fix: port continuous-learning observer fixes

Ports continuous-learning observer signal, storage, remote normalization, and v1 deprecation fixes onto current main.

skills/continuous-learning-v2/scripts/detect-project.sh

@@ -19,7 +19,9 @@
 #   3. git repo root path (fallback, machine-specific)
 #   4. "global" (no project context detected)
 
-_CLV2_HOMUNCULUS_DIR="${HOME}/.claude/homunculus"
+# shellcheck disable=SC1091
+. "$(dirname "${BASH_SOURCE[0]}")/lib/homunculus-dir.sh"
+_CLV2_HOMUNCULUS_DIR="$(_ecc_resolve_homunculus_dir)"
 _CLV2_PROJECTS_DIR="${_CLV2_HOMUNCULUS_DIR}/projects"
 _CLV2_REGISTRY_FILE="${_CLV2_HOMUNCULUS_DIR}/projects.json"
 
@@ -49,6 +51,30 @@ export CLV2_PYTHON_CMD
 CLV2_OBSERVER_PROMPT_PATTERN='Can you confirm|requires permission|Awaiting (user confirmation|confirmation|approval|permission)|confirm I should proceed|once granted access|grant.*access'
 export CLV2_OBSERVER_PROMPT_PATTERN
 
+_clv2_normalize_remote_url() {
+  local url="$1"
+  [ -z "$url" ] && return 0
+
+  local is_network=0
+  case "$url" in
+    file://*) is_network=0 ;;
+    *://*) is_network=1 ;;
+    *@*:*) is_network=1 ;;
+    *) is_network=0 ;;
+  esac
+
+  url=$(printf '%s' "$url" | sed -E 's|://[^@]+@|://|')
+  url=$(printf '%s' "$url" | sed -E 's|^[A-Za-z][A-Za-z0-9+.-]*://||')
+  url=$(printf '%s' "$url" | sed -E 's|^[^@/:]+@([^:/]+):|\1/|')
+  url=$(printf '%s' "$url" | sed -E 's|\.git/?$||; s|/+$||')
+
+  if [ "$is_network" = "1" ]; then
+    printf '%s' "$url" | tr '[:upper:]' '[:lower:]'
+  else
+    printf '%s' "$url"
+  fi
+}
+
 _clv2_detect_project() {
   local project_root=""
   local project_name=""
@@ -94,15 +120,20 @@ _clv2_detect_project() {
     fi
   fi
 
-  # Compute hash from the original remote URL (legacy, for backward compatibility)
-  local legacy_hash_input="${remote_url:-$project_root}"
+  local raw_remote_url="$remote_url"
 
   # Strip embedded credentials from remote URL (e.g., https://ghp_xxxx@github.com/...)
   if [ -n "$remote_url" ]; then
     remote_url=$(printf '%s' "$remote_url" | sed -E 's|://[^@]+@|://|')
   fi
 
-  local hash_input="${remote_url:-$project_root}"
+  local legacy_hash_input="${remote_url:-$project_root}"
+  local normalized_remote=""
+  if [ -n "$remote_url" ]; then
+    normalized_remote=$(_clv2_normalize_remote_url "$remote_url")
+  fi
+
+  local hash_input="${normalized_remote:-${remote_url:-$project_root}}"
   # Prefer Python for consistent SHA256 behavior across shells/platforms.
   # Pass the value via env var and encode as UTF-8 inside Python so the hash
   # is locale-independent (shells vary between UTF-8 / CP932 / CP1252, which
@@ -122,19 +153,33 @@ print(hashlib.sha256(s.encode("utf-8")).hexdigest()[:12])
                  echo "fallback")
   fi
 
-  # Backward compatibility: if credentials were stripped and the hash changed,
-  # check if a project dir exists under the legacy hash and reuse it
-  if [ "$legacy_hash_input" != "$hash_input" ] && [ -n "$_CLV2_PYTHON_CMD" ]; then
-    local legacy_id=""
-    legacy_id=$(_CLV2_HASH_INPUT="$legacy_hash_input" "$_CLV2_PYTHON_CMD" -c '
+  # Backward compatibility: migrate a single legacy project directory from
+  # credential-stripped or raw remote hashes to the normalized remote hash.
+  if [ -n "$_CLV2_PYTHON_CMD" ] && [ ! -d "${_CLV2_PROJECTS_DIR}/${project_id}" ]; then
+    local legacy_inputs=()
+    [ -n "$legacy_hash_input" ] && [ "$legacy_hash_input" != "$hash_input" ] \
+      && legacy_inputs+=("$legacy_hash_input")
+    [ -n "$raw_remote_url" ] && [ "$raw_remote_url" != "$hash_input" ] \
+      && [ "$raw_remote_url" != "$legacy_hash_input" ] \
+      && legacy_inputs+=("$raw_remote_url")
+
+    local legacy_input legacy_id
+    for legacy_input in "${legacy_inputs[@]}"; do
+      legacy_id=$(_CLV2_HASH_INPUT="$legacy_input" "$_CLV2_PYTHON_CMD" -c '
 import os, hashlib
 s = os.environ["_CLV2_HASH_INPUT"]
 print(hashlib.sha256(s.encode("utf-8")).hexdigest()[:12])
 ' 2>/dev/null)
-    if [ -n "$legacy_id" ] && [ -d "${_CLV2_PROJECTS_DIR}/${legacy_id}" ] && [ ! -d "${_CLV2_PROJECTS_DIR}/${project_id}" ]; then
-      # Migrate legacy directory to new hash
-      mv "${_CLV2_PROJECTS_DIR}/${legacy_id}" "${_CLV2_PROJECTS_DIR}/${project_id}" 2>/dev/null || project_id="$legacy_id"
-    fi
+      if [ -n "$legacy_id" ] && [ "$legacy_id" != "$project_id" ] \
+         && [ -d "${_CLV2_PROJECTS_DIR}/${legacy_id}" ]; then
+        if mv "${_CLV2_PROJECTS_DIR}/${legacy_id}" "${_CLV2_PROJECTS_DIR}/${project_id}" 2>/dev/null; then
+          break
+        else
+          project_id="$legacy_id"
+          break
+        fi
+      fi
+    done
   fi
 
   # Export results

skills/continuous-learning-v2/scripts/instinct-cli.py

@@ -38,7 +38,48 @@ except ImportError:
 # Configuration
 # ─────────────────────────────────────────────
 
-HOMUNCULUS_DIR = Path.home() / ".claude" / "homunculus"
+def _resolve_homunculus_dir() -> Path:
+    override = os.environ.get("CLV2_HOMUNCULUS_DIR")
+    if override:
+        if Path(override).is_absolute():
+            return Path(override)
+        print(f"[ecc] CLV2_HOMUNCULUS_DIR={override!r} is not absolute; ignoring", file=sys.stderr)
+
+    xdg = os.environ.get("XDG_DATA_HOME")
+    if xdg:
+        if Path(xdg).is_absolute():
+            return Path(xdg) / "ecc-homunculus"
+        print(f"[ecc] XDG_DATA_HOME={xdg!r} is not absolute; ignoring", file=sys.stderr)
+
+    return Path.home() / ".local" / "share" / "ecc-homunculus"
+
+
+def _strip_remote_credentials(remote_url: str) -> str:
+    return re.sub(r"://[^@]+@", "://", remote_url or "")
+
+
+def _normalize_remote_url(remote_url: str) -> str:
+    if not remote_url:
+        return ""
+
+    is_network = (
+        not remote_url.startswith("file://")
+        and ("://" in remote_url or re.match(r"^[^@/:]+@[^:/]+:", remote_url) is not None)
+    )
+    normalized = _strip_remote_credentials(remote_url)
+    normalized = re.sub(r"^[A-Za-z][A-Za-z0-9+.-]*://", "", normalized)
+    normalized = re.sub(r"^[^@/:]+@([^:/]+):", r"\1/", normalized)
+    normalized = re.sub(r"\.git/?$", "", normalized)
+    normalized = re.sub(r"/+$", "", normalized)
+
+    return normalized.lower() if is_network else normalized
+
+
+def _project_hash(value: str) -> str:
+    return hashlib.sha256(value.encode("utf-8")).hexdigest()[:12]
+
+
+HOMUNCULUS_DIR = _resolve_homunculus_dir()
 PROJECTS_DIR = HOMUNCULUS_DIR / "projects"
 REGISTRY_FILE = HOMUNCULUS_DIR / "projects.json"
 
@@ -177,11 +218,35 @@ def detect_project() -> dict:
     except (subprocess.TimeoutExpired, FileNotFoundError):
         pass
 
-    hash_source = remote_url if remote_url else project_root
-    project_id = hashlib.sha256(hash_source.encode()).hexdigest()[:12]
+    raw_remote_url = remote_url
+    if remote_url:
+        remote_url = _strip_remote_credentials(remote_url)
+
+    legacy_hash_source = remote_url if remote_url else project_root
+    normalized_remote = _normalize_remote_url(remote_url) if remote_url else ""
+    hash_source = normalized_remote if normalized_remote else legacy_hash_source
+    project_id = _project_hash(hash_source)
 
     project_dir = PROJECTS_DIR / project_id
 
+    if not project_dir.exists():
+        legacy_sources = []
+        if legacy_hash_source and legacy_hash_source != hash_source:
+            legacy_sources.append(legacy_hash_source)
+        if raw_remote_url and raw_remote_url not in {hash_source, legacy_hash_source}:
+            legacy_sources.append(raw_remote_url)
+
+        for legacy_source in legacy_sources:
+            legacy_id = _project_hash(legacy_source)
+            legacy_dir = PROJECTS_DIR / legacy_id
+            if legacy_id != project_id and legacy_dir.exists():
+                try:
+                    legacy_dir.rename(project_dir)
+                except OSError:
+                    project_id = legacy_id
+                    project_dir = legacy_dir
+                break
+
     # Ensure project directory structure
     for d in [
         project_dir / "instincts" / "personal",

skills/continuous-learning-v2/scripts/lib/homunculus-dir.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+# Shared continuous-learning-v2 data-directory resolver.
+#
+# Resolution precedence:
+#   1. CLV2_HOMUNCULUS_DIR, when absolute
+#   2. XDG_DATA_HOME/ecc-homunculus, when XDG_DATA_HOME is absolute
+#   3. HOME/.local/share/ecc-homunculus
+
+_ecc_resolve_homunculus_dir() {
+  if [ -n "${CLV2_HOMUNCULUS_DIR:-}" ]; then
+    case "$CLV2_HOMUNCULUS_DIR" in
+      /*) printf '%s\n' "$CLV2_HOMUNCULUS_DIR"; return 0 ;;
+      *) printf '[ecc] CLV2_HOMUNCULUS_DIR=%s is not absolute; ignoring\n' "$CLV2_HOMUNCULUS_DIR" >&2 ;;
+    esac
+  fi
+
+  if [ -n "${XDG_DATA_HOME:-}" ]; then
+    case "$XDG_DATA_HOME" in
+      /*) printf '%s/ecc-homunculus\n' "$XDG_DATA_HOME"; return 0 ;;
+      *) printf '[ecc] XDG_DATA_HOME=%s is not absolute; ignoring\n' "$XDG_DATA_HOME" >&2 ;;
+    esac
+  fi
+
+  case "${HOME:-}" in
+    /*) printf '%s/.local/share/ecc-homunculus\n' "$HOME" ;;
+    *)
+      printf '[ecc] HOME=%s is not absolute; cannot resolve homunculus dir\n' "${HOME:-}" >&2
+      return 1
+      ;;
+  esac
+}

skills/continuous-learning-v2/scripts/migrate-homunculus.sh

@@ -0,0 +1,62 @@
+#!/usr/bin/env bash
+# One-shot migration from the legacy Claude config tree into the
+# continuous-learning-v2 data directory.
+set -euo pipefail
+
+OLD="${HOME}/.claude/homunculus"
+
+# shellcheck disable=SC1091
+. "$(dirname "$0")/lib/homunculus-dir.sh"
+NEW="$(_ecc_resolve_homunculus_dir)"
+
+if [ "$NEW" = "$OLD" ]; then
+  echo "Resolved destination equals source ($OLD); nothing to migrate."
+  exit 0
+fi
+
+if [ ! -d "$OLD" ]; then
+  echo "Nothing to migrate (no $OLD)."
+  exit 0
+fi
+
+if command -v pgrep >/dev/null 2>&1; then
+  if pgrep -f "${HOME}.*observer-loop\\.sh" >/dev/null 2>&1; then
+    echo "Refusing to migrate: observer-loop.sh is running." >&2
+    echo "Exit all Claude Code sessions, then re-run." >&2
+    exit 1
+  fi
+else
+  echo "Warning: pgrep not available; skipping running-observer check." >&2
+fi
+
+mkdir -p "$(dirname "$NEW")"
+
+if [ ! -d "$NEW" ]; then
+  mv "$OLD" "$NEW"
+  echo "Moved $OLD -> $NEW"
+elif [ -z "$(ls -A "$NEW" 2>/dev/null || true)" ]; then
+  rmdir "$NEW"
+  mv "$OLD" "$NEW"
+  echo "Moved $OLD -> $NEW (replaced empty destination)"
+else
+  old_count="$(find "$OLD" -type f 2>/dev/null | wc -l | tr -d ' ')"
+  new_count="$(find "$NEW" -type f 2>/dev/null | wc -l | tr -d ' ')"
+  echo "Refusing to migrate: both paths exist with content." >&2
+  echo "  Old: $OLD ($old_count files)" >&2
+  echo "  New: $NEW ($new_count files)" >&2
+  echo "Resolve manually, then re-run." >&2
+  exit 1
+fi
+
+settings="${HOME}/.claude/settings.json"
+if [ -f "$settings" ] && grep -q '"CLV2_CONFIG"' "$settings" 2>/dev/null; then
+  if grep -q '\.claude/homunculus' "$settings" 2>/dev/null; then
+    cat >&2 <<WARN
+
+Advisory: ~/.claude/settings.json still sets CLV2_CONFIG under the old path.
+Update it to: ${NEW}/config.json
+(Not editing settings.json automatically.)
+
+WARN
+  fi
+fi