blitzstrike 1.0.65 → 1.0.67

package/CHANGELOG.md

@@ -5,6 +5,26 @@ All notable changes to Blitz Strike are documented here.
 The format follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/).
 
+## [1.0.66] — 2026-09-13
+
+### Changed — LLM-driven architecture (Mission Control removed)
+
+Aligned with the LLM-driven model: the LLM is the brain, Blitz Strike is the
+deterministic hands. The deterministic "self-driving" engine is gone.
+
+- **Removed** `src/mission/` (Mission Control loop, 13 deterministic agents,
+  task scheduler, planner, coverage, recovery, router, budget, termination,
+  mission CLI) and the `mission_start`/`status`/`resume`/`stop`/`list` MCP tools.
+- **Added** `route_scan` + `complex_scan` MCP tools — the route-confusion and
+  complex-bug detectors are now directly callable by a driving LLM agent.
+- **Added** `run_enterprise_benchmark` MCP tool (framework-fixture recall).
+- **Rewrote** `src/enterprise-benchmark.ts` to drive the detectors directly
+  (no Mission Control) — 15/15 recall across the 6 fixtures.
+- The 6 `bs-*` skills (step 2) teach the LLM how to drive these tools.
+
+Deterministic moat intact: taint engine, universal taint, route-confusion,
+complex-bugs, strike_verify, finding/evidence engine, browser agent, intel layer.
+
 ## [1.0.65] — 2026-09-13
 
 ### Fixed — breadth-scanner false positives (live MCP verification)
@@ -343,8 +363,8 @@ STRIKE core without replacing it.
 
 ### Added
 
-- **Autonomous no-babysitting orchestration** (the missing piece vs.
-  oh-my-open-pentest's plugin loop):
+- **Autonomous no-babysitting orchestration** (the missing piece vs. a
+  harness-level plugin loop):
   - `runEngagement` now returns the full deliverable **inline** — summary,
     markdown, JSON, and SARIF — so a single call completes a source audit
     (no separate `report` call needed).