* fix: harden NL2SQLTool — read-only by default, parameterized queries, query validation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: address CI lint failures and remove unused import
- Remove unused `sessionmaker` import from test_nl2sql_security.py
- Use `Self` return type on `_apply_env_override` (fixes UP037/F821)
- Fix ruff errors auto-fixed in lib/crewai (UP007, etc.)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: expand _WRITE_COMMANDS and block multi-statement semicolon injection
- Add missing write commands: UPSERT, LOAD, COPY, VACUUM, ANALYZE,
ANALYSE, REINDEX, CLUSTER, REFRESH, COMMENT, SET, RESET
- _validate_query() now splits on ';' and validates each statement
independently; multi-statement queries are rejected outright in
read-only mode to prevent 'SELECT 1; DROP TABLE users' bypass
- Extract single-statement logic into _validate_statement() helper
- Add TestSemicolonInjection and TestExtendedWriteCommands test classes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* ci: retrigger
* fix: use typing_extensions.Self for Python 3.10 compat
* chore: update tool specifications
* docs: document NL2SQLTool read-only default and DML configuration
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: close three NL2SQLTool security gaps (writable CTEs, EXPLAIN ANALYZE, multi-stmt commit)
- Remove WITH from _READ_ONLY_COMMANDS; scan CTE body for write keywords so
writable CTEs like `WITH d AS (DELETE …) SELECT …` are blocked in read-only mode.
- EXPLAIN ANALYZE/ANALYSE now resolves the underlying command; EXPLAIN ANALYZE DELETE
is treated as a write and blocked in read-only mode.
- execute_sql commit decision now checks ALL semicolon-separated statements so
a SELECT-first batch like `SELECT 1; DROP TABLE t` still triggers a commit
when allow_dml=True.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: handle parenthesized EXPLAIN options syntax; remove unused _seed_db
_validate_statement now strips parenthesized options from EXPLAIN (e.g.
EXPLAIN (ANALYZE) DELETE, EXPLAIN (ANALYZE, VERBOSE) DELETE) before
checking whether ANALYZE/ANALYSE is present — closing the bypass where
the options-list form was silently allowed in read-only mode.
Adds three new tests:
- EXPLAIN (ANALYZE) DELETE → blocked
- EXPLAIN (ANALYZE, VERBOSE) DELETE → blocked
- EXPLAIN (VERBOSE) SELECT → allowed
Also removes the unused _seed_db helper from test_nl2sql_security.py.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: update tool specifications
* fix: smarter CTE write detection, fix commit logic for writable CTEs
- Replace naive token-set matching with positional AS() body inspection
to avoid false positives on column names like 'comment', 'set', 'reset'
- Fix execute_sql commit logic to detect writable CTEs (WITH + DELETE/INSERT)
not just top-level write commands
- Add tests for false positive cases and writable CTE commit behavior
- Format nl2sql_tool.py to pass ruff format check
* fix: catch write commands in CTE main query + handle whitespace in AS()
- WITH cte AS (SELECT 1) DELETE FROM users now correctly blocked
- AS followed by newline/tab/multi-space before ( now detected
- execute_sql commit logic updated for both cases
- 4 new tests
* fix: EXPLAIN ANALYZE VERBOSE handling, string literal paren bypass, commit logic for EXPLAIN ANALYZE
- EXPLAIN handler now consumes all known options (ANALYZE, ANALYSE, VERBOSE) before
extracting the real command, fixing 'EXPLAIN ANALYZE VERBOSE SELECT' being blocked
- Paren walker in _extract_main_query_after_cte now skips string literals, preventing
'WITH cte AS (SELECT '\''('\'' FROM t) DELETE FROM users' from bypassing detection
- _is_write_stmt in execute_sql now resolves EXPLAIN ANALYZE to underlying command
via _resolve_explain_command, ensuring session.commit() fires for write operations
- 10 new tests covering all three fixes
* fix: deduplicate EXPLAIN parsing, fix AS( regex in strings, block unknown CTE commands, bump langchain-core
- Refactor _validate_statement to use _resolve_explain_command (single source of truth)
- _iter_as_paren_matches skips string literals so 'AS (' in data doesn't confuse CTE detection
- Unknown commands after CTE definitions now blocked in read-only mode
- Bump langchain-core override to >=1.2.28 (GHSA-926x-3r5x-gfhw)
* fix: add return type annotation to _iter_as_paren_matches
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
The spec generator previously used a hardcoded list of field names to
exclude from init_params_schema. Any new field or computed_field added
to BaseTool (like tool_type from 86ce54f) would silently leak into
tool.specs.json unless someone remembered to update that list.
Now _extract_init_params() dynamically computes BaseTool's fields at
import time via model_fields + model_computed_fields, so any future
additions to BaseTool are automatically excluded.
Fields from intermediate base classes (RagTool, BraveSearchToolBase,
SerpApiBaseTool) are correctly preserved since they're not on BaseTool.
TDD:
- RED: 3 new tests confirming BaseTool field leak, intermediate base
preservation, and future-proofing — all failed before the fix
- GREEN: Dynamic allowlist applied — all 10 tests pass
- Regenerated tool.specs.json (tool_type removed from all tools)
* fix: add SSRF and path traversal protections
CVE-2026-2286: validate_url blocks non-http/https schemes, private
IPs, loopback, link-local, reserved addresses. Applied to 11 web tools.
CVE-2026-2285: validate_path confines file access to the working
directory. Applied to 7 file and directory tools.
* fix: drop unused assignment from validate_url call
* fix: DNS rebinding protection and allow_private flag
Rewrite validated URLs to use the resolved IP, preventing DNS rebinding
between validation and request time. SDK-based tools use pin_ip=False
since they manage their own HTTP clients. Add allow_private flag for
deployments that need internal network access.
* fix: unify security utilities and restore RAG chokepoint validation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor: move validation to security/ package + address review comments
- Move safe_path.py to crewai_tools/security/; add safe_url.py re-export
- Keep utilities/safe_path.py as a backwards-compat shim
- Update all 21 import sites to use crewai_tools.security.safe_path
- files_compressor_tool: validate output_path (user-controlled)
- serper_scrape_website_tool: call validate_url() before building payload
- brightdata_unlocker: validate_url() already called without assignment (no-op fix)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor: move validation to security/ package, keep utilities/ as compat shim
- security/safe_path.py is the canonical location for all validation
- utilities/safe_path.py re-exports for backward compatibility
- All tool imports already point to security.safe_path
- All review comments already addressed in prior commits
* fix: move validation outside try/except blocks, use correct directory validator
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: use resolved paths from validation to prevent symlink TOCTOU, remove unused safe_url.py
---------
Co-authored-by: Alex <alex@crewai.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: add path and URL validation to RAG tools
Add validation utilities to prevent unauthorized file reads and SSRF
when RAG tools accept LLM-controlled paths/URLs at runtime.
Changes:
- New crewai_tools.utilities.safe_path module with validate_file_path(),
validate_directory_path(), and validate_url()
- File paths validated against base directory (defaults to cwd).
Resolves symlinks and ../ traversal. Rejects escape attempts.
- URLs validated: file:// blocked entirely. HTTP/HTTPS resolves DNS
and blocks private/reserved IPs (10.x, 172.16-31.x, 192.168.x,
127.x, 169.254.x, 0.0.0.0, ::1, fc00::/7).
- Validation applied in RagTool.add() — catches all RAG search tools
(JSON, CSV, PDF, TXT, DOCX, MDX, Directory, etc.)
- Removed file:// scheme support from DataTypes.from_content()
- CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true env var for backward compat
- 27 tests covering traversal, symlinks, private IPs, cloud metadata,
IPv6, escape hatch, and valid paths/URLs
* fix: validate path/URL keyword args in RagTool.add()
The original patch validated positional *args but left all keyword
arguments (path=, file_path=, directory_path=, url=, website=,
github_url=, youtube_url=) unvalidated, providing a trivial bypass
for both path-traversal and SSRF checks.
Applies validate_file_path() to path/file_path/directory_path kwargs
and validate_url() to url/website/github_url/youtube_url kwargs before
they reach the adapter. Adds a regression-test file covering all eight
kwarg vectors plus the two existing positional-arg checks.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: address CodeQL and review comments on RAG path/URL validation
- Replace insecure tempfile.mktemp() with inline symlink target in test
- Remove unused 'target' variable and unused tempfile import
- Narrow broad except Exception: pass to only catch urlparse errors;
validate_url ValueError now propagates instead of being silently swallowed
- Fix ruff B904 (raise-without-from-inside-except) in safe_path.py
- Fix ruff B007 (unused loop variable 'family') in safe_path.py
- Use validate_directory_path in DirectorySearchTool.add() so the
public utility is exercised in production code
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* style: fix ruff format + remaining lint issues
* fix: resolve mypy type errors in RAG path/URL validation
- Cast sockaddr[0] to str() to satisfy mypy (socket.getaddrinfo returns
sockaddr where [0] is str but typed as str | int)
- Remove now-unnecessary `type: ignore[assignment]` and
`type: ignore[literal-required]` comments in rag_tool.py
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: unroll dynamic TypedDict key loops to satisfy mypy literal-required
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: allow tmp paths in RAG data-type tests via CREWAI_TOOLS_ALLOW_UNSAFE_PATHS
TemporaryDirectory creates files under /tmp/ which is outside CWD and is
correctly blocked by the new path validation. These tests exercise
data-type handling, not security, so add an autouse fixture that sets
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true for the whole file. Path/URL
security is covered by test_rag_tool_path_validation.py.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: allow tmp paths in search-tool and rag_tool tests via CREWAI_TOOLS_ALLOW_UNSAFE_PATHS
test_search_tools.py has tests for TXTSearchTool, CSVSearchTool,
MDXSearchTool, JSONSearchTool, and DirectorySearchTool that create
files under /tmp/ via tempfile, which is outside CWD and correctly
blocked by the new path validation. rag_tool_test.py has one test
that calls tool.add() with a TemporaryDirectory path.
Add the same autouse allow_tmp_paths fixture used in
test_rag_tool_add_data_type.py. Security is covered separately by
test_rag_tool_path_validation.py.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: update tool specifications
* docs: document CodeInterpreterTool removal and RAG path/URL validation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: address three review comments on path/URL validation
- safe_path._is_private_or_reserved: after unwrapping IPv4-mapped IPv6
to IPv4, only check against IPv4 networks to avoid TypeError when
comparing an IPv4Address against IPv6Network objects.
- safe_path.validate_file_path: handle filesystem-root base_dir ('/')
by not appending os.sep when the base already ends with a separator,
preventing the '//'-prefix bug.
- rag_tool.add: path-detection heuristic now checks for both '/' and
os.sep so forward-slash paths are caught on Windows as well as Unix.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: remove unused _BLOCKED_NETWORKS variable after IPv4/IPv6 split
* chore: update tool specifications
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* refactor: remove CodeInterpreterTool and deprecate code execution params
CodeInterpreterTool has been removed. The allow_code_execution and
code_execution_mode parameters on Agent are deprecated and will be
removed in v2.0. Use dedicated sandbox services (E2B, Modal, etc.)
for code execution needs.
Changes:
- Remove CodeInterpreterTool from crewai-tools (tool, Dockerfile, tests, imports)
- Remove docker dependency from crewai-tools
- Deprecate allow_code_execution and code_execution_mode on Agent
- get_code_execution_tools() returns empty list with deprecation warning
- _validate_docker_installation() is a no-op with deprecation warning
- Bedrock CodeInterpreter (AWS hosted) and OpenAI code_interpreter are NOT affected
* fix: remove empty code_interpreter imports and unused stdlib imports
- Remove empty `from code_interpreter_tool import ()` blocks in both
crewai_tools/__init__.py and tools/__init__.py that caused SyntaxError
after CodeInterpreterTool was removed
- Remove unused `shutil` and `subprocess` imports from agent/core.py
left over from the code execution params deprecation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: remove redundant _validate_docker_installation call and fix list type annotation
- Drop the _validate_docker_installation() call inside the allow_code_execution
block — it fired a second DeprecationWarning identical to the one emitted
just above it, making the warning fire twice.
- Annotate get_code_execution_tools() return type as list[Any] to satisfy mypy
(bare `list` fails the type-arg check introduced by this branch).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* ci: retrigger
* fix: update test_crew.py to remove CodeInterpreterTool references
CodeInterpreterTool was removed from crewai_tools. Update tests to
reflect that get_code_execution_tools() now returns an empty list.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: update tool specifications
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
- Pass RuntimeState through the event bus and enable entity auto-registration
- Introduce checkpointing API:
- .checkpoint(), .from_checkpoint(), and async checkpoint support
- Provider-based storage with BaseProvider and JsonProvider
- Mid-task resume and kickoff() integration
- Add EventRecord tracking and full event serialization with subtype preservation
- Enable checkpoint fidelity via llm_type and executor_type discriminators
- Refactor executor architecture:
- Convert executors, tools, prompts, and TokenProcess to BaseModel
- Introduce proper base classes with typed fields (CrewAgentExecutorMixin, BaseAgentExecutor)
- Add generic from_checkpoint with full LLM serialization
- Support executor back-references and resume-safe initialization
- Refactor runtime state system:
- Move RuntimeState into state/ module with async checkpoint support
- Add entity serialization improvements and JSON-safe round-tripping
- Implement event scope tracking and replay for accurate resume behavior
- Improve tool and schema handling:
- Make BaseTool fully serializable with JSON round-trip support
- Serialize args_schema via JSON schema and dynamically reconstruct models
- Add automatic subclass restoration via tool_type discriminator
- Enhance Flow checkpointing:
- Support restoring execution state and subclass-aware deserialization
- Performance improvements:
- Cache handler signature inspection
- Optimize event emission and metadata preparation
- General cleanup:
- Remove dead checkpoint payload structures
- Simplify entity registration and serialization logic
* chore: update uv.lock with new dependency groups and versioning adjustments
- Added a new revision number and updated resolution markers for Python version compatibility.
- Introduced a 'dev' dependency group with specific versions for various development tools.
- Updated sdist and wheels entries to include upload timestamps for better tracking.
- Adjusted numpy dependencies to specify versions based on Python version markers.
* feat: bump versions to 1.14.0a1
* fix: add base_dir path containment to FileWriterTool
os.path.join does not prevent traversal — joining "./" with "../../../etc/cron.d/pwned"
resolves cleanly outside any intended scope. The tool also called os.makedirs on
the unvalidated path, meaning it would create arbitrary directory structures.
Adds a base_dir parameter that uses os.path.realpath() to resolve the final path
(including symlinks) before checking containment. Any filename or directory argument
that resolves outside base_dir is rejected before any filesystem operation occurs.
When base_dir is not set the tool behaves as before — only use that in fully
sandboxed environments.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: make directory relative to base_dir for better UX
When base_dir is set, the directory arg is now treated as a subdirectory
of base_dir rather than an absolute path. This means the LLM only needs
to specify a filename (and optionally a relative subdirectory) — it does
not need to repeat the base_dir path.
FileWriterTool(base_dir="./output")
→ filename="report.txt" writes to ./output/report.txt
→ filename="f.txt", directory="sub" writes to ./output/sub/f.txt
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: remove directory field from LLM schema when base_dir is set
When a developer sets base_dir, they control where files are written.
The LLM should only supply filename and content — not a directory path.
Adds ScopedFileWriterToolInput (no directory field) which is used when
base_dir is provided at construction, following the same pattern as
FileReadTool/ScrapeWebsiteTool.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: prevent path traversal in FileWriterTool without interface changes
Adds containment check inside _run() using os.path.realpath() to ensure
the resolved file path stays within the resolved directory. Blocks ../
sequences, absolute filenames, and symlink escapes transparently —
no schema or interface changes required.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: use Path.is_relative_to() for path containment check
Replaces startswith(real_directory + os.sep) with Path.is_relative_to(),
which does a proper path-component comparison. This avoids the edge case
where real_directory == "/" produces a "//" prefix, and is safe on
case-insensitive filesystems. Also explicitly rejects the case where
the filepath resolves to the directory itself (not a valid file target).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: fix portability issues in path traversal tests
- test_blocks_traversal_in_filename: use a sibling temp dir instead of
asserting against a potentially pre-existing ../outside.txt
- test_blocks_absolute_path_in_filename: use a temp-dir-derived absolute
path instead of hardcoding /etc/passwd
- test_blocks_symlink_escape: symlink to a temp "outside" dir instead of
/etc, assert target file was not created
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* fix: replace os.system with subprocess.run in unsafe mode pip install
Eliminates shell injection risk (A05) where a malicious library name like
"pkg; rm -rf /" could execute arbitrary host commands. Using list-form
subprocess.run with shell=False ensures the library name is always treated
as a single argument with no shell metacharacter expansion.
Adds two tests: one verifying list-form invocation, one verifying that
shell metacharacters in a library name cannot trigger shell execution.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: use sys.executable -m pip to satisfy S607 linting rule
S607 flags partial executable paths like ["pip", ...]. Using
[sys.executable, "-m", "pip", ...] provides an absolute path and also
ensures installation targets the correct Python environment.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* [SECURITY] Fix sandbox escape vulnerability in CodeInterpreterTool (F-001)
This commit addresses a critical security vulnerability where the CodeInterpreterTool
could be exploited via sandbox escape attacks when Docker was unavailable.
Changes:
- Remove insecure fallback to restricted sandbox in run_code_safety()
- Now fails closed with RuntimeError when Docker is unavailable
- Mark run_code_in_restricted_sandbox() as deprecated and insecure
- Add clear security warnings to SandboxPython class documentation
- Update tests to reflect secure-by-default behavior
- Add test demonstrating the sandbox escape vulnerability
- Update README with security requirements and best practices
The previous implementation would fall back to a Python-based 'restricted sandbox'
when Docker was unavailable. However, this sandbox could be easily bypassed using
Python object introspection to recover the original __import__ function, allowing
arbitrary module access and command execution on the host.
The fix enforces Docker as a requirement for safe code execution. Users who cannot
use Docker must explicitly enable unsafe_mode=True, acknowledging the security risks.
Security Impact:
- Prevents RCE via sandbox escape when Docker is unavailable
- Enforces fail-closed security model
- Maintains backward compatibility via unsafe_mode flag
References:
- https://docs.crewai.com/tools/ai-ml/codeinterpretertool
Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
* Add security fix documentation for F-001
Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
* Add Slack summary for security fix
Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
* Delete SECURITY_FIX_F001.md
* Delete SLACK_SUMMARY.md
* chore: regen cassettes
* chore: regen more cassettes
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
Co-authored-by: Greyson LaLonde <greyson@crewai.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix: remove exclusive locks from read-only storage operations to eliminate lock contention
read operations like search, list_scopes, get_scope_info, count across
LanceDB, ChromaDB, and RAG adapters were holding exclusive locks unnecessarily.
under multi-process prefork workers this caused RedisLock contention triggering
a portalocker bug where AlreadyLocked is raised with the exceptions module as its arg.
- remove store_lock from 7 LanceDB read methods since MVCC handles concurrent reads
- remove store_lock from ChromaDB search/asearch which are thread-safe since v0.4
- remove store_lock from RAG core query and LanceDB adapter query
- wrap lock_store BaseLockException with actionable error message
- add exception handling in encoding_flow/recall_flow ThreadPoolExecutor calls
- fix flow.py double-logging of ancestor listener errors
* fix: remove dead conditional in filter_and_chunk fallback
both branches of the if/else and the except all produced the same
candidates = [scope_prefix] result, making the get_scope_info call
and conditional pointless
* fix: separate lock acquisition from caller body in lock_store
the try/except wrapped the yield inside the contextmanager, which meant
any BaseLockException raised by the caller's code inside the with block
would be caught and re-raised with a misleading "Failed to acquire lock"
message. split into acquire-then-yield so only actual acquisition
failures get the actionable error message.
* feat: add dedicated Brave Search tools for web, news, image, video, local POIs, and Brave's newest LLM Context endpoint
* fix: normalize transformed response shape
* revert legacy tool name
* fix: schema change prevented property resolution
* Update tool.specs.json
* fix: add fallback for search_langugage
* simplify exports
* makes rate-limiting logic per-instance
* fix(brave-tools): correct _refine_response return type annotations
The abstract method and subclasses annotated _refine_response as returning
dict[str, Any] but most implementations actually return list[dict[str, Any]].
Updated base to return Any, and each subclass to match its actual return type.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Joao Moura <joaomdmoura@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
