Compare commits

..

8 Commits

Author SHA1 Message Date
Zamil Majdy
1b7829f471 Merge remote-tracking branch 'origin/dev' into fix/sentry-error-cleanup 2026-03-17 06:17:04 +07:00
Zamil Majdy
8f1bf1d6f3 fix: use is_alive() instead of TimeoutError for thread.join timeout
thread.join(timeout=N) never raises TimeoutError in Python — it always
returns None. Use thread.is_alive() after join to detect timeout.
2026-03-16 16:08:46 +07:00
Zamil Majdy
ce68d97646 fix: refine ValueError suppression to cover plain ValueError paths
execute_node raises plain ValueError for disabled blocks and expired/missing
auth. Use isinstance(ex, ValueError) but exclude NotFoundError and
GraphNotFoundError which could indicate real platform issues.
2026-03-16 15:56:25 +07:00
Zamil Majdy
44aa4db405 fix: use logentry instead of message for Sentry log event filtering
Sentry's LoggingIntegration stores log messages under event["logentry"],
not event["message"]. The previous check was dead code that never matched.
2026-03-16 15:51:39 +07:00
Zamil Majdy
0b0fa35509 fix: update notification tests to match downgraded log levels
Tests were checking mock_logger.error but the log calls were changed to
logger.warning. Update assertions to check mock_logger.warning instead.
2026-03-16 15:40:46 +07:00
Zamil Majdy
77f9cf616d fix: address second round of PR review comments
- Use explicit exception types instead of broad isinstance(ValueError) in
  execute_node to avoid suppressing platform errors like NotFoundError
- Make metadata.google.internal filter GCP-aware (only filter in non-cloud envs)
- Scope log-side "connection refused" filter to AMQP-related messages only
2026-03-16 15:38:20 +07:00
Zamil Majdy
4a6fa5b9ca fix: address PR review comments on Sentry error cleanup
- Make "connection refused" filter AMQP-specific by checking exception
  module/type instead of broadly matching all ConnectionRefusedError
- Add "no credits left" as alternate insufficient balance pattern
- Broaden inactive email filter (OR instead of AND)
- Remove duplicate final-failure log in conn_retry on_retry callback
- Preserve traceback with exc_info=True in notification queue consumer
2026-03-16 15:26:23 +07:00
Zamil Majdy
2166bd8c69 fix(platform): reduce Sentry noise by filtering expected errors and downgrading log levels
- Add `before_send` hook to Sentry to filter known expected errors:
  AMQP/RabbitMQ connection errors, user credential errors (invalid API keys),
  insufficient balance, blocked IP access, Discord token errors,
  Google metadata DNS errors, inactive email recipients
- Downgrade connection retry failures from error to warning in conn_retry
- Stop sending user-caused ValueError exceptions to Sentry in block execution
- Downgrade scheduler job failures and graph validation errors to warning
- Wrap discord_system_alert to catch and warn instead of raising
- Downgrade all notification system errors to warning (batch processing,
  email sending, user lookup, preference handling)
- Downgrade cloud storage cleanup errors to warning
- Downgrade executor shutdown/disconnect errors to warning
2026-03-16 15:10:57 +07:00
26 changed files with 594 additions and 267 deletions

View File

@@ -11,18 +11,34 @@ from backend.copilot.tools import TOOL_REGISTRY
# Shared technical notes that apply to both SDK and baseline modes
_SHARED_TOOL_NOTES = """\
### Sharing files
After `write_workspace_file`, embed the `download_url` in Markdown:
- File: `[report.csv](workspace://file_id#text/csv)`
- Image: `![chart](workspace://file_id#image/png)`
- Video: `![recording](workspace://file_id#video/mp4)`
### Sharing files with the user
After saving a file to the persistent workspace with `write_workspace_file`,
share it with the user by embedding the `download_url` from the response in
your message as a Markdown link or image:
### File references — @@agptfile:
Pass large file content to tools by reference: `@@agptfile:<uri>[<start>-<end>]`
- `workspace://<file_id>` or `workspace:///<path>` — workspace files
- `/absolute/path` — local/sandbox files
- `[start-end]` — optional 1-indexed line range
- Multiple refs per argument supported. Only `workspace://` and absolute paths are expanded.
- **Any file** — shows as a clickable download link:
`[report.csv](workspace://file_id#text/csv)`
- **Image** — renders inline in chat:
`![chart](workspace://file_id#image/png)`
- **Video** — renders inline in chat with player controls:
`![recording](workspace://file_id#video/mp4)`
The `download_url` field in the `write_workspace_file` response is already
in the correct format — paste it directly after the `(` in the Markdown.
### Passing file content to tools — @@agptfile: references
Instead of copying large file contents into a tool argument, pass a file
reference and the platform will load the content for you.
Syntax: `@@agptfile:<uri>[<start>-<end>]`
- `<uri>` **must** start with `workspace://` or `/` (absolute path):
- `workspace://<file_id>` — workspace file by ID
- `workspace:///<path>` — workspace file by virtual path
- `/absolute/local/path` — ephemeral or sdk_cwd file
- E2B sandbox absolute path (e.g. `/home/user/script.py`)
- `[<start>-<end>]` is an optional 1-indexed inclusive line range.
- URIs that do not start with `workspace://` or `/` are **not** expanded.
Examples:
```
@@ -33,16 +49,50 @@ Examples:
@@agptfile:/home/user/script.py
```
**Structured data**: When the entire argument is a single file reference, the platform auto-parses by extension/MIME. Supported: JSON, JSONL, CSV, TSV, YAML, TOML, Parquet, Excel (.xlsx only). Unrecognised formats return plain string.
You can embed a reference inside any string argument, or use it as the entire
value. Multiple references in one argument are all expanded.
**Type coercion**: The platform auto-coerces expanded string values to match block input types (e.g. JSON string → `list[list[str]]`).
**Structured data**: When the **entire** argument value is a single file
reference (no surrounding text), the platform automatically parses the file
content based on its extension or MIME type. Supported formats: JSON, JSONL,
CSV, TSV, YAML, TOML, Parquet, and Excel (.xlsx — first sheet only).
For example, pass `@@agptfile:workspace://<id>` where the file is a `.csv` and
the rows will be parsed into `list[list[str]]` automatically. If the format is
unrecognised or parsing fails, the content is returned as a plain string.
Legacy `.xls` files are **not** supported — only the modern `.xlsx` format.
**Type coercion**: The platform also coerces expanded values to match the
block's expected input types. For example, if a block expects `list[list[str]]`
and the expanded value is a JSON string, it will be parsed into the correct type.
### Media file inputs (format: "file")
Inputs with `"format": "file"` accept `workspace://<file_id>` or `data:<mime>;base64,<payload>`.
Pass the `workspace://` URI directly (do NOT wrap in `@@agptfile:`). This avoids large payloads and preserves binary content.
Some block inputs accept media files — their schema shows `"format": "file"`.
These fields accept:
- **`workspace://<file_id>`** or **`workspace://<file_id>#<mime>`** — preferred
for large files (images, videos, PDFs). The platform passes the reference
directly to the block without reading the content into memory.
- **`data:<mime>;base64,<payload>`** — inline base64 data URI, suitable for
small files only.
When a block input has `format: "file"`, **pass the `workspace://` URI
directly as the value** (do NOT wrap it in `@@agptfile:`). This avoids large
payloads in tool arguments and preserves binary content (images, videos)
that would be corrupted by text encoding.
Example — committing an image file to GitHub:
```json
{
"files": [{
"path": "docs/hero.png",
"content": "workspace://abc123#image/png",
"operation": "upsert"
}]
}
```
### Sub-agent tasks
- Task tool: NEVER set `run_in_background` to true.
- When using the Task tool, NEVER set `run_in_background` to true.
All tasks must run in the foreground.
"""
@@ -78,18 +128,30 @@ def _build_storage_supplement(
## Tool notes
### Shell & filesystem
- Use `bash_exec` for shell commands ({sandbox_type}). Working dir: `{working_dir}`
- All file tools share the same filesystem. Use relative or absolute paths under this dir.
### Shell commands
- The SDK built-in Bash tool is NOT available. Use the `bash_exec` MCP tool
for shell commands — it runs {sandbox_type}.
### Working directory
- Your working directory is: `{working_dir}`
- All SDK file tools AND `bash_exec` operate on the same filesystem
- Use relative paths or absolute paths under `{working_dir}` for all file operations
### Two storage systems — CRITICAL to understand
### Storage — important
1. **{storage_system_1_name}** (`{working_dir}`):
{characteristics}
{persistence}
2. **Persistent workspace** (cloud) — survives across sessions.
- {file_move_name_1_to_2}: use `write_workspace_file`
- {file_move_name_2_to_1}: use `read_workspace_file` with save_to_path
- Save important files to workspace for persistence.
2. **Persistent workspace** (cloud storage):
- Files here **survive across sessions indefinitely**
### Moving files between storages
- **{file_move_name_1_to_2}**: Copy to persistent workspace
- **{file_move_name_2_to_1}**: Download for processing
### File persistence
Important files (code, configs, outputs) should be saved to workspace to ensure they persist.
{_SHARED_TOOL_NOTES}"""

View File

@@ -22,11 +22,13 @@ class AddUnderstandingTool(BaseTool):
@property
def description(self) -> str:
return (
"Store user's business context, workflows, pain points, and automation goals. "
"Call whenever the user shares business info. Each call incrementally merges "
"with existing data — provide only the fields you have."
)
return """Capture and store information about the user's business context,
workflows, pain points, and automation goals. Call this tool whenever the user
shares information about their business. Each call incrementally adds to the
existing understanding - you don't need to provide all fields at once.
Use this to build a comprehensive profile that helps recommend better agents
and automations for the user's specific needs."""
@property
def parameters(self) -> dict[str, Any]:

View File

@@ -408,11 +408,18 @@ class BrowserNavigateTool(BaseTool):
@property
def description(self) -> str:
return (
"Navigate to a URL in a real browser. Returns accessibility tree with @ref IDs "
"for browser_act. Session persists (cookies/auth carry over). "
"For static pages, prefer web_fetch. "
"For SPAs, elements may load late — use browser_act with wait + browser_screenshot to verify. "
"For auth: navigate to login, fill creds with browser_act, then navigate to target."
"Navigate to a URL using a real browser. Returns an accessibility "
"tree snapshot listing the page's interactive elements with @ref IDs "
"(e.g. @e3) that can be used with browser_act. "
"Session persists — cookies and login state carry over between calls. "
"Use this (with browser_act) for multi-step interaction: login flows, "
"form filling, button clicks, or anything requiring page interaction. "
"For plain static pages, prefer web_fetch — no browser overhead. "
"For authenticated pages: navigate to the login page first, use browser_act "
"to fill credentials and submit, then navigate to the target page. "
"Note: for slow SPAs, the returned snapshot may reflect a partially-loaded "
"state. If elements seem missing, use browser_act with action='wait' and a "
"CSS selector or millisecond delay, then take a browser_screenshot to verify."
)
@property
@@ -422,13 +429,13 @@ class BrowserNavigateTool(BaseTool):
"properties": {
"url": {
"type": "string",
"description": "HTTP/HTTPS URL to navigate to.",
"description": "The HTTP/HTTPS URL to navigate to.",
},
"wait_for": {
"type": "string",
"enum": ["networkidle", "load", "domcontentloaded"],
"default": "networkidle",
"description": "Navigation completion strategy (default: networkidle).",
"description": "When to consider navigation complete. Use 'networkidle' for SPAs (default).",
},
},
"required": ["url"],
@@ -547,12 +554,14 @@ class BrowserActTool(BaseTool):
@property
def description(self) -> str:
return (
"Interact with the current browser page using @ref IDs from the snapshot. "
"Actions: click, dblclick, fill, type, scroll, hover, press, "
"Interact with the current browser page. Use @ref IDs from the "
"snapshot (e.g. '@e3') to target elements. Returns an updated snapshot. "
"Supported actions: click, dblclick, fill, type, scroll, hover, press, "
"check, uncheck, select, wait, back, forward, reload. "
"fill clears field first; type appends. "
"wait accepts CSS selector or milliseconds (e.g. '1000'). "
"Returns updated snapshot."
"fill clears the field before typing; type appends without clearing. "
"wait accepts a CSS selector (waits for element) or milliseconds string (e.g. '1000'). "
"Example login flow: fill @e1 with email → fill @e2 with password → "
"click @e3 (submit) → browser_navigate to the target page."
)
@property
@@ -578,21 +587,30 @@ class BrowserActTool(BaseTool):
"forward",
"reload",
],
"description": "Action to perform.",
"description": "The action to perform.",
},
"target": {
"type": "string",
"description": "@ref ID (e.g. '@e3'), CSS selector, or text description.",
"description": (
"Element to target. Use @ref from snapshot (e.g. '@e3'), "
"a CSS selector, or a text description. "
"Required for: click, dblclick, fill, type, hover, check, uncheck, select. "
"For wait: a CSS selector to wait for, or milliseconds as a string (e.g. '1000')."
),
},
"value": {
"type": "string",
"description": "Text for fill/type, key for press (e.g. 'Enter'), option for select.",
"description": (
"For fill/type: the text to enter. "
"For press: key name (e.g. 'Enter', 'Tab', 'Control+a'). "
"For select: the option value to select."
),
},
"direction": {
"type": "string",
"enum": ["up", "down", "left", "right"],
"default": "down",
"description": "Scroll direction (default: down).",
"description": "For scroll: direction to scroll.",
},
},
"required": ["action"],
@@ -739,10 +757,12 @@ class BrowserScreenshotTool(BaseTool):
@property
def description(self) -> str:
return (
"Screenshot the current browser page and save to workspace. "
"annotate=true overlays @ref labels on elements. "
"IMPORTANT: After calling, you MUST immediately call read_workspace_file with the "
"returned file_id to display the image inline."
"Take a screenshot of the current browser page and save it to the workspace. "
"IMPORTANT: After calling this tool, immediately call read_workspace_file "
"with the returned file_id to display the image inline to the user — "
"the screenshot is not visible until you do this. "
"With annotate=true (default), @ref labels are overlaid on interactive "
"elements, making it easy to see which @ref ID maps to which element on screen."
)
@property
@@ -753,12 +773,12 @@ class BrowserScreenshotTool(BaseTool):
"annotate": {
"type": "boolean",
"default": True,
"description": "Overlay @ref labels (default: true).",
"description": "Overlay @ref labels on interactive elements (default: true).",
},
"filename": {
"type": "string",
"default": "screenshot.png",
"description": "Workspace filename (default: screenshot.png).",
"description": "Filename to save in the workspace.",
},
},
}

View File

@@ -108,12 +108,22 @@ class AgentOutputTool(BaseTool):
@property
def description(self) -> str:
return (
"Retrieve execution outputs from a library agent. "
"Identify by agent_name, library_agent_id, or store_slug. "
"Filter by execution_id or run_time. "
"Optionally wait for running executions."
)
return """Retrieve execution outputs from agents in the user's library.
Identify the agent using one of:
- agent_name: Fuzzy search in user's library
- library_agent_id: Exact library agent ID
- store_slug: Marketplace format 'username/agent-name'
Select which run to retrieve using:
- execution_id: Specific execution ID
- run_time: 'latest' (default), 'yesterday', 'last week', or ISO date 'YYYY-MM-DD'
Wait for completion (optional):
- wait_if_running: Max seconds to wait if execution is still running (0-300).
If the execution is running/queued, waits up to this many seconds for completion.
Returns current status on timeout. If already finished, returns immediately.
"""
@property
def parameters(self) -> dict[str, Any]:
@@ -122,27 +132,32 @@ class AgentOutputTool(BaseTool):
"properties": {
"agent_name": {
"type": "string",
"description": "Agent name (fuzzy match).",
"description": "Agent name to search for in user's library (fuzzy match)",
},
"library_agent_id": {
"type": "string",
"description": "Library agent ID.",
"description": "Exact library agent ID",
},
"store_slug": {
"type": "string",
"description": "Marketplace 'username/agent-slug'.",
"description": "Marketplace identifier: 'username/agent-slug'",
},
"execution_id": {
"type": "string",
"description": "Specific execution ID.",
"description": "Specific execution ID to retrieve",
},
"run_time": {
"type": "string",
"description": "Time filter: 'latest', today/yesterday/last week/last 7 days/last month/last 30 days, 'YYYY-MM-DD', or ISO datetime.",
"description": (
"Time filter: 'latest', 'yesterday', 'last week', or 'YYYY-MM-DD'"
),
},
"wait_if_running": {
"type": "integer",
"description": "Max seconds to wait if still running (0-300). Returns current state on timeout.",
"description": (
"Max seconds to wait if execution is still running (0-300). "
"If running, waits for completion. Returns current state on timeout."
),
},
},
"required": [],

View File

@@ -41,9 +41,15 @@ class BashExecTool(BaseTool):
@property
def description(self) -> str:
return (
"Execute a Bash command or script. Shares filesystem with SDK file tools. "
"Useful for scripts, data processing, and package installation. "
"Killed after timeout (default 30s, max 120s)."
"Execute a Bash command or script. "
"Full Bash scripting is supported (loops, conditionals, pipes, "
"functions, etc.). "
"The working directory is shared with the SDK Read/Write/Edit/Glob/Grep "
"tools — files created by either are immediately visible to both. "
"Execution is killed after the timeout (default 30s, max 120s). "
"Returns stdout and stderr. "
"Useful for file manipulation, data processing, running scripts, "
"and installing packages."
)
@property
@@ -53,11 +59,13 @@ class BashExecTool(BaseTool):
"properties": {
"command": {
"type": "string",
"description": "Bash command or script.",
"description": "Bash command or script to execute.",
},
"timeout": {
"type": "integer",
"description": "Max seconds (default 30, max 120).",
"description": (
"Max execution time in seconds (default 30, max 120)."
),
"default": 30,
},
},

View File

@@ -30,7 +30,12 @@ class ContinueRunBlockTool(BaseTool):
@property
def description(self) -> str:
return "Resume block execution after human review approval. Pass the review_id."
return (
"Continue executing a block after human review approval. "
"Use this after a run_block call returned review_required. "
"Pass the review_id from the review_required response. "
"The block will execute with the original pre-approved input data."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -39,7 +44,10 @@ class ContinueRunBlockTool(BaseTool):
"properties": {
"review_id": {
"type": "string",
"description": "review_id from the review_required response.",
"description": (
"The review_id from a previous review_required response. "
"This resumes execution with the pre-approved input data."
),
},
},
"required": ["review_id"],

View File

@@ -23,8 +23,12 @@ class CreateAgentTool(BaseTool):
@property
def description(self) -> str:
return (
"Create a new agent from JSON (nodes + links). Validates, auto-fixes, and saves. "
"Before calling, search for existing agents with find_library_agent."
"Create a new agent workflow. Pass `agent_json` with the complete "
"agent graph JSON you generated using block schemas from find_block. "
"The tool validates, auto-fixes, and saves.\n\n"
"IMPORTANT: Before calling this tool, search for relevant existing agents "
"using find_library_agent that could be used as building blocks. "
"Pass their IDs in the library_agent_ids parameter."
)
@property
@@ -38,21 +42,34 @@ class CreateAgentTool(BaseTool):
"properties": {
"agent_json": {
"type": "object",
"description": "Agent graph with 'nodes' and 'links' arrays.",
"description": (
"The agent JSON to validate and save. "
"Must contain 'nodes' and 'links' arrays, and optionally "
"'name' and 'description'."
),
},
"library_agent_ids": {
"type": "array",
"items": {"type": "string"},
"description": "Library agent IDs as building blocks.",
"description": (
"List of library agent IDs to use as building blocks."
),
},
"save": {
"type": "boolean",
"description": "Save the agent (default: true). False for preview.",
"description": (
"Whether to save the agent. Default is true. "
"Set to false for preview only."
),
"default": True,
},
"folder_id": {
"type": "string",
"description": "Folder ID to save into (default: root).",
"description": (
"Optional folder ID to save the agent into. "
"If not provided, the agent is saved at root level. "
"Use list_folders to find available folders."
),
},
},
"required": ["agent_json"],

View File

@@ -23,7 +23,9 @@ class CustomizeAgentTool(BaseTool):
@property
def description(self) -> str:
return (
"Customize a marketplace/template agent. Validates, auto-fixes, and saves."
"Customize a marketplace or template agent. Pass `agent_json` "
"with the complete customized agent JSON. The tool validates, "
"auto-fixes, and saves."
)
@property
@@ -37,21 +39,32 @@ class CustomizeAgentTool(BaseTool):
"properties": {
"agent_json": {
"type": "object",
"description": "Customized agent JSON with nodes and links.",
"description": (
"Complete customized agent JSON to validate and save. "
"Optionally include 'name' and 'description'."
),
},
"library_agent_ids": {
"type": "array",
"items": {"type": "string"},
"description": "Library agent IDs as building blocks.",
"description": (
"List of library agent IDs to use as building blocks."
),
},
"save": {
"type": "boolean",
"description": "Save the agent (default: true). False for preview.",
"description": (
"Whether to save the customized agent. Default is true."
),
"default": True,
},
"folder_id": {
"type": "string",
"description": "Folder ID to save into (default: root).",
"description": (
"Optional folder ID to save the agent into. "
"If not provided, the agent is saved at root level. "
"Use list_folders to find available folders."
),
},
},
"required": ["agent_json"],

View File

@@ -23,8 +23,12 @@ class EditAgentTool(BaseTool):
@property
def description(self) -> str:
return (
"Edit an existing agent. Validates, auto-fixes, and saves. "
"Before calling, search for existing agents with find_library_agent."
"Edit an existing agent. Pass `agent_json` with the complete "
"updated agent JSON you generated. The tool validates, auto-fixes, "
"and saves.\n\n"
"IMPORTANT: Before calling this tool, if the changes involve adding new "
"functionality, search for relevant existing agents using find_library_agent "
"that could be used as building blocks."
)
@property
@@ -38,20 +42,33 @@ class EditAgentTool(BaseTool):
"properties": {
"agent_id": {
"type": "string",
"description": "Graph ID or library agent ID to edit.",
"description": (
"The ID of the agent to edit. "
"Can be a graph ID or library agent ID."
),
},
"agent_json": {
"type": "object",
"description": "Updated agent JSON with nodes and links.",
"description": (
"Complete updated agent JSON to validate and save. "
"Must contain 'nodes' and 'links'. "
"Include 'name' and/or 'description' if they need "
"to be updated."
),
},
"library_agent_ids": {
"type": "array",
"items": {"type": "string"},
"description": "Library agent IDs as building blocks.",
"description": (
"List of library agent IDs to use as building blocks for the changes."
),
},
"save": {
"type": "boolean",
"description": "Save changes (default: true). False for preview.",
"description": (
"Whether to save the changes. "
"Default is true. Set to false for preview only."
),
"default": True,
},
},

View File

@@ -134,7 +134,11 @@ class SearchFeatureRequestsTool(BaseTool):
@property
def description(self) -> str:
return "Search existing feature requests. Check before creating a new one."
return (
"Search existing feature requests to check if a similar request "
"already exists before creating a new one. Returns matching feature "
"requests with their ID, title, and description."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -230,9 +234,14 @@ class CreateFeatureRequestTool(BaseTool):
@property
def description(self) -> str:
return (
"Create a feature request or add need to existing one. "
"Search first to avoid duplicates. Pass existing_issue_id to add to existing. "
"Never include PII (names, emails, phone numbers, company names) in title/description."
"Create a new feature request or add a customer need to an existing one. "
"Always search first with search_feature_requests to avoid duplicates. "
"If a matching request exists, pass its ID as existing_issue_id to add "
"the user's need to it instead of creating a duplicate. "
"IMPORTANT: Never include personally identifiable information (PII) in "
"the title or description — no names, emails, phone numbers, company "
"names, or other identifying details. Write titles and descriptions in "
"generic, feature-focused language."
)
@property
@@ -242,15 +251,28 @@ class CreateFeatureRequestTool(BaseTool):
"properties": {
"title": {
"type": "string",
"description": "Feature request title. No PII.",
"description": (
"Title for the feature request. Must be generic and "
"feature-focused — do not include any user names, emails, "
"company names, or other PII."
),
},
"description": {
"type": "string",
"description": "What the user wants and why. No PII.",
"description": (
"Detailed description of what the user wants and why. "
"Must not contain any personally identifiable information "
"(PII) — describe the feature need generically without "
"referencing specific users, companies, or contact details."
),
},
"existing_issue_id": {
"type": "string",
"description": "Linear issue ID to add need to (from search results).",
"description": (
"If adding a need to an existing feature request, "
"provide its Linear issue ID (from search results). "
"Omit to create a new feature request."
),
},
},
"required": ["title", "description"],

View File

@@ -18,7 +18,9 @@ class FindAgentTool(BaseTool):
@property
def description(self) -> str:
return "Search marketplace agents by capability."
return (
"Discover agents from the marketplace based on capabilities and user needs."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -27,7 +29,7 @@ class FindAgentTool(BaseTool):
"properties": {
"query": {
"type": "string",
"description": "Search keywords (single keywords work best).",
"description": "Search query describing what the user wants to accomplish. Use single keywords for best results.",
},
},
"required": ["query"],

View File

@@ -51,7 +51,14 @@ class FindBlockTool(BaseTool):
@property
def description(self) -> str:
return "Search blocks by name or description. Returns block IDs for run_block. Always call this FIRST to get block IDs before using run_block."
return (
"Search for available blocks by name or description. "
"Blocks are reusable components that perform specific tasks like "
"sending emails, making API calls, processing text, etc. "
"IMPORTANT: Use this tool FIRST to get the block's 'id' before calling run_block. "
"The response includes each block's id, name, and description. "
"Call run_block with the block's id **with no inputs** to see detailed inputs/outputs and execute it."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -60,11 +67,18 @@ class FindBlockTool(BaseTool):
"properties": {
"query": {
"type": "string",
"description": "Search keywords (e.g. 'email', 'http', 'ai').",
"description": (
"Search query to find blocks by name or description. "
"Use keywords like 'email', 'http', 'text', 'ai', etc."
),
},
"include_schemas": {
"type": "boolean",
"description": "Include full input/output schemas (for agent JSON generation).",
"description": (
"If true, include full input_schema and output_schema "
"for each block. Use when generating agent JSON that "
"needs block schemas. Default is false."
),
"default": False,
},
},

View File

@@ -19,8 +19,13 @@ class FindLibraryAgentTool(BaseTool):
@property
def description(self) -> str:
return (
"Search user's library agents. Returns graph_id, schemas for sub-agent composition. "
"Omit query to list all."
"Search for or list agents in the user's library. Use this to find "
"agents the user has already added to their library, including agents "
"they created or added from the marketplace. "
"When creating agents with sub-agent composition, use this to get "
"the agent's graph_id, graph_version, input_schema, and output_schema "
"needed for AgentExecutorBlock nodes. "
"Omit the query to list all agents."
)
@property
@@ -30,7 +35,10 @@ class FindLibraryAgentTool(BaseTool):
"properties": {
"query": {
"type": "string",
"description": "Search by name/description. Omit to list all.",
"description": (
"Search query to find agents by name or description. "
"Omit to list all agents in the library."
),
},
},
"required": [],

View File

@@ -22,8 +22,20 @@ class FixAgentGraphTool(BaseTool):
@property
def description(self) -> str:
return (
"Auto-fix common agent JSON issues (UUIDs, types, credentials, spacing, etc.). "
"Returns fixed JSON and list of fixes applied."
"Auto-fix common issues in an agent JSON graph. Applies fixes for:\n"
"- Missing or invalid UUIDs on nodes and links\n"
"- StoreValueBlock prerequisites for ConditionBlock\n"
"- Double curly brace escaping in prompt templates\n"
"- AddToList/AddToDictionary prerequisite blocks\n"
"- CodeExecutionBlock output field naming\n"
"- Missing credentials configuration\n"
"- Node X coordinate spacing (800+ units apart)\n"
"- AI model default parameters\n"
"- Link static properties based on input schema\n"
"- Type mismatches (inserts conversion blocks)\n\n"
"Returns the fixed agent JSON plus a list of fixes applied. "
"After fixing, the agent is re-validated. If still invalid, "
"the remaining errors are included in the response."
)
@property

View File

@@ -42,7 +42,12 @@ class GetAgentBuildingGuideTool(BaseTool):
@property
def description(self) -> str:
return "Get the agent JSON building guide (nodes, links, AgentExecutorBlock, MCPToolBlock usage). Call before generating agent JSON."
return (
"Returns the complete guide for building agent JSON graphs, including "
"block IDs, link structure, AgentInputBlock, AgentOutputBlock, "
"AgentExecutorBlock (for sub-agent composition), and MCPToolBlock usage. "
"Call this before generating agent JSON to ensure correct structure."
)
@property
def parameters(self) -> dict[str, Any]:

View File

@@ -25,7 +25,8 @@ class GetDocPageTool(BaseTool):
@property
def description(self) -> str:
return (
"Read full documentation page content by path (from search_docs results)."
"Get the full content of a documentation page by its path. "
"Use this after search_docs to read the complete content of a relevant page."
)
@property
@@ -35,7 +36,10 @@ class GetDocPageTool(BaseTool):
"properties": {
"path": {
"type": "string",
"description": "Doc file path (e.g. 'platform/block-sdk-guide.md').",
"description": (
"The path to the documentation file, as returned by search_docs. "
"Example: 'platform/block-sdk-guide.md'"
),
},
},
"required": ["path"],

View File

@@ -38,7 +38,11 @@ class GetMCPGuideTool(BaseTool):
@property
def description(self) -> str:
return "Get MCP server URLs and auth guide."
return (
"Returns the MCP tool guide: known hosted server URLs (Notion, Linear, "
"Stripe, Intercom, Cloudflare, Atlassian) and authentication workflow. "
"Call before using run_mcp_tool if you need a server URL or auth info."
)
@property
def parameters(self) -> dict[str, Any]:

View File

@@ -88,7 +88,10 @@ class CreateFolderTool(BaseTool):
@property
def description(self) -> str:
return "Create a library folder. Use parent_id to nest inside another folder."
return (
"Create a new folder in the user's library to organize agents. "
"Optionally nest it inside an existing folder using parent_id."
)
@property
def requires_auth(self) -> bool:
@@ -101,19 +104,22 @@ class CreateFolderTool(BaseTool):
"properties": {
"name": {
"type": "string",
"description": "Folder name (max 100 chars).",
"description": "Name for the new folder (max 100 chars).",
},
"parent_id": {
"type": "string",
"description": "Parent folder ID (omit for root).",
"description": (
"ID of the parent folder to nest inside. "
"Omit to create at root level."
),
},
"icon": {
"type": "string",
"description": "Icon identifier.",
"description": "Optional icon identifier for the folder.",
},
"color": {
"type": "string",
"description": "Hex color (#RRGGBB).",
"description": "Optional hex color code (#RRGGBB).",
},
},
"required": ["name"],
@@ -169,8 +175,13 @@ class ListFoldersTool(BaseTool):
@property
def description(self) -> str:
return (
"List library folders. Omit parent_id for full tree. "
"Set include_agents=true when user asks about agents in folders."
"List the user's library folders. "
"Omit parent_id to get the full folder tree. "
"Provide parent_id to list only direct children of that folder. "
"Set include_agents=true to also return the agents inside each folder "
"and root-level agents not in any folder. Always set include_agents=true "
"when the user asks about agents, wants to see what's in their folders, "
"or mentions agents alongside folders."
)
@property
@@ -184,11 +195,17 @@ class ListFoldersTool(BaseTool):
"properties": {
"parent_id": {
"type": "string",
"description": "List children of this folder (omit for full tree).",
"description": (
"List children of this folder. "
"Omit to get the full folder tree."
),
},
"include_agents": {
"type": "boolean",
"description": "Include agents in each folder (default: false).",
"description": (
"Whether to include the list of agents inside each folder. "
"Defaults to false."
),
},
},
"required": [],
@@ -340,7 +357,10 @@ class MoveFolderTool(BaseTool):
@property
def description(self) -> str:
return "Move a folder. Set target_parent_id to null for root."
return (
"Move a folder to a different parent folder. "
"Set target_parent_id to null to move to root level."
)
@property
def requires_auth(self) -> bool:
@@ -353,11 +373,14 @@ class MoveFolderTool(BaseTool):
"properties": {
"folder_id": {
"type": "string",
"description": "Folder ID.",
"description": "ID of the folder to move.",
},
"target_parent_id": {
"type": ["string", "null"],
"description": "New parent folder ID (null for root).",
"description": (
"ID of the new parent folder. "
"Use null to move to root level."
),
},
},
"required": ["folder_id"],
@@ -410,7 +433,10 @@ class DeleteFolderTool(BaseTool):
@property
def description(self) -> str:
return "Delete a folder. Agents inside move to root (not deleted)."
return (
"Delete a folder from the user's library. "
"Agents inside the folder are moved to root level (not deleted)."
)
@property
def requires_auth(self) -> bool:
@@ -473,7 +499,10 @@ class MoveAgentsToFolderTool(BaseTool):
@property
def description(self) -> str:
return "Move agents to a folder. Set folder_id to null for root."
return (
"Move one or more agents to a folder. "
"Set folder_id to null to move agents to root level."
)
@property
def requires_auth(self) -> bool:
@@ -487,11 +516,13 @@ class MoveAgentsToFolderTool(BaseTool):
"agent_ids": {
"type": "array",
"items": {"type": "string"},
"description": "Library agent IDs to move.",
"description": "List of library agent IDs to move.",
},
"folder_id": {
"type": ["string", "null"],
"description": "Target folder ID (null for root).",
"description": (
"Target folder ID. Use null to move to root level."
),
},
},
"required": ["agent_ids"],

View File

@@ -104,11 +104,19 @@ class RunAgentTool(BaseTool):
@property
def description(self) -> str:
return (
"Run or schedule an agent. Automatically checks inputs and credentials. "
"Identify by username_agent_slug ('user/agent') or library_agent_id. "
"For scheduling, provide schedule_name + cron."
)
return """Run or schedule an agent from the marketplace or user's library.
The tool automatically handles the setup flow:
- Returns missing inputs if required fields are not provided
- Returns missing credentials if user needs to configure them
- Executes immediately if all requirements are met
- Schedules execution if cron expression is provided
Identify the agent using either:
- username_agent_slug: Marketplace format 'username/agent-name'
- library_agent_id: ID of an agent in the user's library
For scheduled execution, provide: schedule_name, cron, and optionally timezone."""
@property
def parameters(self) -> dict[str, Any]:
@@ -117,36 +125,40 @@ class RunAgentTool(BaseTool):
"properties": {
"username_agent_slug": {
"type": "string",
"description": "Marketplace format 'username/agent-name'.",
"description": "Agent identifier in format 'username/agent-name'",
},
"library_agent_id": {
"type": "string",
"description": "Library agent ID.",
"description": "Library agent ID from user's library",
},
"inputs": {
"type": "object",
"description": "Input values for the agent.",
"description": "Input values for the agent",
"additionalProperties": True,
},
"use_defaults": {
"type": "boolean",
"description": "Run with default values (confirm with user first).",
"description": "Set to true to run with default values (user must confirm)",
},
"schedule_name": {
"type": "string",
"description": "Name for scheduled execution.",
"description": "Name for scheduled execution (triggers scheduling mode)",
},
"cron": {
"type": "string",
"description": "Cron expression (min hour day month weekday).",
"description": "Cron expression (5 fields: min hour day month weekday)",
},
"timezone": {
"type": "string",
"description": "IANA timezone (default: UTC).",
"description": "IANA timezone for schedule (default: UTC)",
},
"wait_for_result": {
"type": "integer",
"description": "Max seconds to wait for completion (0-300).",
"description": (
"Max seconds to wait for execution to complete (0-300). "
"If >0, blocks until the execution finishes or times out. "
"Returns execution outputs when complete."
),
},
},
"required": [],

View File

@@ -45,10 +45,13 @@ class RunBlockTool(BaseTool):
@property
def description(self) -> str:
return (
"Execute a block. IMPORTANT: Always get block_id from find_block first "
"— do NOT guess or fabricate IDs. "
"Call with empty input_data to see schema, then with data to execute. "
"If review_required, use continue_run_block."
"Execute a specific block with the provided input data. "
"IMPORTANT: You MUST call find_block first to get the block's 'id' - "
"do NOT guess or make up block IDs. "
"On first attempt (without input_data), returns detailed schema showing "
"required inputs and outputs. Then call again with proper input_data to execute. "
"If a block requires human review, use continue_run_block with the "
"review_id after the user approves."
)
@property
@@ -58,14 +61,28 @@ class RunBlockTool(BaseTool):
"properties": {
"block_id": {
"type": "string",
"description": "Block ID from find_block results.",
"description": (
"The block's 'id' field from find_block results. "
"NEVER guess this - always get it from find_block first."
),
},
"block_name": {
"type": "string",
"description": (
"The block's human-readable name from find_block results. "
"Used for display purposes in the UI."
),
},
"input_data": {
"type": "object",
"description": "Input values. Use {} first to see schema.",
"description": (
"Input values for the block. "
"First call with empty {} to see the block's schema, "
"then call again with proper values to execute."
),
},
},
"required": ["block_id", "input_data"],
"required": ["block_id", "block_name", "input_data"],
}
@property

View File

@@ -57,9 +57,10 @@ class RunMCPToolTool(BaseTool):
@property
def description(self) -> str:
return (
"Discover and execute MCP server tools. "
"Call with server_url only to list tools, then with tool_name + tool_arguments to execute. "
"Call get_mcp_guide first for server URLs and auth."
"Connect to an MCP (Model Context Protocol) server to discover and execute its tools. "
"Two-step: (1) call with server_url to list available tools, "
"(2) call again with server_url + tool_name + tool_arguments to execute. "
"Call get_mcp_guide for known server URLs and auth details."
)
@property
@@ -69,15 +70,24 @@ class RunMCPToolTool(BaseTool):
"properties": {
"server_url": {
"type": "string",
"description": "MCP server URL (Streamable HTTP endpoint).",
"description": (
"URL of the MCP server (Streamable HTTP endpoint), "
"e.g. https://mcp.example.com/mcp"
),
},
"tool_name": {
"type": "string",
"description": "Tool to execute. Omit to discover available tools.",
"description": (
"Name of the MCP tool to execute. "
"Omit on first call to discover available tools."
),
},
"tool_arguments": {
"type": "object",
"description": "Arguments matching the tool's input schema.",
"description": (
"Arguments to pass to the selected tool. "
"Must match the tool's input schema returned during discovery."
),
},
},
"required": ["server_url"],

View File

@@ -38,7 +38,11 @@ class SearchDocsTool(BaseTool):
@property
def description(self) -> str:
return "Search platform documentation by keyword. Use get_doc_page to read full results."
return (
"Search the AutoGPT platform documentation for information about "
"how to use the platform, build agents, configure blocks, and more. "
"Returns relevant documentation sections. Use get_doc_page to read full content."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -47,7 +51,10 @@ class SearchDocsTool(BaseTool):
"properties": {
"query": {
"type": "string",
"description": "Documentation search query.",
"description": (
"Search query to find relevant documentation. "
"Use natural language to describe what you're looking for."
),
},
},
"required": ["query"],

View File

@@ -1,81 +0,0 @@
"""Schema regression tests for all registered CoPilot tools.
Validates that every tool in TOOL_REGISTRY produces a well-formed schema:
- description is non-empty
- all `required` fields exist in `properties`
- every property has a `type` and `description`
- total token budget does not regress past 8000 tokens
"""
import json
import pytest
import tiktoken
from backend.copilot.tools import TOOL_REGISTRY
_TOKEN_BUDGET = 8_000
def _get_all_tool_schemas() -> list[tuple[str, object]]:
"""Return (tool_name, openai_schema) pairs for every registered tool."""
return [(name, tool.as_openai_tool()) for name, tool in TOOL_REGISTRY.items()]
_ALL_SCHEMAS = _get_all_tool_schemas()
@pytest.mark.parametrize(
"tool_name,schema",
_ALL_SCHEMAS,
ids=[name for name, _ in _ALL_SCHEMAS],
)
class TestToolSchema:
"""Validate schema invariants for every registered tool."""
def test_description_non_empty(self, tool_name: str, schema: dict) -> None:
desc = schema["function"].get("description", "")
assert desc, f"Tool '{tool_name}' has an empty description"
def test_required_fields_exist_in_properties(
self, tool_name: str, schema: dict
) -> None:
params = schema["function"].get("parameters", {})
properties = params.get("properties", {})
required = params.get("required", [])
for field in required:
assert field in properties, (
f"Tool '{tool_name}': required field '{field}' "
f"not found in properties {list(properties.keys())}"
)
def test_every_property_has_type_and_description(
self, tool_name: str, schema: dict
) -> None:
params = schema["function"].get("parameters", {})
properties = params.get("properties", {})
for prop_name, prop_def in properties.items():
assert (
"type" in prop_def
), f"Tool '{tool_name}', property '{prop_name}' is missing 'type'"
assert (
"description" in prop_def
), f"Tool '{tool_name}', property '{prop_name}' is missing 'description'"
def test_total_schema_token_budget() -> None:
"""Assert total tool schema size stays under the token budget.
This locks in the 34% token reduction from #12398 and prevents future
description bloat from eroding the gains. Budget is set to 8000 tokens.
Note: this measures tool JSON only (not the full system prompt); the actual
baseline for tool schemas alone is ~6470 tokens, giving ~19% headroom.
"""
schemas = [tool.as_openai_tool() for tool in TOOL_REGISTRY.values()]
serialized = json.dumps(schemas)
enc = tiktoken.get_encoding("cl100k_base")
total_tokens = len(enc.encode(serialized))
assert total_tokens < _TOKEN_BUDGET, (
f"Tool schemas use {total_tokens} tokens, exceeding budget of {_TOKEN_BUDGET}. "
f"Description bloat detected — trim descriptions or raise the budget intentionally."
)

View File

@@ -21,7 +21,19 @@ class ValidateAgentGraphTool(BaseTool):
@property
def description(self) -> str:
return "Validate agent JSON for correctness (block_ids, links, types, schemas). On failure, use fix_agent_graph to auto-fix."
return (
"Validate an agent JSON graph for correctness. Checks:\n"
"- All block_ids reference real blocks\n"
"- All links reference valid source/sink nodes and fields\n"
"- Required input fields are wired or have defaults\n"
"- Data types are compatible across links\n"
"- Nested sink links use correct notation\n"
"- Prompt templates use proper curly brace escaping\n"
"- AgentExecutorBlock configurations are valid\n\n"
"Call this after generating agent JSON to verify correctness. "
"If validation fails, either fix issues manually based on the error "
"descriptions, or call fix_agent_graph to auto-fix common problems."
)
@property
def requires_auth(self) -> bool:
@@ -34,7 +46,11 @@ class ValidateAgentGraphTool(BaseTool):
"properties": {
"agent_json": {
"type": "object",
"description": "Agent JSON with 'nodes' and 'links' arrays.",
"description": (
"The agent JSON to validate. Must contain 'nodes' and 'links' arrays. "
"Each node needs: id (UUID), block_id, input_default, metadata. "
"Each link needs: id (UUID), source_id, source_name, sink_id, sink_name."
),
},
},
"required": ["agent_json"],

View File

@@ -59,7 +59,13 @@ class WebFetchTool(BaseTool):
@property
def description(self) -> str:
return "Fetch a public web page. Public URLs only — internal addresses blocked. Returns readable text from HTML by default."
return (
"Fetch the content of a public web page by URL. "
"Returns readable text extracted from HTML by default. "
"Useful for reading documentation, articles, and API responses. "
"Only supports HTTP/HTTPS GET requests to public URLs "
"(private/internal network addresses are blocked)."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -68,11 +74,14 @@ class WebFetchTool(BaseTool):
"properties": {
"url": {
"type": "string",
"description": "Public HTTP/HTTPS URL.",
"description": "The public HTTP/HTTPS URL to fetch.",
},
"extract_text": {
"type": "boolean",
"description": "Extract text from HTML (default: true).",
"description": (
"If true (default), extract readable text from HTML. "
"If false, return raw content."
),
"default": True,
},
},

View File

@@ -321,7 +321,13 @@ class ListWorkspaceFilesTool(BaseTool):
@property
def description(self) -> str:
return "List persistent workspace files. For ephemeral session files, use SDK Glob/Read instead. Optionally filter by path prefix."
return (
"List files in the user's persistent workspace (cloud storage). "
"These files survive across sessions. "
"For ephemeral session files, use the SDK Read/Glob tools instead. "
"Returns file names, paths, sizes, and metadata. "
"Optionally filter by path prefix."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -330,17 +336,24 @@ class ListWorkspaceFilesTool(BaseTool):
"properties": {
"path_prefix": {
"type": "string",
"description": "Filter by path prefix (e.g. '/documents/').",
"description": (
"Optional path prefix to filter files "
"(e.g., '/documents/' to list only files in documents folder). "
"By default, only files from the current session are listed."
),
},
"limit": {
"type": "integer",
"description": "Max files to return (default 50, max 100).",
"description": "Maximum number of files to return (default 50, max 100)",
"minimum": 1,
"maximum": 100,
},
"include_all_sessions": {
"type": "boolean",
"description": "Include files from all sessions (default: false).",
"description": (
"If true, list files from all sessions. "
"Default is false (only current session's files)."
),
},
},
"required": [],
@@ -423,10 +436,18 @@ class ReadWorkspaceFileTool(BaseTool):
@property
def description(self) -> str:
return (
"Read a file from persistent workspace. Specify file_id or path. "
"Small text/image files return inline; large/binary return metadata+URL. "
"Use save_to_path to copy to working dir for processing. "
"Use offset/length for paginated reads."
"Read a file from the user's persistent workspace (cloud storage). "
"These files survive across sessions. "
"For ephemeral session files, use the SDK Read tool instead. "
"Specify either file_id or path to identify the file. "
"For small text files, returns content directly. "
"For large or binary files, returns metadata and a download URL. "
"Use 'save_to_path' to copy the file to the working directory "
"(sandbox or ephemeral) for processing with bash_exec or file tools. "
"Use 'offset' and 'length' for paginated reads of large files "
"(e.g., persisted tool outputs). "
"Paths are scoped to the current session by default. "
"Use /sessions/<session_id>/... for cross-session access."
)
@property
@@ -436,30 +457,48 @@ class ReadWorkspaceFileTool(BaseTool):
"properties": {
"file_id": {
"type": "string",
"description": "File ID from list_workspace_files.",
"description": "The file's unique ID (from list_workspace_files)",
},
"path": {
"type": "string",
"description": "Virtual file path (e.g. '/documents/report.pdf').",
"description": (
"The virtual file path (e.g., '/documents/report.pdf'). "
"Scoped to current session by default."
),
},
"save_to_path": {
"type": "string",
"description": "Copy file to this working directory path for processing.",
"description": (
"If provided, save the file to this path in the working "
"directory (cloud sandbox when E2B is active, or "
"ephemeral dir otherwise) so it can be processed with "
"bash_exec or file tools. "
"The file content is still returned in the response."
),
},
"force_download_url": {
"type": "boolean",
"description": "Always return metadata+URL instead of inline content.",
"description": (
"If true, always return metadata+URL instead of inline content. "
"Default is false (auto-selects based on file size/type)."
),
},
"offset": {
"type": "integer",
"description": "Character offset for paginated reads (0-based).",
"description": (
"Character offset to start reading from (0-based). "
"Use with 'length' for paginated reads of large files."
),
},
"length": {
"type": "integer",
"description": "Max characters to return for paginated reads.",
"description": (
"Maximum number of characters to return. "
"Defaults to full file. Use with 'offset' for paginated reads."
),
},
},
"required": [], # At least one of file_id or path must be provided
"required": [], # At least one must be provided
}
@property
@@ -614,9 +653,15 @@ class WriteWorkspaceFileTool(BaseTool):
@property
def description(self) -> str:
return (
"Write a file to persistent workspace (survives across sessions). "
"Provide exactly one of: content (text), content_base64 (binary), "
f"or source_path (copy from working dir). Max {Config().max_file_size_mb}MB."
"Write or create a file in the user's persistent workspace (cloud storage). "
"These files survive across sessions. "
"For ephemeral session files, use the SDK Write tool instead. "
"Provide content as plain text via 'content', OR base64-encoded via "
"'content_base64', OR copy a file from the ephemeral working directory "
"via 'source_path'. Exactly one of these three is required. "
f"Maximum file size is {Config().max_file_size_mb}MB. "
"Files are saved to the current session's folder by default. "
"Use /sessions/<session_id>/... for cross-session access."
)
@property
@@ -626,31 +671,51 @@ class WriteWorkspaceFileTool(BaseTool):
"properties": {
"filename": {
"type": "string",
"description": "Filename (e.g. 'report.pdf').",
"description": "Name for the file (e.g., 'report.pdf')",
},
"content": {
"type": "string",
"description": "Plain text content. Mutually exclusive with content_base64/source_path.",
"description": (
"Plain text content to write. Use this for text files "
"(code, configs, documents, etc.). "
"Mutually exclusive with content_base64 and source_path."
),
},
"content_base64": {
"type": "string",
"description": "Base64-encoded binary content. Mutually exclusive with content/source_path.",
"description": (
"Base64-encoded file content. Use this for binary files "
"(images, PDFs, etc.). "
"Mutually exclusive with content and source_path."
),
},
"source_path": {
"type": "string",
"description": "Working directory path to copy to workspace. Mutually exclusive with content/content_base64.",
"description": (
"Path to a file in the ephemeral working directory to "
"copy to workspace (e.g., '/tmp/copilot-.../output.csv'). "
"Use this to persist files created by bash_exec or SDK Write. "
"Mutually exclusive with content and content_base64."
),
},
"path": {
"type": "string",
"description": "Virtual path (e.g. '/documents/report.pdf'). Defaults to '/{filename}'.",
"description": (
"Optional virtual path where to save the file "
"(e.g., '/documents/report.pdf'). "
"Defaults to '/{filename}'. Scoped to current session."
),
},
"mime_type": {
"type": "string",
"description": "MIME type. Auto-detected from filename if omitted.",
"description": (
"Optional MIME type of the file. "
"Auto-detected from filename if not provided."
),
},
"overwrite": {
"type": "boolean",
"description": "Overwrite if file exists (default: false).",
"description": "Whether to overwrite if file exists at path (default: false)",
},
},
"required": ["filename"],
@@ -777,7 +842,12 @@ class DeleteWorkspaceFileTool(BaseTool):
@property
def description(self) -> str:
return "Delete a file from persistent workspace. Specify file_id or path."
return (
"Delete a file from the user's persistent workspace (cloud storage). "
"Specify either file_id or path to identify the file. "
"Paths are scoped to the current session by default. "
"Use /sessions/<session_id>/... for cross-session access."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -786,14 +856,17 @@ class DeleteWorkspaceFileTool(BaseTool):
"properties": {
"file_id": {
"type": "string",
"description": "File ID from list_workspace_files.",
"description": "The file's unique ID (from list_workspace_files)",
},
"path": {
"type": "string",
"description": "Virtual file path.",
"description": (
"The virtual file path (e.g., '/documents/report.pdf'). "
"Scoped to current session by default."
),
},
},
"required": [], # At least one of file_id or path must be provided
"required": [], # At least one must be provided
}
@property