Skip to content

armgit / rea

Public Imported from GitHub
0

Reverse engineer anything with agents, from app behavior down to native binaries.

docs(tools): clarify complete inline workflows

morluto41681742ccea
diff --git a/docs/javascript-application-graph.md b/docs/javascript-application-graph.md
index 9446478c6..d62552cbf 100644
--- a/docs/javascript-application-graph.md
+++ b/docs/javascript-application-graph.md
@@ -159,9 +159,8 @@ so callers cannot preserve a stale ID after changing semantic content.
## Structure
-The graph does not impose aggregate caps on roots, nodes, edges, or observations.
-Each properties object is valid JSON with at most 64 keys, depth 6, 512
-structural nodes, and 4,096 characters per string. Field-specific validation
+The graph does not impose aggregate caps on roots, nodes, edges, observations,
+or JSON properties. Properties must be valid JSON; field-specific validation
still applies to paths, identifiers, and evidence values. Extractors report
actual omissions in coverage instead of silently dropping a prefix.
diff --git a/docs/javascript-application-workflows.md b/docs/javascript-application-workflows.md
index 16414e0e1..ccc0dd572 100644
--- a/docs/javascript-application-workflows.md
+++ b/docs/javascript-application-workflows.md
@@ -49,7 +49,7 @@ The extractor covers lexical definitions and reads, literal seeds, static
property slots, object reads/writes/spreads/destructuring, closure captures,
uniquely resolved local calls, argument/return flow, and explicit Promise
construction, chaining, aggregation, await, return, assignment, and
-detachment. It also recovers bounded static candidates for EventEmitter
+detachment. It also recovers static candidates for EventEmitter
registrations/removals and dispatch, Node timers and cancellation handles, asynchronous
`node:child_process` creation and ownership, configuration sources and direct
defaults, request construction and response consumers, parse/coercion/
@@ -58,9 +58,9 @@ validation boundaries, and built-in resource acquisition/release.
Function fingerprints commit normalized syntax, control-flow shape, relation
shape, literal sets, arity, and detected effects without using local names or
source offsets. Equal duplicate fingerprints remain ambiguous. Dynamic
-calls/properties/names, parser recovery, unresolved handles, unsupported API
-shapes, and every reached bound stay explicit unknowns; a missing relation is
-never reported as proven behavioral absence.
+calls/properties/names, parser recovery, unresolved handles, and unsupported API
+shapes stay explicit unknowns; a missing relation is never reported as proven
+behavioral absence.
Semantic relations use static-inference authority. `resolved` means the static
target identity was unique within admitted analysis; it does not mean the path
@@ -122,9 +122,8 @@ relationships recovered by the AST analysis.
Direct return expressions, including expression-bodied arrows, are evaluated
through an execution-free value lattice. Literal object fields and direct
-return sites are retained without count quotas. Calls, dynamic spreads,
-computed keys, parser recovery, and the value-recursion depth guard remain
-partial or unknown.
+return sites are represented in the result. Calls, dynamic spreads, computed
+keys, and parser recovery remain partial or unknown.
Nested callable returns are not assigned to their parent callable. Projected
graph observations carry source ranges but never source text.
diff --git a/docs/javascript-runtime-reconciliation.md b/docs/javascript-runtime-reconciliation.md
index 8ee62aa5a..cdd340079 100644
--- a/docs/javascript-runtime-reconciliation.md
+++ b/docs/javascript-runtime-reconciliation.md
@@ -47,12 +47,7 @@ are complete Evidence objects, not only evidence IDs:
]
}
],
- "runtime_observations": ["INSPECT_WEB_PAGE_EVIDENCE"],
- "limits": {
- "max_runtime_entities": 10000,
- "max_reconciliation_items": 20000,
- "max_static_load_states": 20000
- }
+ "runtime_observations": ["INSPECT_WEB_PAGE_EVIDENCE"]
}
```
@@ -101,13 +96,13 @@ nodes. REA evaluates compatible static candidates conservatively:
3. Without captured bytes, one unique mapped artifact path can produce a
medium-confidence location match.
4. Multiple candidates remain `ambiguous`; no `observed_as` edge is emitted.
- `candidate_static_count` reports the full qualified layer/node count while
- `candidate_static_nodes` retains a deterministic bounded prefix.
+ `candidate_static_count` reports the full qualified layer/node count, and
+ `candidate_static_nodes` includes every unique candidate reference.
5. If captured bytes disagree with the static candidate at the mapped path,
the result is an explicit mismatch. A path never overrides a digest
disagreement.
-6. Missing authorization mappings, incomplete input coverage, and output
- limits remain unknown or truncated rather than becoming absence claims.
+6. Missing authorization mappings and incomplete or truncated input coverage
+ remain unknown or truncated rather than becoming absence claims.
Every successful cross-layer `observed_as` edge has
`authority: cross-layer-reconciliation` and `state: inferred`. The underlying
@@ -124,7 +119,7 @@ classification:
- `resident-in-loaded-asset` means a containing asset was observed, but the
embedded module was not independently observed or shown to execute;
- `not-observed-in-capture` means the entity did not appear in the complete
- bounded captures supplied to this call and its artifact path falls beneath
+ authorized captures supplied to this call and its artifact path falls beneath
an exercised automatic or operator-declared mapping prefix;
- `unknown` covers incomplete captures, layers outside runtime scope, and
unresolved correspondence. Nodes outside a mapped artifact prefix stay
diff --git a/docs/mcp-contracts.md b/docs/mcp-contracts.md
index f299da833..70fdb738c 100644
--- a/docs/mcp-contracts.md
+++ b/docs/mcp-contracts.md
@@ -58,9 +58,8 @@ shutdown rules still apply; REA never kills a process it cannot prove it owns.
## Tool results
Evidence-producing tools return their result and Evidence context inline. Read
-that result directly; do not fetch a bundle or resource to inspect it. Use
-`get_evidence_bundle` only when the task explicitly needs broader retained
-session history or a bundle for transfer.
+that result directly. Use `get_evidence_bundle` when the task needs broader
+retained session history or an explicit bundle for transfer.
## Aggregate native context
diff --git a/docs/product-catalog.json b/docs/product-catalog.json
index 3776a82c2..54e846f92 100644
--- a/docs/product-catalog.json
+++ b/docs/product-catalog.json
@@ -501,9 +501,9 @@
"mcp_prompts": 6
},
"digests": {
- "tools_sha256": "dcc3c3dbe9068ac7ec6774552ca309faaf0a6f5f992dd857b3dffea47f7bbf31",
+ "tools_sha256": "37c7ca2a93d9c78dd5372b88db55626d7ee5474bbb1b82477d14363631d68ddf",
"prompts_sha256": "fa889fc671185ac9c968c6dc8309cf609e709cdc837dbbf39b7cdfadb84ac2d7",
- "combined_sha256": "10ddf103b5e479182562331658d8bb5f128e356002ddb40431371af1a1cf7794",
+ "combined_sha256": "64e291ccdfb45d454eb084b2944e94d5b46fbdec61802cff95ad6bd420125526",
"providers_sha256": "7247eece8fad09c8023af8d5c682d223d7ed7ebd68eac79e9154962a7e03b66b"
}
}
diff --git a/skills/reverse-engineer-anything/SKILL.md b/skills/reverse-engineer-anything/SKILL.md
index 5df0f4ff6..e8e686dd3 100644
--- a/skills/reverse-engineer-anything/SKILL.md
+++ b/skills/reverse-engineer-anything/SKILL.md
@@ -4,7 +4,7 @@ description: Reverse engineer native, managed, Electron/JavaScript, packaged, an
metadata:
version: "23"
tool_count: 111
- catalog_digest: "10ddf103b5e479182562331658d8bb5f128e356002ddb40431371af1a1cf7794"
+ catalog_digest: "64e291ccdfb45d454eb084b2944e94d5b46fbdec61802cff95ad6bd420125526"
---
# REA
diff --git a/skills/reverse-engineer-anything/references/javascript-applications.md b/skills/reverse-engineer-anything/references/javascript-applications.md
index 9b6d8aea0..195e05f1b 100644
--- a/skills/reverse-engineer-anything/references/javascript-applications.md
+++ b/skills/reverse-engineer-anything/references/javascript-applications.md
@@ -1,12 +1,10 @@
# JavaScript and Electron application artifacts
Use `analyze_javascript_application` directly on the operator-supplied ASAR or
-extracted tree. It reads the selected local path without an approval flag or
-configured investigation root. The complete result, graph, and Evidence context
-are returned inline, so inspect them directly without fetching resource links.
-Source-map contents are part of the static analysis. Start from its findings,
-coverage, unknowns, and graph context, then make a focused follow-up only when a
-specific question remains unanswered.
+extracted tree. The complete result, graph, and Evidence context are returned
+inline. Source-map contents are part of the static analysis. Start from its
+findings, coverage, unknowns, and graph context, then make a focused follow-up
+only when a specific question remains unanswered.
BrowserWindow preferences, preload and contextBridge surfaces, IPC
registrations, utility processes, and native binding requests are static syntax
@@ -17,8 +15,8 @@ registration, defaults, or policy enforcement from static analysis.
Use `trace_application_feature` on existing application Evidence for one
literal node ID, route, string, API, IPC channel, module, or native export.
-Choose a direction and finite bounds. Link Hopper or Ghidra Evidence only when
-the exact artifact digest matches.
+Choose a direction and include the complete application Evidence inline. Include
+Hopper or Ghidra Evidence only when its artifact digest matches exactly.
For version comparison, analyze each version once, then call
`compare_application_versions`. Accept only its digest, source-map, structural
@@ -29,9 +27,9 @@ opposite-side coverage; otherwise report unknown.
When the question asks how one exact exported callable's returned object shape
changed, analyze each version once and then call
`compare_javascript_export_shapes` with explicit module paths and export names.
-Use the Evidence IDs returned by the two analysis calls. Accept variant pairing
-only through the tool's unique exact literal discriminant. Cite the comparison
-Evidence and report JSON Pointer changes; dynamic values, ambiguous variants,
-and incomplete parent-property coverage stay unknown. This is static inference,
-not runtime behavior. Use `run_controlled_replay` separately only when the user
-needs approved runtime semantics.
+Include the complete Evidence records from both analysis calls. Accept variant
+pairing only through the tool's unique exact literal discriminant. Cite the
+comparison Evidence and report JSON Pointer changes; dynamic values, ambiguous
+variants, and incomplete parent-property coverage stay unknown. This is static
+inference, not runtime behavior. Use `run_controlled_replay` separately only
+when the user needs approved runtime semantics.