Project-independent foundations for reading, validating and extending ZIP case packages. The authoritative design is docs/architecture.md. The implemented v1 contract is documented in docs/package-format-v1.md. Job state, checkpoints and inbox admission are documented in docs/lifecycle-v1.md. Generic case construction and its input contracts are documented in docs/case-builder-v1.md. Vcore imports for wowdiag/wowsrc are documented in docs/vcore-adapters-v1.md. Authenticated submission of new cases and completed-case feedback is documented in docs/intake-api.md. The HTTP API creates and queues packages; external callers do not need to implement the internal package format. The continuous analysis worker consumes that inbox, routes cases to configured projects and resumes checkpointed analysis after restart.

Requires Python 3.11 or newer.

python -m venv .venv
.\.venv\Scripts\python.exe -m pip install -e ".[test]"
.\.venv\Scripts\python.exe -m pytest

The lifecycle foundation supports one-pass inbox processing, resumable package checkpoints and a deterministic generic CaseBuilder. An async LLM gateway and CaseInterpreter provide interpretation and bounded initial hypothesis generation, with durable per-hypothesis budget accounting. An LLM-driven investigation controller connects read-only queries, durable evidence and asynchronous test handoffs. Final evaluation produces traceable diagnoses or human review. Confirmed diagnoses can produce policy-bound Change Requests, with final output validation and atomic local outbox/review publication. Operational telemetry observes the APIs and continuous worker.

A bounded single-case command-line trial now connects import, analysis and local delivery with telemetry: first real LLM trial. Use python -m viano_bug_analysis.trial --help. Only its run command makes LLM requests; prepare and check do not contact model services. For a new revision, run --planning-mode joint opts into a single interpretation/ hypothesis call with independent block validation: joint case planning. New joint revisions use v2 source constraints and dependency-aware corrections; frozen v1 cases remain replayable.

The trial enables bounded, durable early model-output corrections with explicit validation feedback: early correction, configured through correction.example.toml.

Expected-behavior resolution and the read-only provider contract: expected-behavior-v1.md.

Configurable LLM transport, failover and durable retries: llm-gateway-v1.md, with example configuration.

Gemini stable case caching, implicit cache measurements and separate token/storage cost accounting: context caching, with native Gemini example. Lossless stable/live partition, versioned aliases and offline measurements: stable case cache.

Causal evidence direction, auditable confidence calibration and current-head validation performance: confidence and local performance.

The first domain LLM phase and its source-reference contracts: case-interpretation-v1.md.

Initial hypotheses, revision-wide creation limits and equal budget allocations: hypothesis-builder-v1.md, with analysis configuration.

Durable investigation budget accounting, configurable costs/rewards and stopping rules: budget-manager-v1.md, with budget configuration.

Case-local asynchronous test requests, confirmed feedback and budget-preserving event-driven resume: async-tests-v1.md. Web UI and external bot/client adapters are future integrations.

Read-only packaged source/database queries and the strict tool allowlist: investigation-tools-v1.md.

Shared read-only Git/source/schema and MariaDB research, deterministic case enrichment, bounded investigation prompts and the isolated World test database: project-research-v1.md, with project configuration.

Portable evidence records, provenance, case-wide IDs and novelty-aware budget integration: evidence-store-v1.md.

Resumable, bounded LLM investigation cycles and their controller contracts: investigation-loop-v1.md, with investigation configuration.

Final hypothesis evaluation, traceable diagnoses and controlled human review: diagnosis-builder-v1.md, with diagnosis configuration.

Policy-bound coding requests and validated, resumable local output delivery: change-request-v1.md, with change request configuration.

Opt-in operational logs, safe error chains, metrics, heartbeat/progress and passive queue diagnostics: telemetry-v1.md, with telemetry configuration.

Schlanke Untersuchungsstarts mit gemeinsamer Erstbewertung: Ablauf und Konfiguration.