fix(opsec): block Ghidra RE artifacts + clear ruff backlog + doc fixes

.github/workflows/tests.yml

@@ -28,3 +28,17 @@ jobs:
           pip install -e ".[dev]"
       - name: Run the suite
         run: python -m pytest -q
+
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v5
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.12"
+      - name: Install ruff
+        run: |
+          python -m pip install --upgrade pip
+          pip install "ruff>=0.1.0,<1.0.0"
+      - name: Lint src/ (ruff)
+        run: ruff check src/

.gitignore

@@ -4,6 +4,11 @@ RE_FINDINGS*.md
 *-assessment-*.html
 *reverse-engineering*
 *-RE-*.md
+# Ghidra / binary RE projects (pyghidra-mcp output) — must never enter the public tree
+pyghidra_mcp_projects/
+*ghidra*
+*.gpr
+*.rep
 
 # Python
 __pycache__/
@@ -37,7 +42,6 @@ secrets*
 *.swp
 *.swo
 *~
-.DS_Store
 
 # Seluj
 .seluj/
@@ -55,3 +59,9 @@ ecosystem_audit_*.html
 
 # playwright MCP test artifacts
 .playwright-mcp/
+
+# Cloudflare wrangler local state
+.wrangler/
+
+# uv lock (dev convenience; project builds via setuptools/pip from pyproject)
+uv.lock

AGENTS.md

@@ -5,9 +5,9 @@ Your purpose is to assist users by completing coding tasks, such as solving bugs
 implementing features, and writing tests.
 
 ## Core Directives
-1. PLAN FIRST: Explore the codebase (list_files, read_file). Read this file and README.md.
-   Ask clarifying questions. Articulate the plan using set_plan.
-2. VERIFY WORK: After every modification, use read_file or list_files to confirm success.
+1. PLAN FIRST: Explore the codebase (Glob, Grep, Read). Read this file and README.md.
+   Ask clarifying questions. Articulate the plan (track steps with TaskCreate/TaskUpdate).
+2. VERIFY WORK: After every modification, use Read or Grep to confirm success.
    Do NOT mark a plan step complete until you've verified.
 3. EDIT SOURCE, NOT ARTIFACTS: If a file is a build artifact (dist/, build/, node_modules/,
    __pycache__/, .next/), trace back to its source.

README.md

@@ -6,7 +6,7 @@
   <a href="https://pypi.org/project/korgex/"><img src="https://img.shields.io/pypi/v/korgex?color=3fb950&label=pypi" alt="PyPI version"></a>
   <a href="https://pypi.org/project/korgex/"><img src="https://img.shields.io/pypi/pyversions/korgex?color=2dd4bf" alt="Python versions"></a>
   <a href="https://github.com/New1Direction/korgex/actions/workflows/tests.yml"><img src="https://github.com/New1Direction/korgex/actions/workflows/tests.yml/badge.svg" alt="CI"></a>
-  <img src="https://img.shields.io/badge/tests-1%2C571%20passing-3fb950" alt="tests">
+  <img src="https://img.shields.io/badge/tests-1%2C586%20passing-3fb950" alt="tests">
   <a href="https://registry.modelcontextprotocol.io/"><img src="https://img.shields.io/badge/MCP-registry-2dd4bf" alt="MCP registry"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="License: MIT"></a>
 </p>
@@ -541,7 +541,7 @@ korgex/
 │   └── ...
 ├── docs/                     # CLI reference, comparison, getting-started, tools-reference, …
 ├── spec/korg-ledger-v1/      # the ledger spec (SPEC.md, EVENTS.md)
-├── tests/                    # ~1,571 tests
+├── tests/                    # ~1,586 tests
 ├── .github/workflows/        # Linux CI (3.10–3.13) + PyPI publisher (OIDC)
 ├── pyproject.toml
 └── README.md
@@ -560,7 +560,7 @@ ruff check src/                                   # lint
 pytest -q                                         # the full suite
 ```
 
-The suite is **~1,285 tests** with no live LLM calls (everything is unit-tested) and runs on Linux CI across **Python 3.10, 3.11, 3.12, 3.13** on every push and PR. Major areas: the agent loop (routing, provider schemas, mode/model resolution, loop guards, the stall classifier, compaction), tools (fuzzy Edit, edit-freshness, background Bash, web), the verifiable ledger (hash-chain + causal DAG, redaction, the Ed25519 signed bus), CodeAct (kernel isolation, fuel, the tool bridge), MCP (namespaced multi-server router, OAuth refresh, full round-trip), prompt caching, skills (trust tiers, self-learning, the curator), and the REPL.
+The suite is **~1,586 tests** with no live LLM calls (everything is unit-tested) and runs on Linux CI across **Python 3.10, 3.11, 3.12, 3.13** on every push and PR. Major areas: the agent loop (routing, provider schemas, mode/model resolution, loop guards, the stall classifier, compaction), tools (fuzzy Edit, edit-freshness, background Bash, web), the verifiable ledger (hash-chain + causal DAG, redaction, the Ed25519 signed bus), CodeAct (kernel isolation, fuel, the tool bridge), MCP (namespaced multi-server router, OAuth refresh, full round-trip), prompt caching, skills (trust tiers, self-learning, the curator), and the REPL.
 
 ---
 
@@ -594,7 +594,8 @@ To build locally for inspection: `python -m build` then `python -m twine check d
 
 These exist today; PRs welcome.
 
-- **OpenAI streaming has fewer rendered events than Anthropic.** Anthropic emits thinking blocks and message-delta usage; OpenAI emits only text and tool-call chunks. Both render correctly, but the TUI is richer for Anthropic.- **Dashboard authentication is not implemented.** Don't expose port 8090 publicly without an auth-terminating reverse proxy in front.
+- **OpenAI streaming has fewer rendered events than Anthropic.** Anthropic emits thinking blocks and message-delta usage; OpenAI emits only text and tool-call chunks. Both render correctly, but the TUI is richer for Anthropic.
+- **Dashboard authentication is not implemented.** Don't expose port 8090 publicly without an auth-terminating reverse proxy in front.
 - **The VS Code sidecar is a legacy companion** to the dashboard; korgex's primary interface is the terminal REPL.
 
 ---

ROADMAP.md

@@ -1,5 +1,12 @@
 # Korgex — Next Frontier Roadmap
 
+> ⚠️ **HISTORICAL — kept for reference; do not treat as current.**
+> This roadmap predates korgex's v0.x pivot. It describes a pre-pivot plan (korg-bridge / PyO3
+> → KorgChat, "27 tests"). korgex has since shipped through **v0.35.0** (~1,571 tests) as a
+> provider-agnostic, MCP-native coding agent. For the current state see
+> [`CHANGELOG.md`](CHANGELOG.md) and [`README.md`](README.md). (The AlphaEvolve appendix below
+> is still useful.)
+
 ## Release Sequence
 
 | Version | Status | Scope |