Commit Graph
1977 Commits
Author SHA1 Message Date
N0zoM1z0 2fc47976a0 chore: integrate main for process progress verification 2026-10-10 17:33:17 +08:00
7a56fe6260 fix(setup): honor active client configuration and skill roots (#1504)
* refactor(setup): resolve skill destinations per client

* fix(setup): honor active client configuration and skill roots

* fix(setup): validate effective client scopes and Gemini trust

* fix(setup): treat empty OpenCode overrides as unset

An empty OPENCODE_CONFIG_DIR now stays on the XDG directory, and doctor
and setup inspect global OpenCode files when a custom directory is absent.
Uninstall reports one status per client so a missing earlier layer does
not hide a removed registration.

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-10-10 17:03:43 +08:00
YsopwnableandGitHub b25922e4e8 test(clients): verify native Qwen Pi and Hermes workflows (#1511) 2026-10-10 16:59:32 +08:00
b6ad1f2c3d feat(mcp): compact input schema profile for size-capped providers (kimi-cli/Moonshot) (#1514)
* feat(mcp): add compact input schema profile for size-capped providers

Moonshot's function-calling API rejects a request while any single tool
parameters schema exceeds its literal serialized size cap, so clients
such as kimi-cli fail every request while the default catalog is
attached (#1484).

Add an opt-in REA_MCP_INPUT_SCHEMA_PROFILE=compact server presentation.
Each advertised input schema is rendered within a 13,312-byte budget,
measured to sit below the observed provider cap: annotation prose
(nested descriptions, examples, defaults, titles) is dropped, repeated
annotation-free subschemas are shared through schema-local $defs/$ref
references the provider validates without expansion, and the three
structurally oversized schemas are advertised in a documented reduced
form. The canonical catalog, tool set, output schemas, and server-side
canonical validation are unchanged; the default full profile is
byte-identical to today's advertisement.

Boundary tests pin every compact schema to the budget, keep them valid
JSON Schema that still accepts every canonical example, hold reduced
presentations at three or fewer, and verify canonical rejection still
guards a permissive advertisement. Verified against the real Moonshot
API through kimi-cli: prompts succeed with the compact catalog attached
where the default catalog fails every request with 400.

* fix(mcp): preserve compact schemas through Kimi conversion

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 16:58:43 +08:00
N0zoM1z0 2b6f14f528 fix(process)!: version literal scenario replacement semantics
Keep caller-selected replacement text literal with a callback, preserving
empty-search positions instead of changing their split/join behavior.
Commit the replacement interpretation for captures using custom patterns so
legacy records cannot report this producer correction as a target change.

BREAKING CHANGE: Captures with custom normalization patterns use
literal-replacements-v1 and cannot be compared with legacy unversioned
pattern captures. Capture both sides with the same replacement semantics;
legacy captures remain readable and captures without patterns are unaffected.
2026-10-10 16:57:06 +08:00
openhandsandYsopwnable f51503ef1c fix(process): normalize scenario replacements literally
capture_process_scenario declares normalization patterns as literal text, but\nreplaceAll expands \$&\, \$\`, and \$1\ in the replacement as a replacement\npattern. A caller normalizing text that contains a dollar sign silently gets\nduplicated, spliced, or dropped content in the recorded Evidence instead of\nthe requested literal replacement.\n\nUse split/join, which is literal on both sides and is already the idiom used\nfor exact-literal scenario rules in browserScenarioNormalization.ts.
2026-10-10 16:57:06 +08:00
2bf812772d fix(apple): bound binary plist expansion before decoding keyed archives (#1515)
inspect_keyed_archive passed caller-selected binary plists straight to
plist.parseBinary, which recurses on every object reference and copies
shared containers. A 484-byte archive of forty nested [next, next] arrays
grew the process past 4 GB until it died with no result, which would also
end an MCP server. A 125-byte self-referencing array overflowed the stack
and was reported as an artifact too large to process.

The iterative reference walk that already guards decode_interface_builder
now runs first, with an 8x keyed-archive decode budget. Over-budget depth
or expansion is a limit; a reference cycle is a malformed archive. Its
"decoder" bounds admit the same layouts plist.parseBinary reads, so
accepted archives stay accepted. Interface Builder behavior is unchanged.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 01:44:46 -07:00
a936303723 fix(json): name a leading byte-order mark in rejected JSON input (#1510)
Strict JSON file inputs reject a leading UTF-8 byte-order mark, but the
diagnostic was the parser's own message, which quotes the invisible U+FEFF
as the unexpected token: Unexpected token '', "{"invento"... is not
valid JSON. Editors such as Windows PowerShell 5.1 write that mark by
default, and nothing in the message showed it.

CLI JSON files (whole and streamed), Evidence and snapshot JSON files, and
process scenario files now report that the input begins with a UTF-8
byte-order mark and how to save it. Acceptance is unchanged.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 01:37:41 -07:00
93ca276921 fix(browser): accept HAR files that begin with a byte-order mark (#1509)
HAR 1.2 lets writers emit a UTF-8 byte-order mark and requires readers to
ignore it. The decoder passed ignoreBOM: true to TextDecoder, which keeps
the mark in the decoded text, so a BOM-prefixed export failed as "HAR is
malformed JSON." Decoding now uses the default, which skips one leading
mark. The artifact digest still covers the selected file bytes.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 01:31:31 -07:00
911323c5dd fix(native): page every retained function dossier collection (#1507)
inspect_analysis_view is the recovery path when an analyze_function
dossier exceeds the MCP response budget, but its native facets covered
only procedure, pseudocode, assembly, callers/callees, references, and
value flow. Basic blocks, comments, unresolved calls, referenced strings
and names, and the native API record could not be read from retained
Evidence at all; basic blocks grow with the function just like assembly.

These are now facets: collections page by rows, and native_api is a
singleton. A dossier without an unresolved_calls record reports "not
recorded" rather than the value-flow failure reason.

Refs #1247 and #1065.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 01:31:15 -07:00
f63f12d8ff docs: align the Indonesian README with the other translations (#1512)
Keep the Bahasa Indonesia onboarding text from #1508, and fix the formatting
that left it outside the shared README layout: drop the leading space, point
in-page links at the translated headings, align the analysis table, and link
Bahasa Indonesia from every language selector.

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Dev Cee <24010110166@universitasbumigora.ac.id>
2026-10-10 16:26:52 +08:00
983b070d4d fix(artifacts): record each case collision once at its diverging segment (#1505)
Inventory paired every path under one case spelling with every path under
each other spelling and listed all of them on each occurrence. An archive
with Foo/ and foo/ subtrees of N files each produced N-entry lists on 2N
occurrences: 4,000 such ZIP members yielded a 120 MB inspect_artifact
result and close to 1 GB of memory. The trie walks also recursed once per
path component, so a ZIP name with tens of thousands of components threw
RangeError.

A collision is now recorded at the segment where spellings diverge and
shared down that subtree by an iterative walk. Each occurrence names the
colliding prefix and the first other spelling, plus a count of further
spellings, each of which is its own occurrence.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 01:16:16 -07:00
9e22da845b feat(setup): add native Pi client support (#1376)
* feat(setup): add native Pi client support

* fix(setup): isolate invalid Pi agent directory overrides

Keep malformed Pi path evidence on its client entry so unrelated selected clients can complete setup and doctor. Preserve explicit Pi rejection and block filesystem operations rather than falling back to another directory.

* fix(setup): parse Pi configuration as strict JSON

Pi's installed MCP loader reads mcp.json with a bare JSON.parse and no
BOM tolerance, so comments, trailing commas, a BOM, or an empty existing
file yield loader errors and no servers. Parsing the Pi dialect with
objectSchema.parse(JSON.parse(text)) before the shared empty/JSONC
shortcut rejects those files at every mutation boundary instead of
reporting configured registrations Pi cannot load. A missing file still
initializes a fresh strict-JSON document, other dialects keep their
JSONC/BOM/empty tolerance, and malformed files are never rewritten.

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 16:10:39 +08:00
f970b886aa feat: add Hermes as a supported MCP client (#1403)
* feat: add Hermes as a supported MCP client

Hermes Agent reads stdio MCP servers from `mcp_servers.<name>` in
`config.yaml`. REA had no Hermes client, so setup could not register it and
Hermes users had to wire the server up by hand.

- SupportedClients: add the `hermes` format and client definition, resolving
  the config path from HERMES_HOME, else the platform default that Hermes's own
  resolver uses (LOCALAPPDATA/hermes on Windows, ~/.hermes elsewhere), including
  HERMES_DATA_DIR_SUFFIX.
- ClientConfigurationDocument: parse and serialize Hermes YAML, upserting the
  rea entry into the parsed document so user comments and unrelated settings are
  preserved; emit `enabled: true` since Hermes connects entries unless disabled.
- ClientRegistrationStatus: forward the Hermes location variables so status
  checks resolve the same path as setup.
- Tests: cover path resolution on both platforms and the register/read/uninstall
  round trip, and clear the Hermes location variables between tests.

- delilah 🌸

* docs: document the Hermes client and its config path

- delilah 🌸

* refactor(setup): resolve skill destinations per client

* fix(setup): install Hermes skills in the active profile

* fix(setup): identify each client skill action uniquely

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 16:03:25 +08:00
a0e5e9db2b perf(artifacts)!: name each edge's child through its occurrence (#1493)
Every inventory edge is created from one occurrence and copied that
occurrence's artifact_id and logical_path as child_artifact_id and
logical_path. Edges now keep the occurrence_id reference alone. Edge IDs
still hash the same child and path, read from the occurrence, so they are
unchanged; validation and artifact comparison read the occurrence too.

inspect_artifact output: Transmission.app 1.10 MB to 0.97 MB, Visual
Studio Code.app 15.37 MB to 13.48 MB.

BREAKING CHANGE: Artifact inventory edges no longer include
child_artifact_id or logical_path; read them from the occurrence named by
occurrence_id. The graph commitment changes, so inventory Evidence
recorded by earlier versions no longer validates.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 00:58:05 -07:00
1f692c83e2 perf(artifacts): stop repeating every artifact path as Evidence locations (#1492)
inventory_artifact, inspect_artifact, and extract_artifact copied each
occurrence or extracted file path into Evidence locations, although the
result already names every one. inspect_artifact did so twice, in its own
Evidence and in the nested inventory Evidence. Like other whole-target
Evidence, these now report no locations.

Visual Studio Code.app: inspect_artifact 15.37 MB to 13.07 MB,
extract_artifact 1.40 MB to 1.06 MB.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 00:47:51 -07:00
YsopwnableandGitHub 782e0147cd fix(javascript): retain returned-reference mutation uncertainty (#1471) 2026-10-10 15:46:24 +08:00
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
5f6bb7a5ba perf(apple): state each NIB object's class, label, and ID once (#1477)
The NIBArchive projection synthesizes customClass, label, and objectID so
its records share the ibtool dictionary parser. The parser then returned
those values as class_name, name, and the object ID, and the graph node
kept the synthesized copies in attributes as well. Attributes now omit a
key whose value its canonical field already carries; differing authored
values stay. Transmission.app decode_interface_builder output shrinks
from 6.45 MB to 6.14 MB.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 00:31:00 -07:00
morluto 2596f8da14 test(android): retry verified cleanup during fixture teardown 2026-10-10 15:29:42 +08:00
morluto b12d0c6361 test(artifacts): respect destination filesystem case sensitivity 2026-10-10 15:29:42 +08:00
N0zoM1z0 cbcba2902d docs(website): align Blog community links with the site 2026-10-10 15:28:13 +08:00
N0zoM1z0 07d416505c docs(website): finalize the Touhou essay for publication 2026-10-10 15:28:13 +08:00
N0zoM1z0 3ea0233342 docs(website): simplify the Blog introduction 2026-10-10 15:28:13 +08:00
N0zoM1z0 cf6957e796 feat(website): link the Blog from the homepage introduction 2026-10-10 15:28:13 +08:00
N0zoM1z0 ed200a2302 docs(website): emphasize the reconstruction essay takeaways 2026-10-10 15:28:13 +08:00
N0zoM1z0 7df2050606 docs(website): write the Touhou reconstruction essay 2026-10-10 15:28:13 +08:00
N0zoM1z0 130ffdf6bc docs(website): outline the Touhou reconstruction workflow 2026-10-10 15:28:13 +08:00
N0zoM1z0 b09d02d93c feat(website): add a blog for methods and project notes 2026-10-10 15:28:13 +08:00
1f0775684b fix(artifacts): keep case-distinct archive names in inventory (#1480)
ZIP member names are case-sensitive. Inventory was folding them with a
filesystem case rule, so shrunk APKs never became evidence for the Android
application graph. Logical registration now keeps both spellings and records
an English Unicode case-folding limitation. Extraction fails only when the
destination directory already holds the other spelling.

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-10-10 15:21:16 +08:00
7296f2b5bf perf(javascript)!: stop repeating the semantic identifier strategy per fact (#1474)
Every semantic graph node and relation carried an identifier_strategy
object whose schema admits exactly one value per record type. The
constant made up about 9% of analyze_javascript_application output
(Obsidian app.asar: 12.04 MB to 10.96 MB), and semantic traces repeated
it on every returned fact.

The node_id and relation_id schema descriptions now state how each
identifier is derived.

BREAKING CHANGE: Semantic graph nodes and relations no longer include
identifier_strategy, and relation IDs no longer hash that constant.
Evidence recorded by earlier versions does not validate against the new
semantic graph schema.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 00:13:34 -07:00
3c7b176a3d perf(artifacts): deliver the inspected artifact graph once (#1473)
inspect_artifact nested the complete inventory Evidence and then restated
every artifact node and occurrence as an observation and every edge as a
derived relationship. No caller reads those copies; comparison and tests
use the nested inventory Evidence. On Transmission.app the result shrinks
from 2.46 MB to 1.10 MB.

Observations keep the root manifest and integrity findings.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 00:12:17 -07:00
aa23ec883f feat(clients): register Qwen Code during setup (#1415)
* feat(clients): register Qwen Code during setup

* fix(clients): honor Qwen home and shared skill discovery

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 15:12:09 +08:00
keemsisiandGitHub 934ffd28d1 perf(javascript): derive the application graph ID once
createJavaScriptApplicationGraph hashed the whole graph to derive its
graph_id, then parsed it with the public schema, whose invariant check
hashed the same content again to verify that ID. Validate the content
with every other invariant first, then derive graph_id once from the
validated copy. The public schema still verifies graph_id for stored
and untrusted graphs, and created graphs are unchanged.
2026-10-10 15:09:18 +08:00
79f6756239 docs(website): link the Discord community and REA on X (#1469)
Add an X link beside the GitHub and Discord header icons on every content
page, name the footer links "Join the community" and "Follow us on X", and
close the homepage with a "Join the community" section.

On narrow screens, pad the footer so the floating Top link no longer
covers its last row of links.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 15:00:09 +08:00
YsopwnableandGitHub 78e1308f49 docs(process): clarify normalized terminal line representation 2026-10-10 14:58:15 +08:00
YsopwnableandGitHub 4e3d335439 test(android): retain incomplete cleanup failure reasons (#1443)
Include the full stop disposition in the fixture assertion message, so incomplete owned teardown retains its typed reason in Vitest failure reporters. Preserve the existing cleanup requirement without retries or relaxed ownership checks.

Seven process-boundary tests, full serial typecheck/lint/duplication/format checks, and 19 final-head CI checks pass after integrating the combined-main fixture fix. A controlled failure-rendering probe verifies that the explicit message preserves the reason. The original CI cleanup failure remains unreproduced; this is diagnostic work with a synthetic JADX producer, not a root-cause or real-engine fix.

Refs #1441, #1446, #1448, #1065.
2026-10-10 14:37:49 +08:00
YsopwnableandGitHub ea92328775 fix(mcp): validate doctor probe against its discovered output contract (#1461)
Validate the target-free probe against the named definition discovered from the complete production catalog. Preserve initialized server and inventory observations when the SDK rejects the probe, and retain the schema failure reason, absolute deadline and owned-child cleanup.

The negative stdio replay regression fails on original main and passes the fix; actual production-boundary fault injection confirms rejection. Nine doctor/help tests, serial full static checks and real small-target CLI/MCP parity pass. Successful doctor reports remain byte-identical. No performance or model-token reduction is claimed.

Closes #1454. Refs #1065, #723, #1433.
2026-10-10 14:33:57 +08:00
morlutoandGitHub 28d3cb545c Merge pull request #1463 from morluto/codex/fix-skill-source-discovery
fix(skills): expose authored skill to repository discovery
2026-10-10 14:28:42 +08:00
b118f04492 perf(apple): stop repeating the archive path in Interface Builder evidence (#1460)
Every Interface Builder node and edge evidence record prefixed its
description with the archive's relative path, which artifact_path in the
same record already states. Bundles carry thousands of objects across
localized nibs, so the repeated path made up 6-10% of
decode_interface_builder output (XLD: 7.38 MB to 6.62 MB).

Descriptions now name only the decoded item, such as "object 81" or
"outlet o_quality".

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 23:21:24 -07:00
ef96657d6b perf(javascript): hash each semantic evidence context once (#1457)
The semantic graph's evidence-context registry canonicalized the full
provenance context three times for every node, relation, unknown and
fingerprint: once to hash its ID and twice more to compare against the
stored row. A file has only a few distinct contexts, so nearly all of
that work repeated a known answer.

Interning now keys contexts by their canonical text. Each fact
canonicalizes once, and only a new context is hashed and checked for a
digest collision. IDs and output are unchanged; Obsidian's 334 MB
Evidence is byte-identical and analysis drops from about 47.0 s to
44.4 s.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 23:21:07 -07:00
morluto 696fb834b8 fix(skills): expose authored skill to repository discovery 2026-10-10 14:20:22 +08:00
2781cad201 perf(process): stop padding rendered terminal lines to full width (#1450)
Rendered frames padded every visible row with trailing spaces to the
terminal width. Blank rows cost a full row each and every frame repeats
them, so the padding made up 14-39% of capture Evidence (2 KB of sparse
output produced 228 KB). The padding carried no information: columns is
recorded and serialized_state keeps the exact terminal state.

Lines are now trimmed after normalization, so line.padEnd(columns)
restores the previous value. The comparison contract commits
rendered_line_format so older padded captures do not compare as the
same contract.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 23:18:13 -07:00
YsopwnableandGitHub c89c8f5318 docs(mcp): record real Windows first-query recovery 2026-10-10 14:05:56 +08:00
1ec490f361 fix(javascript): stop replaying earlier writes for each object property write
Repeated property writes to one object made member-mutation collection
cubic. Each write evaluated its target binding to rule out a primitive,
and every evaluation folded all earlier mutation paths, copying every
slot once per path. 2,000 writes to one object took 27 s and 4,000 took
203 s.

- A recorded write always leaves a non-primitive binding value, so only
  the first write to a binding needs the primitive check.
- Apply mutation paths per slot in one pass with the same ordering
  semantics instead of one full slot copy per path.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: N0zoM1z0 <161784452+N0zoM1z0@users.noreply.github.com>
2026-10-10 14:04:31 +08:00
YsopwnableandGitHub 66863b609f test(javascript): reuse comparison node fixtures
Use the established typed graph fixture constructor while retaining right-hand comparison provenance assertions. Restore the unchanged duplicate-code gate on combined main.

Closes #1446. Refs #1434, #1443, #1065.
2026-10-10 14:02:02 +08:00
morlutoandGitHub 817efaca9a Merge pull request #1391 from marnixpluim/fix/electron-import-aliases
fix(javascript): recognize Electron APIs through renamed bindings
2026-10-10 13:57:24 +08:00
morluto 0d2082d36b fix(javascript): recognize unchanged var and let Electron aliases 2026-10-10 13:56:40 +08:00
morlutoandGitHub f1231d4a2c Merge pull request #1382 from BaaRai/fix/cross-branch-multiblock-callee
fix(ghidra): keep the cross-format branch callee multi-block
2026-10-10 13:50:51 +08:00
morlutoandGitHub a957f397ad Merge pull request #1303 from kvalls/codex/windows-ghidra-native-dlls
feat(ghidra): support native PE DLLs on Windows
2026-10-10 13:50:11 +08:00