A stable agentic realization becomes deterministic code. All four exit
criteria met; 163 tests pass.
- crystallization.py: trajectory capture, stability assessment requiring the
same path across several runs, CrystallizedDriver, pytest codegen
- crystallized/test_grant_access.py: generated, runs with no model, carries
its lineage in the docstring
- descendant preserves the ancestor's oracle set, agrees with it across five
lab versions, and still catches a seeded defect
- reversibility shown both ways via new M24 (grant endpoint renamed): the
frozen descendant fails loudly rather than searching, and the agentic
ancestor recovers from the same mutation
F-0007 (open): the 54% cost reduction must not be quoted in support of the
thesis. The T07 runtime is token-free, so the measured saving is one page
fetch, one parse and a two-candidate scoring pass. The saving the concept
actually claims - tokens, latency, retry variance - is unmeasured. Together
with F-0005 this makes a bounded live-model experiment the highest-value next
investment.
Assertions in the generated test are imported rather than restated, so it is
not fully standalone. Deliberate: paraphrased claims would be a second
unverified statement of intent.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1629012@bnt-lap001
Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1629012@bnt-lap001
Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39
False Adaptation Rate = 0/7 across the labelled catalogue and the three E-003
attacks. 11 of 12 mechanical mutations absorbed without a human, so the safety
result is not bought by escalating everything.
- classification.py: total function over three signals, rule order chosen so
every rule that could excuse a regression sits after the rule that reports
one. SAFE_TO_ACCEPT is a two-element closed set, asserted.
- CompositeDriver plus scenarios/full_journey.py: one asset crossing both
surfaces, so UI mutations are visible as surface differences while the
claims they do not touch stay green.
- E-003: surface substitution (new M23), concurrent mechanical+defect,
evidence starvation, provenance laundering. All held.
F-0006 (CONCEPT_DRIFT, resolved): the T02 design listed SEMANTIC_CHANGE as an
outcome the table could produce. It cannot - M12 and M19 are behaviourally
identical, as the lab has asserted since T05. PRODUCT_DEFECT and
SEMANTIC_CHANGE collapse into one escalating outcome, BEHAVIOUR_CHANGED, and
the distinction becomes a human adjudication. INTENT_CHANGED survives but is
detected by the claim fingerprint moving, not inferred from behaviour.
Two classifier defects found and fixed rather than reported: claims downstream
of a failed realization now yield INCONCLUSIVE rather than FAIL (a false
accusation is the mirror image of a false adaptation), and the browser driver
records a page signature so surface change is detectable when the interaction
path is unchanged.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1629012@bnt-lap001
Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39
Two decisions taken with the operator: stdlib HTML driver instead of
Playwright (F-0004), and a deterministic discovery runtime instead of a live
model. Both sit behind interfaces so the alternatives drop in later.
- html.py: stdlib DOM parse and query
- agentic.py: DiscoveryRuntime (agentic arm, ignores data-td by construction)
and RecordedSelectorRuntime (control arm, uses the strongest identifier the
page offers)
- browser.py: per-actor sessions over real HTTP, constructed per call so no
actor inherits another's connection state
- cost/nondeterminism metrics recorded from the first run
F-0005 (CONCEPT_DRIFT): the H-001 result is a narrowing. Where test ids are
preserved, discovery 9/9 and recorded selectors 9/9 - the semantic action buys
nothing. Where they are dropped, discovery 2/3 and recorded 0/3. The concept
model presents semantic actions as generally superior; the evidence says
conditionally superior.
M21 and M22 added mid-task: the deciding side of the axis was N=1. M22 (field
names renamed) defeats the heuristic and is the first concrete evidence that a
live model would add capability, not just cost.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1629012@bnt-lap001
Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39
lab/app.py (users, tenants, auth, resources, sharing, read/write, revoke,
audit), lab/http_api.py (JSON API + browser UI, stdlib only), 20 labelled
composable version-stamped mutations, ground-truth matrix. 48 tests pass.
Detection against the reference scenario: MECHANICAL 0/10 flagged (correct),
DEFECT 6/6, SEMANTIC 2/4 with both inert cases declared.
- F-0002: M16 and M18 initially escaped detection entirely. A use case
protects exactly what it asserts. Resolved by adding two claims already
stated as intent in INTENT.md; the six-mutation catalogue would never have
surfaced this.
- test-id axis added: stable selectors survive most UI mutations, which would
make H-001 trivially false. Mutations now vary on preserves_test_ids so the
hypothesis is analysed split by that axis rather than rigged.
- M12 (semantic deferred revoke) and M19 (defect race) are behaviourally
identical and asserted as such - the discrimination problem as a test.
lab/minimal.py removed; superseded by lab/app.py.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1629012@bnt-lap001
Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39
Alice/Bob/Carol runs end to end, deterministically, replayable from seed.
16 tests pass, no third-party dependencies.
- src/testdriver: intent, provenance, world, actions, drivers, observers,
oracles, evidence, energy, scenario, runner
- lab/minimal.py: the SUT, exposing the independent observation channel
required by D-07
- evidence is stratified S1/S2/S3; Runner refuses to attribute S2/S3 to an
actor; claims are frozen and provenance-checked at construction
- missing evidence yields INCONCLUSIVE, which outranks PASS in the run verdict
- EnergyEvents captured, no scoring (H-005 dormant)
The observation channel records both stored state and an out-of-band
enforcement probe; their disagreement is an invariant and is what detects an
authorization defect that leaves the audit trail intact. A seeded
RevokeIsCosmetic lab fails the run via both the claim and that invariant.
Also closes TD-WP-0001-T02 (stack and commands now exist).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1629012@bnt-lap001
Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39
