Give the launcher and shared command worker one lightweight owner for package-version binding, Windows empty-home handling and Android browser-cache defaults. Preserve per-command preparation and environment restoration, package the owner explicitly, and retain its package and JavaScript recovery CI scopes.
Validation: dispatcher/version/shared-session, home fallback, evaluator/MCP/process cleanup and CI scope tests passed. Functional archive/install/repack, installed static CLI analysis and MCP checks passed; no real Codex/model trial or Windows/Termux runtime qualification was performed.
Keep the maintained manual evaluator, fixture rubrics and semantic tests together under tests/evaluation/model-evals instead of shipping them in dist. Load the same typed owners from the manual runner and update the architecture and client guide. Grading/report contracts and executable logic are unchanged.
* feat(pe): inspect import and delay-load tables
Add inspect_pe_imports / inspect-pe-imports to read PE32/PE32+ import
and delay-load directories without executing the image. The report keeps
DLL names, named and ordinal functions, ILT/IAT RVAs, and a pefile
import hash of the standard import table. A missing directory is
observed absence, not proof the image never imported APIs.
* fix(pe): default PE import fixture options
Allow peImportImage() without an argument so CLI and filesystem tests
can use the KERNEL32 sample without repeating an empty options object.
* test(pe): keep import path cases on the dedicated MCP contract
inspect_pe_imports already rejects relative MCP paths in its own
boundary test. Leave the shared absolute-path matrix to tools whose
handler issue projection matches that suite's expected shape.
* fix(native): index virtual-to-file mapping lookups
mappedFileOffset scans every mapping twice per span, so a parser that
translates one span per table entry costs sections x entries. Add
fileMappingLookup, which builds an O(n log n) interval index once and
answers each span in O(log n) with the same accept, reject and
translation results. A differential test checks it against
mappedFileOffset over randomized overlapping mappings and zero fills.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ra7LM2NyQ7DumdssxbUq5g
* fix(pe): report partial import evidence and exact pefile hashes
- Withhold imphash with an explicit reason whenever the standard import
table is partial (unreadable names or thunks, missing tables), or when
pefile 2024.8.26 would hash a different row sequence: invalid or
truncated names, ordinal 0, descriptors without functions, tables its
bounds or repeat/spread heuristics discard, and its 8192-thunk import
symbol cap. Delay-load issues do not withhold it.
- Hash ordinal imports with pefile's complete ordlookup tables and its
ord<decimal> fallback instead of declining unmapped ordinals.
- Report a nonterminal descriptor whose FirstThunk is zero, and a
delay-load descriptor whose IAT or INT RVA is zero, as malformed_entry
partial coverage instead of a complete empty inventory.
- Directory evidence lists the file spans actually consumed for the
descriptor array and terminator; discontiguous mappings produce
separate spans and separate Evidence ranges.
- Carry exhausted limits as PeImportLimitFailure.limit and derive
recovery from it; the fixed 16 MiB retained-text ceiling reports a
fixed allowance instead of max_file_bytes advice.
- Translate RVAs through the indexed mapping lookup and yield with a
cancellation check every 1024 table entries.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ra7LM2NyQ7DumdssxbUq5g
* fix(pe): read only own ordinal tables for DLL names
DLL names such as constructor and __proto__ pass pefile's name rule but
resolved inherited object members, throwing before the ord<n> fallback.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ra7LM2NyQ7DumdssxbUq5g
* fix(native): preserve PE import facts and prove hash compatibility
* test(native): verify PE import workflows and measured costs
* refactor(native): narrow PE facts across the container union
* docs(native): record integrated PE import validation
* fix(native): bound every PE import RVA span
* docs(native): measure RVA guard completed workflows
* fix(pe): reconcile import coverage with retained rows
* fix(pe): retain partial imports at descriptor mapping gaps
---------
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
Move the synthetic evaluator and its unchanged semantic tests out of the shipped runtime. Retain actual CLI and MCP Evidence separately from the synthetic nine-stage baseline in a versioned verifier artifact, execute its reported conformance checks, and assign the verifier to its CI lane.
Validation: evaluator/state/classifier source suites, compiled CLI/MCP views, verify:readiness, static checks, build and docs passed. Readiness observed coverage is static analysis; fixture runtime behavior and reconstruction closure were not executed.
* feat(javascript): link assignment right-hand sides to their writes
A declaration carries its value forward, but a later assignment to a
variable, a property or through a compound operator stopped the forward
trace at the right-hand-side read. The semantic IR now records one
syntactic assignment flow per simple assignment target (ranges, operator,
owning callable), and the graph projection connects each retained read
of the right-hand side to the write occurrence through a defines
relation. Compound assignments also consume the previous value of the
target; the written value itself stays unknown, keeping the boundary of
#4342 intact.
Fixes#6193
* fix(javascript): preserve computed key assignment ownership
* test(javascript): retain nested callback assignment ownership
* docs(javascript): record assignment influence verification
* test(mcp): isolate mocks and acknowledge cancellation boundaries
* test(javascript): retain CLI diagnostics and current-main verification
---------
Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
The export file read returns permission refusals through Result under the calling operation's name.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Remove test-only completion and historical manifest parsers, use authoritative completion schemas, and keep graph hashing with the validated manifest producer. Verify commitments with independent canonical JSON and SHA-256 checks through domain and public CLI workflows.
Use the existing builtin argument split for the invalid-log-level doctor exemption, removing independent flag scanners from the launcher and reusable CLI test worker. Empty output values and doctor-looking command data now preserve configuration refusal precedence; shell completion stays transport data.
Check fresh and shared frontends with production argument parsing, retain both doctor readiness paths, and verify non-doctor requests stop before the real launcher imports command handlers.
* feat(ghidra): bound one procedure's decompile without closing the session
Fixes#5340
* fix(ghidra): report decompile limit as a request timeout
Keeps BinarySession from marking every Ghidra operation unavailable after one procedure's decompile reaches the limit, and names the MCP tool-call deadline in the remediation.
* fix(ghidra): budget the decompile limit and report cancellation-closed sessions
Adds REA_GHIDRA_DECOMPILE_TIMEOUT_SECONDS to the derived Codex/Kimi tool deadline and forwards it through setup. Marks a remote failure that settles after caller cancellation so the timeout projection no longer promises session reuse.
* feat(ghidra)!: default analyze_function to a retained summary
analyze_function was the one analysis tool never wired into REA's
detail: summary|complete convention, so it always returned the complete
native dossier inline (0.2-10 MB, dominated by value-flow and
references). Agents on tool-result-capped harnesses never reached the
pseudocode.
Add `detail` to analyze_function, defaulting to summary: return a
compact dossier (procedure identity, pseudocode size, facet counts,
value-flow availability) and retain the complete dossier Evidence in
the session. Page pseudocode, references, assembly and value-flow
through normalized_result.parent_evidence_id with inspect_analysis_view,
which already projects every native facet. detail: complete returns the
full dossier inline as before. Delivery detail never reaches the
provider or Evidence identity.
BREAKING CHANGE: analyze_function now defaults to the compact summary
view instead of the complete dossier inline. Pass detail: "complete"
for the previous behavior.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* feat(cli): expose analyze_function detail on the function command
Wire `rea function` into the shared CLI detail-delivery convention
(--detail, --evidence_output) so the CLI and MCP adapters offer the same
summary | complete choice for analyze_function. Summary delivery writes
the complete dossier Evidence to a bundle and returns the compact
summary view; it fails before analysis when --evidence_output is
missing, so no provider work is wasted. The CLI default stays complete
because a one-shot command has no in-process Evidence retention.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* refactor(ghidra): harden analyze_function summary after independent review
FlatlineRoundtable cross-model review (6 lanes) converged on the summary
projection's availability semantics being underspecified. Document that
facet_availability is authoritative over raw pseudocode length, that
code_units are UTF-16 (the unit inspect_analysis_view pages by), and that
value_flow.truncated is meaningful only when value-flow is available.
Parenthesize the nullish-coalescing/comparison for clarity. No behavior
change; declined claims (value-flow "truncated collapse", unresolved_calls
dead code) were schema-impossible or already correct.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* test(ghidra): cover analyze_function detail wiring on both adapters
Close the roundtable's top convergent finding: the summary path had only
domain-projection coverage, not the server/CLI wiring where the breaking
behavior lives.
MCP server (registerEnhancedTools): the default delivers a retained
summary whose complete parent is recorded for paging; delivery detail is
stripped before the provider request; detail: complete returns the full
dossier inline; a registration without retention rejects a summary
request before any provider work.
CLI (rea function): the default returns the complete dossier; --detail
summary without --evidence_output fails before analysis; with the bundle
sink it returns the compact summary and writes the complete Evidence
bundle.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* fix(ghidra): keep analyze_function delivery detail out of provider inputs
Address the five automated review findings on #5660.
P1: `detail` lived in the shared enhancedInputSchemas.analyze_function, so
inspect_native_api composed `{procedure, detail: "summary"}` and the strict
Ghidra analyze_function schema rejected it. Delivery detail is now owned by
the analyze_function MCP tool contract; the handler separates it before any
provider call, and executeFunctionAnalysisEvidence parses the provider input
only. The MCP regression test validates provider input exactly as the
production Ghidra client does and exercises inspect_native_api.
P2: the analyze_function summary Evidence now carries the parent's
relationship_coverage like native facet views, so partial or unknown
caller/callee discovery is not reported as complete.
P2: the summary reports the dossier's declared facet_availability, nulls the
counts of facets the provider declared unavailable, and lists each reason in
unknowns, so Kuna's empty references, comments and basic blocks are not
mistaken for observed absence.
P2: inspect-analysis-view evidence-file sources accept the Evidence bundle
that --evidence_output writes, selecting a record with source.evidence_id
when the bundle holds several; the CLI test reads the saved bundle back
through that route.
Tests that assert the complete dossier over public analyze_function now pass
detail complete, and the oversized-dossier test asserts the summary view it
previously expected to be unsupported.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* fix(ghidra): keep omitted function facets unknown in the summary
The analyze_function summary coerced an omitted unresolved_calls record to
a count of 0 while the native facet view reports the same dossier as "not
recorded", and it carried no counts at all for the pageable
swift_string_literals facets. Count optional records as null when the
dossier omits them, name them in unknowns, and add nullable counts for both
Swift literal facets. The summary Evidence envelope also dropped the
function address: createAnalysisViewEvidence now derives one function-view
predicate for both the address location and relationship coverage.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* fix(scripts): request complete analyze_function dossiers in real-provider checks
The real-provider check scripts call analyze_function over MCP and then
consume the complete dossier: requireFunctionDossier, functionDossierSchema,
.procedure/.pseudocode reads, operation assertions, compare_functions inputs
and the oversized-dossier rejection path. The summary default broke them.
Every such call site now passes detail: "complete". Provider-direct callers
are unchanged because detail is an MCP contract field; the admission-error
sites stay unchanged because provider failures return before the summary
branch.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* fix(ghidra): keep unavailable value-flow counts unknown in the summary
summarizeDossier coerced the five value_flow_* counts to zero when
native_value_flow was null (IDA, Kuna) or declared unavailable (Ghidra),
so the summary reported empty collections while value_flow.available said
otherwise. The counts are now null unless value flow is available, with the
reason already named in unknowns.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* fix(evidence): budget authentication headroom by file shape and serialized size
The evidence-file headroom reserved two parsed copies, calibrated for one
record, and charged strings at two bytes per character. Bundle
authentication additionally holds the schema-parsed bundle, the re-parsed
records and two JSON.stringify results, which expand control characters and
lone surrogates sixfold: a bundle whose raw_result is a million NUL
characters estimated at 2 MB parsed but needed 12 MB of serialized text.
The budget now has a parsed term and a serialized term per file shape, owned
by EvidenceAuthenticationHeadroom and shared by the analysis-view reader and
the bundle importer, which had no guard. Two transient peaks the budget did
not name are removed at their producers: the canonical digest hashes a large
leaf directly instead of concatenating it into its buffer, and the JSON
validator walks containers by cursor so a wide array no longer queues one
entry per member.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* fix(mcp): route analyze_function summary replies to dossier consumers in docs and prompts
The MCP guide, the version-comparison and crash-triage prompt contracts,
the authored skill and the Kuna, IDA and function-matching docs still told
agents to pass analyze_function replies straight to compare_functions or
build_call_path. Under the summary default those consumers reject the reply.
They now name the retained-evidence reference for compare_functions, the
observations fields of match_native_functions, and detail: "complete" for
build_call_path, which accepts only inline dossiers.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* test(evidence): pin validator member order and keep interrupted validation yielding
Independent review of the cursor validator found the interrupted-validation
fixture relied on the old last-first walk: its over-deep head was reached
before the first cooperative yield. The padding now precedes the deep
element so the walk yields first, which is the invariant the test guards.
A new case pins first-defect-in-member-order reporting, skipped
non-enumerable keys no longer count toward the yield cadence, and the
import-headroom test loads the reader through a fresh module graph so it
holds under the services project's shared workers.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AoJZDPcrgmMsCqLG4LfiFb
* fix(ghidra): align deadline bounds and cancellation outcomes
* refactor(ghidra): shorten deadline recovery guidance
* fix(mcp): clarify the scope of inferred decompile deadlines
* test(ghidra): verify deadline workflows and document measured costs
Separate failure and registration cases by their distinct contracts.
Record actual Linux Ghidra, CLI and MCP evidence with measured context,
elapsed time, CPU and memory, and explicit remaining coverage limits.
* docs(ghidra): pin integration and distinguish baseline format failures
* fix(ghidra): own failure lifecycle wording in the provider
* test(ghidra): budget timeout fixture generation before allocation
* fix(analysis): preserve summary provenance and bound bundle guidance
* fix(ghidra): align capability and traversal deadline guidance
* style(config): align deadline guidance formatting
* docs(ghidra): record capability and traversal verification
* docs(analysis): use absolute paths for Evidence files
* docs(analysis): record completed function summary measurements
* docs(analysis): update main integration validation
---------
Co-authored-by: Syed Rishad <rishadzzzz@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
The lane now runs the command users run: it builds the Grafana-shaped HAR
with environment-build and the packed checkout, checks the report, then
runs the bundle with agent-env as before.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ghidra): bound one procedure's decompile without closing the session
Fixes#5340
* fix(ghidra): report decompile limit as a request timeout
Keeps BinarySession from marking every Ghidra operation unavailable after one procedure's decompile reaches the limit, and names the MCP tool-call deadline in the remediation.
* fix(ghidra): budget the decompile limit and report cancellation-closed sessions
Adds REA_GHIDRA_DECOMPILE_TIMEOUT_SECONDS to the derived Codex/Kimi tool deadline and forwards it through setup. Marks a remote failure that settles after caller cancellation so the timeout projection no longer promises session reuse.
* fix(ghidra): align deadline bounds and cancellation outcomes
* refactor(ghidra): shorten deadline recovery guidance
* fix(mcp): clarify the scope of inferred decompile deadlines
* test(ghidra): verify deadline workflows and document measured costs
Separate failure and registration cases by their distinct contracts.
Record actual Linux Ghidra, CLI and MCP evidence with measured context,
elapsed time, CPU and memory, and explicit remaining coverage limits.
* docs(ghidra): pin integration and distinguish baseline format failures
* fix(ghidra): own failure lifecycle wording in the provider
* test(ghidra): budget timeout fixture generation before allocation
* fix(ghidra): align capability and traversal deadline guidance
* style(config): align deadline guidance formatting
* docs(ghidra): record capability and traversal verification
---------
Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
Validate recorded-core program-header projections against the selected pyelftools architecture table after binding e_machine to the snapshot. Preserve numeric unknowns and reject names borrowed from another machine or inconsistent header bytes.
Add source-binding malformed controls and authored auxiliary-header carriers to the existing real CLI/MCP verification lane. Document pinned parser semantics separately from payload interpretation and real crash coverage.
Fixes#6538
Retain module-name displays observed before optional metadata failure so strict objdump framing can use those facts. Preserve uncertainty across name sections and report unknown completeness when unattributed producer warnings concern skipped custom metadata; keep exact warnings, core validation, WAT and artifact provenance.
Validation: focused source/process regressions and 61 real WABT1.0.42 CLI/MCP verifier cases pass. The unmodified official macOS arm64 archive matches its published SHA-256. Coverage includes outer/inner malformed name metadata, valid empty-map controls, stable core/interface facts and cleanup. No inspected WASM target was executed.
Fixes#6885
* feat(cli): add JSON Lines output for row-oriented results (#5487)
- Support opt-in JSON Lines format (--format jsonl) for row-oriented results and collection views with clear record boundaries
- Preserve stable source identities and stream records deterministically line-by-line
- Emit final coverage and limitation metadata as a distinct line with https://rea.dev/schemas/jsonl-coverage-v1.json to prevent confusion with data rows
- Distinguish error outputs with https://rea.dev/schemas/jsonl-error-v1.json
- Reject non-row-oriented results that lack record boundaries with an unreadable_output error
- Document JSON Lines streaming conventions in docs/cli.md
- Add boundary tests covering empty results, multiline strings, partial coverage, large fields, and non-row rejection
* fix(cli): preserve diagnostics, provenance, and nested collections in JSONL
* fix(cli): frame classified failures and reject unrepresented JSONL facets
---------
Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
Read Apktool 3's producer string dialect before YAML can discard hashes or
reinterpret values. Preserve older YAML behavior and decode producer escapes once.
Select the exact root AndroidManifest.xml resource in REA's JADX bridge and
derive summaries once with namespace-aware XML parsing. Preserve decoded text,
summarize before its display cap, invalidate cached facts with the loaded session,
and remove superseded upstream manifest handlers. Keep the engine pinned to 0.7.1.
Validated Apktool parser/provider and public adapter controls; compiled the bridge
against the verified pinned JAR and ran its real Java regressions plus public CLI
and stdio MCP manifest parity checks. Real Apktool execution remains unverified;
the new manifest fixtures use plain XML. No Android application was executed.
Fixes#6804Fixes#6866Fixes#6863Fixes#6819
