@nathapp/nax 0.61.2 → 0.62.0-canary.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +6 -3
  2. package/dist/nax.js +33298 -32037
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -15,6 +15,7 @@ nax is an **orchestrator, not an agent** — it doesn't write code itself. It dr
15
15
  - **Extensible** — plugin system for routing, review, reporting, and post-run actions
16
16
  - **Language-aware** — auto-detects Go, Rust, Python, TypeScript from manifest files; adapts commands, test structure, and mocking patterns per language
17
17
  - **Semantic review** — LLM-based behavioral review against story acceptance criteria; catches stubs, placeholders, and out-of-scope changes
18
+ - **Adversarial review** — LLM-based adversarial code review that probes for input handling, error paths, and abandoned implementations
18
19
 
19
20
  ## Install
20
21
 
@@ -46,7 +47,7 @@ See [docs/](docs/) for full guides on configuration, test strategies, monorepo s
46
47
  ## How It Works
47
48
 
48
49
  ```
49
- (plan →) acceptance setup → route → execute → verify → review → escalate → loop → regression gate → acceptance
50
+ (plan →) acceptance setup → route → execute → verify → review (semantic + adversarial) → escalate → loop → regression gate → acceptance
50
51
  ```
51
52
 
52
53
  1. **Plan** *(optional)* — Generate `prd.json` from a spec file using an LLM
@@ -55,7 +56,7 @@ See [docs/](docs/) for full guides on configuration, test strategies, monorepo s
55
56
  4. **Context** — Gather relevant code, tests, and project standards per story
56
57
  5. **Execute** — Run agent session (Claude Code, Codex, Gemini CLI, or ACP)
57
58
  6. **Verify** — Run scoped tests; rectify on failure before escalating
58
- 7. **Review** — Run lint + typecheck; autofix before escalating
59
+ 7. **Review** — Run lint + typecheck + semantic review + adversarial review; autofix before escalating
59
60
  8. **Escalate** — On repeated failure, retry with a higher model tier
60
61
  9. **Loop** — Repeat steps 3–8 per story until all pass or a cost/iteration limit is hit
61
62
  10. **Regression gate** — Run full test suite after all stories pass
@@ -142,10 +143,12 @@ After all stories pass, nax runs the full test suite once. If it fails, it retri
142
143
 
143
144
  See [Regression Gate Guide](docs/guides/regression-gate.md).
144
145
 
145
- ### Parallel Execution
146
+ ### Parallel & Isolated Execution
146
147
 
147
148
  Stories are batched by compatibility (same model tier, similar complexity) and run in parallel within each batch. Use `--parallel <n>` to control concurrency. Sequential mode uses a deferred regression gate; parallel mode always runs regression at the end.
148
149
 
150
+ Even in sequential mode, stories can be isolated in per-story git worktrees (`execution.storyIsolation: "worktree"`) to prevent cross-story state leakage.
151
+
149
152
  See [Parallel Execution Guide](docs/guides/parallel-execution.md).
150
153
 
151
154
  ### Monorepo Support