Extended deterministic test to write serialized evidence record to
OS temp directory, read back from disk, parse JSON, and assert deep
structural equality. Verified: five structured arrays preserved with
correct lengths; exact inputs unchanged; identity fields intact; null
metadata fields survive round-trip. Temp file cleaned in finally block.
Zero live model calls. Zero browser calls. No production code or
canonical-helper modifications. Experiment 4 original structured
output remains unavailable.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Signed-off-by: robbond <rob@rdbsolutions.co.uk>
Apparatus-level pure serialization function that preserves all five
focused-deconstruction arrays (observations, uncertainties, assumptions,
relationships, possibleFollowUpQuestions) plus exact inputs and execution
metadata from the existing checkpoint — without modifying production code.
Deterministic verification: syntax check pass, 79/79 assertions pass
(including 28 new evidence-ser tests), zero live calls.
Experiment 4's missing structured output cannot be reconstructed (never
persisted by the apparatus). No new semantic evidence produced.
Controlled synthetic experiment (Iteration 4): fixed recruitment scenario with
synthetic answer showed partial preservation of the broader feasibility uncertainty.
The model correctly preserved timing estimates as observations but narrowed the
investigation to hiring pipeline logistics rather than cross-area launch feasibility.
Add focusedInvestigationInput {targetDescription, question, answer} to
composeDeepInvestigationCheckpoint() return object. These are the actual
invocation values: targetDescription from situationGraph node, question
is previousQuestion (NOT node.openQuestion), answer is function param.
Deterministic verification: syntax check passed; source-inspection test
assertions E10/E11 added and pass (0 failures). Call-count ownership:
up to 3 live generateReconstruction calls (focusedDeconstruct +
reconsiderCompletedEpisode + synthesizeCurrentUnderstanding).
No provider, graph, or production behavior changed.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Changed the facilitator-view-adapter to prefer node.description over
node.openQuestion for unresolved unknown items. This is a reversible
presentation change only — graph identity, reasoning-state ownership,
openQuestion generation, and resolved-unknown presentation are unchanged.
Owning test assertions updated to reflect new display contract:
- open-question-presentation.test.js: assertion target shifts from
question text to description text
- facilitator-view-adapter.test.js: deduplication tests use distinct
descriptions so nodes remain distinguishable after the change
Documentation: hypothesis experiment record and handoff return note.
Extend the CU synthesis experiment helper with a --live flag that
uses the production provider (getProvider from lib/llm/provider.js)
for live model invocation. Preserves deterministic mode unchanged.
Adds 10 new deterministic tests verifying live-mode wiring via
injected mock provider: fixture pass-through, single invocation,
schema correctness, immutability, persistence safety, and regression
of existing deterministic behaviour. Zero network calls in all tests.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Remove the 140-line Iteration 16 test section (commit 5d4e7b5) that
represented manually supplied checkpoint values as evidence of
target-scoped contribution behaviour. The section used extractLiveExperimentCheckpoint
to construct mock result objects simulating multi-episode state transitions
but could not observe contributions — the deterministic seam has no
contributions field in its return shape.
Preserves: all pre-existing checkpoint tests, Iteration 15 source-level
assertions, synthetic CU synthesis tests, and existing helper imports.
Add Iteration 16 test extension that documents the behavioral evidence
boundary for target-scoped contribution filtering:
- Observable via extractLiveExperimentCheckpoint:
* Node A pre-episode graph state (graphCheckpoint.nodeCount)
* B's fresh deconstruction trigger (providerGenerateCalls increments)
* Graph/findings continuity (reasoningState turnCount advanced)
- Blocked from deterministic seam (no contributions field in checkpoint):
* Historical contribution retention for non-current targets
* B contribution associated with targetNodeId
* Both A and B surviving in postEpisodeContributions
* B prep scope receiving B-specific contribution
Uses mock result objects to simulate the two-target sequence
(n_enterprise_customer_signing -> n_product_launch_decision) and
explicitly documents which assertions can and cannot be verified.
Historical contributions for a different Open Question node no longer
suppress fresh focused deconstruction of the current target. Only
contributions whose targetNodeId matches the current target are counted
towards suppressing redundant deconstruction.
Adds deriveInvestigationLearning to episode-preparation.js: pure function that maps resolvedNodeIds + Contributions + Findings to investigation learning propositions, preserving node.label question text and contribution-provenance ordering.
Owning tests prove: correct provenance, cross-question isolation, eligibility rule (null/agree eligible; not_quite/not_relevant excluded), unresolved exclusion, no-eligible-material omission, text preservation, and provenance authority over originatingTargetNodeId shortcut.
- Zod validator: plausibleInterpretations accepts empty string (zero interpretations) while remaining required and string-typed
- Prompt instruction: SECTION B now explicitly requests "" instead of absence prose when no plausible inputs exist
- Report generation/update paths derive hasPlausibleInterpretations from actual synthesized data rather than hard-coding true
- Tests: updated validation contract, added hasPlausibleInterpretations derivation assertions, updated seam tests to use derived values
Controlled A/B (zero-Findings scenario, Qwen): unresolved uncertainty exposure
did not contaminate supported understanding or plausible interpretation.
No production changes. No report semantic changes.
- Helper now supports --variant visible which appends unresolved Open Questions
as a separate NON-EVIDENCE section to the baseline prompt (built via production
buildOverviewSynthesisPrompt)
- Default (--variant hidden, or no flag) remains production path
- No production code changed; apparatus-only extension
- Deterministic A/B control proven by existing 34/34 test suite
synthesizeInvestigationOverview() called provider.generateReconstruction(prompt, modelName)
without an output contract. Without a structured-output schema the provider defaults to its
initial-reconstruction format which lacks { understanding, plausibleInterpretations }, causing
'Missing or invalid required fields' validation failure.
Add overviewOutputSchema (JSON-schema matching validateOverviewResponse contract) and pass as
third argument, matching the proven pattern in synthesizeCurrentUnderstanding().
53/53 tests PASS. Co-Authored-By: Claude Code <noreply@anthropic.com>
Production: synthesizeInvestigationOverview() now passes providerResult.response
to validateOverviewResponse() instead of the raw envelope, matching the proven
pattern in current-understanding-synthesis.js.
Regression: fakeProvider returns real-provider envelope shape { response, providerApiPath }
and four new regression tests verify unwrapping succeeds with valid response
and fails correctly with invalid response inside the envelope.
Handoff: documented defect confirmed, fix applied, and owning regression added.
- Add nullish coalescing on fix.findings ?? [] so absent findings
array in a fixture is represented as zero Findings [] for the A/B
input apparatus.
- Append product-launch second controlled case (live-product-launch-
start-response.json) with zero Findings to the epistemic comparison
test suite. All 34 tests pass deterministically.
- Update docs/current-handoff.md to record the zero-Findings case.
Retained deterministic input-control test proving that A/B apparatus
correctly holds supportedEvidence, findings, plausibleInterpretations,
scenarioState, and providerConfig constant while only varying unresolved
question visibility. Added buildOverviewSynthesisPrompt identity proof
that full vs filtered graph produce identical prompt text.
Corrected handoff semantics: deterministic input filtering does NOT prove
model output behaviour; live two-call semantic comparison remains required.
Preserved prior imperfect live evidence with correct qualification about
uncontrolled plausibleInterpretations divergence.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Deterministic test (17 cases) proves A/B inputs are correctly controlled:
- supportedEvidence identical in A and B
- findings identical in A and B
- plausibleInterpretations identical (fixed canonical interpretation) in A and B
- scenarioState identical in A and B
- providerConfig identical in A and B
- only unresolvedQuestions visibility differs (A=hidden, B=canonical)
- unresolved questions excluded from evidence and plausible interpretations
- fixed interpretation carries NON-EVIDENCE epistemic status
Also corrects Loop 2 documentation to reflect that three-category
invariance was NOT established (plausibleInterpretations differed
between calls despite identical input), retaining only the narrower
valid finding: no unresolved Open Question was promoted to evidence.
Co-Authored-By: Claude Code <noreply@anthropic.com>
robbondandClaude Code