Add workflow commands to CLI #424
Merged
+409
−128
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Caution Review failedThe pull request is closed. WalkthroughRefactors several utility import paths, updates a utils docstring, removes the legacy single workflow status CLI and its re-exports, and adds a pluralized workflows CLI group with new describe, resume, suspend, and cancel command implementations plus package-level exports; updates cloud CLI wiring and one logger import. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant User
participant CLI as cloud.workflows.describe
participant Utils as Auth/Resolve
participant MCP as MCPApp/Client
participant Server as Workflow Server (SSE)
User->>CLI: mcp-agent cloud workflows describe <server|url> <run_id>
CLI->>Utils: setup_authenticated_client / resolve_server (if ID)
alt Input is URL
CLI->>Server: Derive SSE endpoint (/sse)
else Input is Server ID
Utils-->>CLI: serverUrl from appServerInfo
CLI->>Server: Build SSE endpoint (/sse)
end
CLI->>MCP: init app + register server
CLI->>MCP: gen_client("workflow_server")
CLI->>Server: call tool "workflows-get_status" { run_id }
Server-->>CLI: status payload
CLI-->>User: Print status (text/json/yaml)
sequenceDiagram
autonumber
participant User
participant CLI as cloud.workflows.cancel
participant Utils as Auth/Resolve
participant MCP as MCPApp/Client
participant Server as Workflow Server (SSE)
User->>CLI: mcp-agent cloud workflows cancel <server|url> <run_id> [--reason]
CLI->>Utils: setup_authenticated_client / resolve_server
CLI->>MCP: init app + register SSE server
CLI->>Server: call tool "workflows-cancel" { run_id }
Server-->>CLI: result.success (text/bool)
alt success
CLI-->>User: Print confirmation with Run ID (+ reason)
else failure
CLI-->>User: CLIError
end
sequenceDiagram
autonumber
participant User
participant CLI as cloud.workflows.resume/suspend
participant Utils as Auth/Resolve
participant MCP as MCPApp/Client
participant Server as Workflow Server (SSE)
User->>CLI: ... workflows (resume|suspend) <server|url> <run_id> [--payload]
CLI->>Utils: setup_authenticated_client / resolve_server
CLI->>MCP: init app + register SSE server
CLI->>Server: call tool "workflows-resume" { run_id, signal=(resume|suspend), payload? }
Server-->>CLI: result.success
CLI-->>User: Success or CLIError
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60 minutes Possibly related PRs
Suggested reviewers
Poem
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (16)
✨ Finishing Touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Merged
This stack of pull requests is managed by Graphite. Learn more about stacking. |
This was referenced Sep 5, 2025
jtcorbett
force-pushed
the
09-05-add_workflow_commands_to_cli
branch
from
b703ddf to
964b3ed
Compare
jtcorbett
force-pushed
the
09-05-do_not_allow_unsupported_server_urls_as_arguments
branch
2 times, most recently
from
6456278 to
edc93a2
Compare
jtcorbett
force-pushed
the
09-05-add_workflow_commands_to_cli
branch
3 times, most recently
from
fe4bb49 to
1b139f7
Compare
jtcorbett
force-pushed
the
09-05-do_not_allow_unsupported_server_urls_as_arguments
branch
from
897130c to
0998161
Compare
jtcorbett
changed the base branch from
09-05-do_not_allow_unsupported_server_urls_as_arguments
to
graphite-base/424
jtcorbett
force-pushed
the
09-05-add_workflow_commands_to_cli
branch
from
1b139f7 to
6a1876e
Compare
jtcorbett
force-pushed
the
graphite-base/424
branch
from
0998161 to
1dd21da
Compare
jtcorbett
changed the base branch from
graphite-base/424
to
09-05-do_not_allow_unsupported_server_urls_as_arguments
jtcorbett
changed the base branch from
09-05-do_not_allow_unsupported_server_urls_as_arguments
to
graphite-base/424
jtcorbett
force-pushed
the
graphite-base/424
branch
from
1dd21da to
c0fc9f6
Compare
jtcorbett
force-pushed
the
09-05-add_workflow_commands_to_cli
branch
from
6a1876e to
621e33c
Compare
jtcorbett
force-pushed
the
09-05-add_workflow_commands_to_cli
branch
from
6e6696c to
50eaf6f
Compare
saqadri
approved these changes
Sep 8, 2025
jtcorbett
force-pushed
the
09-05-add_workflow_commands_to_cli
branch
from
48c65a9 to
2a07045
Compare
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 7
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/mcp_agent/cli/cloud/commands/servers/list/main.py (1)
148-155: Fix created_at sorting to avoid aware/naive datetime comparisonCurrent key may mix timezone-aware datetimes with a naive fallback, causing TypeError and silently disabling sorting. Use a numeric key.
- elif sort_field_lower in ['created', 'created_at', 'date']: - return created_at or datetime.min.replace(tzinfo=None if created_at is None else created_at.tzinfo) + elif sort_field_lower in ['created', 'created_at', 'date']: + # Use epoch seconds; None sorts first + try: + return created_at.timestamp() if created_at else float('-inf') + except Exception: + return float('-inf')
🧹 Nitpick comments (12)
src/mcp_agent/cli/cloud/commands/utils.py (1)
1-1: Align wording with broader "cloud" scopeUpdate messages/docstrings to avoid “servers”-specific phrasing now that this module backs logger/workflows too.
@@ - raise CLIError( - "Must be logged in to access servers. Run 'mcp-agent login'." - ) + raise CLIError( + "Must be logged in to access cloud resources. Run 'mcp-agent login'." + ) @@ -def handle_server_api_errors(func): - """Decorator to handle common API errors for server commands. +def handle_server_api_errors(func): + """Decorator to handle common API errors for cloud commands.Also applies to: 29-36, 81-89
src/mcp_agent/cli/cloud/commands/workflows/resume/__init__.py (1)
1-5: Split suspend into its own package for symmetryRe-exporting suspend from the resume package can be confusing. Mirror the other commands for discoverability.
-"""MCP Agent Cloud workflow resume and suspend commands.""" - -from .main import resume_workflow, suspend_workflow - -__all__ = ["resume_workflow", "suspend_workflow"] +"""MCP Agent Cloud workflow resume command.""" + +from .main import resume_workflow + +__all__ = ["resume_workflow"]New file to add (for clarity and symmetry):
# src/mcp_agent/cli/cloud/commands/workflows/suspend/__init__.py """MCP Agent Cloud workflow suspend command.""" from ..resume.main import suspend_workflow # or move implementation alongside this package __all__ = ["suspend_workflow"]Remember to update the aggregator (workflows/init.py) and CLI wiring accordingly.
src/mcp_agent/cli/cloud/commands/workflows/resume/main.py (3)
53-57: Result parsing is brittle; handle JSON/boolean content robustlyAssuming text “true” is narrow. Prefer checking JSON content or booleans, then text fallback.
- success = result.content[0].text if result.content else False - if isinstance(success, str): - success = success.lower() == 'true' + success = False + if result.content: + item = result.content[0] + # Prefer JSON/boolean content if present + if hasattr(item, "data"): + data = getattr(item, "data") + success = bool(data.get("success", data)) if isinstance(data, dict) else bool(data) + elif hasattr(item, "text"): + txt = item.text.strip().lower() + success = txt in {"true", "ok", "1", "success"}Also applies to: 60-63
93-99: Use parsed JSON payload instead of discarding itYou detect JSON but don’t use it; send a typed object when possible.
if payload: try: - json.loads(payload) + payload = json.loads(payload) console.print("[dim]Resuming with JSON payload...[/dim]") except json.JSONDecodeError: console.print("[dim]Resuming with text payload...[/dim]")
119-125: Mirror payload parsing for suspendSame improvement as resume.
if payload: try: - json.loads(payload) + payload = json.loads(payload) console.print("[dim]Suspending with JSON payload...[/dim]") except json.JSONDecodeError: console.print("[dim]Suspending with text payload...[/dim]")src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py (3)
43-49: Tighten server tool surface (allow-list the cancel tool)Limit exposed tools for this transient client to just what’s needed.
Apply:
context.server_registry.registry["workflow_server"] = MCPServerSettings( name="workflow_server", description=f"Deployed MCP server {server_url}", url=sse_url, - transport="sse" + transport="sse", + allowed_tools={"workflows-cancel"}, )
60-65: UX: success should be green, not a warningMinor polish.
Apply:
- console.print("[yellow]⚠[/yellow] Successfully cancelled workflow") + console.print("[green]✅[/green] Successfully cancelled workflow")
22-35: DRY: extract shared server URL + SSE helpersBoth workflows commands duplicate server URL resolution and SSE URL shaping. Consider adding to .../utils.py:
Example helpers (outside this file):
def resolve_server_url_or_raise(server_id_or_url: str) -> str: if server_id_or_url.startswith(("http://", "https://")): return server_id_or_url client = setup_authenticated_client() server = resolve_server(client, server_id_or_url) server_url = getattr(getattr(server, "appServerInfo", None), "serverUrl", None) if not server_url: raise CLIError(f"Server '{server_id_or_url}' is not deployed or has no server URL") return server_url def ensure_sse_url(server_url: str) -> str: return f"{server_url.rstrip('/')}/sse" if not server_url.endswith("/sse") else server_urlThen here:
server_url = resolve_server_url_or_raise(server_id_or_url) sse_url = ensure_sse_url(server_url)Also applies to: 43-43
src/mcp_agent/cli/cloud/commands/workflows/describe/main.py (4)
47-52: Limit exposed tools to only status toolReduce blast radius for the ad-hoc client.
Apply:
context.server_registry.registry["workflow_server"] = MCPServerSettings( name="workflow_server", description=f"Deployed MCP server {server_url}", url=sse_url, - transport="sse" + transport="sse", + allowed_tools={"workflows-get_status"}, )
66-73: Avoid shadowing built-in 'format' and use safe YAML dumpRename variable to output_format and switch to yaml.safe_dump.
Apply:
- format: str = "text" + output_format: str = "text" @@ - if format == "json": + if output_format == "json": print(json.dumps(workflow_status, indent=2)) - elif format == "yaml": - print(yaml.dump(workflow_status, default_flow_style=False)) + elif output_format == "yaml": + print(yaml.safe_dump(workflow_status, default_flow_style=False)) else: # text format print_workflow_status(workflow_status) @@ -def describe_workflow( +def describe_workflow( server_id_or_url: str = typer.Argument(..., help="Server ID or URL hosting the workflow"), run_id: str = typer.Argument(..., help="Run ID of the workflow to describe"), - format: Optional[str] = typer.Option("text", "--format", help="Output format (text|json|yaml)"), + output_format: Optional[str] = typer.Option("text", "--format", help="Output format (text|json|yaml)"), ) -> None: @@ - if format not in ["text", "json", "yaml"]: + if output_format not in ["text", "json", "yaml"]: console.print("[red]Error: --format must be 'text', 'json', or 'yaml'[/red]") raise typer.Exit(6) - run_async(_describe_workflow_async(server_id_or_url, run_id, format)) + run_async(_describe_workflow_async(server_id_or_url, run_id, output_format))Also applies to: 79-83, 92-96, 96-96
106-113: Include timezone when formatting Created timeCurrent output drops TZ info. Normalize to UTC and indicate it explicitly.
Apply:
- from datetime import datetime + from datetime import datetime, timezone created_dt = datetime.fromisoformat(created_at.replace('Z', '+00:00')) - created_at = created_dt.strftime('%Y-%m-%d %H:%M:%S') + if created_dt.tzinfo is not None: + created_dt = created_dt.astimezone(tz=timezone.utc) + created_at = created_dt.strftime('%Y-%m-%d %H:%M:%S UTC')
39-41: DRY: reuse shared helpers for URL resolution and SSE shapingSame duplication as in cancel command; see suggested utils in that comment.
Would simplify to:
server_url = resolve_server_url_or_raise(server_id_or_url) sse_url = ensure_sse_url(server_url)Also applies to: 43-54
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
uv.lockis excluded by!**/*.lock
📒 Files selected for processing (16)
src/mcp_agent/cli/cloud/commands/logger/tail/main.py(1 hunks)src/mcp_agent/cli/cloud/commands/servers/delete/main.py(1 hunks)src/mcp_agent/cli/cloud/commands/servers/describe/main.py(1 hunks)src/mcp_agent/cli/cloud/commands/servers/list/main.py(1 hunks)src/mcp_agent/cli/cloud/commands/utils.py(1 hunks)src/mcp_agent/cli/cloud/commands/workflow/__init__.py(0 hunks)src/mcp_agent/cli/cloud/commands/workflow/status/__init__.py(0 hunks)src/mcp_agent/cli/cloud/commands/workflow/status/main.py(0 hunks)src/mcp_agent/cli/cloud/commands/workflows/__init__.py(1 hunks)src/mcp_agent/cli/cloud/commands/workflows/cancel/__init__.py(1 hunks)src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py(1 hunks)src/mcp_agent/cli/cloud/commands/workflows/describe/__init__.py(1 hunks)src/mcp_agent/cli/cloud/commands/workflows/describe/main.py(1 hunks)src/mcp_agent/cli/cloud/commands/workflows/resume/__init__.py(1 hunks)src/mcp_agent/cli/cloud/commands/workflows/resume/main.py(1 hunks)src/mcp_agent/cli/cloud/main.py(3 hunks)
💤 Files with no reviewable changes (3)
- src/mcp_agent/cli/cloud/commands/workflow/init.py
- src/mcp_agent/cli/cloud/commands/workflow/status/init.py
- src/mcp_agent/cli/cloud/commands/workflow/status/main.py
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-07-22T18:59:49.368Z
Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-07-22T18:59:49.368Z
Learning: Applies to examples/usecases/reliable_conversation/examples/reliable_conversation/src/utils/config.py : Configuration values such as quality_threshold, max_refinement_attempts, consolidation_interval, and evaluator_model_provider must be loaded from mcp_agent.config.yaml.
Applied to files:
src/mcp_agent/cli/cloud/commands/servers/describe/main.py
🧬 Code graph analysis (9)
src/mcp_agent/cli/cloud/commands/workflows/resume/__init__.py (1)
src/mcp_agent/cli/cloud/commands/workflows/resume/main.py (2)
resume_workflow(78-100)suspend_workflow(104-126)
src/mcp_agent/cli/cloud/commands/logger/tail/main.py (1)
src/mcp_agent/cli/cloud/commands/utils.py (1)
setup_authenticated_client(18-36)
src/mcp_agent/cli/cloud/commands/workflows/__init__.py (4)
src/mcp_agent/cli/cloud/commands/workflows/describe/main.py (1)
describe_workflow(78-96)src/mcp_agent/cli/cloud/commands/workflows/resume/main.py (2)
resume_workflow(78-100)suspend_workflow(104-126)src/mcp_agent/executor/workflow.py (1)
cancel(403-424)src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py (1)
cancel_workflow(73-87)
src/mcp_agent/cli/cloud/commands/workflows/describe/main.py (4)
src/mcp_agent/cli/exceptions.py (1)
CLIError(4-9)src/mcp_agent/config.py (2)
MCPServerSettings(52-113)LoggerSettings(531-576)src/mcp_agent/mcp/gen_client.py (1)
gen_client(16-41)src/mcp_agent/cli/cloud/commands/utils.py (3)
setup_authenticated_client(18-36)resolve_server(53-77)handle_server_api_errors(80-105)
src/mcp_agent/cli/cloud/commands/workflows/cancel/__init__.py (1)
src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py (1)
cancel_workflow(73-87)
src/mcp_agent/cli/cloud/commands/workflows/describe/__init__.py (1)
src/mcp_agent/cli/cloud/commands/workflows/describe/main.py (1)
describe_workflow(78-96)
src/mcp_agent/cli/cloud/commands/workflows/resume/main.py (4)
src/mcp_agent/cli/exceptions.py (1)
CLIError(4-9)src/mcp_agent/config.py (2)
MCPServerSettings(52-113)LoggerSettings(531-576)src/mcp_agent/mcp/gen_client.py (1)
gen_client(16-41)src/mcp_agent/cli/cloud/commands/utils.py (3)
setup_authenticated_client(18-36)resolve_server(53-77)handle_server_api_errors(80-105)
src/mcp_agent/cli/cloud/main.py (3)
src/mcp_agent/cli/cloud/commands/workflows/describe/main.py (1)
describe_workflow(78-96)src/mcp_agent/cli/cloud/commands/workflows/resume/main.py (2)
resume_workflow(78-100)suspend_workflow(104-126)src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py (1)
cancel_workflow(73-87)
src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py (5)
src/mcp_agent/cli/exceptions.py (1)
CLIError(4-9)src/mcp_agent/app.py (2)
config(154-155)logger(190-207)src/mcp_agent/config.py (2)
MCPServerSettings(52-113)LoggerSettings(531-576)src/mcp_agent/mcp/gen_client.py (1)
gen_client(16-41)src/mcp_agent/cli/cloud/commands/utils.py (3)
setup_authenticated_client(18-36)resolve_server(53-77)handle_server_api_errors(80-105)
🔇 Additional comments (13)
src/mcp_agent/cli/cloud/commands/logger/tail/main.py (1)
20-20: Import path realignment — OKSwitched to the centralized cloud utils; no behavior change.
src/mcp_agent/cli/cloud/commands/servers/list/main.py (1)
11-16: Import path update — OKUtilities now sourced from the centralized cloud utils module.
src/mcp_agent/cli/cloud/commands/servers/describe/main.py (1)
10-16: Import path update — OKConsistent with the centralized cloud utils module.
src/mcp_agent/cli/cloud/commands/servers/delete/main.py (1)
9-14: Import path update — OKCentralized utils import looks correct; call sites unchanged.
src/mcp_agent/cli/cloud/commands/workflows/describe/__init__.py (1)
1-5: Package export — OK — alias verified
Re-exports are clean; public surface is explicit, and thestatusalias is correctly wired in src/mcp_agent/cli/cloud/main.py (lines 151–152).src/mcp_agent/cli/cloud/commands/workflows/cancel/__init__.py (1)
1-5: Package export — OKDocstring + explicit all are good.
src/mcp_agent/cli/cloud/commands/workflows/__init__.py (1)
3-12: Clean exports and grouping look goodCentralizing the command exports here is clear and consistent with the new workflows group. No issues.
src/mcp_agent/cli/cloud/commands/workflows/resume/main.py (2)
58-59: No change needed: CLI resume command correctly calls the only registered tool
Server code registers onlyworkflows-resumevia@mcp.tool(name="workflows-resume"); there is noworkflows-suspendor genericworkflows-signaltool to call.Likely an incorrect or invalid review comment.
45-51: Remove headers propagation suggestion
TheAppServerInfomodel doesn’t include aheadersfield, so referencingserver.appServerInfo.headerswill not compile.Likely an incorrect or invalid review comment.
src/mcp_agent/cli/cloud/main.py (2)
145-155: Workflows group wiring looks correctNew Typer group and command registrations (describe/status/resume/suspend/cancel) are consistent and discoverable.
212-214: Nice: workflows attached under cloud with clear helpGood placement and help text. No action needed.
src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py (1)
54-54: Remove verification check:workflows-cancelis already registered via@mcp.tool(name="workflows-cancel")insrc/mcp_agent/server/app_server.py.src/mcp_agent/cli/cloud/commands/workflows/describe/main.py (1)
55-58: No issues found: “workflows-get_status” is registered and SSE URL handling is consistent
The @mcp.tool decorator in src/mcp_agent/server/app_server.py registersworkflows-get_status, and other workflow commands correctly useserver_url.rstrip('/')for SSE URLs.
Comment on lines
+52
to
+55
| tool_params = {"run_id": run_id} | ||
|
|
||
| result = await client.call_tool("workflows-cancel", tool_params) | ||
|
|
There was a problem hiding this comment.
Fix: forward --reason to server tool call
The CLI accepts --reason but doesn’t forward it, so the server never receives it.
Apply:
- tool_params = {"run_id": run_id}
+ tool_params = {"run_id": run_id}
+ if reason is not None:
+ tool_params["reason"] = reason📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| tool_params = {"run_id": run_id} | |
| result = await client.call_tool("workflows-cancel", tool_params) | |
| tool_params = {"run_id": run_id} | |
| if reason is not None: | |
| tool_params["reason"] = reason | |
| result = await client.call_tool("workflows-cancel", tool_params) |
🤖 Prompt for AI Agents
In src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py around lines 52 to
55, the CLI parses a --reason flag but doesn’t include it in the payload sent to
the server; update the tool_params construction to include the reason (e.g., add
"reason": reason or conditionally add when reason is not None) so the await
client.call_tool("workflows-cancel", tool_params) forwards the reason to the
server.
Comment on lines
+56
to
+59
| success = result.content[0].text if result.content else False | ||
| if isinstance(success, str): | ||
| success = success.lower() == 'true' | ||
|
|
There was a problem hiding this comment.
🛠️ Refactor suggestion
Harden tool response parsing (accept bool/JSON/text “ok”)
Parsing assumes a text "true". Make it robust to boolean or JSON payloads.
Apply:
- success = result.content[0].text if result.content else False
- if isinstance(success, str):
- success = success.lower() == 'true'
+ success = False
+ if result.content:
+ item = result.content[0]
+ payload = getattr(item, "json", None) or getattr(item, "data", None) or getattr(item, "text", None)
+ if isinstance(payload, dict) and "success" in payload:
+ success = bool(payload["success"])
+ elif isinstance(payload, str):
+ success = payload.strip().lower() in {"true", "ok", "success", "1", "yes"}Committable suggestion skipped: line range outside the PR's diff.
Comment on lines
+68
to
+69
| except Exception as e: | ||
| raise CLIError(f"Error cancelling workflow with run ID {run_id}: {str(e)}") from e |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Preserve CLIError semantics (avoid double-wrapping)
Re-raise CLIError as-is so exit codes/messages are preserved.
Apply:
- except Exception as e:
- raise CLIError(f"Error cancelling workflow with run ID {run_id}: {str(e)}") from e
+ except CLIError:
+ raise
+ except Exception as e:
+ raise CLIError(f"Error cancelling workflow with run ID {run_id}: {e}") from e📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| except Exception as e: | |
| raise CLIError(f"Error cancelling workflow with run ID {run_id}: {str(e)}") from e | |
| except CLIError: | |
| raise | |
| except Exception as e: | |
| raise CLIError(f"Error cancelling workflow with run ID {run_id}: {e}") from e |
🤖 Prompt for AI Agents
In src/mcp_agent/cli/cloud/commands/workflows/cancel/main.py around lines 68-69,
the except block rewraps every Exception into a new CLIError which double-wraps
existing CLIError instances; change the handler to check if the caught exception
is already a CLIError and re-raise it unchanged (raise e), otherwise wrap
non-CLIError exceptions with CLIError(f"Error cancelling workflow with run ID
{run_id}: {str(e)}") from e so exit codes/messages are preserved.
Comment on lines
+46
to
+52
| sse_url = f"{server_url}/sse" if not server_url.endswith('/sse') else server_url | ||
| context.server_registry.registry["workflow_server"] = MCPServerSettings( | ||
| name="workflow_server", | ||
| description=f"Deployed MCP server {server_url}", | ||
| url=sse_url, | ||
| transport="sse" | ||
| ) |
There was a problem hiding this comment.
BUG: potential double slash in SSE URL
server_url like "https://host/" becomes "https://host//sse". Use rstrip('/') as done in cancel command.
Apply:
- sse_url = f"{server_url}/sse" if not server_url.endswith('/sse') else server_url
+ sse_url = f"{server_url.rstrip('/')}/sse" if not server_url.endswith('/sse') else server_url📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| sse_url = f"{server_url}/sse" if not server_url.endswith('/sse') else server_url | |
| context.server_registry.registry["workflow_server"] = MCPServerSettings( | |
| name="workflow_server", | |
| description=f"Deployed MCP server {server_url}", | |
| url=sse_url, | |
| transport="sse" | |
| ) | |
| sse_url = f"{server_url.rstrip('/')}/sse" if not server_url.endswith('/sse') else server_url | |
| context.server_registry.registry["workflow_server"] = MCPServerSettings( | |
| name="workflow_server", | |
| description=f"Deployed MCP server {server_url}", | |
| url=sse_url, | |
| transport="sse" | |
| ) |
🤖 Prompt for AI Agents
In src/mcp_agent/cli/cloud/commands/workflows/describe/main.py around lines 46
to 52, the SSE URL construction can produce a double slash when server_url ends
with '/', so normalize server_url first using rstrip('/') and then build sse_url
from that normalized value (only append "/sse" if the normalized string does not
already end with "/sse") — mirror the same normalization used in the cancel
command to avoid duplicated slashes.
Comment on lines
+59
to
+63
| workflow_status = result.content[0].text if result.content else {} | ||
| if isinstance(workflow_status, str): | ||
| workflow_status = json.loads(workflow_status) | ||
|
|
||
| if not workflow_status: |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Harden tool response parsing (dict/JSON/text)
Current logic assumes text then JSON.loads; handle JSON/object payloads too.
Apply:
- workflow_status = result.content[0].text if result.content else {}
- if isinstance(workflow_status, str):
- workflow_status = json.loads(workflow_status)
+ workflow_status = {}
+ if result.content:
+ item = result.content[0]
+ payload = getattr(item, "json", None) or getattr(item, "data", None) or getattr(item, "text", None)
+ if isinstance(payload, str):
+ workflow_status = json.loads(payload)
+ elif isinstance(payload, dict):
+ workflow_status = payload📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| workflow_status = result.content[0].text if result.content else {} | |
| if isinstance(workflow_status, str): | |
| workflow_status = json.loads(workflow_status) | |
| if not workflow_status: | |
| # Harden parsing of tool response: support raw JSON, dicts, or text | |
| - workflow_status = result.content[0].text if result.content else {} | |
| - if isinstance(workflow_status, str): | |
| workflow_status = {} | |
| if result.content: | |
| item = result.content[0] | |
| # Try JSON payload, then raw data, then text | |
| payload = getattr(item, "json", None) \ | |
| or getattr(item, "data", None) \ | |
| or getattr(item, "text", None) | |
| if isinstance(payload, str): | |
| workflow_status = json.loads(payload) | |
| elif isinstance(payload, dict): | |
| workflow_status = payload | |
| if not workflow_status: |
🤖 Prompt for AI Agents
In src/mcp_agent/cli/cloud/commands/workflows/describe/main.py around lines
59–63, the code assumes the tool response is text that can be JSON.parsed;
update parsing to accept a dict/object or JSON/text: if result.content exists,
take the first content item and if it is a dict/object use it directly, if it is
a string attempt json.loads inside a try/except (catch
ValueError/JSONDecodeError) and fall back to the original string or {} as
appropriate, and ensure workflow_status is normalized to a dict (e.g., {} when
empty or when parsing fails) before the subsequent "if not workflow_status"
check.
| from mcp_agent.cli.utils.ux import console | ||
| from mcp_agent.config import MCPServerSettings, Settings, LoggerSettings | ||
| from mcp_agent.mcp.gen_client import gen_client | ||
| from ...utils import setup_authenticated_client, resolve_server, handle_server_api_errors |
There was a problem hiding this comment.
Blocking: resolve_server() uses run_async; calling it from async causes nested event loop errors
resolve_server() internally calls run_async; invoking it inside _signal_workflow_async (already running in an event loop) can raise “asyncio.run() cannot be called from a running event loop”. Use an async resolver.
Apply this diff to switch to an async resolver:
-from ...utils import setup_authenticated_client, resolve_server, handle_server_api_errors
+from ...utils import setup_authenticated_client, resolve_server, handle_server_api_errors
+from ...utils import resolve_server_async # new async helper
@@
- client = setup_authenticated_client()
- server = resolve_server(client, server_id_or_url)
+ client = setup_authenticated_client()
+ server = await resolve_server_async(client, server_id_or_url)Add this helper in src/mcp_agent/cli/cloud/commands/utils.py:
# utils.py
from typing import Union
from mcp_agent.cli.core.utils import run_async # already present
from mcp_agent.app_client import MCPAppClient
from mcp_agent.app_types import MCPApp, MCPAppConfiguration # adjust to actual types
from .utils import parse_app_identifier # wherever it's defined
async def resolve_server_async(client: MCPAppClient, id_or_url: str) -> Union[MCPApp, MCPAppConfiguration]:
app_id, config_id = parse_app_identifier(id_or_url)
if config_id:
return await client.get_app_configuration(app_config_id=config_id)
return await client.get_app(app_id=app_id)Also applies to: 27-36
🤖 Prompt for AI Agents
In src/mcp_agent/cli/cloud/commands/workflows/resume/main.py around line 14,
resolve_server() uses run_async and causes nested event loop errors when called
from async code; replace it with an async resolver by adding
resolve_server_async to src/mcp_agent/cli/cloud/commands/utils.py (as described
in the review) which accepts an MCPAppClient and id_or_url and awaits
client.get_app or client.get_app_configuration, then import resolve_server_async
in this file and update the calls where resolve_server is used (also at lines
~27-36) to await resolve_server_async instead of calling resolve_server,
removing any synchronous run_async wrappers.
Comment on lines
+73
to
+74
| except Exception as e: | ||
| raise CLIError(f"Error {signal_name}ing workflow with run ID {run_id}: {str(e)}") from e |
There was a problem hiding this comment.
Fix user-facing grammar in error messages (“resumeing”)
Map to proper gerunds.
- except Exception as e:
- raise CLIError(f"Error {signal_name}ing workflow with run ID {run_id}: {str(e)}") from e
+ except Exception as e:
+ gerund = {"resume": "resuming", "suspend": "suspending"}.get(signal_name, f"{signal_name}ing")
+ raise CLIError(f"Error {gerund} workflow with run ID {run_id}: {str(e)}") from e📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| except Exception as e: | |
| raise CLIError(f"Error {signal_name}ing workflow with run ID {run_id}: {str(e)}") from e | |
| except Exception as e: | |
| gerund = {"resume": "resuming", "suspend": "suspending"}.get(signal_name, f"{signal_name}ing") | |
| raise CLIError(f"Error {gerund} workflow with run ID {run_id}: {str(e)}") from e |
🤖 Prompt for AI Agents
In src/mcp_agent/cli/cloud/commands/workflows/resume/main.py around lines 73-74,
the error message uses a naive string concatenation that produces incorrect
gerunds like "resumeing"; replace that with a small helper that converts the
verb in signal_name to its correct gerund form before formatting the message
(handle common rules: verbs ending in "ie" -> replace with "ying", verbs ending
in "e" -> drop the "e" and add "ing", handle short vowel-consonant by doubling
the final consonant, otherwise add "ing"), then use that gerund in the CLIError
message so it reads e.g. "resuming workflow" instead of "resumeing workflow".
2a07045 to
24d3845
Compare
jtcorbett
changed the base branch from
graphite-base/424
to
09-08-temporarily_exclude_cli_from_test_coverage
jtcorbett
changed the base branch from
09-08-temporarily_exclude_cli_from_test_coverage
to
graphite-base/424
jtcorbett
force-pushed
the
graphite-base/424
branch
from
d7e0a61 to
8108d90
Compare
jtcorbett
force-pushed
the
09-05-add_workflow_commands_to_cli
branch
from
24d3845 to
d0f0d96
Compare
Merge activity
|
This was referenced Sep 8, 2025
andrew-lastmile
added a commit
that referenced
this pull request
Sep 11, 2025
* Temporarily exclude CLI from test coverage (#429) ### TL;DR Exclude CLI code from test coverage metrics for now. Will add tests when we're done sprinting 10000 mph  <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Tests** * Adjusted test coverage collection to exclude non-critical CLI components, resulting in more accurate coverage metrics for core functionality. * **Chores** * Updated coverage reporting configuration to align with the new exclusion rules, ensuring consistent results across local and CI runs. <!-- end of auto-generated comment: release notes by coderabbit.ai --> * Add workflow commands to CLI (#424) ### TL;DR Added workflow management commands to the MCP Agent CLI, including describe, suspend, resume, and cancel operations. ### What changed? - Added four new workflow management commands: - `describe_workflow`: Shows detailed information about a workflow execution - `suspend_workflow`: Pauses a running workflow execution - `resume_workflow`: Resumes a previously suspended workflow - `cancel_workflow`: Permanently stops a workflow execution - Implemented corresponding API client methods in `WorkflowAPIClient`: - `suspend_workflow` - `resume_workflow` - `cancel_workflow` - Updated the CLI structure to expose these commands under `mcp-agent cloud workflows` - Added an alias for `describe_workflow` as `status` for backward compatibility ### How to test? Test the new workflow commands with a running workflow: ``` # Get workflow details mcp-agent cloud workflows describe run_abc123 mcp-agent cloud workflows status run_abc123 # alias # Suspend a workflow mcp-agent cloud workflows suspend run_abc123 # Resume a workflow (with optional payload) mcp-agent cloud workflows resume run_abc123 mcp-agent cloud workflows resume run_abc123 --payload '{"data": "value"}' # Cancel a workflow (with optional reason) mcp-agent cloud workflows cancel run_abc123 mcp-agent cloud workflows cancel run_abc123 --reason "User requested cancellation" ``` ### Why make this change? These commands provide essential workflow lifecycle management capabilities to users, allowing them to monitor and control workflow executions through the CLI. The ability to suspend, resume, and cancel workflows gives users more control over long-running operations and helps manage resources more efficiently. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - New Features - Introduced “workflows” CLI group with commands: describe (alias: status), resume, suspend, and cancel. - Describe supports text, JSON, and YAML output; all commands work with server ID or URL and include improved error messages. - Refactor - Renamed CLI group from “workflow” to “workflows” and reorganized command registrations. - Consolidated internal utility imports (no behavior change). - Chores - Updated module descriptions. - Removed legacy workflow status package/exports in favor of the new workflows commands. <!-- end of auto-generated comment: release notes by coderabbit.ai --> * add servers workflow subcommand (#428) # Add servers workflows subcommand This PR adds a new `workflows` subcommand to the `mcp-agent cloud servers` command that allows users to list workflows associated with a specific server. The command supports: - Filtering by workflow status - Limiting the number of results - Multiple output formats (text, JSON, YAML) - Accepting server IDs, app config IDs, or server URLs as input Examples: ``` mcp-agent cloud servers workflows app_abc123 mcp-agent cloud servers workflows https://server.example.com --status running mcp-agent cloud servers workflows apcnf_xyz789 --limit 10 --format json ``` The PR also cleans up the examples in the existing workflow commands and adds the necessary API client support for listing workflows. * add workflow list and runs (#430) ### TL;DR Reorganized workflow commands `mcp-agent cloud workflows runs` `mcp-agent cloud workflows list` `mcp-agent cloud server workflows` (alias of workflows list) ### What changed? - Moved `list_workflows_for_server` from the servers module to the workflows module as `list_workflow_runs` - Added new workflow commands: `list_workflows` and `list_workflow_runs` - Updated CLI command structure to make workflows commands more intuitive - Applied consistent code formatting with black across all server and workflow related files ### How to test? Test the new and reorganized workflow commands: ```bash # List available workflow definitions mcp-agent cloud workflows list app_abc123 # List workflow runs (previously under servers workflows) mcp-agent cloud workflows runs app_abc123 # Test with different output formats mcp-agent cloud workflows list app_abc123 --format json mcp-agent cloud workflows runs app_abc123 --format yaml # Verify existing commands still work mcp-agent cloud servers list mcp-agent cloud workflows describe app_abc123 run_xyz789 ``` * [ez] Move deploy command to cloud namespace (#431) ### TL;DR Added `cloud deploy` command as an alias for the existing `deploy` command. * First pass at implementing the mcp-agent CLI (#409) * Initial scaffolding * initial CLI * checkpoint * checkpoint 2 * various updates to cli * fix lint and format * fix: should load secrets.yaml template instead when running init cli command * fix: prevent None values in either mcp-agent secrets and config yaml files from overwriting one another when merging both * fix: when running config check, use get_settings() instead of Settings() to ensure settings are loaded. * fix: handle None values for servers in MCPSettings so it defaults to empty dict and update secrets.yaml template so it does not overwrite mcp servers in config * Inform users to save and close editor to continue when running config edit command * fix: Update openai, anthropic and azure regex for keys cli command * Sort model list by provider and model name * Add filtering support for models list cli command * disable untested commands * lint, format, gen_schema * get rid of accidental otlp exporter changes from another branch * get rid of accidental commit from other branch --------- Co-authored-by: StreetLamb <[email protected]> * Docs MVP (#436) * Initial scaffolding * initial CLI * checkpoint * checkpoint 2 * various updates to cli * fix lint and format * fix: should load secrets.yaml template instead when running init cli command * fix: prevent None values in either mcp-agent secrets and config yaml files from overwriting one another when merging both * fix: when running config check, use get_settings() instead of Settings() to ensure settings are loaded. * fix: handle None values for servers in MCPSettings so it defaults to empty dict and update secrets.yaml template so it does not overwrite mcp servers in config * Inform users to save and close editor to continue when running config edit command * fix: Update openai, anthropic and azure regex for keys cli command * Sort model list by provider and model name * Add filtering support for models list cli command * disable untested commands * Fixes to docs * Updating the main.py and !developer_secrets for secrets * updating python entry files to main.py * Fix tracer.py --------- Co-authored-by: StreetLamb <[email protected]> Co-authored-by: Andrew Hoh <[email protected]> * fix: max complete token for openai gen structured (#438) * Fix regression in CLI ("cloud cloud") * docs fixes * Fix top-level cli cloud commands (deploy, login, etc) * Add eager tool validation to ensure json serializability of input params/result types * More docs updates * Refactor workflow runs list to use MCP tool calls (#439) ### TL;DR Refactored the workflow runs listing command to use MCP tool calls instead of direct API client calls. ### What changed? - Replaced the direct API client approach with MCP tool calls to retrieve workflow runs - Added a new `_list_workflow_runs_async` function that uses the MCP App and gen_client to communicate with the server - Improved status filtering and display logic to work with both object and dictionary response formats - Enhanced error handling and formatting of workflow run information - Updated the workflow data processing to handle different response formats more robustly ### How to test? ```bash # List workflow runs from a server mcp-agent cloud workflows runs <server_id_or_url> # Filter by status mcp-agent cloud workflows runs <server_id_or_url> --status running # Limit results mcp-agent cloud workflows runs <server_id_or_url> --limit 10 # Change output format mcp-agent cloud workflows runs <server_id_or_url> --format json ``` <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - New Features - Add status filtering for workflow runs, with common aliases (e.g., timeout → timed_out). - Add an optional limit to constrain the number of results. - Allow server selection via direct URL or config-based server ID. - Refactor - Update text output: columns now show Workflow ID, Name, Status, Run ID, Created; Principal removed. - Improve date formatting and consistent JSON/YAML/Text rendering. - Bug Fixes - Clearer error messages and safer handling when server info is missing or no data is returned. <!-- end of auto-generated comment: release notes by coderabbit.ai --> * Update workflows commands UI to be more consistant with the rest of the CLI (#432) ### TL;DR Improved CLI workflow command output formatting with better visual indicators and consistent styling. ### How to test? ``` mcp-agent cloud workflows cancel <run-id> mcp-agent cloud workflows describe <run-id> mcp-agent cloud workflows resume <run-id> ``` <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Style** * Cancel workflow: added a blank line before the status and changed the success icon to 🚫 (yellow). * Describe workflow: replaced panel UI with a clean, header-based text layout (“🔍 Workflow Details”), showing name with colorized status and fields for Workflow ID, Run ID, and Created. Updated status indicators with emojis and colors; timestamp is now plain text on its own line. * Resume workflow: success message now applies consistent coloring to the entire line for improved readability. <!-- end of auto-generated comment: release notes by coderabbit.ai --> * Feature: Update Workflow Tool Calls to Work with workflow_id (#435) * Support for workflow_id and run_id * Update temporal workflow registry * tests * Update LLMS.txt * Fix config * Return bool for cancel result * Validate ids provided * Fix cancel workflow id * Fix workflows-resume response * Add workflow-name specific resume and cancel tools * Fix return type * Fix examples * Remove redundant workflows-{name}-tool tool calls * Add _workflow_status back * Use registry helper * Changes from review * Add back evaluator_optimizer enum fix * Fix a hang that can happen at shutdown (#440) * Fix a shutdown hang * Fix tests * fix taskgroup closed in a different context than when it was started in error * some PR feedback fixes * PR feedback * Fix random failures of server aggregator not found for agent in temporal (#441) * Fix a shutdown hang * Fix tests * fix taskgroup closed in a different context than when it was started in error * some PR feedback fixes * Fix random failures of server aggregator not found for agent in temporal environment * Bump pyproject version * Fix gateway URL resolution (#443) * Fix gateway URL resolution Removed incorrect dependence on ServerRegistry for gateway URLs; the gateway is not an MCP server. App server (src/mcp_agent/server/app_server.py) builds workflow memo with: - gateway_url precedence: X-MCP-Gateway-URL or X-Forwarded-Url → reconstruct X-Forwarded-Proto/Host/Prefix → request.base_url → MCP_GATEWAY_URL env. - gateway_token precedence: X-MCP-Gateway-Token → MCP_GATEWAY_TOKEN env. Worker-side (SystemActivities/SessionProxy) uses memo.gateway_url and gateway_token; falls back to worker env. Client proxy helpers (src/mcp_agent/mcp/client_proxy.py): - _resolve_gateway_url: explicit param → context → env → local default. - Updated public signatures to drop server_registry parameter. * Cloud/deployable temporal example (#395) * Move workflows to workflows.py file * Fix router example * Add remaining dependencies * Update orchestrator to @app.async_tool example * Changes from review * Fix interactive_workflow to be runnable via tool * Fix resume tool params * Fix: Use helpful typer and invoke for root cli commands (#444) * Use helpful typer and invoke for root cli commands * Fix lint * Fix enum check (#445) * Fix/swap relative mcp agent dependency on deploy (#446) * Update wrangler wrapper to handle requirements.txt processing * Fix backup handling * pass api key to workflow (#447) * pass api key to workflow * guard against settings not existing --------- Co-authored-by: John Corbett <[email protected]> Co-authored-by: Sarmad Qadri <[email protected]> Co-authored-by: StreetLamb <[email protected]> Co-authored-by: Yi <[email protected]> Co-authored-by: Ryan Holinshead <[email protected]> Co-authored-by: roman-van-der-krogt <[email protected]>
This was referenced Sep 12, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
TL;DR
Added workflow management commands to the MCP Agent CLI, including describe, suspend, resume, and cancel operations.
What changed?
describe_workflow: Shows detailed information about a workflow executionsuspend_workflow: Pauses a running workflow executionresume_workflow: Resumes a previously suspended workflowcancel_workflow: Permanently stops a workflow executionWorkflowAPIClient:suspend_workflowresume_workflowcancel_workflowmcp-agent cloud workflowsdescribe_workflowasstatusfor backward compatibilityHow to test?
Test the new workflow commands with a running workflow:
Why make this change?
These commands provide essential workflow lifecycle management capabilities to users, allowing them to monitor and control workflow executions through the CLI. The ability to suspend, resume, and cancel workflows gives users more control over long-running operations and helps manage resources more efficiently.
Summary by CodeRabbit
New Features
Refactor
Chores