Route six artifact verifiers through the canonical complete MCP output and error parsers. Remove duplicated JSON/schema interpretation while retaining Evidence authentication, provider provenance, independent CLI parsing and CLI/MCP parity checks. Validate malformed success/error envelopes at the shared boundary.
Validation: 11 boundary tests, Go compiler verifier (30 cases), and synthetic IL2CPP/Flutter verifier workflows passed; typecheck/lint passed. PCAP readiness passed with stub tools, but capture inspection is unsupported on macOS. Linux-only binary-layout and EVM verifier toolchains were unavailable.
Upgrade Zod to 4.6.6 and refresh locked license inventories. Preserve REA's established timestamp spellings through one shared UTC/offset grammar, including completion-verifier consumers. Size the stdin resource regression from the child's actual heap capacity.
Fixes#7173
Includes the dependency and inventory changes proposed in #7184.
Co-authored-by: tijo95 <georgesarmede@gmail.com>
Scope MCP discovery, setup, doctor, status and recovery guidance by selected tool families using one contract inventory and shared catalog identity. Preserve default discovery, canonical validation and complete Evidence.
Fixes#3246. Builds on #3026. Real libcrypto workflow verifies all 5,367 exports and identical complete Evidence. Static/source/build/docs/Windows/package/Greptile checks pass; ten assertions reproduced identically on clean main and feature across Node 24/22, with cancelled coverage explicitly unverified. Merge uses the user-authorized bypass for baseline failures and unchecked human-readiness declarations, without attesting human review.
Co-authored-by: 0xLLVEL <fakhrezan1@gmail.com>
Co-authored-by: Codebuff <noreply@codebuff.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add opt-in bounded output-schema advertisements while preserving the full default, canonical server validation and complete structured content. Verify real stdio discovery under a 1 MiB receive cap, all 5,367 libcrypto export coordinates, complete Evidence parity, whole-task serialization estimates and resource bounds.
Fixes#2512. Integrates #7054 by Akshad Jogi with original authorship retained.
Co-authored-by: Akshad Jogi <akshadjogi@gmail.com>
Move shared request parsing into its application owner, migrate all consumers, and remove six duplicated admission blocks while preserving cancellation and validation policy.
Keep operator-selected JavaScript paths in verifier parent Evidence while retaining canonical comparison guards. Validated with 204 passing tests, 3 Linux-x64-only skips, typecheck, lint, and test discovery.
Share ordered schema positions between Gemini literal checks, DeepSeek regex
checks, and catalog array-shape checks. Reuse the canonical keyword and local
reference owners; keep unreferenced instance literals opaque and unresolved
external or dynamic targets unknown.
Gemini and catalog checks now catch constraints in schemas reached through
references into examples. Preserve source paths, resource scopes, cycles and
regex occurrence counts. Align fixture first-error selection with the native
Gemini check and use consistent bracketed array locations in diagnostics.
Validation: 55 focused tests passed, including full/compact MCP catalogs;
typecheck, lint, discovery, and Node source-loader checks passed. The old
Gemini scanner reproduced the local-reference false negative. Installed
Gemini and DeepSeek clients were not run.
Migrate twelve application service files to the existing provider input owner,
preserving schema causes, cancellation precedence, caller selection, and
retained Evidence. Keep flows with distinct error policies separate.
Replace the DeepSeek verifier's recursive object scan with schema-position
traversal using the canonical keyword and local-reference owners. Literal
pattern fields no longer cause false regex failures; patternProperties keys
are checked alongside actual pattern constraints in native regex modes.
Validation: 271 focused workflow/service tests and six verifier regressions
passed; static checks, discovery, and actual Node source-loader smoke passed.
The baseline scanner reproduced the new regressions. Installed DeepSeek client
execution was not run.
Centralize ELF section and Godot trailer declarations while preserving caller admission policies. Route six PE entrypoints through canonical DOS ownership so relocation data cannot establish a PE header, and update NativeAOT interpretation identity and verifier dependency coverage.
Share exact ELF program-header facts across nine consumers while preserving their admission and precision policies. Centralize conformance path and digest binding, retain verifier-specific checks, and route fixture-owner changes to CI qualification.
This reverts commit 7336a566ac (#7119).
After #7120 and the other merges of 2026-10-25 grew inspect_analysis_view's
complete input schema (71,762 bytes plus 3,003 bytes of examples), the 64 KiB
fitting from #7119 could no longer keep instance level 3 and fell back to
level 2. That summarized the inline Evidence source and the view selector
collections, so main CI failed in toolInputReferences, toolSchemaValidity,
analysisViewMcp, absoluteLocalPathSchema, javascriptFactsViewMcp and
godotPckMcp. #7119's own CI ran against bc143125e, before that growth.
Reverting restores the complete full-profile advertisement while the size
limit is redesigned against these contracts (#4081 stays open).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Refs: #7135
* fix(mcp)!: return a compact binary_session status by default
binary_session {} with no target open returned about 66 KB, most of it
provider rejection diagnostics and candidate capability sets that the
skill's recovery flow re-reads on every retry. 6.8.0 grew it by 21%
because the shared regex capability limitation began repeating setting
bounds and step-by-step recovery for every search operation of every
provider (#6099, #6267, #6301, #7049) and IDA gained that limitation for
its two search operations (#4862).
The regex limitation now states the effective deadline and heap, their
sources and where to change them; the deadline and heap errors keep the
full recovery. binary_session gains detail: summary (default) or
complete. The summary keeps open state, target identity, the binding,
route capabilities, run, activity and health status, each candidate's
availability and target-support status, code and reason, and every
tool's availability, reason, remediation and modes, and lists the
fields it leaves out in omitted_fields. Complete detail returns the
previous shape. The CLI capabilities and providers commands keep
complete provider facts through the same application projection.
BREAKING CHANGE: binary_session {} no longer returns
analysis_provider_candidates[].availability.diagnostics,
target_support.diagnostics or capabilities, or tool_availability group
surface, effects and annotations. Pass {"detail": "complete"} to get
them.
Fixes#7109
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): key binary_session output fields by detail
The output schema accepted detail: "complete" with summary candidates or
tool groups, and a summary without omitted_fields, so detail did not
tell callers which fields existed. Each session kind is now crossed
with a detail-specific shape: a summary requires omitted_fields and
summary-only candidates and tool groups; complete requires diagnostics,
candidate capabilities and static tool flags and forbids omitted_fields.
Both the canonical schema and the SDK-validated advertised schema reject
mismatched shapes.
The verifier helper accepts summary candidates only for a validated MCP
summary; CLI provider output still requires candidate capabilities.
Regex limitation tests check values, sources and setting names instead
of whole sentences.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): fit every advertised input schema within the 64 KiB client limit
Claude Desktop drops a local connector tool whose compact-JSON input
schema exceeds 64 KiB. The full input profile advertised
compare_web_captures at 171,867 bytes and inspect_analysis_view at
71,632 bytes, because the self-contained projection inlines the
complete producer capture schemas once per side.
The full advertisement now fits the limit at its producing boundary.
A property whose schema repeats an earlier sibling's points at it, and
schemas below the deepest instance level that fits are summarized as
their types, size constraints and descriptions. Every rewrite widens the
advertisement through the existing relaxation rules for oneOf, not,
if/then/else, contains and unevaluated keywords, so canonical inputs
stay accepted and the canonical contract still validates every call.
Schemas within the limit are unchanged, and the compact profile is
still presented from the complete projection.
Numeric const and enum literals are also relaxed in the advertisement,
like boolean literals, since Gemini accepts only string enum members.
Fixes#4081
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): keep fitted input summaries widening and at the deepest fitting level
Array summaries took item types only from `items`, so a tuple such as
`{prefixItems: [{type: string}], items: {type: number}}` was advertised
as a number array that rejected `["a", 1]`. Item types now include tuple
positions from `prefixItems`, a draft-07 `items` array, and
`additionalItems`, and stay unconstrained when later elements are open.
A summary can also be longer than the schema it replaces (a nullable
array becomes an anyOf), so candidate size is not monotone in the
retained depth and stopping at the first overflow could skip a deeper
candidate that fits. A schema is now kept whole when its summary is not
smaller, and fitting searches from the deepest level down.
Property tests check that every summary accepts what its schema accepts
over every catalog input subschema and synthetic tuples, and that the
fitted schema is the deepest fitting candidate. The browser comparison
boundary test now expects a malformed `after` capture to be rejected
canonically, since `after` is advertised as the same schema as `before`;
the same malformation on `before` stays advertised-invalid.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat(binary-layout): admit ELF32 i386, ARM and MIPS layout profiles
inspect_binary_layout refused every ELF32 object, so router and IoT
firmware (ARM32, MIPS32) got no layout facts at all.
The pwntools adapter now admits EXEC/DYN/REL objects in these profiles:
ELF64 x86-64, ELF32 i386, ELF32 little-endian ARM and ELF32 little- or
big-endian MIPS. Header fields are read in the declared byte order, the
ELF32 header is bounds-checked at 52 bytes, and pwntools' own reported
architecture, class and byte order must match the admitted profile.
Other machines, classes and byte orders keep an unsupported_target
refusal that names the admitted profiles.
The output schema admits exactly those architecture combinations, and
the Evidence subject now names the reported machine instead of always
claiming x86_64.
verify:binary:layout cross-compiles i386, ARM, MIPS and MIPSel
executables and relocatable objects (never executed) and checks every
section name, address, offset and size against GNU readelf through CLI
and MCP. The real-binary-layout workflow installs those toolchains.
Refs #6934
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* ci(binary-layout): install target libc headers for ELF32 fixtures
--no-install-recommends skips the libc6-dev-*-cross packages the cross
compilers only recommend, so the i686 fixture fell back to the host's
/usr/include and failed to find bits/libc-header-start.h. Install the
four target libc development packages explicitly.
Refs #6934
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(binary-layout): size the minimum symbol entry by ELF class
The relocation reference check required a 24-byte Elf64_Sym entry, so
every positive symbol reference in an ELF32 report was refused as
unreadable output. Elf32_Sym is 16 bytes; take the minimum from the
reported class. A 64-bit table with 16-byte entries is still refused.
Refs #6934
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(binary-layout): compare ELF32 symbols and relocations with readelf
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
Preserve GitHub User metadata for Copilot while excluding it from generated human thanks and accepted prose credits. Extend the real inventory/render/check regression and document the known agent identity.
Convert native directory separators only at Git patch argument production. Exercise fresh, applied and invalid dependency patches in private copies, preserving protectNTFS, and select the regression for Windows CI.
Replace the spelling-based mock inventory with one binding-aware Oxlint rule. Canonical test projects own isolation for both Vitest and lint; external temporary CLI probes avoid concurrent test discovery.
Validated actual local Git and Oxlint execution, resolved-policy parity, CI selection and report tests. Native Windows verification remains with CI. Refs: #7050
Remove the redundant async declaration from the Ghidra session assertion helper so its existing callers receive assertion failures within their synchronous error boundary. Keep call order unchanged.
Validation: a public-helper Node subprocess accepts authored valid handshake facts and rejects incomplete analysis and a target-digest mismatch. The regression failed for the original async declaration with Missing expected exception, then passed with the fix. No installed Ghidra execution was performed.
overflow into the remediation and ended the reason with the session
continuation sentence, but the real-Ghidra boundary check still required
the old reason text, so every lane that runs verifyGhidraBoundaries failed
on real Ghidra.
* fix(android): report DEX static values of static final fields
Fixes#6397
* fix(android): request DEX static values only for class inspection
* fix(android): range-check wide DEX static values
* fix(android): move the bridge to version 7 after main took 6
---------
Co-authored-by: Abelo9996 <Abelo9996@users.noreply.github.com>
* feat(artifacts): inventory and extract Node.js single executable application blobs
Adds a node-sea artifact reader that locates the NODE_SEA_BLOB payload in
Mach-O sections, ELF notes and PE RCDATA resources, decodes the blob
header, main script, optional snapshot and code cache, and named assets,
and extracts their stored bytes through the existing safe output tree.
The executable is never run. Resource-tree errors in a PE without a
NODE_SEA_BLOB name stay with native classification; truncated, unknown
or over-limit SEA declarations fail closed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016y53PdpyMAp9RSW65fatHe
* fix(artifacts): reuse PE resource facts and bound SEA asset tables
Move the bounded NODE_SEA_BLOB name probe into the shared PE resource
layout module so SEA admission uses the same header and section mapping
as the full parser; the layout reader now accepts a header prefix with
the file size. Bound SEA asset count and decoded name bytes before
records are created and report resource bounds as limit failures. Offer
the JavaScript next probe only for main scripts with a source suffix.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016y53PdpyMAp9RSW65fatHe
* fix(artifacts): make SEA metadata construction cancellable
---------
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: morluto <76467478+morluto@users.noreply.github.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(firmware): inspect flattened devicetree blobs
Adds inspect-devicetree and inspect_devicetree for FDT v16/v17 blobs
without target execution or external dependencies. Results include
validated headers, reservations, a node/property tree with bounded raw
previews, and derived standard values and selected phandle references.
Parsing enforces file, tree, and decoded representation budgets and
rejects malformed input without partial success. Summary delivery
supports retained Evidence pagination, with tests covering parsing,
service validation, CLI delivery, and MCP access after the input is
removed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016y53PdpyMAp9RSW65fatHe
* fix(firmware): reject conflicting devicetree phandles and bound page summaries
A node whose phandle and linux,phandle disagree no longer resolves under
either value; the conflict is reported as a limitation. Finalization
failures after a completed read retain the file-snapshot-hash partial
observation, matching the Go provider. Devicetree view pages carry
fixed-size context and counts instead of repeating summary strings, so a
large bootargs no longer pushes every page over the MCP response budget.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016y53PdpyMAp9RSW65fatHe
---------
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: morluto <76467478+morluto@users.noreply.github.com>
* feat(elf): inspect Linux kernel module metadata
Adds inspect-kernel-module and inspect_kernel_module for ELF32/ELF64
ET_REL Linux kernel modules, read statically without executing them.
Reports ordered .modinfo entries with duplicates preserved, __versions
symbol CRCs, the presence of .gnu.linkonce.this_module and __ksymtab,
.init.text and .exit.text sizes, and an appended module signature
trailer with its PKCS#7 byte range and SHA-256. gzip, xz and zstd
containers are reported unsupported with external decompression as the
next probe. Malformed headers and exhausted entry budgets return no
partial success.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016y53PdpyMAp9RSW65fatHe
* fix(elf): bound kernel module ksymtab listing and tighten contracts
Charge listed __ksymtab* sections against max_entries, omit section names
longer than 256 bytes with ksymtab_name_exceeds_limit, and aggregate the
non-file-backed limitation so repeated huge names cannot inflate Evidence.
Use fixedTupleSchema for the signature pad bytes with projection parity
tests, and assert the late-cancellation reason and retained observation.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016y53PdpyMAp9RSW65fatHe
* fix: resolve merge integration errors
---------
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: morluto <76467478+morluto@users.noreply.github.com>
Keep each admitted HTTP handler owned through Evidence writes and error rendering, including after its client disconnects. Close joins graceful transport shutdown and handler work before publishing completion, and propagates exact late failures while preserving ordinary request diagnostics.
Share lifecycle ownership across OpenAI, Anthropic, and Gemini fixtures while retaining protocol-specific parsing and responses. Exercise real disconnects, graceful concurrent and repeated close, ordinary 400s, and opaque late failures.
Use JSON.parse directly in package verification and retain one parsed Cursor recovery snapshot. Route native command source loading through the shared transform-service owner so completed command cleanup leaves no transform child.
Preserve JSONC validation and caller inputs. Cover the actual public source-loading lifecycle with an authored command and verified process lineage.
* feat(pe): inspect TLS callbacks and load configuration
Adds inspect-pe-load-config and inspect_pe_load_config for PE32 and
PE32+ images, with artifact hashes and file ranges in the returned
evidence. Reports callback addresses and mappings, plus size-covered
security-cookie, SafeSEH, CFG, EH-continuation and XFG fields;
flag-derived mitigation claims are explicitly labeled inferred. Missing
directories remain null, and malformed storage or exhausted read budgets
return errors without partial success. Adds documentation and tests for
service validation, CLI/MCP access, malformed inputs and stable-file
handling.
x86 images that declare the legacy 64-byte load-config directory are
read to the structure's own Size when those bytes are file-backed, as
the Windows loader does.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016y53PdpyMAp9RSW65fatHe
* fix(pe): retain snapshot facts and bound load-config section lookup
Keep the completed stable-read path, SHA-256 and byte count as a
file-snapshot-hash partial observation when descriptor close fails or is
cancelled. Report the checked Size span as structure_location and add it
to Evidence locations beside the declared directory range. Resolve
callback sections through a sorted segment index built once per image,
keeping the ambiguity failure. Pin every load-config field to offsets
transcribed from the PE/COFF spec and llvm COFF.h at its exact Size
boundary for PE32 and PE32+.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016y53PdpyMAp9RSW65fatHe
---------
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.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>
morluto