Eleven tests were named "beyond the former ..." and pinned a value just above
a limit that no longer exists. Each now states and checks the current
contract:
- jsonShape: the caller's byte allowance is the only bound; a shape that fits
exactly is complete and one byte less is a capacity refusal.
- Hopper download: chunks arriving just inside the stall bound complete (the
trickle case already covers the total bound).
- Firmware: a selected analysis_timeout_ms above the default governs the owned
command, expressed from the default constant.
- Provider process output, CDP resources/timeline/WebMCP frames, Playwright
steps/artifacts/Electron waits, scenario diff and Bun ELF names: renamed to
the unbounded-count or exact-selection contract they check, with a note on
what bound (if any) still applies and where it is covered.
The six JavaScript analyzer tests with the same naming are left to their
workstream.
Refs #10515
* feat(javascript)!: require the runtime parse-failure count and active Electron execution paths
The V8 Inspector projection always writes scripts.parse_failed_total and the
active Electron service always commits parameters.resolved_paths, so both are
now required. Runtime reconciliation reads the admitted execution paths only
and no longer falls back to request-spelled paths in parameters, and checks
the observed executable path against them on every capture.
JavaScriptStaticAnalysis.routes and module_runtime keep their omission, which
current producers still make (a checkpoint that cannot retain route facts; no
recovered factory runtime); their comments now say so instead of naming
historical analyses.
BREAKING CHANGE: JavaScript runtime observations without
scripts.parse_failed_total, and active Electron Evidence without
parameters.resolved_paths, are refused as malformed; recreate the observation.
* test(javascript): give the shared Node reconciliation fixture the required parse-failure count
* feat(browser)!: require browser observation facts their producers always write (#10991)
* feat(browser)!: require browser observation facts their producers always write
The source-map fetcher always writes effective_url (string or null), the web
bundle analyzer always writes schema_property_names_coverage, and the CDP
storage fingerprinter always marks IndexedDB schema fingerprints with
projection_version 2. Each is now required. The IndexedDB marker is tied to
its scope by a discriminated union and derived from the scope in the
producer, so compare_web_captures no longer carries the store-only
projection branch.
response_identity and the WebMCP consequential hint keep their omission,
which current producers still make (a body not fully read; an invalid
annotation); the guide no longer attributes it to historical captures.
BREAKING CHANGE: source-map items without effective_url, WebMCP declarations
without schema_property_names_coverage, and IndexedDB schema fingerprints
without projection_version are refused as malformed; recreate the capture.
* feat(managed)!: refuse members beside a null signature resolution (#10992)
* feat(managed)!: refuse members beside a null signature resolution
signature_resolution is null only when member decoding exceeded capacity,
and the capacity-recovery producer then examines no members. The managed
member inspection schema now enforces that: a null resolution with any
field, method, member reference, call edge or field access is malformed.
With that rule, every admitted inspection with members attests type-name
resolution, so the raw-digest fallback is unreachable and is deleted:
comparableSides, hasSignatureResolution, the comparison's
signatureResolutionExamined flag and the "does not attest" limitation. The
shared workflow example that carried resolved digests beside a null
attestation now attests resolution.
BREAKING CHANGE: managed member Evidence with a null signature_resolution
and any examined member is refused as malformed; recreate the observation.
* docs: describe historical Evidence by what the format revision now refuses (#10993)
SQLite worker_timeout_ms is required, so the SQLite guide no longer reads a
missing value as unknown settings. The IL2CPP, ESP image and process capture
guides now say that bundles exported without evidence_format are refused,
while a standalone record from an earlier release is still read with the
stated omission semantics (records carry no format marker yet). The route
inventory guide describes a parent without route_inventory by its meaning
rather than by its age.
* refactor(javascript): require static analysis coverage from the JavaScript worker (#11001)
* refactor(javascript): require static analysis coverage from the JavaScript worker
Both JavaScript static producers always write analysis_coverage: the
analyzer measures it on every parsed source and the failed-parse result
carries an unexamined coverage. The worker schema and the static analysis
type therefore require it, the preload-discovery checkpoint copies it
unconditionally, and ElectronBoundaryAnalysis reads Electron applicability
and examination limits from it alone. The fallback that re-derived Electron
use from semantic module links and retained references for analyses
without coverage is deleted, as are the graph and builder branches for a
missing coverage.
Retained Evidence graph observations are unchanged: the analysis view still
counts a stored JavaScript observation without analysis_coverage as
unmeasured, since standalone records carry no format marker yet.
The worker runs from the same build as its parent, so no external caller
sees the stricter reply schema.
* feat(browser)!: require storage fingerprint, Link context, mapping index and invalid-map identity facts (#11002)
* feat(browser)!: require storage fingerprint, Link context, mapping index and invalid-map identity facts
Each field is written by its only producer on every capture:
- The CDP storage capture always writes content_fingerprints,
fingerprint_algorithm and fingerprints_complete, so their schema defaults
are removed.
- The CDP Link header projection always writes context_url and
context_scope, so they are required.
- The source-map fetcher writes source_index and declaration_index on every
mapping row, so they are required.
- The fetcher judges a map invalid only after reading its complete body. A
separate invalidSourceMapItem builder now takes the response identity as a
required argument, and the schema's invalid member requires
response_identity; fetch_failed keeps it optional because those rows can
come from a body that was not fully read.
The browser and source-location guides no longer describe these fields as
optional for older saved captures.
BREAKING CHANGE: page inspections without the storage fingerprint fields or
Link context fields, source-map mapping rows without their indexes, and
invalid source-map items without response_identity are refused as malformed;
recreate the capture.
* test(browser): keep source-omission coverage on a still-defaulted field and refuse a missing fingerprint algorithm
* feat(browser)!: require web-bundle target origin, inspection producer facts, scenario redirect state and exclusion kind (#11014)
feat(browser)!: require web-bundle target origin, page inspection producer facts, scenario redirect state and exclusion kind
Each field is written by its only producer on every record:
- buildCaptureObservation always writes capture.target_origin (the validated
origin or null), so analyze_web_bundle Evidence and both web-bundle view
results require it; the view's conditional spread is gone.
- The CDP page capture always writes accessibility node states, script
frame_id (null when unattributed) and worker opener_target_id and
parent_frame_id, so their schema defaults are removed.
- PlaywrightScenarioNetwork writes redirected_from_transaction_state exactly
when the predecessor ID is null, so request events now require it there and
still refuse it on linked events.
- The reference-source importer writes entry_kind on every exclusion
(unknown when the kind was not observed), so it is required.
The browser scenario contract and CLI guide no longer describe older
captures or exclusions without these fields.
BREAKING CHANGE: web-bundle analyses without capture.target_origin, page
inspections without these script, accessibility or worker fields, scenario
network events with a null predecessor and no redirect state, and reference
source graphs whose exclusions lack entry_kind are refused as malformed;
recreate the capture or re-import the source.
Comparing retained scenario captures flattened each side's unique step
map, so a step_id duplicated on one side vanished from that side's map;
the same id arriving uniquely on the other side then landed in
before_only/after_only and produced a missing_before_step or
missing_after_step failure for a step the duplicate side still retains.
The comparison reported both the duplicate and a definite absence for
the same id, a stronger claim than the ambiguity supports.
Alignment now keeps a duplicated id out of the absence lists on both
sides: the id stays unaligned with its duplicate failure, but no capture
is described as missing a step it retains. Genuinely missing ids keep
their missing_* classification and absence lists.
Fixes#7415
Co-Authored-By: gensokyo-dev <gensokyo-dev@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.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>
fix: repair main after bulk merge
Restore typecheck after #3826 called uniqueBy, and align the red fixtures
with the merged pcap, browser, IDA, and Hopper contracts.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: morluto <morluto@users.noreply.github.com>
* fix(setup): offer Hopper installation only where setup can install it
On a host where automated Hopper installation is ineligible (Windows,
macOS below 12 or with an unknown version, or an unsupported or
unidentified Linux distribution), an unhealthy setup without a Hopper
launcher ended by advising "Rerun with --yes --install-hopper", and the
same run then refused that request. The eligibility rule existed twice
(the discovery proposal and the explicit-install gate, with separate macOS
parsers that disagreed on malformed versions), and the final advice
consulted neither.
Make setup discovery the single owner of Hopper install eligibility. The
explicit gate refuses with the unchanged copy through hopperInstallRefusal,
and the final advice offers --install-hopper only where the host is
eligible; ineligible hosts fall back to doctor remediation. hostRemediation
now checks only the Node.js runtime. An empty or unparseable macOS version
is now refused by the explicit gate instead of installing.
Fixes#3944
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: drop merge-only formatter changes
* test: align inherited fixtures with current analysis contracts
* test(ida): assert search recovery instead of diagnostic prose
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
Keep ordinary UTF-8 digests and secret redaction, separate malformed UTF-16 preimages, and record storage fingerprint provenance. Compare legacy hashed snapshots as unknown without treating encoding metadata as a target change. Cover producer boundaries and real owned-browser CLI/MCP workflows.
BREAKING CHANGE: legacy hashed browser storage remains readable but comparisons return unknown until both sides are recaptured.
Co-authored-by: gongfpp <22683417+gongfpp@users.noreply.github.com>
Retain scenario selection limitations independently of known changes. Compare known status, MIME and byte observations for each redirect hop without inventing missing facts.
Refs: #3172, #3173
Require process retention accounting, browser network transaction identity, and all web comparison dimensions. Remove obsolete omission repairs and derive completeness from the owning producer facts.
BREAKING CHANGE: Historical captures without current producer accounting or transaction identity, and web diffs missing accessibility or storage dimensions, are rejected.
Deliver complete Evidence directly through MCP with required nullable analysis profiles and immutable per-server delivery settings. Bind selected environments at construction and require typed cleanup outcomes with retained retry ownership.
Remove test-only routing, duplicate session and snapshot metadata, producer-field repairs, and ambiguous provider arguments. Separate artifact byte identity from occurrence classification and retain typed source-map and partial native facts across CLI, MCP, and verifier consumers.
BREAKING CHANGE: obsolete Evidence envelopes, session aliases, incomplete snapshots, and missing normalized producer facts are no longer accepted.
* feat(browser): capture correlated network content and lifecycle evidence
Keep request identities and redirect relationships across ordered scenario events.
Capture selected browser-exposed bytes and duplicate headers through modular
readers, settle bounded reads before cleanup, and preserve unavailable states.
Keep content-selection mismatches and legacy network coverage unknown during
comparison. Verify real CLI/MCP, installed package, and browser lifecycle paths.
Refs #774
Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)
* fix(browser): align capture defaults and redact encoded media metadata
Correct the complete documented request and legacy default expectation caught by CI. Cover and redact encoded declared values in captured body media types.
Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)
* test(browser): verify polling capture cutoff completeness
Accept incomplete event coverage only when the continuously polling fixture has explicit unfinished requests; retain failures for other missing or truncated sections. Include actual completeness and unfinished transactions in diagnostics.
Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)
* fix(hopper): report unavailable procedure body coverage
* refactor!: simplify runtime tools and remove replay engines
Keep direct inspection, capture, and comparison tools. Bind handlers to named contracts and let agents compose experiments with commands and local fixture servers.
BREAKING CHANGE: Remove controlled replay, Node characterization, finite replay-machine, managed runtime planning, and redundant string-tracing tools. Retire process replay, shims, reactive scenarios, custom checkpoints, and active browser replay and origin-scope inputs.
* refactor(test): colocate pure-domain tests and reduce test debt
Move focused immutable domain/contracts/adapter tests from
tests/composition/** beside their production owners under src/** as
colocated *.test.ts/*.fixture.ts, and relocate persistence-shaped
composition tests under tests/boundary/filesystem/**. Update import
paths, the Vitest project topology (shared worker context for pure
domain/contracts and recording-port service projects), the test
migration ledger, testing docs, and AGENTS.md to match.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* docs: remove test migration ledger
The cutover is complete and the ledger is no longer referenced anywhere
in source, scripts, or the docs gate. Drop the standalone artifact.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* docs: clean up stale migration artifacts
Remove empty directories left by the test migration and replace the
"final cutover" language in docs/testing.md with standing PR guidance
that no longer references the completed migration.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix: repair CI failures from schema, knip, and stale generated artifacts
Three root causes fixed:
1. catalog-schemas.mjs: valuesAt only traversed anyOf from Zod's
toJSONSchema, not oneOf. The webScreenshotDiffSchema change to a
discriminated union produces oneOf, so the product catalog generator
could not derive the web_screenshot_diff schema version. Add oneOf
traversal.
2. conformancePackage.ts: the test rewrite removed the only imports of
ScenarioManifest, ReplayPlan, ShimPlan, and ExpectedEvidence, making
them unused exports that knip flags. Remove the dead type aliases.
3. Regenerate stale artifacts (product catalog, MCP tool catalog, skill
metadata, conformance manifest) that drifted from the source changes.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>