Save typed response fields and reuse generated IDs or authentication values across browser scenario requests, UI observations and navigation through the shared CLI/MCP workflow.
Preserve exact numbers, retained Evidence, explicit source/coverage limits and prospective page-value semantics. Bound response decoding, retained spellings and request serialization before allocation, and protect marked response values across source records, follow-up text and planned screenshots.
Integrates Edgar Arakelyan's #7162, including follow-ups through 9f5191ab0. Final local validation: 560 feature-branch tests and 561 current-main integration tests, static/build/docs checks and real PocketBase CLI/MCP privacy workflows. Whole-task comparison and verification limits are recorded in docs/verification/browser-saved-values-2026-10-26.md.
Co-authored-by: Edgar Arakelyan <edgar.arakelyan@scale.com>
* feat(browser): record when scenario requests were observed and how long they took
Request events carry observed_at, the wall-clock time the provider observed
the request start, and finished or failed events carry the browser's
elapsed_ms when it reports one. Both are optional, so earlier captures still
parse, and scenario comparisons leave them out as a committed built-in rule.
The real-Chrome network lane checks every request and finished response is
timed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(environment): time browser scenario records so their state learns a write clock
Scenario records take startedDateTime from when each request was observed and
time from the browser's duration, as HAR entries are timed. A timed scenario
of the book session learns the same clock and serves the same writes as its
HAR; an untimed one keeps record order and learns no clock, as before.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(environment): document scenario request times and timed scenario records
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): start scenario records at the browser's own request start
The provider observes a request up to tens of milliseconds after the browser
starts it while it reads other responses, so a record starting then and
ending after the browser's duration mixed two clocks. Finished and failed
events now carry the browser's started_at, records prefer it and fall back to
observed_at, and comparisons drop it too. Tests cover the fallback for a
request that never ended or ended twice, a partly untimed capture keeping
record order, comparing an untimed capture with a timed one, and the
real-Chrome lane checks every finished request carries the browser's start
and duration.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(environment): document the browser start time, its fallback lag and older readers
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(environment): record the scenario timing verification
Gates, the real-Chrome lane, prompt-recorded and re-recorded published
scenario captures built with and without their times, the stale published
environments left unrepublished, and the review.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(browser): compare timed completion events in the request-time comparison test
The comparison test's captures had no finished or failed events, so dropping
started_at and elapsed_ms from them went untested. The captures now end one
request and fail the other, the test asserts both carry times, compares them
shifted by seven seconds and against an untimed capture, and a control shows
a changed failure on a timed completion is still reported.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
* feat(environment): report what an environment serves with an environment-coverage view
A new inspect_analysis_view kind over capture Evidence. It projects the
state an environment derives with the given template rules and reports
each tool as answered from state, replayed with its view reason, a served
write, or a withheld write with its reason, the records behind it and a
hint about what to record next. The hints cover every write reason, so a
new reason without one fails to compile.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(environment): build an environment bundle in one command
rea environment-build <capture> [directory] inspects a HAR (or reads
capture Evidence), projects the environment manifest from the in-memory
Evidence, authenticates the pair, prepares the state and writes the bundle
environment-export writes. Every bundle file is byte-identical to the
three-step path for the same capture and options.
The report adds the capture and manifest identities, the coverage summary,
warnings (a loopback capture named after its file, credential-named body
members by pointer) and the next command. --dry-run writes nothing. The
default template rules are the four the published environments use.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(environment): cover environment-build and the coverage view
Domain tests check the hint table against the state view's reasons, the
summary, and the view against the environment-state view it summarizes.
Service tests build the fixture capture and compare every file with the
three-step path, a dry run, loopback naming and the refusals. A CLI test
compares a HAR built in one step with the three CLI steps byte for byte,
and an MCP test projects the view from every source kind.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(environment): build the real-agentenv lane's bundle with environment-build
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>
* docs(environment): document environment-build and the coverage view
The agent environments guide opens with the one-step build: the report,
the hint for each withheld write reason, and what a bundle ships. The CLI
guide, the capture guide and the skill reference name the command and the
environment-coverage view.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): harden environment-build after review
- The credential scan walks with its own stack, so a deeply nested body
cannot crash the build, and it also reports credential-named header
names, query names, form body members and string arrays.
- The build checks SIGINT between stages: cancelled before the bundle
stage it writes nothing, during the write it names the written bundle.
- A dry run opens the package tarball, so it refuses what a build refuses.
- Repeated template rules are refused, a HAR saved as .json gets a hint,
file-derived names follow the bundle name rules, `localhost.` counts as
a loopback origin, and the next command is shell-quoted.
- --capture-timeout-ms passes through to the HAR inspection, and a
missing directory is refused before inspection.
- The no-observation hint covers updates and deletes of entities the state
never held; the coverage view states that it does not apply the
serve-time admission checks; the inspect_analysis_view description
names the view.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(environment): state the build's conditions and record its verification
The guides now state when the one-step bundle equals the three-step one,
which headers inspection excludes, what the credential warning scans, how
cancellation behaves, and that the coverage view does not apply the
serve-time admission checks. The spec folder records the census, the end
to end runs, the gates and the review.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): dispatch a pending interrupt before each build stage check
The manifest, state and coverage stages run synchronously, so a SIGINT
that arrived during them was only dispatched once the bundle write had
begun. Each check now yields first, so an interrupt before the bundle
stage cancels the build with nothing written.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(browser): send declared requests from a scenario page with a request step
A capture_browser_scenario step `request` sends one declared HTTP request
through the page's own fetch, with its cookies and session, the way the
application's frontend would, and reads the whole response so the capture
records the transaction like any other. The path must resolve to the start
URL's origin, and the page must be on that origin when the step runs.
Query values and header values may be literals or declared secrets, and a
header may read its value from a cookie or a local storage entry, which is
then redacted from later records like a declared secret. `expected_status`
fails the step on any other status. Scenarios without a request step are
unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(browser): verify request steps in a real browser through to a built environment
verify:browser:request records a write session against a fixture item API
that refuses writes without its CSRF cookie header and stored bearer
token. It checks that every request lands in its own step, that the page
values authenticated each write and appear in no record, header or body,
that an unexpected status fails the step and cancels the rest, and that
environment-build serves the recorded create, update and delete.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(environment): export environment bundles over MCP
export_environment_bundle writes the bundle environment-build writes, from
capture Evidence retained in the session or one capture Evidence file,
into an absolute output directory that must not exist and whose parent
must exist, as extract_firmware and export_web_scripts require; it never
creates the parent or reuses a directory. It returns the same report,
whose schema now lives in the domain so the CLI and the tool share it, and
dry_run reports without writing. A loopback capture without a file needs a
name. The build's refusal messages no longer name CLI flags.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): scan scenario credentials, own the dry-run tarball and serialize Evidence once
A browser scenario's retained header values and the query parameters of its recorded URLs are scanned for credential
names as a HAR's are, through a review projection of its records. A dry run admits and releases the package tarball
through the export's regular-file scope, so a close it cannot confirm keeps its owner, and checks for cancellation
after that last await. Evidence is written into one exactly sized buffer instead of chunks joined by a copy.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(environment): record the review round's checks
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(skill): build agent environments from a prompt with request steps and the bundle tool
Add the environments reference to the skill and install it with setup: record
against a disposable instance, sign in through the UI, write with request
steps and read each write back, check coverage, re-record by withheld reason
and export the bundle. Route it from SKILL.md, name agent environments in the
skill description, and document the request step, the export tool and
recording writes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(browser): split the request lane and header resolution into smaller functions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* style(environment): format the build spec
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): say when an untimed capture learns no write clock
Coverage of a capture whose records are not all timed, which includes every
browser scenario capture, now states that the state learns no clock, so an
update stamped with a server-set modification time stays unexplained-change
however often it is recorded.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(skill): give agents a whole scenario shape with step timeouts
Agents guessed the scenario schema field by field and two hung on steps
without timeout_ms. The reference now starts from a complete scenario with a
timeout on every step, and says a scenario capture cannot serve updates the
application stamps with a modification time.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(browser): keep request steps on their origin and their page values redacted
- Follow no redirects: a redirect fails the step and nothing reaches the
location it names (checked in real Chrome), and check the page's origin
again in the page as the request is sent.
- Send nothing once the step's time has run out or it was cancelled while
header values were read; the in-page deadline is what remains of the step's.
- Keep every page value redacted under a repeated or colliding label, keep a
value's first marker when it is read again, and leave values shorter than
8 characters unredacted rather than rewriting ids, ports and hosts.
- Refuse a header name given twice, User-Agent (Chrome drops it) and line
breaks in literal values and prefixes; fail before sending when a secret or
page value holds them.
- Append query entries after the path's literal query without re-encoding it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(environment): document request step limits and word bundle refusals for both surfaces
Document redirects, timeouts, page value redaction, HttpOnly cookie sources
and header refusals for request steps. Refusals shared by environment-build
and export_environment_bundle no longer name CLI flags, and the retained
loopback refusal no longer prints an empty file name. The skill reference
asks for read-backs after each write, shows the coverage view's source, names
package_tarball for unreleased builds and the browser path a scenario ships.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): scan every form occurrence and MIME-less scenario bodies
The build's credential scan collapsed form bodies with Object.fromEntries, so a
repeated field kept only its last occurrence: `api_key=secret&api_key=` warned
about nothing although the Evidence ships the value, and repeated values were
undercounted. Form fields are now scanned as ordered name/value pairs, as
headers and query strings already are.
The review projection of a capture_browser_scenario dropped a request body
recorded without a media type, so the scan never saw it. Review keeps such a
body's text with an empty media type; the manifest projection still reads only
bodies it can classify.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(browser): close request step edge cases from the second review
- Append query entries correctly after a path ending in "?", "&" or "#".
- Refuse 3xx expected statuses, which an unfollowed redirect can never
report, and say a redirected write may already have been applied.
- Redact a page value also as fetch sends it, without surrounding spaces
and tabs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(environment): document page value body costs, redirects and MCP dry runs
Document that reading a page value shrinks the bodies a capture keeps under
the default allocation limit, that redirected writes may have landed, that
the MCP dry_run still checks its output directory and which refusals name
the tool, and keep the .har hint in the HAR-as-JSON refusal for both
surfaces.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(environment): record the prompt-to-environment verification
Gates, the real-browser lanes, five environments built from prompts by an
agent on disposable VMs and evaluated with two models, and the two reviews.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(skill): count rollback failures from the managed skill files
The environments reference made the skill eight files, so the recovery tests now derive the counts they expect from
MANAGED_SKILL_FILES instead of fixing them at six and seven.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(adb): restore the portable Java float pattern a merge rewrote
A lint autofix during a merge unescaped the hyphens in javaFloatValuePattern, which is invalid in a v-mode character
class, so the advertised start_adb_activity schema failed to compile in every JS regex mode. The file now matches main.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(browser): show the request step inside a whole scenario
Every JSON example in the browser scenario guide is a capture_browser_scenario input the catalog test parses, so the
request step example now sits in a launch scenario instead of standing alone.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): scan structured HAR form params and the request side of unattributed scenario transactions
A HAR request recorded with postData.params and no text is scanned by those parameters, each occurrence counting, and
the review projection keeps the request side of a scenario transaction whose response cannot be attributed, so the
credential warning covers what evidence.json ships in both cases.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): validate build paths and read dry-run tarballs
* fix(environment): report bodies too large for the credential scan
Text bodies over the scan's 4 MiB limit, including a response decoded only as a prefix, are reported as a
credential-scan-incomplete warning by record and side, never by content, so an absent credential-named-members
warning no longer reads as a complete check. The spec and agent-environments guide also state the path validation and
dry-run tarball read that e52ae1cd added.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(verification): release cold source transform services
* fix(javascript): retain capture context along covered mutation paths
* fix(environment): guard request dispatch and report export limits
* fix(environment): admit serialized exports and scan HAR form fallbacks
* fix(environment): admit in-memory build inputs against heap headroom and scan SaveHar null-text forms
The inspected HAR's Evidence and the projected manifest are checked against live heap headroom before they are
serialized, with the same check the file route uses, so a capture too large to parse and seal is refused as
resource_constraint before anything is written. A request whose postData text is SaveHar's null is scanned by its
structured params.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): measure the credential scan limit in UTF-8 bytes
A body counts against the 4 MiB limit by its UTF-8 length, not its UTF-16 code units, so multibyte text over the
limit is reported as unscanned instead of parsed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(browser): send request steps only before their deadline and keep page reads on the start origin
The page receives the step's absolute deadline and a one-second start window, so a busy page that runs the request
late, or after the step is cancelled, sends nothing; local storage is read only on the start origin; the response is
drained without keeping its body; an unparseable path is a field issue; retained Evidence is refused for heap headroom
before it is serialized; and the skill says how to reach server-assigned ids.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* style: format integrated export admission
* fix(javascript): erase inline type imports before binding values
* fix(browser): run the request lane under the shared verifier command owner
The browser request lane runs each CLI call through createPackageVerifierCommands on a private runtime root, so a
timeout, output overflow or failure stops the CLI and the browser it launched before the root is removed, and a failed
stop is reported with the root retained. The verification record states the lane's current counts.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(environment): scan scenario content by event and read bodies by their media type
A browser scenario's credential scan reads every retained network-content event, including a response attached
mid-flight and a transaction no record represents, with event pointers, and each transaction URL's query once; the
review record projection it replaces is removed. A body is parsed as a form or as JSON by its recorded media type,
falling back to its shape, so valid forms such as `password=x&` are scanned and sentences are not read as forms.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
Derive exported Docker image versions from .nvmrc through generated package metadata. Align active setup translations with patched Node release floors and verify actual CLI exports, real Docker/agentenv, package and website workflows.
Eight built-test shards pass; three unrelated managed source failures reproduce on clean main and remain tracked in #6650.
Refs #6480
Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
* fix(mcp): escalate transient failures before asking for a restart
Give dropped connections and startup failures one bounded retry, then a
scripted handoff to the user. Point timeout recovery at a named request
field or REA_* setting instead of telling agents those limits are fixed.
Co-authored-by: morluto <morluto@users.noreply.github.com>
* fix(process): stop unexpected command failures from recommending a retry
The catch can already have launched the target, and the projection stays
non-retryable. Tell the user to check the inputs and run doctor instead.
Co-authored-by: morluto <morluto@users.noreply.github.com>
* fix(mcp): limit retries to safe calls and recommended settings
A dropped connection may already have changed the target, and a bad
catalog rejects the same startup every time. Retry only a repeatable
call, and change a setting only when the remediation recommends it.
Co-authored-by: morluto <morluto@users.noreply.github.com>
* test(mcp): match recovery guidance across wrapped lines
Startup handoff capitalization and markdown wrapping still carry the
same sentences. Compare the prose with whitespace collapsed.
Co-authored-by: morluto <morluto@users.noreply.github.com>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: morluto <morluto@users.noreply.github.com>
Teach client deadline recovery before REA results can be discarded, distinguish
producer-owned server budgets, and preserve Evidence/cleanup uncertainty.
Include actual Codex CLI recovery probes and CLI/MCP regression coverage.
Fixes#5598
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)
Explain process-scoped startup settings in shared CLI/MCP timeout guidance and the bundled skill. Preserve Evidence and cleanup before restarting REA, reconnect MCP, and allow enough client request time.
Validated with focused tests, static/docs/package checks, real Ghidra CLI/MCP recovery, and a completed 591-second EXE analysis under CPU and memory limits.
Route user browser actions to passive observation and agent actions to declared scenarios. Clarify requested artifacts, step outcomes, connect navigation and cleanup, and the limits of listener and request-initiator evidence. Distinguish discarded raw headers from retained response metadata. Update the bundled skill to version 42 with matching package metadata.
Validation on the synchronized revision: docs (5 tests), typecheck/lint, formatting, 61 focused tests, and real Linux Chromium launch/connect and passive CLI probes. Verified declared steps, requested artifacts, digests, external page preservation, temporary form reset and cleanup. Native Windows/macOS and separate follow-up tools were not rerun. Package install/update and CLI/MCP verification passed earlier on 738d02a, before this main sync.
Co-authored-by: 0xRafie <155859586+0xRafie@users.noreply.github.com>
Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Inspect bounded recorded raw HTTP/XML SAZ archives and page retained capture Evidence. Preserve exact stored bytes and provenance, validate ZIP/XML integrity, and require an enforceable decoder memory bound.
Verified 356 real recorded sessions against independent byte and metadata oracles, public CLI/MCP parity, retained pages, and related interface checks. Current Fiddler Everywhere GUI and non-Linux producer workflows remain unverified.
Co-authored-by: zahhak <1792039+zahhak@users.noreply.github.com>
Co-authored-by: N0zoM1z0 <161784452+N0zoM1z0@users.noreply.github.com>
Put setup, developer commands, MCP replies, and investigation recipes before
client details and implementation references. Preserve existing guide anchors,
examples, provenance, partial-result recovery, and provider restrictions.
Correct verified documentation drift, synchronize the Ghidra capability
wording, and regenerate metadata for skill version 40. Keep uncertain platform
and lifecycle findings unchanged. Refs #2156.
Validation: 56 focused tests, check:fast, docs:check, VitePress production build,
format and link/example checks. Real isolated CLI/MCP probes cover Ghidra,
NativeAOT, HAR, cancellation, Chrome, large ELF delivery, native type limits,
and the new JS/managed/process/setup recipes. Heavy work uses two CPUs;
a resource-heavy DOM probe was stopped and replaced by a smaller real CDP
payload-limit control. Windows, macOS GUI, ADB, and the full CI matrix were
not executed.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat(native): admit raw binaries with caller-supplied architecture and entry
* fix(native): honor raw-binary preparation and entry identity
* fix(ghidra): stream raw snapshot attestation with cancellation
* fix(native): preserve and validate raw lifecycle entries
---------
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
Guide task-centered recovery from observed client, registration, PATH and
provider blockers. Install the recovery reference, document exact JavaScript
module selectors, and require clarification before searching for an unnamed
app. Validate public setup in isolated Codex accounts and preserve failed
or unrecognized tool outcomes in the existing evaluator.
Refs: #1587
BREAKING CHANGE: Optional verify:agent reports now use schemaVersion 4.
Consumers must accept expectedFirstTool: null and targetClarificationPassed
for missing-target scenarios. Production CLI/MCP contracts are unchanged.
The skill's CLI fallback printed the complete application Evidence to
stdout. A real ASAR produces hundreds of megabytes (334 MB for Obsidian),
which an agent then reads into its context. Save the Evidence to a file
and project a summary or module page with inspect-analysis-view instead.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Add explicit summary, facet, item and paged views of retained analysis Evidence without repeating analysis. Preserve captured observations, graph validation, artifact identity, coverage and complete default results.
Fixes#1050
Verified with focused source, CLI, pinned-SDK schema and MCP tests, serial static checks, and one complete native Windows Notion ASAR workflow. Real Hopper/Ghidra verification was not performed for this provider-independent projection change.
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
* chore(release/6.0.0): release rea-agents 5.1.0
* chore: normalize release product catalog
* chore(release): correct 6.0.0 candidate and migration notes
Keep the recorded application checkpoint unchanged. The upstream history walk
stops at the merged side-branch release commit and omits older unreleased main
commits; restore the missing notes and absolute-path migration instructions.
Set all release metadata to the agreed SemVer 6.0.0.
Assisted-by: Sakuya (gensokyo-skills:sakuya-checkpointed-execution)
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: N0zoM1z0 <1705004398@qq.com>
* 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
main now carries #1037 (skill version 30, reworded native binary row):
- README_ja/ar/ko/zh: take main's tables and count
trace_dylib_resolution in the artifact graph row (5 -> 6).
- Skill: move to version 31.
- Regenerate the product catalog, conformance manifest, skill digest and
package metadata (137 tools).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
main now carries #964 (skill version 29, macOS native row 7 -> 8):
- README_ja/ar/ko/zh: take main's tables and count
trace_dylib_resolution in the artifact graph row (5 -> 6).
- Skill: move to version 30.
- Regenerate the product catalog, conformance manifest, skill digest and
package metadata (136 tools).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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 <noreply@anthropic.com>
Resolve conflicts against main:
- 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
trace_dylib_resolution in the artifact graph row (5 -> 6).
- Skill: the references gain the trace_dylib_resolution 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 <noreply@anthropic.com>
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 <noreply@anthropic.com>
Add trace_dylib_resolution (CLI trace-dylib-resolution) to the artifact
family. For the active Mach-O, or every executable in the active .app
(the main app, XPC services, extensions, login items, helpers), it
reports which file each dylib load reaches and how.
A pure TypeScript reader decodes FAT and Mach-O load commands:
LC_LOAD/WEAK/REEXPORT/LAZY/UPWARD_DYLIB, including the newer
dylib_use_command encoding with weak, re-export, upward and delayed-init
flags, plus LC_ID_DYLIB, LC_RPATH, LC_DYLD_ENVIRONMENT and code-signature
presence. Malformed tables are reported with the failing command instead
of being guessed.
Resolution follows dyld:
- @executable_path comes from each process root;
- @loader_path comes from the loading image, or from the owner of the
LC_RPATH entry being expanded;
- @rpath searches the loader's rpaths first, then up the load chain;
- dependencies load dependents-first in load-command order, once per
process, and a matching install name reuses an already loaded image;
- symlinks are followed inside the analyzed root, and escapes stop.
Every candidate path is reported with its outcome. Each edge resolves to
resolved, conditional (an outside-root candidate such as /usr/lib/swift
precedes), unresolved, or undetermined. Absolute and shared-cache system
paths are never checked against the host. Derived findings cover
unresolved required or weak loads, absent earlier @rpath candidates (with
library validation left unknown), and LC_DYLD_ENVIRONMENT.
verify:macos-bundle now also:
- checks every traced image against otool -l;
- asserts each resolution status on a clang-built fixture that adds a
missing Overrides rpath, an absolute rpath, and a delay-init library;
- compares the predicted load order of two process roots with what dyld
loads under DYLD_PRINT_LIBRARIES.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
project_apple_application_graph accepted only IPA inventories. It now
also projects macOS .app directories and ZIP or DMG inventories that
contain applications. It reports application roots, platforms, and
every nested bundle with its path-convention role, layout, parent,
Info.plist path, executable candidates, and signing paths:
- roles: app extensions, XPC services (including inside frameworks),
frameworks, login items, system and driver extensions, plug-ins,
resource bundles, and helper or nested applications;
- privileged helpers in Contents/Library/LaunchServices and launchd
plists in Contents/Library/LaunchAgents or LaunchDaemons;
- direct files of Contents/Helpers;
- symlinks by path. Their targets are not inventoried, so versioned
frameworks are described through their real Versions/<version>/
directories.
AppleDouble sidecars (._* and __MACOSX/) are excluded from roles. A DMG
whose contents could not be inventoried is reported as partial. Other
inventory formats remain input errors. The projection still reads no
plist or CMS semantics; it points callers at inspect_plist.
The result schema is additive. projection_id now covers the new fields,
so IPA projection IDs differ from earlier versions.
verify:macos-bundle compiles a source-owned app with clang (CLT only).
It packs it as a directory, a ditto ZIP, and an APFS DMG, and checks
identical anatomy through the CLI with stdio MCP parity. It runs in the
macOS CI job.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* 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
typescript 5.9.3 to 7.0.2, vitest 4.1.10 to 5.0.3 (plus
@vitest/coverage-v8 and @fast-check/vitest 0.5.0 for peer compat),
@Modelcontextprotocol/client and server 2.0.0 to 2.3.1. Migrate the
removed describe.sequential to concurrent:false and regenerate
package metadata and product catalog.
Also restore byte-faithful reads in parseCliJsonInput: the safeJson
migration dropped the fatal UTF-8 check from #613. Vitest 5 requires
Node 22/24/26+, so verify on Node 24 (repo-pinned toolchain).
## Changes
Related to #545 and the permission-system removal in #555.
- Upgrade the shipped skill to v24 and remove obsolete filesystem grants, per-call approval flags, Electron file-root configuration, and DMG approval flags. Calls follow the user-requested investigation directly. Keep setup plan confirmation, actual OS requirements, and process/archive lifecycle boundaries.
- Correct the passive browser guide: endpoint/scope come from requests; ordinary local URL queries are retained, while credentials remain redacted.
- Audit canonical tool effects: declare possible DMG process/temp-directory effects, mark fresh extraction non-idempotent, and mark comparisons of supplied captures/PNGs as closed-world. Align artifact-provider capability effects with temporary mount-directory writes.
- Retain non-read-only hints for calls that add Evidence to the session; document that annotations are hints and that clients control their confirmation UI. Do not mislabel session mutations as read-only to suppress prompts.
- Regenerate package, skill, MCP, and product metadata from source.
## Verification
- `npm run test:focused -- <11 affected test files>`: **40 tests passed**, including skill transaction/backup/idempotence, SDK tools/list annotations, actual local capture/PNG comparisons, artifact extraction/containment/cancellation, DMG launcher/cleanup seam, setup confirmation, browser MCP and scenario MCP, CLI catalog parity.
- `npm run check`: typecheck, lint, format, knip, package metadata.
- `npm run docs:check`: generated catalogs, skill metadata, documentation facts, completion ledger, error schema.
No local real Hopper/Ghidra run: their adapters and analysis operations are unchanged. Native macOS DMG behavior is covered locally through the launcher seam; no local macOS/hdiutil claim is made.
Real browser verification passed using existing Headless Chrome143.0.7499.4: actual CLI/stdio MCP,9,331,407-byte PNG, passive capture/source maps, and owned/external scenario cleanup. An initial full Chrome143 run failed the existing screenshot-height assertion (1397 versus1536); the dedicated headless-shell run passed the complete verifier without code changes. The verifier run-lineage field remained unavailable; no lineage-coverage claim is made. Browser download into `.codex` was blocked by CDN403, so the successful run used an existing browser without changing host configuration.
