fix(claude): honor CLAUDE_CONFIG_DIR when listing session history (#374)

Author: mbektas

CHANGELOG.md

@@ -14,6 +14,10 @@ For each release we list user-facing changes grouped as **Added**, **Changed**,
 
 - **Provider SDKs load on first use instead of at module import** (#370). `import notebook_intelligence` no longer imports `litellm`, `openai`, `ollama`, or the `anthropic` SDK; `litellm`, `openai`, and `anthropic` load the first time their provider is actually used (for Claude mode that includes the client construction and model refresh NBI runs at startup), while `ollama` still loads during extension startup when the provider enumerates local models. This roughly halves the server-extension import time (a cost the Jupyter server pays on every start), with the biggest effect on Windows machines where antivirus scanning amplifies the many-small-file SDK imports (#368). When NBI does load litellm, it now defaults `LITELLM_LOCAL_MODEL_COST_MAP=true` so litellm reads its bundled model-cost map rather than fetching it over HTTP at import; set the env var to `false` to restore the fetch.
 
+### Fixed
+
+- **Session history follows `CLAUDE_CONFIG_DIR`** (#373). The chat-sidebar resume picker and the launcher tile's session list always read transcripts from `~/.claude/projects`, so both came up empty when the Claude CLI was configured with `CLAUDE_CONFIG_DIR` and wrote its transcripts elsewhere. The session listing now resolves the CLI's config dir the same way the skills and spinner-verbs paths already did.
+
 ## [5.1.0] - UNRELEASED
 
 5.1.0 builds on 5.0.x with a focus on Claude-mode agent visibility. Tool calls the agent runs now render as persistent status cards with inline diffs and collapsible grouping, the generating indicator can cycle custom verbs, and cancelling a turn tears down the whole process tree the agent spawned instead of leaking it. It also adds two opt-in security guardrails (an MCP stdio-command allowlist and a default-token-password check on shared filesystems) and an always-visible mode for chat feedback. No traitlet, env-var, REST route, or on-disk-format renames or removals; every new admin surface is opt-in and listed below.

docs/admin-guide.md

@@ -46,16 +46,16 @@ Manual edits to `config.json` while JupyterLab is running require a JupyterLab r
 
 ## Persistent-volume layout
 
-| Path                                      | Persist?    | Notes                                                                                                                           |
-| ----------------------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------- |
-| `~/.jupyter/nbi/config.json`              | Yes         | User's chosen provider, models, MCP servers, plus plaintext API keys. Treat as a secret.                                        |
-| `~/.jupyter/nbi/user-data.json`           | Yes         | Encrypted GitHub Copilot access token, written when "remember login" is enabled. Encrypted with `NBI_GH_ACCESS_TOKEN_PASSWORD`. |
-| `~/.jupyter/nbi/rules/`                   | Yes         | User's ruleset markdown files.                                                                                                  |
-| `~/.jupyter/nbi/mcp.json`                 | Yes         | User's MCP server config (alternative to managing via the Settings dialog).                                                     |
-| `~/.claude/skills/`                       | Yes         | User-scope Claude skills (including managed skills).                                                                            |
-| `~/.claude/projects/`                     | Yes         | Claude Code session transcripts. Required for "Resume previous Claude session". Managed by Claude CLI, not NBI.                 |
-| `<env-prefix>/share/jupyter/nbi/`         | No (image)  | Org-wide base config. Bake into your container image.                                                                           |
-| Project-scope `<project>/.claude/skills/` | Per project | Lives in the user's working directory. Persists if the working directory does.                                                  |
+| Path                                      | Persist?    | Notes                                                                                                                                                                                                                                               |
+| ----------------------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `~/.jupyter/nbi/config.json`              | Yes         | User's chosen provider, models, MCP servers, plus plaintext API keys. Treat as a secret.                                                                                                                                                            |
+| `~/.jupyter/nbi/user-data.json`           | Yes         | Encrypted GitHub Copilot access token, written when "remember login" is enabled. Encrypted with `NBI_GH_ACCESS_TOKEN_PASSWORD`.                                                                                                                     |
+| `~/.jupyter/nbi/rules/`                   | Yes         | User's ruleset markdown files.                                                                                                                                                                                                                      |
+| `~/.jupyter/nbi/mcp.json`                 | Yes         | User's MCP server config (alternative to managing via the Settings dialog).                                                                                                                                                                         |
+| `~/.claude/skills/`                       | Yes         | User-scope Claude skills (including managed skills).                                                                                                                                                                                                |
+| `~/.claude/projects/`                     | Yes         | Claude Code session transcripts. Required for "Resume previous Claude session". Managed by Claude CLI, not NBI. When `CLAUDE_CONFIG_DIR` is set, this (and `~/.claude/skills/`) lives under `$CLAUDE_CONFIG_DIR` instead; NBI follows the override. |
+| `<env-prefix>/share/jupyter/nbi/`         | No (image)  | Org-wide base config. Bake into your container image.                                                                                                                                                                                               |
+| Project-scope `<project>/.claude/skills/` | Per project | Lives in the user's working directory. Persists if the working directory does.                                                                                                                                                                      |
 
 For Kubeflow or KubeSpawner: mount the user's home directory on a PVC and ensure `~/.jupyter` and `~/.claude` are inside that mount. Anything else (`/tmp`, `~/.cache`) can be ephemeral.
 

docs/troubleshooting.md

@@ -112,6 +112,8 @@ ls ~/.claude/skills/             # Claude skills
 ls ~/.claude/projects/           # Claude session transcripts
 ```
 
+If `CLAUDE_CONFIG_DIR` is set, the Claude CLI keeps its skills and session transcripts under `$CLAUDE_CONFIG_DIR` instead of `~/.claude`, and NBI reads from the same place.
+
 > Do not share the contents of `~/.jupyter/nbi/config.json` or `~/.jupyter/nbi/user-data.json` — they contain API keys or your encrypted GitHub token.
 
 ## "Skills reloaded" banner keeps appearing

notebook_intelligence/claude_sessions.py

@@ -4,10 +4,12 @@
 
 Claude Code persists each conversation as a line-delimited JSON file at::
 
-    ~/.claude/projects/<cwd-encoded>/<session-id>.jsonl
+    <claude-config-dir>/projects/<cwd-encoded>/<session-id>.jsonl
 
-where ``<cwd-encoded>`` is the session cwd with path separators replaced by
-dashes (e.g. ``/Users/me/proj`` -> ``-Users-me-proj``).
+where ``<claude-config-dir>`` is ``~/.claude`` unless the CLI's
+``CLAUDE_CONFIG_DIR`` env var overrides it, and ``<cwd-encoded>`` is the
+session cwd with path separators replaced by dashes (e.g.
+``/Users/me/proj`` -> ``-Users-me-proj``).
 
 This module reads those files for the current Jupyter working directory and
 returns lightweight metadata (id, timestamps, first user message preview) so
@@ -32,6 +34,8 @@
 from pathlib import Path
 from typing import Optional
 
+from notebook_intelligence.util import get_claude_config_dir
+
 log = logging.getLogger(__name__)
 
 _PREVIEW_MAX_CHARS = 160
@@ -104,10 +108,10 @@ def encode_cwd(cwd: str) -> str:
 def get_sessions_dir(cwd: str, claude_home: Optional[str] = None) -> Path:
     """Return the directory containing session transcripts for ``cwd``.
 
-    ``claude_home`` defaults to ``~/.claude`` but can be overridden (useful
-    for tests and for the ``CLAUDE_CONFIG_DIR`` convention).
+    ``claude_home`` defaults to the CLI's own config dir (``CLAUDE_CONFIG_DIR``
+    when set, else ``~/.claude``) but can be overridden, mainly for tests.
     """
-    home = Path(claude_home) if claude_home else Path.home() / ".claude"
+    home = Path(claude_home) if claude_home else Path(get_claude_config_dir())
     return home / "projects" / encode_cwd(cwd)
 
 
@@ -393,8 +397,8 @@ def list_all_sessions(
 ) -> list[ClaudeSessionInfo]:
     """List every resumable Claude session on disk, newest first.
 
-    Walks ``~/.claude/projects/*/`` directly so the result is the same
-    set of sessions ``claude --resume`` can recover. ``history.jsonl`` is
+    Walks ``<claude-config-dir>/projects/*/`` directly so the result is the
+    same set of sessions ``claude --resume`` can recover. ``history.jsonl`` is
     NOT used as a gating source because recent Claude Code versions don't
     reliably populate it (notably for SDK-driven invocations), and
     history-first lookups silently dropped real, on-disk sessions.
@@ -412,7 +416,7 @@ def list_all_sessions(
     activity. Per-transcript parse results are mtime-cached so repeated
     calls don't reparse every file.
     """
-    home = Path(claude_home) if claude_home else Path.home() / ".claude"
+    home = Path(claude_home) if claude_home else Path(get_claude_config_dir())
     projects_dir = home / "projects"
 
     sessions: list[ClaudeSessionInfo] = []

notebook_intelligence/config.py

@@ -8,6 +8,7 @@
 import tempfile
 from typing import Optional
 
+from notebook_intelligence.util import get_claude_config_dir
 from notebook_intelligence.feature_flags import (
     CHAT_MODEL_OVERRIDES,
     CLAUDE_SETTINGS_OVERRIDES,
@@ -219,8 +220,7 @@ def rules_directory(self) -> str:
     def user_skills_directory(self) -> str:
         # Mirrors Claude's own CLAUDE_CONFIG_DIR override so the extension picks up
         # skills from the same directory Claude is using.
-        base = os.environ.get('CLAUDE_CONFIG_DIR') or os.path.join(os.path.expanduser('~'), '.claude')
-        return os.path.join(base, 'skills')
+        return os.path.join(get_claude_config_dir(), 'skills')
 
     def project_skills_directory(self, project_root: str) -> str:
         return os.path.join(project_root, '.claude', 'skills')

notebook_intelligence/extension.py

@@ -63,7 +63,7 @@
 )
 import notebook_intelligence.github_copilot as github_copilot
 from notebook_intelligence.built_in_toolsets import built_in_toolsets
-from notebook_intelligence.util import ThreadSafeWebSocketConnector, get_jupyter_root_dir, set_jupyter_root_dir, is_builtin_tool_enabled_in_env, is_provider_enabled_in_env, VALID_CODING_AGENT_LAUNCHERS, compute_effective_disabled_launchers, validate_coding_agent_launcher_ids, resolve_claude_cli_path, resolve_opencode_cli_path, resolve_pi_cli_path, resolve_copilot_cli_path, resolve_codex_cli_path, safe_anchor_uri, has_dangerous_text_codepoints, split_csv
+from notebook_intelligence.util import ThreadSafeWebSocketConnector, get_claude_config_dir, get_jupyter_root_dir, set_jupyter_root_dir, is_builtin_tool_enabled_in_env, is_provider_enabled_in_env, VALID_CODING_AGENT_LAUNCHERS, compute_effective_disabled_launchers, validate_coding_agent_launcher_ids, resolve_claude_cli_path, resolve_opencode_cli_path, resolve_pi_cli_path, resolve_copilot_cli_path, resolve_codex_cli_path, safe_anchor_uri, has_dangerous_text_codepoints, split_csv
 from notebook_intelligence.context_factory import RuleContextFactory
 from notebook_intelligence.skillset import SKILL_NAME_REGEX
 
@@ -428,10 +428,7 @@ def _scrub_credentials_for_wire(claude_settings: dict, string_overrides: dict) -
 
 
 def _read_claude_spinner_verbs() -> Optional[dict]:
-    settings_path = os.path.join(
-        os.environ.get('CLAUDE_CONFIG_DIR') or os.path.join(os.path.expanduser('~'), '.claude'),
-        'settings.json'
-    )
+    settings_path = os.path.join(get_claude_config_dir(), 'settings.json')
     try:
         with open(settings_path) as f:
             data = json.load(f)

notebook_intelligence/util.py

@@ -95,6 +95,19 @@ def safe_jupyter_path(path: str) -> Path:
     return target_path
 
 
+def get_claude_config_dir() -> str:
+    """Claude Code's config dir: CLAUDE_CONFIG_DIR when set, else ``~/.claude``.
+
+    Mirrors the CLI's own override so every surface that reads CLI-owned
+    state (session transcripts, skills, settings.json) looks where the CLI
+    actually writes. Read per call rather than memoized: it's a dict lookup,
+    and tests toggle the env var between cases.
+    """
+    return os.environ.get("CLAUDE_CONFIG_DIR") or os.path.join(
+        os.path.expanduser("~"), ".claude"
+    )
+
+
 _cached_cli_paths: dict[str, Optional[str]] = {}
 
 

tests/test_claude_sessions.py

@@ -974,3 +974,64 @@ def counting_reader(path):
         second = list_all_sessions(claude_home=str(fake_claude_home))
         assert len(second) == 1
         assert call_count["n"] == 0  # served from cache
+
+
+class TestClaudeConfigDirDefault:
+    """The claude_home default must follow CLAUDE_CONFIG_DIR (issue #373).
+
+    The CLI writes transcripts under $CLAUDE_CONFIG_DIR/projects when the
+    env var is set; the handler calls list_all_sessions without a
+    claude_home, so the default is what production traffic exercises.
+    """
+
+    def test_get_sessions_dir_honors_claude_config_dir(
+        self, monkeypatch, tmp_path
+    ):
+        override = tmp_path / "workspace" / ".claude"
+        monkeypatch.setenv("CLAUDE_CONFIG_DIR", str(override))
+        result = get_sessions_dir("/some/cwd")
+        assert result == override / "projects" / encode_cwd("/some/cwd")
+
+    def test_get_sessions_dir_defaults_to_home_claude(
+        self, monkeypatch, tmp_path
+    ):
+        monkeypatch.delenv("CLAUDE_CONFIG_DIR", raising=False)
+        monkeypatch.setenv("HOME", str(tmp_path))
+        monkeypatch.setenv("USERPROFILE", str(tmp_path))
+        result = get_sessions_dir("/some/cwd")
+        assert result == tmp_path / ".claude" / "projects" / encode_cwd(
+            "/some/cwd"
+        )
+
+    def test_list_all_sessions_reads_claude_config_dir(
+        self, monkeypatch, tmp_path
+    ):
+        override = tmp_path / "workspace" / ".claude"
+        cwd = str(tmp_path / "proj")
+        _write_jsonl(
+            override / "projects" / encode_cwd(cwd) / "abc.jsonl",
+            [_user_line("abc", "hello from the override dir", cwd=cwd)],
+        )
+        monkeypatch.setenv("CLAUDE_CONFIG_DIR", str(override))
+
+        sessions = list_all_sessions()
+
+        assert [s.session_id for s in sessions] == ["abc"]
+        assert sessions[0].preview == "hello from the override dir"
+
+    def test_list_all_sessions_ignores_home_claude_when_overridden(
+        self, monkeypatch, tmp_path
+    ):
+        home = tmp_path / "home"
+        cwd = str(tmp_path / "proj")
+        _write_jsonl(
+            home / ".claude" / "projects" / encode_cwd(cwd) / "old.jsonl",
+            [_user_line("old", "stale home transcript", cwd=cwd)],
+        )
+        override = tmp_path / "workspace" / ".claude"
+        override.mkdir(parents=True)
+        monkeypatch.setenv("HOME", str(home))
+        monkeypatch.setenv("USERPROFILE", str(home))
+        monkeypatch.setenv("CLAUDE_CONFIG_DIR", str(override))
+
+        assert list_all_sessions() == []