@heretek-ai/epistemic-swarm 0.7.0 → 0.7.2

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "epistemic-swarm",
-  "version": "0.7.0",
+  "version": "0.7.2",
   "description": "High-Integrity Dialectic Research Agent Harness for Claude Code enforcing empirical evidence over parametric hallucination.",
   "author": {
     "name": "Heretek AI",

package/bin/cli.js

@@ -74,6 +74,7 @@ Options:
   --mode <mode>         Operating mode (research, audit, scout, hybrid, brainstorm)
   --engine <engine>     Search engine (duckduckgo, brave, firecrawl, searxng)
   --depth <n>           Max dialectic iterations (1-4)
+  --backend <b>         Agent runtime: auto (host-native), claude, opencode
   --dir <path>          Path to .research workspace directory (default: .research)
 
 Examples:

package/extensions/pi/index.js

@@ -49,7 +49,13 @@ function callMcp(tool, args = {}, ctx = {}) {
     {
       encoding: 'utf-8',
       cwd: ctx.cwd || process.cwd(),
-      env: { ...process.env, PYTHONPATH: PKG_ROOT },
+      // Project root: evidence defaults under <project>/.research instead
+      // of the server process cwd.
+      env: {
+        ...process.env,
+        PYTHONPATH: PKG_ROOT,
+        IUMBTEMS_PROJECT_DIR: ctx.cwd || process.cwd(),
+      },
     }
   );
   return {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@heretek-ai/epistemic-swarm",
-  "version": "0.7.0",
+  "version": "0.7.2",
   "description": "IUMBTEMS: I Use My Brain To Express My Self — High-Integrity Dialectic Research Agent Harness for Claude Code, OpenCode V2, Pi, OMP (oh-my-pi), Gemini CLI, Codex CLI, and AntiGravity",
   "main": "bin/cli.js",
   "bin": {

package/plugins/darkharvest/skills/darkharvest/scripts/harvest.py

@@ -59,11 +59,19 @@ TEXT_EXTS = {".md", ".json", ".toml", ".yaml", ".yml", ".txt", ".py", ".js", ".t
 DEFAULT_MAX_FILES = 120
 DEFAULT_MAX_BYTES = 400_000
 DEFAULT_TIMEOUT = 120
+DEFAULT_BASE_DIR = ".research"
+MAX_SCAN_DEPTH = 3
+MAX_SINGLE_FILE_BYTES = 100_000
+SNIPPET_CHARS = 4000
+
+SPDX_APACHE2 = "Apache-2.0"
+PERMISSIVE_SPDX = frozenset({"MIT", SPDX_APACHE2, "BSD-3-Clause", "ISC"})
+COPYLEFT_SPDX = frozenset({"GPL", "AGPL"})
 
 SPDX_MAP = {
     "mit": "MIT",
-    "apache-2.0": "Apache-2.0",
-    "apache 2.0": "Apache-2.0",
+    "apache-2.0": SPDX_APACHE2,
+    "apache 2.0": SPDX_APACHE2,
     "bsd-3-clause": "BSD-3-Clause",
     "bsd 3-clause": "BSD-3-Clause",
     "isc": "ISC",
@@ -97,43 +105,74 @@ def detect_license(text):
 
 
 def scan_tree(root, max_files=DEFAULT_MAX_FILES, max_bytes=DEFAULT_MAX_BYTES):
-    entries = []
-    total_bytes = 0
-    manifests = {}
-    license_text = ""
-    readme_head = ""
+    root = Path(root)
+    state = _ScanState()
     for dirpath, dirnames, filenames in os.walk(root):
         dirnames[:] = [d for d in dirnames if d not in SKIP_DIRS]
         rel = Path(dirpath).relative_to(root)
-        depth = len(rel.parts) if str(rel) != "." else 0
-        if depth > 3:
+        if (len(rel.parts) if str(rel) != "." else 0) > MAX_SCAN_DEPTH:
             dirnames[:] = []
             continue
+        prefix = "" if str(rel) == "." else str(rel) + os.sep
         for f in sorted(filenames):
-            if len(entries) >= max_files or total_bytes >= max_bytes:
-                return entries, manifests, license_text, readme_head, True
-            fp = Path(dirpath) / f
-            try:
-                size = fp.stat().st_size
-            except OSError:
-                continue
-            if size > 100_000:
-                continue
-            rel_p = str(rel / f) if str(rel) != "." else f
-            entries.append(rel_p)
-            if f in MANIFEST_FILES or Path(f).suffix in TEXT_EXTS:
-                try:
-                    content = fp.read_text(encoding="utf-8", errors="replace")
-                except OSError:
-                    continue
-                total_bytes += len(content.encode("utf-8", errors="replace"))
-                if f in MANIFEST_FILES and f not in manifests:
-                    manifests[f] = content[:4000]
-                if f.lower().startswith("license") and not license_text:
-                    license_text = content[:4000]
-                if f.lower() == "readme.md" and not readme_head:
-                    readme_head = content[:4000]
-    return entries, manifests, license_text, readme_head, False
+            if state.capped(max_files, max_bytes):
+                return state.finish(truncated=True)
+            _scan_file(dirpath, prefix + f, state)
+    return state.finish(truncated=False)
+
+
+class _ScanState:
+    """Mutable accumulator for one scan_tree pass (keeps helpers small)."""
+
+    def __init__(self):
+        self.entries = []
+        self.total_bytes = 0
+        self.manifests = {}
+        self.license_text = ""
+        self.readme_head = ""
+
+    def capped(self, max_files, max_bytes):
+        return len(self.entries) >= max_files or self.total_bytes >= max_bytes
+
+    def finish(self, truncated):
+        return (
+            self.entries,
+            self.manifests,
+            self.license_text,
+            self.readme_head,
+            truncated,
+        )
+
+
+def _scan_file(dirpath, rel_entry, state):
+    filename = os.path.basename(rel_entry)
+    try:
+        size = (Path(dirpath) / filename).stat().st_size
+    except OSError:
+        return
+    if size > MAX_SINGLE_FILE_BYTES:
+        return
+    state.entries.append(rel_entry)
+    if filename in MANIFEST_FILES or Path(filename).suffix in TEXT_EXTS:
+        _capture_text(dirpath, filename, state)
+
+
+def _capture_text(dirpath, filename, state):
+    try:
+        content = (Path(dirpath) / filename).read_text(
+            encoding="utf-8", errors="replace"
+        )
+    except OSError:
+        return
+    state.total_bytes += len(content.encode("utf-8", errors="replace"))
+    snippet = content[:SNIPPET_CHARS]
+    if filename in MANIFEST_FILES and filename not in state.manifests:
+        state.manifests[filename] = snippet
+    lowered = filename.lower()
+    if lowered.startswith("license") and not state.license_text:
+        state.license_text = snippet
+    if lowered == "readme.md" and not state.readme_head:
+        state.readme_head = snippet
 
 
 def harvest_repo(
@@ -141,7 +180,7 @@ def harvest_repo(
     max_files=DEFAULT_MAX_FILES,
     max_bytes=DEFAULT_MAX_BYTES,
     timeout=DEFAULT_TIMEOUT,
-    base_dir=".research",
+    base_dir=DEFAULT_BASE_DIR,
 ):
     started = datetime.now(timezone.utc).isoformat()
     tmp = tempfile.mkdtemp(prefix="darkharvest-")
@@ -162,9 +201,7 @@ def harvest_repo(
         )
         spdx = detect_license(license_text + manifests.get("package.json", ""))
         harvestable = (
-            "depend-or-vendor"
-            if spdx in ("MIT", "Apache-2.0", "BSD-3-Clause", "ISC")
-            else "clean-room-rebuild-only"
+            "depend-or-vendor" if spdx in PERMISSIVE_SPDX else "clean-room-rebuild-only"
         )
         hasher = SourceHasher(Path(base_dir))
         cache_blob = (
@@ -174,7 +211,7 @@ def harvest_repo(
         )
         source_hash = hasher.store_source(url, cache_blob, f"Darkharvest {url}")
         warnings = []
-        if spdx in ("GPL", "AGPL"):
+        if spdx in COPYLEFT_SPDX:
             warnings.append(
                 "⚠️ LICENSE: strong copyleft — spec rebuild only, never vendor"
             )
@@ -209,7 +246,7 @@ def main():
     ap.add_argument("--max-files", type=int, default=DEFAULT_MAX_FILES)
     ap.add_argument("--max-bytes", type=int, default=DEFAULT_MAX_BYTES)
     ap.add_argument("--timeout", type=int, default=DEFAULT_TIMEOUT)
-    ap.add_argument("--dir", default=".research")
+    ap.add_argument("--dir", default=DEFAULT_BASE_DIR)
     args = ap.parse_args()
 
     if not re.match(r"^https?://", args.repo):

package/plugins/factory/skills/factory/scripts/factory.py

@@ -150,7 +150,7 @@ def cmd_expansion(args):
     state["expansion"]["loops_planned"] = n
     save_state(args.run, state)
     done = 0
-    for i in range(1, n + 1):
+    for _ in range(1, n + 1):
         if stop_requested(args.run):
             print(f"🛑 STOP file present — halting after {done}/{n} loops.")
             break

package/plugins/opencode/index.js

@@ -71,7 +71,16 @@ function callMcp(tool, args = {}, cwd = undefined) {
         [MCP_SERVER, 'call', tool, JSON.stringify(args || {})],
         {
           cwd: cwd || process.cwd(),
-          env: { ...process.env, PYTHONPATH: PKG_ROOT },
+          // Host hint: the runner defaults to the host-native backend
+          // (opencode run here), unless the caller passes backend explicitly.
+          // Project root: evidence defaults under <project>/.research instead
+          // of the server process cwd.
+          env: {
+            ...process.env,
+            PYTHONPATH: PKG_ROOT,
+            IUMBTEMS_HOST: 'opencode',
+            IUMBTEMS_PROJECT_DIR: cwd || process.cwd(),
+          },
         }
       );
     } catch (err) {
@@ -160,6 +169,11 @@ const TOOL_CATALOG = [
           description: 'Run in mock/dry-run mode without external API charges',
           default: false,
         },
+        backend: {
+          type: 'string',
+          enum: ['auto', 'claude', 'opencode'],
+          description: 'Agent runtime backend (default auto = host-native)',
+        },
       },
       required: ['objective'],
     },
@@ -180,6 +194,11 @@ const TOOL_CATALOG = [
           description: 'Run in mock mode without invoking LLM tokens',
           default: false,
         },
+        backend: {
+          type: 'string',
+          enum: ['auto', 'claude', 'opencode'],
+          description: 'Agent runtime backend (default auto = host-native)',
+        },
       },
       required: ['target'],
     },
@@ -200,6 +219,11 @@ const TOOL_CATALOG = [
           description: 'Run in mock mode without invoking LLM tokens',
           default: false,
         },
+        backend: {
+          type: 'string',
+          enum: ['auto', 'claude', 'opencode'],
+          description: 'Agent runtime backend (default auto = host-native)',
+        },
       },
       required: ['feature'],
     },
@@ -220,6 +244,11 @@ const TOOL_CATALOG = [
           description: 'Run in mock/dry-run mode without external API charges',
           default: false,
         },
+        backend: {
+          type: 'string',
+          enum: ['auto', 'claude', 'opencode'],
+          description: 'Agent runtime backend (default auto = host-native)',
+        },
       },
       required: ['objective'],
     },
@@ -253,6 +282,11 @@ const TOOL_CATALOG = [
           description: 'Run in mock mode without invoking LLM tokens',
           default: false,
         },
+        backend: {
+          type: 'string',
+          enum: ['auto', 'claude', 'opencode'],
+          description: 'Agent runtime backend (default auto = host-native)',
+        },
       },
       required: ['objective'],
     },
@@ -852,6 +886,12 @@ async function registerHostCommands(host) {
 
 async function registerHostTools(host) {
   if (typeof host?.tool?.transform !== 'function') return [];
+  // Accepted asymmetry (parity spec section 5): this plugin shape
+  // (command/tool transform + session hooks + event subscriptions) has no
+  // tool.execute.before registration point, so host webfetch/websearch calls
+  // cannot be intercepted the way Claude Code's hooks/hooks.json does.
+  // Steering lives in command templates (epistemic search first); a host API
+  // for pre-execution guards would close this for real.
   const registration = await host.tool.transform((draft) => {
     for (const [name, spec] of Object.entries(buildToolMap())) {
       draft.add({

package/plugins/opencode/tui.js

@@ -48,6 +48,68 @@ function readJson(file) {
   }
 }
 
+/** Config-derived status fields; nulls when config is absent/invalid. */
+function configFields(research) {
+  const out = { mode: null, searchEngine: null, maxIterations: null };
+  const cfg = readJson(path.join(research, 'config.json'));
+  if (cfg && typeof cfg === 'object') {
+    out.mode = cfg.mode ?? null;
+    out.searchEngine = cfg.search_engine ?? null;
+    out.maxIterations = cfg.max_iterations ?? null;
+  }
+  return out;
+}
+
+const REPORT_NAMES = [
+  'final_synthesis.md',
+  'brainstorm_report.md',
+  'code_audit_report.md',
+  'oss_scout_report.md',
+];
+
+/** Report files present in the workspace, with mtimes. */
+function presentReports(research) {
+  const reports = [];
+  for (const name of REPORT_NAMES) {
+    try {
+      const st = statSync(path.join(research, name));
+      reports.push({ name, mtimeMs: st.mtimeMs });
+    } catch {
+      /* absent report */
+    }
+  }
+  return reports;
+}
+
+/** Count of frontier nodes not yet settled/closed, or null when absent. */
+function openFrontierCount(research) {
+  const frontier = readJson(path.join(research, 'frontier.json'));
+  if (!frontier || typeof frontier !== 'object') return null;
+  const nodes = Array.isArray(frontier.nodes)
+    ? frontier.nodes
+    : Object.values(frontier.nodes || {});
+  return nodes.filter((n) => n && n.status !== 'settled' && n.status !== 'closed').length;
+}
+
+/** Degraded-claim counts from the ledger + requeue sidecar. */
+function degradedCounts(research) {
+  const out = { stale: 0, suspect: 0, requeued: 0 };
+  const ledger = readJson(path.join(research, 'ledger', 'claim_status.json'));
+  if (Array.isArray(ledger)) {
+    const last = new Map();
+    for (const e of ledger) {
+      if (e && typeof e.claim_id === 'string') last.set(e.claim_id, e.to_status);
+    }
+    for (const s of last.values()) {
+      if (s === 'STALE') out.stale += 1;
+      else if (s === 'SUSPECT') out.suspect += 1;
+    }
+  }
+  const requeue = readJson(path.join(research, 'requeue.json'));
+  if (Array.isArray(requeue)) out.requeued = requeue.length;
+  return out;
+}
+
 /**
  * Snapshot the workspace status. Pure fs reads; safe on missing workspace.
  * Exported for tests.
@@ -71,44 +133,10 @@ export function readSwarmStatus(root) {
   } catch {
     return status;
   }
-  const cfg = readJson(path.join(research, 'config.json'));
-  if (cfg && typeof cfg === 'object') {
-    status.mode = cfg.mode ?? null;
-    status.searchEngine = cfg.search_engine ?? null;
-    status.maxIterations = cfg.max_iterations ?? null;
-  }
-  for (const name of [
-    'final_synthesis.md',
-    'brainstorm_report.md',
-    'code_audit_report.md',
-    'oss_scout_report.md',
-  ]) {
-    try {
-      const st = statSync(path.join(research, name));
-      status.reports.push({ name, mtimeMs: st.mtimeMs });
-    } catch {
-      /* absent report */
-    }
-  }
-  const frontier = readJson(path.join(research, 'frontier.json'));
-  if (frontier && typeof frontier === 'object') {
-    const nodes = Array.isArray(frontier.nodes) ? frontier.nodes : Object.values(frontier.nodes || {});
-    const open = nodes.filter((n) => n && n.status !== 'settled' && n.status !== 'closed');
-    status.frontierOpen = open.length;
-  }
-  const ledger = readJson(path.join(research, 'ledger', 'claim_status.json'));
-  if (Array.isArray(ledger)) {
-    const last = new Map();
-    for (const e of ledger) {
-      if (e && typeof e.claim_id === 'string') last.set(e.claim_id, e.to_status);
-    }
-    for (const s of last.values()) {
-      if (s === 'STALE') status.stale += 1;
-      else if (s === 'SUSPECT') status.suspect += 1;
-    }
-  }
-  const requeue = readJson(path.join(research, 'requeue.json'));
-  if (Array.isArray(requeue)) status.requeued = requeue.length;
+  Object.assign(status, configFields(research));
+  status.reports = presentReports(research);
+  status.frontierOpen = openFrontierCount(research);
+  Object.assign(status, degradedCounts(research));
   return status;
 }
 

package/runner/claim_store.py

@@ -52,9 +52,15 @@ def _has_fts5(conn: sqlite3.Connection) -> bool:
 class ClaimStore:
     def __init__(self, base_dir: Path, db_path: Optional[Path] = None):
         self.base_dir = Path(os.path.realpath(str(base_dir)))
-        self.db_path = Path(os.path.realpath(str(db_path))) if db_path else (self.base_dir / "claims.sqlite")
+        self.db_path = (
+            Path(os.path.realpath(str(db_path)))
+            if db_path
+            else (self.base_dir / "claims.sqlite")
+        )
         self.db_path.parent.mkdir(parents=True, exist_ok=True)
-        self.conn = sqlite3.connect(str(self.db_path))
+        # uri=False is explicit: a plain filesystem path must never be
+        # interpreted as a SQLite URI connection string (S8706).
+        self.conn = sqlite3.connect(str(self.db_path), uri=False)
         self.conn.row_factory = sqlite3.Row
         self.fts5 = _has_fts5(self.conn)
         self._create_schema()
@@ -115,7 +121,10 @@ class ClaimStore:
             );
             """
         )
-        cur.execute("INSERT OR IGNORE INTO meta(key, value) VALUES ('schema_version', ?)", (str(SCHEMA_VERSION),))
+        cur.execute(
+            "INSERT OR IGNORE INTO meta(key, value) VALUES ('schema_version', ?)",
+            (str(SCHEMA_VERSION),),
+        )
         if self.fts5:
             cur.execute(
                 """
@@ -338,7 +347,9 @@ def reindex(base_dir: Path, store: Optional[ClaimStore] = None) -> Dict[str, Any
 
 def main(argv: Optional[List[str]] = None) -> int:
     parser = argparse.ArgumentParser(description="IUMBTEMS derived claim index")
-    parser.add_argument("--dir", default=".research", help="Path to .research workspace")
+    parser.add_argument(
+        "--dir", default=".research", help="Path to .research workspace"
+    )
     sub = parser.add_subparsers(dest="command")
     sub.add_parser("reindex", help="Rebuild claims.sqlite from flat files")
     search_p = sub.add_parser("search", help="Search claim statements")