CyberSecurityUPandClaude Opus 4.6 1f8ccb6f9e fix(3.6.8): recon time budget — 5min cap prevents recon from eating entire run ...

- Add RECON_TOTAL_BUDGET_SECS (300s) total wall-clock cap across all rounds
- Per-round budget directive in prompt: 30-50 commands max, stop early if enough intel
- Elapsed time check between rounds: skip remaining if budget exhausted
- Remaining time communicated to follow-up rounds for self-pacing
- RELEASE.md updated with recon budget section

Previously: subscription CLI recon ran 150+ commands over 15 min, exploitation never started.
Now: recon caps at 5 min total, then proceeds to agent exploitation.

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

2026-08-08 10:10:43 -03:00

..

app

fix(3.6.8): auth resilience — circuit breaker pauses run on token revocation, preserves findings

2026-08-08 09:14:21 -03:00

crates/harness

fix(3.6.8): recon time budget — 5min cap prevents recon from eating entire run

2026-08-08 10:10:43 -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