): preserve typed string values and verify real searches 2026-10-09 05:12:36 +08:00
morluto 35f1ddd6bc fix(hopper): resolve FAT loaders and original file coordinates 2026-10-09 05:12:36 +08:00
morluto b2d5bc1109 fix(hopper): validate annotation destinations and symbol extents 2026-10-09 05:12:36 +08:00
morluto e44cb45908 fix(session): serialize snapshot lifecycle with admitted requests 2026-10-09 04:37:43 +08:00
morluto 5945915f91 test: prune redundant cases and promote configuration lifecycle coverage 2026-10-09 02:58:03 +08:00
morluto d830cb79b3 fix(analysis): resolve procedure identities and preserve literal queries 2026-10-09 02:42:39 +08:00
morluto f2e22e13a6 fix(hopper): preserve native navigation and annotation semantics 2026-10-09 02:42:39 +08:00
morluto 2f71375efc fix(hopper)!: bind analysis to the active target and correct boundary contracts
Preserve native document identity, nullable bookmark labels, address diagnostics, segment-end byte prefixes, and verified file mappings. Validate batch rename addresses before mutation.

BREAKING CHANGE: remove set_current_document. Use open_binary to switch targets; document arguments are scoped to the active target.
2026-10-09 02:05:31 +08:00
5a67c7fc54 fix(hopper): diagnose MCP provider failures with stage, state, and request context (#1044)
* fix(hopper): diagnose MCP provider failures with stage, state, and request context

* fix(hopper): retain health at the actual provider lifecycle boundary

* test(hopper): distinguish socket loss from later observed process exit

* test(hopper): cover observed exit separately from socket-first replies

---------

Co-authored-by: N0zoM1z0 <1705004398@qq.com>
2026-10-09 00:33:56 +08:00
40e18b2e37 fix(domain): preserve prototype-named JSON members through Evidence boundaries (#1049)
* fix(domain): preserve prototype-named JSON members through Evidence boundaries

Zod's z.json() record projection drops own __proto__ members as a
prototype-pollution guard, so provider replies carrying them lost evidence
before hashing/serialization and CLI/MCP output. The shared schema now
validates with z.json() as before, then rebuilds the value keeping
prototype-named own members as ordinary data properties (__proto__ via
Object.defineProperty, so the prototype is never mutated).

parseHarJson no longer rejects __proto__ members; the explicit unsupported
case from #992 is replaced with a preservation regression, and the
inspect_web_network_capture contract text is updated to match.

Fixes #1036

* fix(domain): bound JSON depth and oversized payloads at parsing boundaries

jsonValueSchema re-walked hostile input through z.json()'s recursive core, so a deeply nested payload from an MCP tool argument, inline evidence, provider result, or keyed archive threw RangeError: Maximum call stack size exceeded instead of a validation issue. The schema now runs an iterative depth guard first and keeps z.json() for full JSON semantics behind it, which also turns cyclic values into validation errors. The 1000-edge limit stays far below the range where the recursive core overflows its stack (measured between 2000 and 3000 on Node 24) while leaving room for legitimately deep target-derived trees such as compiled NIB view hierarchies, and the guard narrows with a typed record check instead of any or unchecked casts. The non-recursive JSON Schema advertisement stays intact on both the public and standard projection paths. Two payload sizes get explicit budgets tied to their producer constraints: web text artifacts reject beyond the 16 MiB source budget the web tooling already advertises, and native UI screenshot base64 beyond the 64 MiB helper output budget. Regenerated product catalog, skill catalog digest, and completion-ledger manifest follow the schema-boundary change.

* fix(validation): preserve depth diagnostics across process inputs

---------

Co-authored-by: DeryFerd <deryferdikao125@gmail.com>
Co-authored-by: N0zoM1z0 <1705004398@qq.com>
2026-10-08 21:32:48 +08:00
6a7650e93c fix(mcp): flatten root union input schemas (#1062)
* fix(mcp): flatten root union input schemas

* fix(mcp): preserve minimum input requirements in object schemas

---------

Co-authored-by: N0zoM1z0 <1705004398@qq.com>
2026-10-08 20:54:51 +08:00
5ccb9241be perf(mcp): advertise each tool JSON Schema once per target (#1059)
The MCP SDK reconverts every registered Zod schema on each tools/list.
With 139 tools that is ~45 ms of Zod JSON Schema work per listing, for a
catalog that cannot change after registration. Memoize the advertised
input and output projections per target on the registration clones.

Listings are byte-identical; repeated tools/list drops from ~62 ms to
~18 ms on the stdio server.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 17:31:08 +08:00
YsopwnableandGitHub 163ee09a74 feat(native): inspect recorded crashes through pwntools and pwndbg (#1054)
* feat(native): inspect recorded crashes through pwntools and pwndbg

* fix(native): bind core note semantics to raw owner bytes

* fix(native): validate recorded core ABI and evidence scalars

* fix(native): require complete recorded note interpretations

* fix(native): bind physical core notes to original headers
2026-10-08 16:50:31 +08:00
YsopwnableandGitHub 7af7bc88ce feat(evm): inspect offline bytecode interfaces through EVMole (#1051)
* feat(evm): inspect offline bytecode interfaces through evmole

* fix(evm): distinguish unsupported bytecode targets

* style(evm): format verifier string-prefix checks
2026-10-08 15:32:05 +08:00
Kaoru0822andClaude Opus 5.5 3362dfa31e chore: merge main into feat/dylib-resolution
main now carries #1037 (skill version 30, reworded native binary row):
- README_ja/ar/ko/zh: take main's tables and count
  trace_dylib_resolution in the artifact graph row (5 -> 6).
- Skill: move to version 31.
- Regenerate the product catalog, conformance manifest, skill digest and
  package metadata (137 tools).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 06:31:43 +00:00
Kaoru0822andClaude Opus 5.5 6fa6300987 chore: merge main into feat/dylib-resolution
main now carries #964 (skill version 29, macOS native row 7 -> 8):
- README_ja/ar/ko/zh: take main's tables and count
  trace_dylib_resolution in the artifact graph row (5 -> 6).
- Skill: move to version 30.
- Regenerate the product catalog, conformance manifest, skill digest and
  package metadata (136 tools).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 06:23:44 +00:00
YsopwnableandGitHub 4fc6565b0f feat(native): inspect offline ELF layout through pwntools (#1037)
* feat(native): inspect offline ELF layout through pwntools

* fix(build): prepare offline ELF verification on clean runners

* fix(native): preserve snapshot acquisition cancellation

* fix(native): handle sectionless ELF and retain decoder diagnostics

* test(native): verify malformed symbol table entry sizes

* fix(native): respect inherited limits and unused segment fields

* fix(native): preserve packed relocations and decoder launch constraints

* fix(native): validate symbol spans and preserve resource failures

* fix(native): preserve diagnostic completeness and memory failures

* fix(native): guard bridge imports against allocation failures

* fix(native): validate relocation symbol and section references

* fix(native): retain diagnostics through compounded cleanup failures

* fix(native): preserve unresolved relocation section references

* fix(native): bound linkage evidence and preserve CPU signal diagnostics

* fix(native): preserve file-size resource failure evidence

* fix(native): retain opaque linkage names and late cancellation output

* test(native): make CPU-limit fixture robust across runners

* fix(native): verify resource failure branches before interpreting exits

* fix(native): validate declared ELF string references

* fix(native): validate section-name table before decoding

* fix(native): enforce canonical ELF name-table escapes
2026-10-08 14:22:08 +08:00
Kaoru0822andClaude Opus 5.5 2a7dcb77c1 chore: merge main into feat/native-call-observation
Resolve conflicts against main:
- package.json: ship both the LLDB tracer bridge and main's process run
  token reader sources.
- README.md: take main's simplified English README, which no longer has
  the tool-family table.
- README_ja.md: take main's reworded table and count
  observe_native_calls in the macOS native row (7 -> 8).
- Skill: the references gain the observe_native_calls paragraph, so the
  version moves to 29 (main already uses 28).
- Regenerate the product catalog, conformance manifest, skill digest and
  package metadata (135 tools). The MCP tool catalog is now built rather
  than committed (#997), so it is removed here.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 04:58:36 +00:00
Kaoru0822andClaude Opus 5.5 5acdb9dc6f chore: merge main into feat/dylib-resolution
Resolve conflicts against main:
- README.md: take main's simplified English README, which no longer has
  the tool-family table.
- README_ja.md: take main's reworded table and count
  trace_dylib_resolution in the artifact graph row (5 -> 6).
- Skill: the references gain the trace_dylib_resolution paragraph, so
  the version moves to 29 (main already uses 28).
- Regenerate the product catalog, conformance manifest, skill digest and
  package metadata (135 tools). The MCP tool catalog is now built rather
  than committed (#997), so it is removed here.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 04:45:50 +00:00
6b55de017b fix(mcp): bound capture comparison input schema depth (#1005)
* fix(mcp): advertise JSON values without recursive schemas

`z.json()` projects a self-referential `$defs/__schema0` entry. Twenty
tool input schemas and 123 output schemas carried it, and clients or
model APIs that reject recursive JSON Schemas refuse the whole tool
list. Every JSON value satisfies `{}`, so the shared JSON value schema
now advertises that. Runtime parsing still admits only JSON values.

Refs #919

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

* fix(mcp): keep advertised input schemas within model function-calling limits

Some model providers reject the whole tool list when any input schema
contains a recursive $ref or nests deeper than 10 levels (fixes #919).
Sanitize the advertised wire projection: break cyclic $refs, bound nesting
depth, and drop unreachable $defs. Canonical Zod contracts are untouched.

---------

Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: sx4im <sx4im@users.noreply.github.com>
Co-authored-by: N0zoM1z0 <1705004398@qq.com>
2026-10-08 12:26:00 +08:00