Commit Graph
18 Commits
Author SHA1 Message Date
a1b5d51a8d feat(go): inspect embedded binary build metadata (#1363)
* feat(go): inspect embedded binary build metadata

* fix(go): preserve byte metadata and validate container mappings

* fix(go): support moduleless legacy build metadata

Recognize optional module string headers in declared zero-filled memory while rejecting ambiguous and unmapped pointers. Preserve the original module-pointer field as the zero-byte source anchor.

Classify initial symlink-loop and overlong-path failures as invalid input, with CLI and MCP regressions.

* fix(go): reject undersized PE optional headers

* fix(native): stabilize ELF memory checks and clean up exec wrappers

Use existing parent/group/run-token ownership for caller-selected Python launchers, which can exec through a shell or prlimit. Add cancellation regressions for the valid wrapper and wrong-parent/token cases.

Replace the timing-dependent 30,000-section memory workload with a valid 32 MiB padded ELF under a 64 MiB address-space limit. Check the same image successfully through CLI and MCP before requiring a typed memory failure, preserving the production timeout and all error assertions.

Validation: npm run check and check:fast passed; 61 focused tests passed including Go CLI/MCP and session snapshots. Real decoder probes with pinned packages passed on Python 3.12.3 and 3.12.14. The full local ELF verifier is blocked by this container's procps/process-ownership boundary; the exact pushed head requires GitHub's real-binary-layout lane.

* test: repair Electron fixtures and stabilize catalog startup checks

Declare Electron imports in option, preload override, and path-resolution fixtures after upstream began requiring proven API provenance. Retain all option and preload assertions and adjust exact source ranges for the added import line.

Use the existing bounded acceptance timeout for the cold catalog lifecycle test instead of a separate 15-second ceiling. This retains the coverage allowance and all catalog, error, and cleanup assertions without retries.

Validation: npm run check, final check:fast, formatting and diff checks passed. Source path regression and Go boundary/MCP/service checks passed. All 20 Go CLI cases and both supported-host runtime cases passed on rerun; two macOS-only cases skipped on Linux. A prior contended local run timed out once in a Go CLI diagnostic; that case passed on rerun. Electron process-boundary verification is blocked locally by procps namespace inspection and requires fresh CI.

* test(mcp): isolate nested schema references between tool contracts

Clear Ajv's non-meta schema registry after each root, including compilation failures. Disabling root registration alone leaves nested IDs available to later tools and can let a dangling reference pass the catalog gate.

Add regressions for leakage after successful and failed compilation while retaining shared meta-schema validators. The regression failed before the fix; all 11 schema cases and full npm run check pass. Reviewed independently.

* test(ci): align Go effects and source-map verification contracts

Audit the Go inspector wording as static metadata inspection. Assert retained source declaration indexes in BOM reconstruction and the compiler-derived nested-map oracle. Keep a 45,000-map admission control below the 32 MiB output budget and the 50,000-map overflow case above it with the expanded representation.

Validation: reproduced all four failing assertions, then passed 120 focused tests and the final admission suite. npm run check and real Chrome 154 / esbuild 0.25.10 source-map verification passed, including all four nested-map scenarios and verified process lineage.

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-12 11:34:02 +08:00
Lluís AriñoandGitHub 0b7fc40eee fix(contracts): mark foreign execution and device mutation destructive (#1904)
MCP annotations derived destructiveHint only from mayDiscardData, so tools
that run the analysis target or a caller-selected executable
(capture_process_scenario, observe_native_calls) and tools that change an
attached Android device (install/uninstall/push/start/stop) advertised
destructiveHint: false.

Add explicit executesForeignCode and mutatesDevice effect flags, audit them
across all 170 tool effect records, and derive
destructiveHint = mayDiscardData || executesForeignCode || mutatesDevice.
readOnlyHint semantics are unchanged.

Hopper/Ghidra metadata writers (set_address_name, set_addresses_names,
set_bookmark, set_comment, set_inline_comment, annotate_native_function)
can replace or clear existing analyst names and comments, so they now
declare mayDiscardData as well.

A contract test pins the destructive set and requires every tool whose
description mentions running, launching, executing, starting, installing or
uninstalling to declare one of the new flags or carry a reasoned exception,
so wording and effects cannot silently drift. The binary_session effects
output schema carries the new flags.
2026-10-12 01:09:01 +08:00
a8a9c4d817 fix(mcp): express inspect_analysis_view selector constraints in the contract schema (#1705)
The item view advertised its four selector alternatives independently of the
selected collection, while collection-specific constraints lived only in a
superRefine that does not survive JSON Schema conversion. Clients validating
against tools/list could not discover that modules accept only path/node_id
and sections/symbols accept only index/name.

Replace the refined object with a discriminated union on collection so the
converted draft-2020-12 schema rejects the same combinations the MCP server
rejects. Runtime selection semantics are unchanged.

Fixes #1695

Co-authored-by: Saim Shafique <sx4imm@gmail.com>
2026-10-11 19:55:16 +08:00
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
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
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 abc4f47683 build: separate runtime artifacts and supervise command ownership 2026-10-09 20:11:17 +08:00
YsopwnableandGitHub e1afbc1914 perf(mcp): reuse input schemas without losing caller guidance (#1162) 2026-10-09 11:38:07 +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
7425f70fd0 fix(mcp): advertise JSON values without recursive schemas (#995)
`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>
Co-authored-by: N0zoM1z0 <1705004398@qq.com>
2026-10-08 11:48:57 +08:00
morluto 9c3479ed95 test(mcp): consolidate SDK schema checks and scenario ports 2026-10-08 04:03:24 +08:00
fe64fd65d9 fix(mcp): reject unknown MCP tool inputs (#975)
* fix(mcp): reject unknown official tool inputs

* fix(mcp): reject unknown native tool inputs

* test(mcp): follow native contract module move

* fix(mcp): reject unknown remaining tool inputs

* fix(mcp): satisfy strict unknown and browser input schemas

Remove obsolete approval fields from residual-unknown fixtures, project update inputs explicitly, and stop passing target_id to list-targets parsing.

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-10-08 01:10:53 +08:00
YsopwnableandGitHub 6aa9afb549 refactor(process): separate capture implementation from analyst workflows (#988)
* refactor(process): separate capture implementation from analyst workflows

* fix(ci): generate source catalog before shard tests
2026-10-08 00:46:21 +08:00
morlutoandGitHub 4a6073810a fix(contracts): align CLI/MCP boundary contracts (#946)
* fix(cli): validate native scenario and preserve JSON paths

* fix(process): reject invalid UTF-8 JSON inputs

* fix(cli): retain missing JSON path diagnostics

* test(cli): cover relative brace and bracket JSON paths

* test(cli): reject missing native scenario steps

* fix(mcp): advertise reserved process environment key

* fix(process): reject NUL in process scenario values

* fix(process): advertise NUL input constraints to MCP

* fix(cli): report scenario input schema issues

* fix(contracts): align CLI and MCP input validation

* fix(mcp): document semantic output constraints

* fix(mcp): describe process journal compatibility

* docs: regenerate catalog after schema grouping

* docs: regenerate catalog after main merge

* fix(cli): preserve JSON and native UI input diagnostics

* test(mcp): reuse advertised tool schemas in managed flow
2026-10-08 00:03:36 +08:00
morlutoandGitHub e0d76ae80d fix(mcp): advertise reserved process environment key (#949) 2026-10-07 19:58:51 +08:00
morlutoandGitHub e07b81649e refactor!: simplify runtime tools and remove replay engines (#572)
* fix(hopper): report unavailable procedure body coverage

* refactor!: simplify runtime tools and remove replay engines

Keep direct inspection, capture, and comparison tools. Bind handlers to named contracts and let agents compose experiments with commands and local fixture servers.

BREAKING CHANGE: Remove controlled replay, Node characterization, finite replay-machine, managed runtime planning, and redundant string-tracing tools. Retire process replay, shims, reactive scenarios, custom checkpoints, and active browser replay and origin-scope inputs.
2026-10-05 21:15:04 +08:00
morlutoandGitHub b5e98915c6 fix(tools)!: simplify direct invocation and harden boundary contracts (#555)
Remove REA permission grants, scope ceilings, approval confirmations, and inert settings. Preserve selected local evidence, accept caller-chosen commands and paths, and report actual runtime failures.

Harden provider results, schema serialization, snapshot evidence binding, archive paths, source maps, native screenshots, managed EH parsing, and cancellation cleanup. Regenerate tool metadata and document direct invocation.

BREAKING CHANGE: Removed permission configuration and policy commands, approval fields, filesystem scope inputs, and fixed confirmation options. Process capture inherits the host environment and accepts command names; callers must refresh tool schemas and migrate removed fields.
2026-10-05 20:16:44 +08:00
N0zoM1z0andGitHub 4007b20fc2 fix(mcp): emit valid schemas for empty arrays (#535)
Replace empty tuples with a shared empty-array schema. Validate all input
and output schemas against Draft 2020-12 during catalog generation and
packaged MCP verification, with runtime and catalog regression coverage.

Closes #528

Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)
2026-10-05 15:32:58 +08:00