v0.2.4

Update CHANGELOG.md

Signed-off-by: Andreas Reichel <andreas@manticore-projects.com>

v0.2.3

fix(llm): make request timeout configurable; document local model sizing

Add AURSCAN_TIMEOUT (seconds, default 180) so slow CPU-only local
backends aren't killed mid-generation by the previously hard-coded
deadline. Surface actionable guidance instead of opaque "context
deadline exceeded", give each fallback URL its own full budget, and
send max_tokens on the OpenAI call.

Document which local models are suitable (size-vs-suitability table,
VRAM guidance) and the two settings users get wrong: num_ctx and
AURSCAN_TIMEOUT.

Closes #8, #1

Signed-off-by: Andreas Reichel <andreas@manticore-projects.com>

v0.2.2

fix: version information

v0.2.0

chore(release): bump PKGBUILD to 0.2.0            (tag: v0.2.0)

docs: document two-stage pipeline, local LLM backend and custom rules
docs: add example extra-instructions file emphasising provenance
feat(cli): route scans through the pipeline; add --rules-only
feat(pipeline): orchestrate rules -> reputation -> LLM with offline fallback
feat(config): load user auditor-instruction overrides
feat(scan): OpenAI-compatible local backend, reputation & static signals
feat(rules): add deterministic static-rule pre-filter

Proof of Concept

Initial working version.