CyberSecurityUPandClaude Opus 4.6 e956b482b9 fix(3.6.8): JSON parse resilience + diagnostics for local model failures ...

- extract_findings: log when model output has no JSON (was silent drop)
- extract_findings: auto-fix trailing-comma JSON (common LLM mistake)
- pipeline: emit response tail when agent returns 0 parseable findings
- Helps diagnose why small/local models produce 0 findings on valid targets

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-08-07 09:51:50 -03:00

..

app

fix(3.6.8): better Ollama error messages, empty-evidence findings go to needs-review, single-model vote warning

2026-08-06 15:21:37 -03:00

crates/harness

fix(3.6.8): JSON parse resilience + diagnostics for local model failures

2026-08-07 09:51:50 -03:00

templates

feat: proof screenshots in reports (finding-correlated) + source-able env.sh (#37)

2026-07-31 20:32:15 -03:00

.gitignore

chore: remove test artifacts, ignore scan debris (#35)

2026-07-31 15:39:00 -03:00

Cargo.lock

fix(3.6.8): better Ollama error messages, empty-evidence findings go to needs-review, single-model vote warning

2026-08-06 15:21:37 -03:00

Cargo.toml

fix(3.6.8): better Ollama error messages, empty-evidence findings go to needs-review, single-model vote warning

2026-08-06 15:21:37 -03:00

creds.example.yaml

docs: full creds.yaml reference (web/multi-role/ssh/windows/cloud) in TUTORIAL + example file

2026-07-02 08:44:00 -03:00