HAL9000
e18ac5f23c
CI / lint (pull_request) Successful in 20s
CI / quality (pull_request) Successful in 21s
CI / push-validation (pull_request) Successful in 20s
CI / build (pull_request) Successful in 24s
CI / typecheck (pull_request) Successful in 50s
CI / security (pull_request) Successful in 59s
CI / helm (pull_request) Successful in 44s
CI / integration_tests (pull_request) Successful in 4m41s
CI / unit_tests (pull_request) Successful in 5m24s
CI / docker (pull_request) Successful in 52s
CI / coverage (pull_request) Successful in 7m38s
CI / e2e_tests (pull_request) Successful in 2m14s
CI / status-check (pull_request) Successful in 1s
CI / benchmark-regression (push) Failing after 0s
CI / benchmark-publish (push) Failing after 0s
CI / lint (push) Successful in 18s
CI / quality (push) Successful in 40s
CI / typecheck (push) Successful in 41s
CI / security (push) Successful in 42s
CI / build (push) Successful in 25s
CI / push-validation (push) Successful in 30s
CI / helm (push) Successful in 56s
CI / e2e_tests (push) Successful in 3m3s
CI / unit_tests (push) Successful in 4m3s
CI / integration_tests (push) Successful in 4m8s
CI / docker (push) Successful in 52s
CI / coverage (push) Successful in 7m22s
CI / status-check (push) Successful in 1s
The validate_path() function in file_tools.py used str.startswith() to verify that a resolved path stays within the sandbox root. This allowed sibling directories whose names share a string prefix with the sandbox (e.g. /tmp/sandbox-escape/ bypassing /tmp/sandbox/) to escape the containment check. Replace the string prefix check with Path.relative_to(root), which performs a proper OS-level path prefix comparison using path separators. Add a Behave regression scenario tagged @tdd_issue @tdd_issue_7558 that exercises the prefix-collision bypass to prevent regressions. ISSUES CLOSED: #7558
264 lines
11 KiB
Gherkin
264 lines
11 KiB
Gherkin
Feature: Built-in File Tools
|
|
As a developer
|
|
I want built-in file operation tools
|
|
So that agents can read, write, edit, delete, list, and search files safely
|
|
|
|
# ---- File Read ----
|
|
|
|
Scenario: Read a file with default encoding
|
|
Given a temporary sandbox directory
|
|
And a file "hello.txt" with content "Hello, World!"
|
|
When I execute the "builtin/file-read" tool with path "hello.txt"
|
|
Then the tool result should be successful
|
|
And the output "content" should be "Hello, World!"
|
|
And the output "encoding" should be "utf-8"
|
|
And the output "size" should be greater than 0
|
|
|
|
Scenario: Read a file with offset and limit
|
|
Given a temporary sandbox directory
|
|
And a file "lines.txt" with lines "line1,line2,line3,line4,line5"
|
|
When I execute the "builtin/file-read" tool with path "lines.txt" offset 1 limit 2
|
|
Then the tool result should be successful
|
|
And the output "content" should contain "line2"
|
|
And the output "content" should contain "line3"
|
|
And the output "content" should not contain "line1"
|
|
|
|
# ---- File Write ----
|
|
|
|
Scenario: Write a new file
|
|
Given a temporary sandbox directory
|
|
When I execute the "builtin/file-write" tool with path "new.txt" and content "created"
|
|
Then the tool result should be successful
|
|
And the output "created" should be boolean true
|
|
And the output "size" should be greater than 0
|
|
And the file "new.txt" should exist in the sandbox
|
|
|
|
Scenario: Overwrite an existing file
|
|
Given a temporary sandbox directory
|
|
And a file "existing.txt" with content "old content"
|
|
When I execute the "builtin/file-write" tool with path "existing.txt" and content "new content"
|
|
Then the tool result should be successful
|
|
And the output "created" should be boolean false
|
|
|
|
Scenario: Write file creates parent directories
|
|
Given a temporary sandbox directory
|
|
When I execute the "builtin/file-write" tool with path "sub/dir/file.txt" and content "nested"
|
|
Then the tool result should be successful
|
|
And the file "sub/dir/file.txt" should exist in the sandbox
|
|
|
|
# ---- File Edit ----
|
|
|
|
Scenario: Edit file with single replacement
|
|
Given a temporary sandbox directory
|
|
And a file "edit.txt" with content "foo bar foo"
|
|
When I execute the "builtin/file-edit" tool replacing "foo" with "baz"
|
|
Then the tool result should be successful
|
|
And the output "replacements" should equal 1
|
|
|
|
Scenario: Edit file with replace_all
|
|
Given a temporary sandbox directory
|
|
And a file "edit.txt" with content "foo bar foo"
|
|
When I execute the "builtin/file-edit" tool replacing all "foo" with "baz"
|
|
Then the tool result should be successful
|
|
And the output "replacements" should equal 2
|
|
|
|
Scenario: Edit file with old_text not found raises error
|
|
Given a temporary sandbox directory
|
|
And a file "edit.txt" with content "foo bar"
|
|
When I execute the "builtin/file-edit" tool replacing "notfound" with "baz"
|
|
Then the tool result should not be successful
|
|
And the tool result error should mention "not found"
|
|
|
|
# ---- File Delete ----
|
|
|
|
Scenario: Delete an existing file
|
|
Given a temporary sandbox directory
|
|
And a file "delete-me.txt" with content "doomed"
|
|
When I execute the "builtin/file-delete" tool with path "delete-me.txt"
|
|
Then the tool result should be successful
|
|
And the output "existed" should be boolean true
|
|
And the file "delete-me.txt" should not exist in the sandbox
|
|
|
|
Scenario: Delete a nonexistent file
|
|
Given a temporary sandbox directory
|
|
When I execute the "builtin/file-delete" tool with path "ghost.txt"
|
|
Then the tool result should be successful
|
|
And the output "existed" should be boolean false
|
|
|
|
# ---- File List ----
|
|
|
|
Scenario: List directory contents
|
|
Given a temporary sandbox directory
|
|
And a file "a.txt" with content "a"
|
|
And a file "b.py" with content "b"
|
|
When I list directory "." with the file-list tool
|
|
Then the tool result should be successful
|
|
And the output files list should contain at least 2 entries
|
|
|
|
Scenario: List directory with pattern filter
|
|
Given a temporary sandbox directory
|
|
And a file "a.txt" with content "a"
|
|
And a file "b.py" with content "b"
|
|
When I list directory "." filtering by pattern "*.txt"
|
|
Then the tool result should be successful
|
|
And all listed files should match pattern "*.txt"
|
|
|
|
Scenario: List directory recursively
|
|
Given a temporary sandbox directory
|
|
And a file "sub/deep.txt" with content "deep"
|
|
When I list directory "." recursively with the file-list tool
|
|
Then the tool result should be successful
|
|
And the output files list should contain at least 1 entries
|
|
|
|
# ---- File Search ----
|
|
|
|
Scenario: Search files for pattern
|
|
Given a temporary sandbox directory
|
|
And a file "haystack.txt" with content "needle in a haystack"
|
|
When I search directory "." for pattern "needle"
|
|
Then the tool result should be successful
|
|
And the search matches should contain at least 1 result
|
|
|
|
Scenario: Search with max_results limit
|
|
Given a temporary sandbox directory
|
|
And a file "many.txt" with lines "match,match,match,match,match"
|
|
When I search directory "." for pattern "match" with max_results 2
|
|
Then the tool result should be successful
|
|
And the search matches should contain exactly 2 results
|
|
|
|
# ---- Path Traversal Prevention ----
|
|
|
|
Scenario: Path traversal with dotdot is rejected
|
|
Given a temporary sandbox directory
|
|
When I execute the "builtin/file-read" tool with path "../../etc/passwd"
|
|
Then the tool result should not be successful
|
|
And the tool result error should mention "traversal"
|
|
|
|
Scenario: Path traversal in write is rejected
|
|
Given a temporary sandbox directory
|
|
When I execute the "builtin/file-write" tool with path "../escape.txt" and content "evil"
|
|
Then the tool result should not be successful
|
|
And the tool result error should mention "traversal"
|
|
|
|
Scenario: Path traversal in delete is rejected
|
|
Given a temporary sandbox directory
|
|
When I execute the "builtin/file-delete" tool with path "../../etc/passwd"
|
|
Then the tool result should not be successful
|
|
And the tool result error should mention "traversal"
|
|
|
|
@tdd_issue @tdd_issue_7558
|
|
Scenario: Path traversal with sandbox name prefix collision is rejected
|
|
Given a temporary sandbox directory
|
|
And a sibling directory with a name that is a prefix of the sandbox name
|
|
When I attempt to read a file in the sibling escape directory
|
|
Then the tool result should not be successful
|
|
And the tool result error should mention "traversal"
|
|
|
|
# ---- ChangeSet Capture ----
|
|
|
|
Scenario: ChangeSet captures write operations
|
|
Given a temporary sandbox directory
|
|
And a changeset capture with plan_id "plan-001"
|
|
When I write a file through changeset-wrapped tools
|
|
Then the changeset should have 1 entry
|
|
And the changeset entry operation should be "create"
|
|
|
|
Scenario: ChangeSet captures edit operations
|
|
Given a temporary sandbox directory
|
|
And a file "cs-edit.txt" with content "hello world"
|
|
And a changeset capture with plan_id "plan-002"
|
|
When I edit a file through changeset-wrapped tools
|
|
Then the changeset should have 1 entry
|
|
And the changeset entry operation should be "modify"
|
|
|
|
Scenario: ChangeSet captures delete operations
|
|
Given a temporary sandbox directory
|
|
And a file "cs-delete.txt" with content "bye"
|
|
And a changeset capture with plan_id "plan-003"
|
|
When I delete a file through changeset-wrapped tools
|
|
Then the changeset should have 1 entry
|
|
And the changeset entry operation should be "delete"
|
|
|
|
Scenario: ChangeSet summary generation
|
|
Given a temporary sandbox directory
|
|
And a changeset capture with plan_id "plan-004"
|
|
When I perform multiple changeset-tracked operations
|
|
Then the changeset summary should mention the total count
|
|
And the changeset summary should mention operation types
|
|
|
|
Scenario: ChangeSet clear resets tracking
|
|
Given a temporary sandbox directory
|
|
And a changeset capture with plan_id "plan-005"
|
|
When I write a file through changeset-wrapped tools
|
|
And I clear the changeset
|
|
Then the changeset should have 0 entries
|
|
|
|
Scenario: Empty changeset summary
|
|
Given a changeset capture with plan_id "plan-empty"
|
|
Then the changeset summary should be "No changes recorded"
|
|
|
|
# ---- Tool Registration Helper ----
|
|
|
|
Scenario: Register all file tools
|
|
Given a tool registry
|
|
When I register all file tools
|
|
Then the registry should contain 6 tools
|
|
And the registry should contain tool "builtin/file-read"
|
|
And the registry should contain tool "builtin/file-write"
|
|
And the registry should contain tool "builtin/file-edit"
|
|
And the registry should contain tool "builtin/file-delete"
|
|
And the registry should contain tool "builtin/file-list"
|
|
And the registry should contain tool "builtin/file-search"
|
|
|
|
Scenario: Register file tools with changeset
|
|
Given a tool registry
|
|
And a changeset capture with plan_id "plan-reg"
|
|
When I register file tools with changeset
|
|
Then the registry should contain 6 tools
|
|
|
|
# ---- ChangeSet model fields ----
|
|
|
|
Scenario: ChangeSetEntry stores before and after hashes
|
|
Given a temporary sandbox directory
|
|
And a file "hash-test.txt" with content "original"
|
|
And a changeset capture with plan_id "plan-hash"
|
|
When I edit "hash-test.txt" through changeset-wrapped tools
|
|
Then the changeset entry should have a before_hash
|
|
And the changeset entry should have an after_hash
|
|
And the before_hash and after_hash should differ
|
|
|
|
Scenario: File list on non-directory raises error
|
|
Given a temporary sandbox directory
|
|
And a file "notadir.txt" with content "x"
|
|
When I list directory "notadir.txt" with the file-list tool
|
|
Then the tool result should not be successful
|
|
And the tool result error should mention "not a directory"
|
|
|
|
Scenario: File search on non-directory raises error
|
|
Given a temporary sandbox directory
|
|
And a file "notadir.txt" with content "x"
|
|
When I search directory "notadir.txt" for pattern "x"
|
|
Then the tool result should not be successful
|
|
And the tool result error should mention "not a directory"
|
|
|
|
Scenario: File search skips directories in results
|
|
Given a temporary sandbox directory
|
|
And a subdirectory "subdir" in the sandbox
|
|
And a file "subdir/content.txt" with content "findme"
|
|
When I search directory "." for pattern "findme"
|
|
Then the tool result should be successful
|
|
And the search matches should contain at least 1 result
|
|
|
|
Scenario: ChangeSet detect_operation fallback create
|
|
Given a temporary sandbox directory
|
|
And a changeset capture with plan_id "plan-fallback"
|
|
When I write a new file through raw changeset capture
|
|
Then the changeset entry operation should be "create"
|
|
|
|
Scenario: ChangeSet detect_operation fallback modify
|
|
Given a temporary sandbox directory
|
|
And a file "existing-cs.txt" with content "some content"
|
|
And a changeset capture with plan_id "plan-modify-fallback"
|
|
When I overwrite a file through raw changeset capture
|
|
Then the changeset entry operation should be "modify"
|