You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 4652bed
Browse filesBrowse the repository at this point in the historyBrowse files
fix: keep data_diff and the tool daemon within read-only and release rules; address review findings
- data_diff refuses any source, target or where_clause that is not one complete read-only
query (classifier read, single statement, balanced parentheses, no side-effect or dynamic
query() calls) before connecting, checks every statement it runs, and opens every
connector read-only. sql_check keeps its stricter rules (shared read-only-sql helper).
- isBlockedStatement classifies the whole pattern, so leading comments and multi-statement
patterns stay hard-blocked.
- Redshift values in batch references get their backslashes escaped.
- Tool daemon: the idle timer waits for a pending file release; only a request that ran a
tool leads to a release, and a stop is answered without waiting for one; the socket is
owner-only.
- Workspace: refresh clears the active adapter before closing it; a snapshot removed
mid-read lists no skills; copies into .claude/skills are opt-in with
ALTIMATE_CLAUDE_SKILL_SYNC=1 (the Claude Code plugin sets it).
- Analyst effort ignores non-object model params and output_config without effort; managed
output preferences resolve files against their own directory; warehouse_add shares the
registry's project root; mcp --allow-write help names the hard blocks.
- Docs for warehouse_add's local writes, Claude Code skill copies, analyst effort and
answer_commit; tests for each change.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Copy file name to clipboardExpand all lines: docs/docs/configure/agents.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -30,6 +30,8 @@ The agent for asking questions about your data. Truly read-only mode for safe da
30
30
-**Schema/warehouse/finops**: All inspection tools available
31
31
-**Workspace knowledge**: Loads workspace and project skills; reads workspace memory and views this checkout's memory audit log. Can read files bundled with skills, including global skills stored outside the project. Reloading memory syncs the local copy with the workspace, which can remove a local copy of a block the workspace archived. Saving memory is done with `builder`.
32
32
-**Config overrides**: A permission config such as `"*": "allow"` cannot turn file edits, SQL writes (including data diffs of arbitrary queries), shell, memory saves, warehouse connection or MCP config changes, training imports, sample project setup, feedback submission, batch tool calls or delegation beyond `data-explorer` back on. A global `"*": "allow"` does turn on MCP and custom tools for analyst, including ones that write (for example a SQL MCP server); to keep them from analyst, put the `"*": "allow"` under `agent.builder` instead of the global config, or deny those tools under `agent.analyst.permission`.
33
+
-**Reasoning effort**: On adaptive-thinking models the analyst requests `high` effort unless the agent or model options already choose one. Set `ALTIMATE_ANALYST_EFFORT` (`low`, `medium`, `high`, `xhigh`, `max`, or `off` to send none) to change it.
34
+
-**Final answers**: `answer_commit` asks the interactive analyst once per turn to re-check any number that did not appear in tool output before the answer is committed.
33
35
34
36
!!! tip
35
37
Use `analyst` when exploring data to ensure no accidental writes. Switch to `builder` when you're ready to create or modify models.
Source writes are refused by default. Without `--allow-write`, source queries request database-enforced read-only execution on PostgreSQL, SQLite and DuckDB. For other connection types, read-only is enforced by SQL classification only; stored functions with side effects are not blocked — use a read-only database user. The server prints this caveat on stderr at startup and includes it in `warehouse_list` for each affected connection. Add `--allow-write` to enable SQL write permissions; existing hard safety blocks still apply. `sql_materialize` always requires a read-only source query and writes only into the server session's temporary `scratch` warehouse. Scratch tables disappear when the server exits. Large results may include a local spill file path that your client can open with any file reader. Spill files use a private directory and are deleted when the server exits. Local `tool_output.max_lines` and `tool_output.max_bytes` settings control output limits; remote agent configuration is not loaded.
40
+
Source writes are refused by default. Without `--allow-write`, source queries request database-enforced read-only execution on PostgreSQL, SQLite and DuckDB. For other connection types, read-only is enforced by SQL classification only; stored functions with side effects are not blocked — use a read-only database user. The server prints this caveat on stderr at startup and includes it in `warehouse_list` for each affected connection. Add `--allow-write` to enable SQL write permissions; existing hard safety blocks still apply (`DROP DATABASE`, `DROP SCHEMA` and `TRUNCATE` stay blocked). `warehouse_add` may write local connection configuration (the connections file and the operating system credential store) even in read-only mode. `sql_materialize` always requires a read-only source query and writes only into the server session's temporary `scratch` warehouse. Scratch tables disappear when the server exits. Large results may include a local spill file path that your client can open with any file reader. Spill files use a private directory and are deleted when the server exits. Local `tool_output.max_lines` and `tool_output.max_bytes` settings control output limits; remote agent configuration is not loaded.
Copy file name to clipboardExpand all lines: docs/docs/configure/skills.md
+4Lines changed: 4 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -341,3 +341,7 @@ The skill list the agent sees marks each skill with where it was found:
341
341
When more than one skill fits a task, the agent is told to load the one from the highest source in that order, and to fall back to a lower source only when nothing higher covers the task. So a skill your team added to the workspace is preferred over a similar skill another team left in the repository. The label comes from the skill's location, not from anything written in the skill.
342
342
343
343
One exception: a project skill with exactly the same name as a workspace skill replaces it, and is listed as `project`. That keeps a skill you are editing in the repository, and may later publish, from being shadowed by the workspace's older copy.
344
+
345
+
### Copies for Claude Code
346
+
347
+
In a linked project that has a `.claude` directory, each workspace sync can also write the workspace skills into `.claude/skills/` so Claude Code finds them. Copies are written only when `ALTIMATE_CLAUDE_SKILL_SYNC=1` is set; the Altimate Code plugin for Claude Code sets it when it refreshes the workspace. The copies are marked as owned by Altimate Code and git-ignored, and they are withdrawn when you unlink the project or sign out (withdrawal runs whether or not the variable is set).
0 commit comments