robbondandClaude Code d387b66c03 test(confidence-engine): clarify controlled report experiment boundary ...

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>

2026-09-30 12:30:36 +01:00

..

archive

refactor(confidence-engine): compact current-handoff to operational snapshot; archive v0.61 experiment history to ch19

2026-09-07 07:51:08 +01:00

design-evolution

refactor(confidence-engine): compact current-handoff to operational snapshot; archive v0.61 experiment history to ch19

2026-09-07 07:51:08 +01:00

01_Confidence_Engine_Founding_Principles.md

docs: principles and story docs

2026-08-05 19:34:57 +01:00

02_Confidence_Engine_Product_Story.md

docs: principles and story docs

2026-08-05 19:34:57 +01:00

03_Confidence_Engine_Language_Guide.md

docs: principles and story docs

2026-08-05 19:34:57 +01:00

04_Rob_Thinking_Model.md

docs: principles and story docs

2026-08-05 19:34:57 +01:00

architectural-principles.md

architecture: define investigation turn cycle

2026-08-05 16:14:22 +01:00

behaviour-selection.md

docs: narrow behaviour-selection to v0.1 implementation brief

2026-08-05 17:52:01 +01:00

checkpoint-60b93.md

fix(reasoning): preserve investigation ownership across selection and question rejection

2026-08-17 17:58:45 +01:00

Confidence_Engine_Return_to_Origin_Methodology_Context_2026-08-18.md

docs: preserve domain-independent facilitator principles

2026-08-19 18:39:35 +01:00

confidence-engine-decomposition-and-atomic-reasoning-specification.md

doc: decomposition document for codex reasoning development

2026-08-05 06:14:40 +01:00

confidence-engine-product-checkpoint-2026-09-08.md

docs(confidence-engine): checkpoint commercially testable product loop

2026-09-08 10:40:21 +01:00

context-routing-validation.md

experiment: validate cross-boundary context routing

2026-08-06 15:58:41 +01:00

current-handoff.md

test(confidence-engine): clarify controlled report experiment boundary

2026-09-30 12:30:36 +01:00

current-implementation-verification.md

experiment: verify current project state against implementation

2026-08-06 14:16:57 +01:00

current-project-state.md

test(confidence-engine): control report epistemic comparison inputs

2026-09-30 11:44:51 +01:00

current-working-principles.md

docs: preserve domain-independent facilitator principles

2026-08-19 18:39:35 +01:00

design-evolution-log.md

docs(confidence-engine): promote design evolution archive index

2026-09-03 11:49:42 +01:00

facilitator-behaviour.md

architecture: introduce investigation state assessment

2026-08-05 16:09:24 +01:00

failure-modes.md

architecture: define investigation turn cycle

2026-08-05 16:14:22 +01:00

investigation-narrative.md

architecture: introduce investigation narrative layer

2026-08-05 15:53:22 +01:00

investigation-state-assessment-contract.md

docs: clarify Confidence Engine context authority

2026-08-19 11:49:30 +01:00

investigation-state-assessment.md

docs: clarify Confidence Engine context authority

2026-08-19 11:49:30 +01:00

investigation-turn-cycle.md

exp(18): implement investigation state assessment layer

2026-08-05 17:52:18 +01:00

methodology-checkpoint-return-to-origin.md

docs: preserve Confidence Engine methodology continuity

2026-08-19 10:46:05 +01:00

orchestrator-contract.md

experiment: archive historical project documents

2026-08-06 14:24:52 +01:00

project-knowledge-inventory.md

docs(confidence-engine): route design evolution provenance through archive index

2026-09-03 11:56:36 +01:00

reasoning-contract-backlog.md

docs: narrow behaviour-selection to v0.1 implementation brief

2026-08-05 17:52:01 +01:00

reasoning-production-path-map.md

docs: map reasoning requirements to production path

2026-08-08 11:08:37 +01:00

reasoning-refinement-requirements.md

docs: close reasoning fidelity v0.8 first pass

2026-08-09 17:25:19 +01:00

success-signals.md

architecture: define investigation turn cycle

2026-08-05 16:14:22 +01:00

task-context-packs.md

docs(confidence-engine): route design evolution provenance through archive index

2026-09-03 11:56:36 +01:00

ui-mock-reference.md

experiment: separate ui mock reference from deferred backlog

2026-08-06 14:47:34 +01:00

v0.6-reasoning-architecture.md

docs: document v0.6 reasoning architecture

2026-08-03 07:24:46 +01:00

v0.7-ui-mock-mode.md

feat: add mock-mode docs and additional e2e tests (long investigation, recovery states)

2026-08-05 08:38:44 +01:00