Preserve observed terminal-call sites and callee flags across function views, raw bridge responses, Evidence, and snapshot replay. Version analysis profiles so older unqualified results cannot be reused.
Qualify Ghidra function extents without changing external no-return flags or claiming recovery of excluded code.
Validation: 76 focused tests, check:fast, docs:check, formatting, and the full Ghidra 12.1.4 host lane pass. Real CLI and all five stdio MCP function views retain the terminal-call evidence; returning puts calls remain unflagged. The reported stripped Rust ELF and Windows host remain unverified.
Fixes#1658
Check function and label ownership in the existing namespace before renaming. Keep same-address renames idempotent and reject duplicate batch members inside their individual transactions. Extend real-provider namespace checks for single and batch collisions without conflating function and label fixture names.
Validation: real Ghidra 12.1.4 host-native verification passed on macOS ARM64 with JDK 21.0.12.1, including public CLI/stdIO MCP, qualified-name round trips, rollback, source-byte immutability, and complete cleanup. Windows mutation authority remains unchanged.
Fixes#1649
* feat(ghidra): admit set_address_name and set_addresses_names
Ghidra sessions rejected the existing naming tools with "operation is not declared by this provider", so agents had to use annotate_native_function, which returns a complete function dossier per rename and cannot name data addresses.
The Java bridge now names a local function entry (namespace-aware, like annotate_native_function) or creates/renames the primary label at any other mapped address, verifying readback. set_addresses_names applies each address in its own transaction and reports per-address booleans. Both are mutating capabilities: excluded from read-only (Windows P0) handshakes and from snapshot replay.
* fix(ghidra): normalize qualified symbol names and reject empty leaves
Share namespace-aware leaf normalization across functions and primary labels. Invalid qualified leaves now return false for naming operations without marking the provider unavailable; function annotations retain typed invalid-input errors.
Extend real CLI/MCP namespace verification with namespaced globals, readback replay, failed-name rollback, mixed batches, and capability checks.
Validation: 75 focused tests and npm run check pass. Ghidra 12.1.4/JDK 21 namespace verification passes on macOS arm64 with unchanged source bytes and complete cleanup. The full host lane passes this workflow before the existing entry-alias fixture fails because the compiler places its interior label at the function entry.
---------
Co-authored-by: morluto <[email protected]>
* fix(ghidra): clear wrong no-return flags before serving a session
Auto-analysis can flag ordinary functions as no-return (stream readers,
__cxa_guard_acquire, ...). Their callers then end at the call and the
decompiler truncates them. Run a postScript before the bridge that clears the
flag on functions containing a real RET and re-disassembles the call sites that
were terminators.
Co-Authored-By: Claude Sonnet 5.5 <[email protected]>
* fix(ghidra): refit in place and scope no-return call-site repair
Keep function types by refitting the owning functions with fixupFunctionBody
instead of removing and recreating them. Only redo call sites whose callee was
actually cleared (including thunks to it), skip sites followed by a function
start or x86 padding so real end calls do not run on, and always log the result.
Co-Authored-By: Claude Sonnet 5.5 <[email protected]>
* fix(ghidra): constrain no-return repair to admitted return evidence
---------
Co-authored-by: Claude Sonnet 5.5 <[email protected]>
Co-authored-by: morluto <[email protected]>
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.
* perf(hopper): resolve string search records once per query
search_strings called _string_inventory(document) once per match, and each
call sorts every string address and rebuilds the record dict, so a query cost
O(matches x strings log strings). Resolve the inventory once per search.
Warm search, 50% matches, fake document, best of 7: 1000 strings 186 -> 0.5 ms,
4000 strings 3161 -> 2.1 ms, 8000 strings 13121 -> 4.9 ms; output byte-identical.
* perf(hopper): skip record resolution for empty string searches
Resolving the full string inventory for a query with no matches added a sort
of every string address that the previous code never performed. Return early
when nothing matches. Zero-match search on a warm document, best of 7:
64000 strings 35.9 ms before this change, 4.0 ms after (main: 3.9 ms).
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.
Collect references from the complete owned function body and exact entry,
including instruction-interior destinations and embedded-data sources.
Bind the corrected semantics to the analysis profile so legacy snapshots
cannot replay incomplete results. Preserve snapshot mismatch reasons and
recovery advice through CLI and MCP without disturbing live sessions.
Return exact entry candidates for ambiguous function names. Expand the
real-provider regression workflow and replace redundant parser assertions
with malformed-output coverage through the pinned MCP client.
Verified with Ghidra 12.1.4 on macOS arm64: full host-native lane, real
CLI/MCP boundary probes, 30 focused tests, and typecheck/lint.
Validate native annotation text before mutation and escape surrogate code units in Java bridge JSON replies. Reject unsupported text with field and index diagnostics while preserving supported Unicode and line endings.
Probe real CLI/MCP annotation, transport, mapping, rollback and cleanup behavior; replace seven redundant unit tests with E2E and SDK boundary coverage.
Preserve boundary diagnostics, resolve procedure names before bare hex addresses, and launch the inspected JVM directly on macOS for verifiable startup cancellation. Keep private socket paths within host limits and retain ownership when cleanup is incomplete.
Exercise the fixes through real CLI/MCP Ghidra workflows and provider-boundary integration tests, replacing redundant unit coverage.
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.
* fix(process): stop failing captures on tokens macOS cannot expose
On a busy macOS 26 host the residual process sweep fails every capture:
KERN_PROCARGS2 omits the environment of Apple platform binaries for any
caller and fails with EINVAL for processes owned by another account, so an
unrelated process created after the capture baseline escalates to a hard
cleanup failure with cleanup_incomplete.
Report environment withholding distinctly from the Darwin token reader by
reading the platform-binary flag through csops, carry the effective uid in
the process table, and re-read unresolved tokens with a bounded retry plus a
final liveness confirmation so transient exec and exit states settle.
Candidates whose token the OS provably withholds, foreign-uid candidates,
and candidates that exited during validation are now recorded as unverified
processes instead of failing an otherwise clean capture or being signaled.
Related candidates and every other unreadable candidate stay fail-closed.
* test(process): align ownership lanes with the uid-aware process table
The Darwin sweep reads the effective uid through ps, so the offline
verification lanes' syscall allowlists must accept the new argv in
verify-binary-layout and verify-evm-interface. The foreign-uid ownership
test requires POSIX process uids; skip it where the platform has none
(the curated Windows lane).
* fix(verify): recognize UID-bearing ownership process tables
---------
Co-authored-by: N0zoM1z0 <[email protected]>
* 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 <[email protected]>
Co-authored-by: N0zoM1z0 <[email protected]>
* 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
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 <[email protected]>
Add observe_native_calls (CLI: observe-native-calls <path> <input-json>). It
launches the active Mach-O as an owned process under `lldb --batch`, stops at
caller-selected functions or Objective-C methods, records each entry and
auto-continues:
- thread, image, symbol, load and file address;
- raw integer argument registers and optional caller frames;
- for methods, the selector read from _cmd and the receiver's dynamic class,
from LLDB's runtime reader without running target code.
No expression is evaluated and no existing process is attached. The run ends
on exit, max_events or duration_ms; REA then kills the process and confirms
that it is gone. The result also carries exit status, bounded stdout/stderr,
breakpoint resolution with partial coverage for unresolved requests, and
limitations. A target LLDB may not debug fails with a debugger-attach-denied
reason and remediation.
verify:native-calls checks the tool through the CLI and stdio MCP against a
compiled fixture, compares breakpoint addresses with nm, exercises every
outcome, and checks hardened-runtime targets with and without get-task-allow.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
* perf(graph): avoid repeated traversal edge scans and copies
* fix(android)!: preserve JVM settings and reuse metadata sessions
Read class metadata without generating application source, retain immutable serialized APK sessions, and join owned cleanup on cancellation and shutdown.
BREAKING CHANGE: Android analysis now requires a full JDK 17 or newer with its compiler module for the packaged Java source bridge.
* feat(ghidra): edit function annotations atomically
Return annotation readback and refreshed function analysis through CLI and MCP. Own each database transaction, invalidate caches and immutable snapshots, preserve executable bytes, and retain the Windows mutation boundary.
Assisted-by: Nitori (gensokyo-skills:nitori-reverse-engineering)
* fix(ghidra): preserve qualified function annotation identity
Preserve namespaces during local name writes and match qualified readback to the refreshed dossier. Add a producer-shaped regression and verify a real namespaced C++ function through the CLI.
Assisted-by: Nitori (gensokyo-skills:nitori-reverse-engineering)
* test(ghidra): align verification with annotation authority
Keep strict capability and profile checks while admitting the explicit session metadata operation. Verify packaged transport authority and atomic transaction commitments and preserve a read-only Windows expectation.
Assisted-by: Nitori (gensokyo-skills:nitori-reverse-engineering)
* feat(ghidra): enable Windows x64 read-only analysis
* test(ghidra): exercise native Windows runtime boundaries
* test(ghidra): verify current Windows inventory and isolate ACL observer
* fix(ghidra): align Windows admission and address P0 review
* feat(ghidra): admit explicit DOS COM analysis
Carry caller-selected COM interpretation through CLI, MCP and target
identity, seed real-mode entry/context before Ghidra analysis, and verify
complete loaded bytes, source mappings and measured register context.
Keep original binaries unchanged and PSP/runtime coverage explicit.
Assisted-by: Nitori (gensokyo-skills:nitori-reverse-engineering)
* fix(verification): validate COM package selection before allocating fixtures
* feat(ghidra): verify DOS load images and expose memory evidence
Verify measured source bytes, mapped regions, fixups and entries against
the immutable MZ snapshot, retaining independent checks and raw evidence.
Expose loaded byte reads and authoritative original file offsets through
both CLI and MCP, with focused and actual Ghidra DOS verification.
Assisted-by: Nitori (gensokyo-skills:nitori-reverse-engineering)
* fix(cli): describe memory inspection arguments
* test(ghidra): align bridge fixtures and CLI capability accounting
morluto