Compare commits

..

9 Commits

Author SHA1 Message Date
Zamil Majdy
3d880cd591 refactor(backend/copilot): move imports to module level
- Move KEY_WORKFLOWS and TOOL_REGISTRY imports to top of file
- Better code organization following Python conventions
2026-03-06 23:15:39 +07:00
Zamil Majdy
73f5ff9983 test(backend/copilot): add tests for auto-generated tool documentation
- Test tool documentation structure (sections, format)
- Test that all TOOL_REGISTRY tools are included
- Test workflow sections are present
- Test no duplicate tools
- Verify markdown formatting compliance
- All 6 tests passing
2026-03-06 23:15:39 +07:00
Zamil Majdy
6d9faf5f91 refactor(backend/copilot): auto-generate tool docs in supplement, simplify default prompt
- Add _generate_tool_documentation() to auto-generate tool list from TOOL_REGISTRY
- Extract KEY_WORKFLOWS constant to prompt_constants.py for maintainability
- Append auto-generated tool docs + workflow guidance to system prompt supplement
- Simplify DEFAULT_SYSTEM_PROMPT to minimal tone/style baseline (Langfuse handles details)
- Add KEY WORKFLOWS section covering MCP integration, agent creation, folder management
- Ensures tool documentation stays in sync with actual implementations
- Fix Pyright error by safely accessing description field with .get()
2026-03-06 23:10:42 +07:00
Zamil Majdy
7774717104 docs(backend/copilot): document web_search and web_fetch in tool supplement
Add clear documentation for web_search and web_fetch to the shared tool notes
that get appended to all system prompts (Langfuse or default). This ensures
the copilot knows to use web_search for general web queries instead of
incorrectly using find_block to search for web search blocks.

- web_search: For current information beyond knowledge cutoff
- web_fetch: For retrieving content from specific URLs
2026-03-06 23:10:42 +07:00
Zamil Majdy
89ed628609 fix(backend/copilot): capture tool results in transcript
Tool results (StreamToolOutputAvailable) were being added to session.messages
but NOT to transcript_builder, causing the transcript to miss tool executions.
This made the copilot claim '(no tool used)' when tools were actually called.

Now tool results are captured as user messages with tool_result content blocks,
matching the Claude API transcript format and ensuring --resume has complete
conversation history including all tool interactions.
2026-03-06 23:10:42 +07:00
Zamil Majdy
d56452898a hotfix(backend/copilot): refactor transcript to SDK-based atomic full-context model (#12318)
## Summary

Major refactor to eliminate CLI transcript race conditions and simplify
the codebase by building transcripts directly from SDK messages instead
of reading CLI files.

## Problem

The previous approach had race conditions:
- SDK reads CLI transcript file during stop hook
- CLI may not have finished writing → incomplete transcript
- Complex merge logic to detect and fix incomplete writes
- ~200 lines of synthetic entry detection and merge code

## Solution

**Atomic Full-Context Transcript Model:**
- Build transcript from SDK messages during streaming
(`TranscriptBuilder`)
- Each upload REPLACES the previous transcript entirely (atomic)
- No CLI file reading → no race conditions
- Eliminates all merge complexity

## Key Changes

### Core Refactor
- **NEW**: `transcript_builder.py` - Build JSONL from SDK messages
during streaming
- **SIMPLIFIED**: `transcript.py` - Removed merge logic, simplified
upload/download
- **SIMPLIFIED**: `service.py` - Use TranscriptBuilder, removed stop
hook callback
- **CLEANED**: `security_hooks.py` - Removed `on_stop` parameter

### Performance & Code Quality
- **orjson migration**: Use `backend.util.json` (2-3x faster than
stdlib)
- Added `fallback` parameter to `json.loads()` for cleaner error
handling
- Moved SDK imports to top-level per code style guidelines

### Bug Fixes
- Fixed garbage collection bug in background task handling
- Fixed double upload bug in timeout handling  
- Downgraded PII-risk logging from WARNING to DEBUG
- Added 30s timeout to prevent session lock hang

## Code Removed (~200 lines)

- `merge_with_previous_transcript()` - No longer needed
- `read_transcript_file()` - No longer needed
- `CapturedTranscript` dataclass - No longer needed
- `_on_stop()` callback - No longer needed
- Synthetic entry detection logic - No longer needed
- Manual append/merge logic in finally block - No longer needed

## Testing

-  All transcript tests passing (24/24)
-  Verified with real session logs showing proper transcript growth
-  Verified with Langfuse traces showing proper turn tracking (1-8)

## Transcript Growth Pattern

From session logs:
- **Turn 1**: 2 entries (initial)
- **Turn 2**: 5 entries (+3), 2257B uploaded
- **Turn N**: ~2N entries (linear growth)

Each upload is the **complete atomic state** - always REPLACES, never
incremental.

## Files Changed

```
backend/copilot/sdk/transcript_builder.py (NEW)   | +140 lines
backend/copilot/sdk/transcript.py                  | -198, +125 lines  
backend/copilot/sdk/service.py                     | -214, +160 lines
backend/copilot/sdk/security_hooks.py              | -33, +10 lines
backend/copilot/sdk/transcript_test.py             | -85, +36 lines
backend/util/json.py                               | +45 lines
```

**Net result**: -200 lines, more reliable, faster JSON operations.

## Migration Notes

This is a **breaking change** for any code that:
- Directly calls `merge_with_previous_transcript()` or
`read_transcript_file()`
- Relies on incremental transcript uploads
- Expects stop hook callbacks

All internal usage has been updated.

---

@ntindle - Tagging for autogpt-reviewer
2026-03-06 21:03:49 +07:00
Otto
3e108a813a fix(backend): Use db_manager for workspace in add_graph_execution (#12312)
When `add_graph_execution` is called from a context where the global
Prisma client isn't connected (e.g. CoPilot tools, external API), the
call to `get_or_create_workspace(user_id)` crashes with
`ClientNotConnectedError` because it directly accesses
`UserWorkspace.prisma()`.

The fix adds `workspace_db` to the existing `if prisma.is_connected()`
fallback pattern, consistent with how all other DB calls in the function
already work.

**Sentry:** AUTOGPT-SERVER-83T (and ~15 related issues going back to Jan
2026)

---
Co-authored-by: Reinier van der Leer (@Pwuts) <pwuts@agpt.co>

Co-authored-by: Reinier van der Leer (@Pwuts) <pwuts@agpt.co>
2026-03-06 08:48:15 +01:00
Zamil Majdy
0b9e0665dd Merge branch 'dev' of github.com:Significant-Gravitas/AutoGPT 2026-03-06 02:32:36 +07:00
Zamil Majdy
f6f268a1f0 Merge branch 'dev' of github.com:Significant-Gravitas/AutoGPT into HEAD 2026-03-06 02:29:56 +07:00
39 changed files with 747 additions and 3788 deletions

View File

@@ -1,164 +0,0 @@
import logging
import autogpt_libs.auth
import fastapi
import backend.api.features.store.db as store_db
import backend.api.features.store.model as store_model
logger = logging.getLogger(__name__)
router = fastapi.APIRouter(
prefix="/admin/waitlist",
tags=["store", "admin", "waitlist"],
dependencies=[fastapi.Security(autogpt_libs.auth.requires_admin_user)],
)
@router.post(
"",
summary="Create Waitlist",
response_model=store_model.WaitlistAdminResponse,
)
async def create_waitlist(
request: store_model.WaitlistCreateRequest,
user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
):
"""
Create a new waitlist (admin only).
Args:
request: Waitlist creation details
user_id: Authenticated admin user creating the waitlist
Returns:
WaitlistAdminResponse with the created waitlist details
"""
return await store_db.create_waitlist_admin(
admin_user_id=user_id,
data=request,
)
@router.get(
"",
summary="List All Waitlists",
response_model=store_model.WaitlistAdminListResponse,
)
async def list_waitlists():
"""
Get all waitlists with admin details (admin only).
Returns:
WaitlistAdminListResponse with all waitlists
"""
return await store_db.get_waitlists_admin()
@router.get(
"/{waitlist_id}",
summary="Get Waitlist Details",
response_model=store_model.WaitlistAdminResponse,
)
async def get_waitlist(
waitlist_id: str = fastapi.Path(..., description="The ID of the waitlist"),
):
"""
Get a single waitlist with admin details (admin only).
Args:
waitlist_id: ID of the waitlist to retrieve
Returns:
WaitlistAdminResponse with waitlist details
"""
return await store_db.get_waitlist_admin(waitlist_id)
@router.put(
"/{waitlist_id}",
summary="Update Waitlist",
response_model=store_model.WaitlistAdminResponse,
)
async def update_waitlist(
request: store_model.WaitlistUpdateRequest,
waitlist_id: str = fastapi.Path(..., description="The ID of the waitlist"),
):
"""
Update a waitlist (admin only).
Args:
waitlist_id: ID of the waitlist to update
request: Fields to update
Returns:
WaitlistAdminResponse with updated waitlist details
"""
return await store_db.update_waitlist_admin(waitlist_id, request)
@router.delete(
"/{waitlist_id}",
summary="Delete Waitlist",
)
async def delete_waitlist(
waitlist_id: str = fastapi.Path(..., description="The ID of the waitlist"),
):
"""
Soft delete a waitlist (admin only).
Args:
waitlist_id: ID of the waitlist to delete
Returns:
Success message
"""
await store_db.delete_waitlist_admin(waitlist_id)
return {"message": "Waitlist deleted successfully"}
@router.get(
"/{waitlist_id}/signups",
summary="Get Waitlist Signups",
response_model=store_model.WaitlistSignupListResponse,
)
async def get_waitlist_signups(
waitlist_id: str = fastapi.Path(..., description="The ID of the waitlist"),
):
"""
Get all signups for a waitlist (admin only).
Args:
waitlist_id: ID of the waitlist
Returns:
WaitlistSignupListResponse with all signups
"""
return await store_db.get_waitlist_signups_admin(waitlist_id)
@router.post(
"/{waitlist_id}/link",
summary="Link Waitlist to Store Listing",
response_model=store_model.WaitlistAdminResponse,
)
async def link_waitlist_to_listing(
waitlist_id: str = fastapi.Path(..., description="The ID of the waitlist"),
store_listing_id: str = fastapi.Body(
..., embed=True, description="The ID of the store listing"
),
):
"""
Link a waitlist to a store listing (admin only).
When the linked store listing is approved/published, waitlist users
will be automatically notified.
Args:
waitlist_id: ID of the waitlist
store_listing_id: ID of the store listing to link
Returns:
WaitlistAdminResponse with updated waitlist details
"""
return await store_db.link_waitlist_to_listing_admin(waitlist_id, store_listing_id)

View File

@@ -22,7 +22,6 @@ from backend.data.notifications import (
AgentApprovalData,
AgentRejectionData,
NotificationEventModel,
WaitlistLaunchData,
)
from backend.notifications.notifications import queue_notification_async
from backend.util.exceptions import DatabaseError
@@ -1731,29 +1730,6 @@ async def review_store_submission(
# Don't fail the review process if email sending fails
pass
# Notify waitlist users if this is an approval and has a linked waitlist
if is_approved and submission.StoreListing:
try:
frontend_base_url = (
settings.config.frontend_base_url
or settings.config.platform_base_url
)
store_agent = (
await prisma.models.StoreAgent.prisma().find_first_or_raise(
where={"storeListingVersionId": submission.id}
)
)
creator_username = store_agent.creator_username or "unknown"
store_url = f"{frontend_base_url}/marketplace/agent/{creator_username}/{store_agent.slug}"
await notify_waitlist_users_on_launch(
store_listing_id=submission.StoreListing.id,
agent_name=submission.name,
store_url=store_url,
)
except Exception as e:
logger.error(f"Failed to notify waitlist users on agent approval: {e}")
# Don't fail the approval process
# Convert to Pydantic model for consistency
return store_model.StoreSubmission(
listing_id=(submission.StoreListing.id if submission.StoreListing else ""),
@@ -2001,557 +1977,3 @@ async def get_agent_as_admin(
)
return graph
def _waitlist_to_store_entry(
waitlist: prisma.models.WaitlistEntry,
) -> store_model.StoreWaitlistEntry:
"""Convert a WaitlistEntry to StoreWaitlistEntry for public display."""
return store_model.StoreWaitlistEntry(
waitlistId=waitlist.id,
slug=waitlist.slug,
name=waitlist.name,
subHeading=waitlist.subHeading,
videoUrl=waitlist.videoUrl,
agentOutputDemoUrl=waitlist.agentOutputDemoUrl,
imageUrls=waitlist.imageUrls or [],
description=waitlist.description,
categories=waitlist.categories or [],
)
async def get_waitlist() -> list[store_model.StoreWaitlistEntry]:
"""Get all active waitlists for public display."""
try:
waitlists = await prisma.models.WaitlistEntry.prisma().find_many(
where=prisma.types.WaitlistEntryWhereInput(isDeleted=False),
)
# Filter out closed/done waitlists and sort by votes (descending)
excluded_statuses = {
prisma.enums.WaitlistExternalStatus.CANCELED,
prisma.enums.WaitlistExternalStatus.DONE,
}
active_waitlists = [w for w in waitlists if w.status not in excluded_statuses]
sorted_list = sorted(active_waitlists, key=lambda x: x.votes, reverse=True)
return [_waitlist_to_store_entry(w) for w in sorted_list]
except Exception as e:
logger.error(f"Error fetching waitlists: {e}")
raise DatabaseError("Failed to fetch waitlists") from e
async def get_user_waitlist_memberships(user_id: str) -> list[str]:
"""Get all waitlist IDs that a user has joined."""
try:
user = await prisma.models.User.prisma().find_unique(
where={"id": user_id},
include={"JoinedWaitlists": True},
)
if not user or not user.JoinedWaitlists:
return []
return [w.id for w in user.JoinedWaitlists]
except Exception as e:
logger.error(f"Error fetching user waitlist memberships: {e}")
raise DatabaseError("Failed to fetch waitlist memberships") from e
async def add_user_to_waitlist(
waitlist_id: str, user_id: str | None, email: str | None
) -> store_model.StoreWaitlistEntry:
"""
Add a user to a waitlist.
For logged-in users: connects via joinedUsers relation
For anonymous users: adds email to unaffiliatedEmailUsers array
"""
if not user_id and not email:
raise ValueError("Either user_id or email must be provided")
try:
# Find the waitlist
waitlist = await prisma.models.WaitlistEntry.prisma().find_unique(
where={"id": waitlist_id},
include={"JoinedUsers": True},
)
if not waitlist:
raise ValueError(f"Waitlist {waitlist_id} not found")
if waitlist.isDeleted:
raise ValueError(f"Waitlist {waitlist_id} is no longer available")
if waitlist.status in [
prisma.enums.WaitlistExternalStatus.CANCELED,
prisma.enums.WaitlistExternalStatus.DONE,
]:
raise ValueError(f"Waitlist {waitlist_id} is closed")
if user_id:
# Check if user already joined
joined_user_ids = [u.id for u in (waitlist.JoinedUsers or [])]
if user_id in joined_user_ids:
# Already joined - return waitlist info
logger.debug(f"User {user_id} already joined waitlist {waitlist_id}")
else:
# Connect user to waitlist
await prisma.models.WaitlistEntry.prisma().update(
where={"id": waitlist_id},
data={"JoinedUsers": {"connect": [{"id": user_id}]}},
)
logger.info(f"User {user_id} joined waitlist {waitlist_id}")
# If user was previously in email list, remove them
# Use transaction to prevent race conditions
if email:
async with transaction() as tx:
current_waitlist = await tx.waitlistentry.find_unique(
where={"id": waitlist_id}
)
if current_waitlist and email in (
current_waitlist.unaffiliatedEmailUsers or []
):
updated_emails: list[str] = [
e
for e in (current_waitlist.unaffiliatedEmailUsers or [])
if e != email
]
await tx.waitlistentry.update(
where={"id": waitlist_id},
data={"unaffiliatedEmailUsers": updated_emails},
)
elif email:
# Add email to unaffiliated list if not already present
# Use transaction to prevent race conditions with concurrent signups
async with transaction() as tx:
# Re-fetch within transaction to get latest state
current_waitlist = await tx.waitlistentry.find_unique(
where={"id": waitlist_id}
)
if current_waitlist:
current_emails: list[str] = list(
current_waitlist.unaffiliatedEmailUsers or []
)
if email not in current_emails:
current_emails.append(email)
await tx.waitlistentry.update(
where={"id": waitlist_id},
data={"unaffiliatedEmailUsers": current_emails},
)
# Mask email for logging to avoid PII exposure
parts = email.split("@") if "@" in email else []
local = parts[0] if len(parts) > 0 else ""
domain = parts[1] if len(parts) > 1 else "unknown"
masked = (local[0] if local else "?") + "***@" + domain
logger.info(f"Email {masked} added to waitlist {waitlist_id}")
else:
logger.debug(f"Email already exists on waitlist {waitlist_id}")
# Re-fetch to return updated data
updated_waitlist = await prisma.models.WaitlistEntry.prisma().find_unique(
where={"id": waitlist_id}
)
return _waitlist_to_store_entry(updated_waitlist or waitlist)
except ValueError:
raise
except Exception as e:
logger.error(f"Error adding user to waitlist: {e}")
raise DatabaseError("Failed to add user to waitlist") from e
# ============== Admin Waitlist Functions ==============
def _waitlist_to_admin_response(
waitlist: prisma.models.WaitlistEntry,
) -> store_model.WaitlistAdminResponse:
"""Convert a WaitlistEntry to WaitlistAdminResponse."""
joined_count = len(waitlist.JoinedUsers) if waitlist.JoinedUsers else 0
email_count = (
len(waitlist.unaffiliatedEmailUsers) if waitlist.unaffiliatedEmailUsers else 0
)
return store_model.WaitlistAdminResponse(
id=waitlist.id,
createdAt=waitlist.createdAt.isoformat() if waitlist.createdAt else "",
updatedAt=waitlist.updatedAt.isoformat() if waitlist.updatedAt else "",
slug=waitlist.slug,
name=waitlist.name,
subHeading=waitlist.subHeading,
description=waitlist.description,
categories=waitlist.categories or [],
imageUrls=waitlist.imageUrls or [],
videoUrl=waitlist.videoUrl,
agentOutputDemoUrl=waitlist.agentOutputDemoUrl,
status=waitlist.status or prisma.enums.WaitlistExternalStatus.NOT_STARTED,
votes=waitlist.votes,
signupCount=joined_count + email_count,
storeListingId=waitlist.storeListingId,
owningUserId=waitlist.owningUserId,
)
async def create_waitlist_admin(
admin_user_id: str,
data: store_model.WaitlistCreateRequest,
) -> store_model.WaitlistAdminResponse:
"""Create a new waitlist (admin only)."""
logger.info(f"Admin {admin_user_id} creating waitlist: {data.name}")
try:
waitlist = await prisma.models.WaitlistEntry.prisma().create(
data=prisma.types.WaitlistEntryCreateInput(
name=data.name,
slug=data.slug,
subHeading=data.subHeading,
description=data.description,
categories=data.categories,
imageUrls=data.imageUrls,
videoUrl=data.videoUrl,
agentOutputDemoUrl=data.agentOutputDemoUrl,
owningUserId=admin_user_id,
status=prisma.enums.WaitlistExternalStatus.NOT_STARTED,
),
include={"JoinedUsers": True},
)
return _waitlist_to_admin_response(waitlist)
except Exception as e:
logger.error(f"Error creating waitlist: {e}")
raise DatabaseError("Failed to create waitlist") from e
async def get_waitlists_admin() -> store_model.WaitlistAdminListResponse:
"""Get all waitlists with admin details."""
try:
waitlists = await prisma.models.WaitlistEntry.prisma().find_many(
where=prisma.types.WaitlistEntryWhereInput(isDeleted=False),
include={"JoinedUsers": True},
order={"createdAt": "desc"},
)
return store_model.WaitlistAdminListResponse(
waitlists=[_waitlist_to_admin_response(w) for w in waitlists],
totalCount=len(waitlists),
)
except Exception as e:
logger.error(f"Error fetching waitlists for admin: {e}")
raise DatabaseError("Failed to fetch waitlists") from e
async def get_waitlist_admin(
waitlist_id: str,
) -> store_model.WaitlistAdminResponse:
"""Get a single waitlist with admin details."""
try:
waitlist = await prisma.models.WaitlistEntry.prisma().find_unique(
where={"id": waitlist_id},
include={"JoinedUsers": True},
)
if not waitlist:
raise ValueError(f"Waitlist {waitlist_id} not found")
if waitlist.isDeleted:
raise ValueError(f"Waitlist {waitlist_id} has been deleted")
return _waitlist_to_admin_response(waitlist)
except ValueError:
raise
except Exception as e:
logger.error(f"Error fetching waitlist {waitlist_id}: {e}")
raise DatabaseError("Failed to fetch waitlist") from e
async def update_waitlist_admin(
waitlist_id: str,
data: store_model.WaitlistUpdateRequest,
) -> store_model.WaitlistAdminResponse:
"""Update a waitlist (admin only)."""
logger.info(f"Updating waitlist {waitlist_id}")
try:
# Check if waitlist exists first
existing = await prisma.models.WaitlistEntry.prisma().find_unique(
where={"id": waitlist_id}
)
if not existing:
raise ValueError(f"Waitlist {waitlist_id} not found")
if existing.isDeleted:
raise ValueError(f"Waitlist {waitlist_id} has been deleted")
# Build update data from explicitly provided fields
# Use model_fields_set to allow clearing fields by setting them to None
field_mappings = {
"name": data.name,
"slug": data.slug,
"subHeading": data.subHeading,
"description": data.description,
"categories": data.categories,
"imageUrls": data.imageUrls,
"videoUrl": data.videoUrl,
"agentOutputDemoUrl": data.agentOutputDemoUrl,
"storeListingId": data.storeListingId,
}
update_data: dict[str, Any] = {
k: v for k, v in field_mappings.items() if k in data.model_fields_set
}
# Add status if provided (already validated as enum by Pydantic)
if "status" in data.model_fields_set and data.status is not None:
update_data["status"] = data.status
if not update_data:
# No updates, just return current data
return await get_waitlist_admin(waitlist_id)
waitlist = await prisma.models.WaitlistEntry.prisma().update(
where={"id": waitlist_id},
data=prisma.types.WaitlistEntryUpdateInput(**update_data),
include={"JoinedUsers": True},
)
# We already verified existence above, so this should never be None
assert waitlist is not None
return _waitlist_to_admin_response(waitlist)
except ValueError:
raise
except Exception as e:
logger.error(f"Error updating waitlist {waitlist_id}: {e}")
raise DatabaseError("Failed to update waitlist") from e
async def delete_waitlist_admin(waitlist_id: str) -> None:
"""Soft delete a waitlist (admin only)."""
logger.info(f"Soft deleting waitlist {waitlist_id}")
try:
# Check if waitlist exists first
waitlist = await prisma.models.WaitlistEntry.prisma().find_unique(
where={"id": waitlist_id},
)
if not waitlist:
raise ValueError(f"Waitlist {waitlist_id} not found")
if waitlist.isDeleted:
raise ValueError(f"Waitlist {waitlist_id} has already been deleted")
await prisma.models.WaitlistEntry.prisma().update(
where={"id": waitlist_id},
data={"isDeleted": True},
)
except ValueError:
raise
except Exception as e:
logger.error(f"Error deleting waitlist {waitlist_id}: {e}")
raise DatabaseError("Failed to delete waitlist") from e
async def get_waitlist_signups_admin(
waitlist_id: str,
) -> store_model.WaitlistSignupListResponse:
"""Get all signups for a waitlist (admin only)."""
try:
waitlist = await prisma.models.WaitlistEntry.prisma().find_unique(
where={"id": waitlist_id},
include={"JoinedUsers": True},
)
if not waitlist:
raise ValueError(f"Waitlist {waitlist_id} not found")
signups: list[store_model.WaitlistSignup] = []
# Add user signups
for user in waitlist.JoinedUsers or []:
signups.append(
store_model.WaitlistSignup(
type="user",
userId=user.id,
email=user.email,
username=user.name,
)
)
# Add email signups
for email in waitlist.unaffiliatedEmailUsers or []:
signups.append(
store_model.WaitlistSignup(
type="email",
email=email,
)
)
return store_model.WaitlistSignupListResponse(
waitlistId=waitlist_id,
signups=signups,
totalCount=len(signups),
)
except ValueError:
raise
except Exception as e:
logger.error(f"Error fetching signups for waitlist {waitlist_id}: {e}")
raise DatabaseError("Failed to fetch waitlist signups") from e
async def link_waitlist_to_listing_admin(
waitlist_id: str,
store_listing_id: str,
) -> store_model.WaitlistAdminResponse:
"""Link a waitlist to a store listing (admin only)."""
logger.info(f"Linking waitlist {waitlist_id} to listing {store_listing_id}")
try:
# Verify the waitlist exists
waitlist = await prisma.models.WaitlistEntry.prisma().find_unique(
where={"id": waitlist_id}
)
if not waitlist:
raise ValueError(f"Waitlist {waitlist_id} not found")
if waitlist.isDeleted:
raise ValueError(f"Waitlist {waitlist_id} has been deleted")
# Verify the store listing exists
listing = await prisma.models.StoreListing.prisma().find_unique(
where={"id": store_listing_id}
)
if not listing:
raise ValueError(f"Store listing {store_listing_id} not found")
updated_waitlist = await prisma.models.WaitlistEntry.prisma().update(
where={"id": waitlist_id},
data={"StoreListing": {"connect": {"id": store_listing_id}}},
include={"JoinedUsers": True},
)
# We already verified existence above, so this should never be None
assert updated_waitlist is not None
return _waitlist_to_admin_response(updated_waitlist)
except ValueError:
raise
except Exception as e:
logger.error(f"Error linking waitlist to listing: {e}")
raise DatabaseError("Failed to link waitlist to listing") from e
async def notify_waitlist_users_on_launch(
store_listing_id: str,
agent_name: str,
store_url: str,
) -> int:
"""
Notify all users on waitlists linked to a store listing when the agent is launched.
Args:
store_listing_id: The ID of the store listing that was approved
agent_name: The name of the approved agent
store_url: The URL to the agent's store page
Returns:
The number of notifications sent
"""
logger.info(f"Notifying waitlist users for store listing {store_listing_id}")
try:
# Find all active waitlists linked to this store listing
# Exclude DONE and CANCELED to prevent duplicate notifications on re-approval
waitlists = await prisma.models.WaitlistEntry.prisma().find_many(
where={
"storeListingId": store_listing_id,
"isDeleted": False,
"status": {
"not_in": [
prisma.enums.WaitlistExternalStatus.DONE,
prisma.enums.WaitlistExternalStatus.CANCELED,
]
},
},
include={"JoinedUsers": True},
)
if not waitlists:
logger.info(
f"No active waitlists found for store listing {store_listing_id}"
)
return 0
notification_count = 0
launched_at = datetime.now(tz=timezone.utc)
for waitlist in waitlists:
# Track notification results for this waitlist
users_to_notify = waitlist.JoinedUsers or []
failed_user_ids: list[str] = []
# Notify registered users
for user in users_to_notify:
try:
notification_data = WaitlistLaunchData(
agent_name=agent_name,
waitlist_name=waitlist.name,
store_url=store_url,
launched_at=launched_at,
)
notification_event = NotificationEventModel[WaitlistLaunchData](
user_id=user.id,
type=prisma.enums.NotificationType.WAITLIST_LAUNCH,
data=notification_data,
)
await queue_notification_async(notification_event)
notification_count += 1
except Exception as e:
logger.error(
f"Failed to send waitlist launch notification to user {user.id}: {e}"
)
failed_user_ids.append(user.id)
# Note: For unaffiliated email users, you would need to send emails directly
# since they don't have user IDs for the notification system.
# This could be done via a separate email service.
# For now, we log these for potential manual follow-up or future implementation.
has_pending_email_users = bool(waitlist.unaffiliatedEmailUsers)
if has_pending_email_users:
logger.info(
f"Waitlist {waitlist.id} has {len(waitlist.unaffiliatedEmailUsers)} "
f"unaffiliated email users that need email notifications"
)
# Only mark waitlist as DONE if all registered user notifications succeeded
# AND there are no unaffiliated email users still waiting for notifications
if not failed_user_ids and not has_pending_email_users:
await prisma.models.WaitlistEntry.prisma().update(
where={"id": waitlist.id},
data={"status": prisma.enums.WaitlistExternalStatus.DONE},
)
logger.info(f"Updated waitlist {waitlist.id} status to DONE")
elif failed_user_ids:
logger.warning(
f"Waitlist {waitlist.id} not marked as DONE due to "
f"{len(failed_user_ids)} failed notifications"
)
elif has_pending_email_users:
logger.warning(
f"Waitlist {waitlist.id} not marked as DONE due to "
f"{len(waitlist.unaffiliatedEmailUsers)} pending email-only users"
)
logger.info(
f"Sent {notification_count} waitlist launch notifications for store listing {store_listing_id}"
)
return notification_count
except Exception as e:
logger.error(
f"Error notifying waitlist users for store listing {store_listing_id}: {e}"
)
# Don't raise - we don't want to fail the approval process
return 0

View File

@@ -224,102 +224,6 @@ class ReviewSubmissionRequest(pydantic.BaseModel):
internal_comments: str | None = None # Private admin notes
class StoreWaitlistEntry(pydantic.BaseModel):
"""Public waitlist entry - no PII fields exposed."""
waitlistId: str
slug: str
# Content fields
name: str
subHeading: str
videoUrl: str | None = None
agentOutputDemoUrl: str | None = None
imageUrls: list[str]
description: str
categories: list[str]
class StoreWaitlistsAllResponse(pydantic.BaseModel):
listings: list[StoreWaitlistEntry]
# Admin Waitlist Models
class WaitlistCreateRequest(pydantic.BaseModel):
"""Request model for creating a new waitlist."""
name: str
slug: str
subHeading: str
description: str
categories: list[str] = []
imageUrls: list[str] = []
videoUrl: str | None = None
agentOutputDemoUrl: str | None = None
class WaitlistUpdateRequest(pydantic.BaseModel):
"""Request model for updating a waitlist."""
name: str | None = None
slug: str | None = None
subHeading: str | None = None
description: str | None = None
categories: list[str] | None = None
imageUrls: list[str] | None = None
videoUrl: str | None = None
agentOutputDemoUrl: str | None = None
status: prisma.enums.WaitlistExternalStatus | None = None
storeListingId: str | None = None # Link to a store listing
class WaitlistAdminResponse(pydantic.BaseModel):
"""Admin response model with full waitlist details including internal data."""
id: str
createdAt: str
updatedAt: str
slug: str
name: str
subHeading: str
description: str
categories: list[str]
imageUrls: list[str]
videoUrl: str | None = None
agentOutputDemoUrl: str | None = None
status: prisma.enums.WaitlistExternalStatus
votes: int
signupCount: int # Total count of joinedUsers + unaffiliatedEmailUsers
storeListingId: str | None = None
owningUserId: str
class WaitlistSignup(pydantic.BaseModel):
"""Individual signup entry for a waitlist."""
type: str # "user" or "email"
userId: str | None = None
email: str | None = None
username: str | None = None # For user signups
class WaitlistSignupListResponse(pydantic.BaseModel):
"""Response model for listing waitlist signups."""
waitlistId: str
signups: list[WaitlistSignup]
totalCount: int
class WaitlistAdminListResponse(pydantic.BaseModel):
"""Response model for listing all waitlists (admin view)."""
waitlists: list[WaitlistAdminResponse]
totalCount: int
class UnifiedSearchResult(pydantic.BaseModel):
"""A single result from unified hybrid search across all content types."""

View File

@@ -8,8 +8,6 @@ import autogpt_libs.auth
import fastapi
import fastapi.responses
import prisma.enums
import pydantic
from autogpt_libs.auth.dependencies import get_optional_user_id
import backend.data.graph
import backend.util.json
@@ -83,74 +81,6 @@ async def update_or_create_profile(
return updated_profile
##############################################
############## Waitlist Endpoints ############
##############################################
@router.get(
"/waitlist",
summary="Get the agent waitlist",
tags=["store", "public"],
response_model=store_model.StoreWaitlistsAllResponse,
)
async def get_waitlist():
"""
Get all active waitlists for public display.
"""
waitlists = await store_db.get_waitlist()
return store_model.StoreWaitlistsAllResponse(listings=waitlists)
@router.get(
"/waitlist/my-memberships",
summary="Get waitlist IDs the current user has joined",
tags=["store", "private"],
)
async def get_my_waitlist_memberships(
user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
) -> list[str]:
"""Returns list of waitlist IDs the authenticated user has joined."""
return await store_db.get_user_waitlist_memberships(user_id)
@router.post(
path="/waitlist/{waitlist_id}/join",
summary="Add self to the agent waitlist",
tags=["store", "public"],
response_model=store_model.StoreWaitlistEntry,
)
async def add_self_to_waitlist(
user_id: str | None = fastapi.Security(get_optional_user_id),
waitlist_id: str = fastapi.Path(..., description="The ID of the waitlist to join"),
email: pydantic.EmailStr | None = fastapi.Body(
default=None, embed=True, description="Email address for unauthenticated users"
),
):
"""
Add the current user to the agent waitlist.
"""
if not user_id and not email:
raise fastapi.HTTPException(
status_code=400,
detail="Either user authentication or email address is required",
)
try:
waitlist_entry = await store_db.add_user_to_waitlist(
waitlist_id=waitlist_id, user_id=user_id, email=email
)
return waitlist_entry
except ValueError as e:
error_msg = str(e)
if "not found" in error_msg:
raise fastapi.HTTPException(status_code=404, detail="Waitlist not found")
# Waitlist exists but is closed or unavailable
raise fastapi.HTTPException(status_code=400, detail=error_msg)
except Exception:
raise fastapi.HTTPException(
status_code=500, detail="An error occurred while joining the waitlist"
)
##############################################
############### Agent Endpoints ##############
##############################################

View File

@@ -19,7 +19,6 @@ from prisma.errors import PrismaError
import backend.api.features.admin.credit_admin_routes
import backend.api.features.admin.execution_analytics_routes
import backend.api.features.admin.store_admin_routes
import backend.api.features.admin.waitlist_admin_routes
import backend.api.features.builder
import backend.api.features.builder.routes
import backend.api.features.chat.routes as chat_routes
@@ -300,11 +299,6 @@ app.include_router(
tags=["v2", "admin"],
prefix="/api/store",
)
app.include_router(
backend.api.features.admin.waitlist_admin_routes.router,
tags=["v2", "admin"],
prefix="/api/store",
)
app.include_router(
backend.api.features.admin.credit_admin_routes.router,
tags=["v2", "admin"],

View File

@@ -116,7 +116,6 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"
CLAUDE_4_5_HAIKU = "claude-haiku-4-5-20251001"
CLAUDE_4_6_OPUS = "claude-opus-4-6"
CLAUDE_4_6_SONNET = "claude-sonnet-4-6"
CLAUDE_3_HAIKU = "claude-3-haiku-20240307"
# AI/ML API models
AIML_API_QWEN2_5_72B = "Qwen/Qwen2.5-72B-Instruct-Turbo"
@@ -275,9 +274,6 @@ MODEL_METADATA = {
LlmModel.CLAUDE_4_6_OPUS: ModelMetadata(
"anthropic", 200000, 128000, "Claude Opus 4.6", "Anthropic", "Anthropic", 3
), # claude-opus-4-6
LlmModel.CLAUDE_4_6_SONNET: ModelMetadata(
"anthropic", 200000, 64000, "Claude Sonnet 4.6", "Anthropic", "Anthropic", 3
), # claude-sonnet-4-6
LlmModel.CLAUDE_4_5_OPUS: ModelMetadata(
"anthropic", 200000, 64000, "Claude Opus 4.5", "Anthropic", "Anthropic", 3
), # claude-opus-4-5-20251101

View File

@@ -83,8 +83,7 @@ class StagehandRecommendedLlmModel(str, Enum):
GPT41_MINI = "gpt-4.1-mini-2025-04-14"
# Anthropic
CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929" # Keep for backwards compat
CLAUDE_4_6_SONNET = "claude-sonnet-4-6"
CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"
@property
def provider_name(self) -> str:
@@ -138,7 +137,7 @@ class StagehandObserveBlock(Block):
model: StagehandRecommendedLlmModel = SchemaField(
title="LLM Model",
description="LLM to use for Stagehand (provider is inferred)",
default=StagehandRecommendedLlmModel.CLAUDE_4_6_SONNET,
default=StagehandRecommendedLlmModel.CLAUDE_4_5_SONNET,
advanced=False,
)
model_credentials: AICredentials = AICredentialsField()
@@ -228,7 +227,7 @@ class StagehandActBlock(Block):
model: StagehandRecommendedLlmModel = SchemaField(
title="LLM Model",
description="LLM to use for Stagehand (provider is inferred)",
default=StagehandRecommendedLlmModel.CLAUDE_4_6_SONNET,
default=StagehandRecommendedLlmModel.CLAUDE_4_5_SONNET,
advanced=False,
)
model_credentials: AICredentials = AICredentialsField()
@@ -325,7 +324,7 @@ class StagehandExtractBlock(Block):
model: StagehandRecommendedLlmModel = SchemaField(
title="LLM Model",
description="LLM to use for Stagehand (provider is inferred)",
default=StagehandRecommendedLlmModel.CLAUDE_4_6_SONNET,
default=StagehandRecommendedLlmModel.CLAUDE_4_5_SONNET,
advanced=False,
)
model_credentials: AICredentials = AICredentialsField()

View File

@@ -0,0 +1,29 @@
"""Prompt constants for CoPilot - workflow guidance and supplementary documentation.
This module contains workflow patterns and guidance that supplement the main system prompt.
These are appended dynamically to the prompt along with auto-generated tool documentation.
"""
# Workflow guidance for key tool patterns
# This is appended after the auto-generated tool list to provide usage patterns
KEY_WORKFLOWS = """
## KEY WORKFLOWS
### MCP Integration Workflow
When using `run_mcp_tool`:
1. **Known servers** (use directly): Notion (https://mcp.notion.com/mcp), Linear (https://mcp.linear.app/mcp), Stripe (https://mcp.stripe.com), Intercom (https://mcp.intercom.com/mcp), Cloudflare (https://mcp.cloudflare.com/mcp), Atlassian (https://mcp.atlassian.com/mcp)
2. **Unknown servers**: Use `web_search("{{service}} MCP server URL")` to find the endpoint
3. **Discovery**: Call `run_mcp_tool(server_url)` to see available tools
4. **Execution**: Call `run_mcp_tool(server_url, tool_name, tool_arguments)`
5. **Authentication**: If credentials needed, user will be prompted. When they confirm, retry immediately with same arguments.
### Agent Creation Workflow
When using `create_agent`:
1. Always check `find_library_agent` first for existing solutions
2. Call `create_agent` with description
3. **If `suggested_goal` returned**: Present to user, ask for confirmation, call again with suggested goal if accepted
4. **If `clarifying_questions` returned**: After user answers, call again with original description AND answers in `context` parameter
### Folder Management
Use folder tools (`create_folder`, `list_folders`, `move_agents_to_folder`) to organize agents in the user's library for better discoverability."""

View File

@@ -127,7 +127,6 @@ def create_security_hooks(
sdk_cwd: str | None = None,
max_subtasks: int = 3,
on_compact: Callable[[], None] | None = None,
on_stop: Callable[[str, str], None] | None = None,
) -> dict[str, Any]:
"""Create the security hooks configuration for Claude Agent SDK.
@@ -136,15 +135,12 @@ def create_security_hooks(
- PostToolUse: Log successful tool executions
- PostToolUseFailure: Log and handle failed tool executions
- PreCompact: Log context compaction events (SDK handles compaction automatically)
- Stop: Capture transcript path for stateless resume (when *on_stop* is provided)
Args:
user_id: Current user ID for isolation validation
sdk_cwd: SDK working directory for workspace-scoped tool validation
max_subtasks: Maximum concurrent Task (sub-agent) spawns allowed per session
on_stop: Callback ``(transcript_path, sdk_session_id)`` invoked when
the SDK finishes processing — used to read the JSONL transcript
before the CLI process exits.
on_compact: Callback invoked when SDK starts compacting context.
Returns:
Hooks configuration dict for ClaudeAgentOptions
@@ -311,30 +307,6 @@ def create_security_hooks(
on_compact()
return cast(SyncHookJSONOutput, {})
# --- Stop hook: capture transcript path for stateless resume ---
async def stop_hook(
input_data: HookInput,
tool_use_id: str | None,
context: HookContext,
) -> SyncHookJSONOutput:
"""Capture transcript path when SDK finishes processing.
The Stop hook fires while the CLI process is still alive, giving us
a reliable window to read the JSONL transcript before SIGTERM.
"""
_ = context, tool_use_id
transcript_path = cast(str, input_data.get("transcript_path", ""))
sdk_session_id = cast(str, input_data.get("session_id", ""))
if transcript_path and on_stop:
logger.info(
f"[SDK] Stop hook: transcript_path={transcript_path}, "
f"sdk_session_id={sdk_session_id[:12]}..."
)
on_stop(transcript_path, sdk_session_id)
return cast(SyncHookJSONOutput, {})
hooks: dict[str, Any] = {
"PreToolUse": [HookMatcher(matcher="*", hooks=[pre_tool_use_hook])],
"PostToolUse": [HookMatcher(matcher="*", hooks=[post_tool_use_hook])],
@@ -344,9 +316,6 @@ def create_security_hooks(
"PreCompact": [HookMatcher(matcher="*", hooks=[pre_compact_hook])],
}
if on_stop is not None:
hooks["Stop"] = [HookMatcher(matcher=None, hooks=[stop_hook])]
return hooks
except ImportError:
# Fallback for when SDK isn't available - return empty hooks

View File

@@ -12,7 +12,6 @@ import subprocess
import sys
import uuid
from collections.abc import AsyncGenerator
from dataclasses import dataclass
from typing import Any, cast
import openai
@@ -21,6 +20,9 @@ from claude_agent_sdk import (
ClaudeAgentOptions,
ClaudeSDKClient,
ResultMessage,
TextBlock,
ThinkingBlock,
ToolResultBlock,
ToolUseBlock,
)
from langfuse import propagate_attributes
@@ -42,6 +44,7 @@ from ..model import (
update_session_title,
upsert_chat_session,
)
from ..prompt_constants import KEY_WORKFLOWS
from ..response_model import (
StreamBaseResponse,
StreamError,
@@ -57,6 +60,7 @@ from ..service import (
_generate_session_title,
_is_langfuse_configured,
)
from ..tools import TOOL_REGISTRY
from ..tools.e2b_sandbox import get_or_create_sandbox
from ..tools.sandbox import WORKSPACE_PREFIX, make_session_path
from ..tools.workspace_files import get_manager
@@ -74,11 +78,11 @@ from .tool_adapter import (
from .transcript import (
cleanup_cli_project_dir,
download_transcript,
read_transcript_file,
upload_transcript,
validate_transcript,
write_transcript_to_tempfile,
)
from .transcript_builder import TranscriptBuilder
logger = logging.getLogger(__name__)
config = ChatConfig()
@@ -137,19 +141,6 @@ _setup_langfuse_otel()
_background_tasks: set[asyncio.Task[Any]] = set()
@dataclass
class CapturedTranscript:
"""Info captured by the SDK Stop hook for stateless --resume."""
path: str = ""
sdk_session_id: str = ""
raw_content: str = ""
@property
def available(self) -> bool:
return bool(self.path)
_SDK_CWD_PREFIX = WORKSPACE_PREFIX
# Heartbeat interval — keep SSE alive through proxies/LBs during tool execution.
@@ -160,8 +151,37 @@ _HEARTBEAT_INTERVAL = 10.0 # seconds
# Appended to the system prompt to inform the agent about available tools.
# The SDK built-in Bash is NOT available — use mcp__copilot__bash_exec instead,
# which has kernel-level network isolation (unshare --net).
def _generate_tool_documentation() -> str:
"""Auto-generate tool documentation from TOOL_REGISTRY.
This generates a complete list of available tools with their descriptions,
ensuring the documentation stays in sync with the actual tool implementations.
"""
docs = "\n## AVAILABLE TOOLS\n\n"
# Sort tools alphabetically for consistent output
for name in sorted(TOOL_REGISTRY.keys()):
tool = TOOL_REGISTRY[name]
schema = tool.as_openai_tool()
desc = schema["function"].get("description", "No description available")
# Format as bullet list with tool name in code style
docs += f"- **`{name}`**: {desc}\n"
# Add workflow guidance for key tools
docs += KEY_WORKFLOWS
return docs
_SHARED_TOOL_NOTES = """\
### Web search and research
- **`web_search(query)`** — Search the web for current information (uses Claude's
native web search). Use this when you need up-to-date information, facts,
statistics, or current events that are beyond your knowledge cutoff.
- **`web_fetch(url)`** — Retrieve and analyze content from a specific URL.
Use this when you have a specific URL to read (documentation, articles, etc.).
### 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
@@ -451,6 +471,49 @@ def _cleanup_sdk_tool_results(cwd: str) -> None:
pass
def _format_sdk_content_blocks(blocks: list) -> list[dict[str, Any]]:
"""Convert SDK content blocks to transcript format.
Handles TextBlock, ToolUseBlock, ToolResultBlock, and ThinkingBlock.
Unknown block types are logged and skipped.
"""
result: list[dict[str, Any]] = []
for block in blocks or []:
if isinstance(block, TextBlock):
result.append({"type": "text", "text": block.text})
elif isinstance(block, ToolUseBlock):
result.append(
{
"type": "tool_use",
"id": block.id,
"name": block.name,
"input": block.input,
}
)
elif isinstance(block, ToolResultBlock):
result.append(
{
"type": "tool_result",
"tool_use_id": block.tool_use_id,
"content": block.content,
}
)
elif isinstance(block, ThinkingBlock):
result.append(
{
"type": "thinking",
"thinking": block.thinking,
"signature": block.signature,
}
)
else:
logger.warning(
f"[SDK] Unknown content block type: {type(block).__name__}. "
f"This may indicate a new SDK version with additional block types."
)
return result
async def _compress_messages(
messages: list[ChatMessage],
) -> tuple[list[ChatMessage], bool]:
@@ -806,6 +869,11 @@ async def stream_chat_completion_sdk(
user_id=user_id, session_id=session_id, message_length=len(message)
)
# Structured log prefix: [SDK][<session>][T<turn>]
# Turn = number of user messages (1-based), computed AFTER appending the new message.
turn = sum(1 for m in session.messages if m.role == "user")
log_prefix = f"[SDK][{session_id[:12]}][T{turn}]"
session = await upsert_chat_session(session)
# Generate title for new sessions (first user message)
@@ -823,10 +891,11 @@ async def stream_chat_completion_sdk(
message_id = str(uuid.uuid4())
stream_id = str(uuid.uuid4())
stream_completed = False
ended_with_stream_error = False
e2b_sandbox = None
use_resume = False
resume_file: str | None = None
captured_transcript = CapturedTranscript()
transcript_builder = TranscriptBuilder()
sdk_cwd = ""
# Acquire stream lock to prevent concurrent streams to the same session
@@ -841,7 +910,7 @@ async def stream_chat_completion_sdk(
if lock_owner != stream_id:
# Another stream is active
logger.warning(
f"[SDK] Session {session_id} already has an active stream: {lock_owner}"
f"{log_prefix} Session already has an active stream: {lock_owner}"
)
yield StreamError(
errorText="Another stream is already active for this session. "
@@ -865,7 +934,7 @@ async def stream_chat_completion_sdk(
sdk_cwd = _make_sdk_cwd(session_id)
os.makedirs(sdk_cwd, exist_ok=True)
except (ValueError, OSError) as e:
logger.error("[SDK] [%s] Invalid SDK cwd: %s", session_id[:12], e)
logger.error("%s Invalid SDK cwd: %s", log_prefix, e)
yield StreamError(
errorText="Unable to initialize working directory.",
code="sdk_cwd_error",
@@ -909,12 +978,13 @@ async def stream_chat_completion_sdk(
):
return None
try:
return await download_transcript(user_id, session_id)
return await download_transcript(
user_id, session_id, log_prefix=log_prefix
)
except Exception as transcript_err:
logger.warning(
"[SDK] [%s] Transcript download failed, continuing without "
"--resume: %s",
session_id[:12],
"%s Transcript download failed, continuing without " "--resume: %s",
log_prefix,
transcript_err,
)
return None
@@ -926,21 +996,34 @@ async def stream_chat_completion_sdk(
)
use_e2b = e2b_sandbox is not None
system_prompt = base_system_prompt + (
_E2B_TOOL_SUPPLEMENT
if use_e2b
else _LOCAL_TOOL_SUPPLEMENT.format(cwd=sdk_cwd)
# Generate tool documentation and append appropriate supplement
tool_docs = _generate_tool_documentation()
system_prompt = (
base_system_prompt
+ tool_docs
+ (
_E2B_TOOL_SUPPLEMENT
if use_e2b
else _LOCAL_TOOL_SUPPLEMENT.format(cwd=sdk_cwd)
)
)
# Process transcript download result
transcript_msg_count = 0
if dl:
is_valid = validate_transcript(dl.content)
dl_lines = dl.content.strip().split("\n") if dl.content else []
logger.info(
"%s Downloaded transcript: %dB, %d lines, " "msg_count=%d, valid=%s",
log_prefix,
len(dl.content),
len(dl_lines),
dl.message_count,
is_valid,
)
if is_valid:
logger.info(
f"[SDK] Transcript available for session {session_id}: "
f"{len(dl.content)}B, msg_count={dl.message_count}"
)
# Load previous FULL context into builder
transcript_builder.load_previous(dl.content, log_prefix=log_prefix)
resume_file = write_transcript_to_tempfile(
dl.content, session_id, sdk_cwd
)
@@ -948,16 +1031,14 @@ async def stream_chat_completion_sdk(
use_resume = True
transcript_msg_count = dl.message_count
logger.debug(
f"[SDK] Using --resume ({len(dl.content)}B, "
f"{log_prefix} Using --resume ({len(dl.content)}B, "
f"msg_count={transcript_msg_count})"
)
else:
logger.warning(
f"[SDK] Transcript downloaded but invalid for {session_id}"
)
logger.warning(f"{log_prefix} Transcript downloaded but invalid")
elif config.claude_agent_use_resume and user_id and len(session.messages) > 1:
logger.warning(
f"[SDK] No transcript available for {session_id} "
f"{log_prefix} No transcript available "
f"({len(session.messages)} messages in session)"
)
@@ -979,25 +1060,6 @@ async def stream_chat_completion_sdk(
sdk_model = _resolve_sdk_model()
# --- Transcript capture via Stop hook ---
# Read the file content immediately — the SDK may clean up
# the file before our finally block runs.
def _on_stop(transcript_path: str, sdk_session_id: str) -> None:
captured_transcript.path = transcript_path
captured_transcript.sdk_session_id = sdk_session_id
content = read_transcript_file(transcript_path)
if content:
captured_transcript.raw_content = content
logger.info(
f"[SDK] Stop hook: captured {len(content)}B from "
f"{transcript_path}"
)
else:
logger.warning(
f"[SDK] Stop hook: transcript file empty/missing at "
f"{transcript_path}"
)
# Track SDK-internal compaction (PreCompact hook → start, next msg → end)
compaction = CompactionTracker()
@@ -1005,7 +1067,6 @@ async def stream_chat_completion_sdk(
user_id,
sdk_cwd=sdk_cwd,
max_subtasks=config.claude_agent_max_subtasks,
on_stop=_on_stop if config.claude_agent_use_resume else None,
on_compact=compaction.on_compact,
)
@@ -1040,7 +1101,10 @@ async def stream_chat_completion_sdk(
session_id=session_id,
trace_name="copilot-sdk",
tags=["sdk"],
metadata={"resume": str(use_resume)},
metadata={
"resume": str(use_resume),
"conversation_turn": str(turn),
},
)
_otel_ctx.__enter__()
@@ -1074,9 +1138,9 @@ async def stream_chat_completion_sdk(
query_message = f"{query_message}\n\n{attachments.hint}"
logger.info(
"[SDK] [%s] Sending query — resume=%s, total_msgs=%d, "
"%s Sending query — resume=%s, total_msgs=%d, "
"query_len=%d, attached_files=%d, image_blocks=%d",
session_id[:12],
log_prefix,
use_resume,
len(session.messages),
len(query_message),
@@ -1105,8 +1169,13 @@ async def stream_chat_completion_sdk(
await client._transport.write( # noqa: SLF001
json.dumps(user_msg) + "\n"
)
# Capture user message in transcript (multimodal)
transcript_builder.add_user_message(content=content_blocks)
else:
await client.query(query_message, session_id=session_id)
# Capture actual user message in transcript (not the engineered query)
# query_message may include context wrappers, but transcript needs raw input
transcript_builder.add_user_message(content=current_message)
assistant_response = ChatMessage(role="assistant", content="")
accumulated_tool_calls: list[dict[str, Any]] = []
@@ -1150,8 +1219,8 @@ async def stream_chat_completion_sdk(
sdk_msg = done.pop().result()
except StopAsyncIteration:
logger.info(
"[SDK] [%s] Stream ended normally (StopAsyncIteration)",
session_id[:12],
"%s Stream ended normally (StopAsyncIteration)",
log_prefix,
)
break
except Exception as stream_err:
@@ -1160,8 +1229,8 @@ async def stream_chat_completion_sdk(
# so the session can still be saved and the
# frontend gets a clean finish.
logger.error(
"[SDK] [%s] Stream error from SDK: %s",
session_id[:12],
"%s Stream error from SDK: %s",
log_prefix,
stream_err,
exc_info=True,
)
@@ -1173,9 +1242,9 @@ async def stream_chat_completion_sdk(
break
logger.info(
"[SDK] [%s] Received: %s %s "
"%s Received: %s %s "
"(unresolved=%d, current=%d, resolved=%d)",
session_id[:12],
log_prefix,
type(sdk_msg).__name__,
getattr(sdk_msg, "subtype", ""),
len(adapter.current_tool_calls)
@@ -1184,6 +1253,15 @@ async def stream_chat_completion_sdk(
len(adapter.resolved_tool_calls),
)
# Capture SDK messages in transcript
if isinstance(sdk_msg, AssistantMessage):
content_blocks = _format_sdk_content_blocks(sdk_msg.content)
model_name = getattr(sdk_msg, "model", "")
transcript_builder.add_assistant_message(
content_blocks=content_blocks,
model=model_name,
)
# Race-condition fix: SDK hooks (PostToolUse) are
# executed asynchronously via start_soon() — the next
# message can arrive before the hook stashes output.
@@ -1210,10 +1288,10 @@ async def stream_chat_completion_sdk(
await asyncio.sleep(0)
else:
logger.warning(
"[SDK] [%s] Timed out waiting for "
"%s Timed out waiting for "
"PostToolUse hook stash "
"(%d unresolved tool calls)",
session_id[:12],
log_prefix,
len(adapter.current_tool_calls)
- len(adapter.resolved_tool_calls),
)
@@ -1221,9 +1299,9 @@ async def stream_chat_completion_sdk(
# Log ResultMessage details for debugging
if isinstance(sdk_msg, ResultMessage):
logger.info(
"[SDK] [%s] Received: ResultMessage %s "
"%s Received: ResultMessage %s "
"(unresolved=%d, current=%d, resolved=%d)",
session_id[:12],
log_prefix,
sdk_msg.subtype,
len(adapter.current_tool_calls)
- len(adapter.resolved_tool_calls),
@@ -1232,8 +1310,8 @@ async def stream_chat_completion_sdk(
)
if sdk_msg.subtype in ("error", "error_during_execution"):
logger.error(
"[SDK] [%s] SDK execution failed with error: %s",
session_id[:12],
"%s SDK execution failed with error: %s",
log_prefix,
sdk_msg.result or "(no error message provided)",
)
@@ -1258,8 +1336,8 @@ async def stream_chat_completion_sdk(
out_len = len(str(response.output))
extra = f", output_len={out_len}"
logger.info(
"[SDK] [%s] Tool event: %s, tool=%s%s",
session_id[:12],
"%s Tool event: %s, tool=%s%s",
log_prefix,
type(response).__name__,
getattr(response, "toolName", "N/A"),
extra,
@@ -1268,8 +1346,8 @@ async def stream_chat_completion_sdk(
# Log errors being sent to frontend
if isinstance(response, StreamError):
logger.error(
"[SDK] [%s] Sending error to frontend: %s (code=%s)",
session_id[:12],
"%s Sending error to frontend: %s (code=%s)",
log_prefix,
response.errorText,
response.code,
)
@@ -1314,17 +1392,28 @@ async def stream_chat_completion_sdk(
has_appended_assistant = True
elif isinstance(response, StreamToolOutputAvailable):
tool_result_content = (
response.output
if isinstance(response.output, str)
else str(response.output)
)
session.messages.append(
ChatMessage(
role="tool",
content=(
response.output
if isinstance(response.output, str)
else str(response.output)
),
content=tool_result_content,
tool_call_id=response.toolCallId,
)
)
# Capture tool result in transcript as user message with tool_result content
transcript_builder.add_user_message(
content=[
{
"type": "tool_result",
"tool_use_id": response.toolCallId,
"content": tool_result_content,
}
]
)
has_tool_results = True
elif isinstance(response, StreamFinish):
@@ -1335,8 +1424,8 @@ async def stream_chat_completion_sdk(
# server shutdown). Log and let the safety-net / finally
# blocks handle cleanup.
logger.warning(
"[SDK] [%s] Streaming loop cancelled (asyncio.CancelledError)",
session_id[:12],
"%s Streaming loop cancelled (asyncio.CancelledError)",
log_prefix,
)
raise
finally:
@@ -1350,7 +1439,8 @@ async def stream_chat_completion_sdk(
except (asyncio.CancelledError, StopAsyncIteration):
# Expected: task was cancelled or exhausted during cleanup
logger.info(
"[SDK] Pending __anext__ task completed during cleanup"
"%s Pending __anext__ task completed during cleanup",
log_prefix,
)
# Safety net: if tools are still unresolved after the
@@ -1359,9 +1449,9 @@ async def stream_chat_completion_sdk(
# them now so the frontend stops showing spinners.
if adapter.has_unresolved_tool_calls:
logger.warning(
"[SDK] [%s] %d unresolved tool(s) after stream loop — "
"%s %d unresolved tool(s) after stream loop — "
"flushing as safety net",
session_id[:12],
log_prefix,
len(adapter.current_tool_calls) - len(adapter.resolved_tool_calls),
)
safety_responses: list[StreamBaseResponse] = []
@@ -1372,8 +1462,8 @@ async def stream_chat_completion_sdk(
(StreamToolInputAvailable, StreamToolOutputAvailable),
):
logger.info(
"[SDK] [%s] Safety flush: %s, tool=%s",
session_id[:12],
"%s Safety flush: %s, tool=%s",
log_prefix,
type(response).__name__,
getattr(response, "toolName", "N/A"),
)
@@ -1386,8 +1476,8 @@ async def stream_chat_completion_sdk(
# StreamFinish is published by mark_session_completed in the processor.
if not stream_completed and not ended_with_stream_error:
logger.info(
"[SDK] [%s] Stream ended without ResultMessage (stopped by user)",
session_id[:12],
"%s Stream ended without ResultMessage (stopped by user)",
log_prefix,
)
closing_responses: list[StreamBaseResponse] = []
adapter._end_text_if_open(closing_responses)
@@ -1408,69 +1498,36 @@ async def stream_chat_completion_sdk(
) and not has_appended_assistant:
session.messages.append(assistant_response)
# --- Upload transcript for next-turn --resume ---
# After async with the SDK task group has exited, so the Stop
# hook has already fired and the CLI has been SIGTERMed. The
# CLI uses appendFileSync, so all writes are safely on disk.
if config.claude_agent_use_resume and user_id:
# With --resume the CLI appends to the resume file (most
# complete). Otherwise use the Stop hook path.
if use_resume and resume_file:
raw_transcript = read_transcript_file(resume_file)
logger.debug("[SDK] Transcript source: resume file")
elif captured_transcript.path:
raw_transcript = read_transcript_file(captured_transcript.path)
logger.debug(
"[SDK] Transcript source: stop hook (%s), read result: %s",
captured_transcript.path,
f"{len(raw_transcript)}B" if raw_transcript else "None",
)
else:
raw_transcript = None
# Transcript upload is handled exclusively in the finally block
# to avoid double-uploads (the success path used to upload the
# old resume file, then the finally block overwrote it with the
# stop hook content — which could be smaller after compaction).
if not raw_transcript:
logger.debug(
"[SDK] No usable transcript — CLI file had no "
"conversation entries (expected for first turn "
"without --resume)"
)
if raw_transcript:
# Shield the upload from generator cancellation so a
# client disconnect / page refresh doesn't lose the
# transcript. The upload must finish even if the SSE
# connection is torn down.
await asyncio.shield(
_try_upload_transcript(
user_id,
session_id,
raw_transcript,
message_count=len(session.messages),
)
)
logger.info(
"[SDK] [%s] Stream completed successfully with %d messages",
session_id[:12],
len(session.messages),
)
if ended_with_stream_error:
logger.warning(
"%s Stream ended with SDK error after %d messages",
log_prefix,
len(session.messages),
)
else:
logger.info(
"%s Stream completed successfully with %d messages",
log_prefix,
len(session.messages),
)
except BaseException as e:
# Catch BaseException to handle both Exception and CancelledError
# (CancelledError inherits from BaseException in Python 3.8+)
if isinstance(e, asyncio.CancelledError):
logger.warning("[SDK] [%s] Session cancelled", session_id[:12])
logger.warning("%s Session cancelled", log_prefix)
error_msg = "Operation cancelled"
else:
error_msg = str(e) or type(e).__name__
# SDK cleanup RuntimeError is expected during cancellation, log as warning
if isinstance(e, RuntimeError) and "cancel scope" in str(e):
logger.warning(
"[SDK] [%s] SDK cleanup error: %s", session_id[:12], error_msg
)
logger.warning("%s SDK cleanup error: %s", log_prefix, error_msg)
else:
logger.error(
f"[SDK] [%s] Error: {error_msg}", session_id[:12], exc_info=True
)
logger.error("%s Error: %s", log_prefix, error_msg, exc_info=True)
# Append error marker to session (non-invasive text parsing approach)
# The finally block will persist the session with this error marker
@@ -1481,8 +1538,8 @@ async def stream_chat_completion_sdk(
)
)
logger.debug(
"[SDK] [%s] Appended error marker, will be persisted in finally",
session_id[:12],
"%s Appended error marker, will be persisted in finally",
log_prefix,
)
# Yield StreamError for immediate feedback (only for non-cancellation errors)
@@ -1514,47 +1571,61 @@ async def stream_chat_completion_sdk(
try:
await asyncio.shield(upsert_chat_session(session))
logger.info(
"[SDK] [%s] Session persisted in finally with %d messages",
session_id[:12],
"%s Session persisted in finally with %d messages",
log_prefix,
len(session.messages),
)
except Exception as persist_err:
logger.error(
"[SDK] [%s] Failed to persist session in finally: %s",
session_id[:12],
"%s Failed to persist session in finally: %s",
log_prefix,
persist_err,
exc_info=True,
)
# --- Upload transcript for next-turn --resume ---
# This MUST run in finally so the transcript is uploaded even when
# the streaming loop raises an exception. The CLI uses
# appendFileSync, so whatever was written before the error/SIGTERM
# is safely on disk and still useful for the next turn.
if config.claude_agent_use_resume and user_id:
# the streaming loop raises an exception.
# The transcript represents the COMPLETE active context (atomic).
if config.claude_agent_use_resume and user_id and session is not None:
try:
# Prefer content captured in the Stop hook (read before
# cleanup removes the file). Fall back to the resume
# file when the stop hook didn't fire (e.g. error before
# completion) so we don't lose the prior transcript.
raw_transcript = captured_transcript.raw_content or None
if not raw_transcript and use_resume and resume_file:
raw_transcript = read_transcript_file(resume_file)
# Build complete transcript from captured SDK messages
transcript_content = transcript_builder.to_jsonl()
if raw_transcript and session is not None:
await asyncio.shield(
_try_upload_transcript(
user_id,
session_id,
raw_transcript,
message_count=len(session.messages),
)
if not transcript_content:
logger.warning(
"%s No transcript to upload (builder empty)", log_prefix
)
elif not validate_transcript(transcript_content):
logger.warning(
"%s Transcript invalid, skipping upload (entries=%d)",
log_prefix,
transcript_builder.entry_count,
)
else:
logger.warning(f"[SDK] No transcript to upload for {session_id}")
logger.info(
"%s Uploading complete transcript (entries=%d, bytes=%d)",
log_prefix,
transcript_builder.entry_count,
len(transcript_content),
)
# Shield upload from cancellation - let it complete even if
# the finally block is interrupted. No timeout to avoid race
# conditions where backgrounded uploads overwrite newer transcripts.
await asyncio.shield(
upload_transcript(
user_id=user_id,
session_id=session_id,
content=transcript_content,
message_count=len(session.messages),
log_prefix=log_prefix,
)
)
except Exception as upload_err:
logger.error(
f"[SDK] Transcript upload failed in finally: {upload_err}",
"%s Transcript upload failed in finally: %s",
log_prefix,
upload_err,
exc_info=True,
)
@@ -1565,33 +1636,6 @@ async def stream_chat_completion_sdk(
await lock.release()
async def _try_upload_transcript(
user_id: str,
session_id: str,
raw_content: str,
message_count: int = 0,
) -> bool:
"""Strip progress entries and upload transcript (with timeout).
Returns True if the upload completed without error.
"""
try:
async with asyncio.timeout(30):
await upload_transcript(
user_id, session_id, raw_content, message_count=message_count
)
return True
except asyncio.TimeoutError:
logger.warning(f"[SDK] Transcript upload timed out for {session_id}")
return False
except Exception as e:
logger.error(
f"[SDK] Failed to upload transcript for {session_id}: {e}",
exc_info=True,
)
return False
async def _update_title_async(
session_id: str, message: str, user_id: str | None = None
) -> None:
@@ -1600,7 +1644,7 @@ async def _update_title_async(
title = await _generate_session_title(
message, user_id=user_id, session_id=session_id
)
if title:
if title and user_id:
await update_session_title(session_id, title)
logger.debug(f"[SDK] Generated title for {session_id}: {title}")
except Exception as e:

View File

@@ -7,7 +7,7 @@ from unittest.mock import AsyncMock, patch
import pytest
from .service import _prepare_file_attachments
from .service import _generate_tool_documentation, _prepare_file_attachments
@dataclass
@@ -145,3 +145,94 @@ class TestPrepareFileAttachments:
assert "Read tool" not in result.hint
assert len(result.image_blocks) == 1
class TestGenerateToolDocumentation:
"""Tests for auto-generated tool documentation from TOOL_REGISTRY."""
def test_generate_tool_documentation_structure(self):
"""Test that tool documentation has expected structure."""
docs = _generate_tool_documentation()
# Check main sections exist
assert "## AVAILABLE TOOLS" in docs
assert "## KEY WORKFLOWS" in docs
# Verify no duplicate sections
assert docs.count("## AVAILABLE TOOLS") == 1
assert docs.count("## KEY WORKFLOWS") == 1
def test_tool_documentation_includes_key_tools(self):
"""Test that documentation includes essential copilot tools."""
docs = _generate_tool_documentation()
# Core agent workflow tools
assert "`create_agent`" in docs
assert "`run_agent`" in docs
assert "`find_library_agent`" in docs
assert "`edit_agent`" in docs
# MCP integration
assert "`run_mcp_tool`" in docs
# Browser automation
assert "`browser_navigate`" in docs
# Folder management
assert "`create_folder`" in docs
def test_tool_documentation_format(self):
"""Test that each tool follows bullet list format."""
docs = _generate_tool_documentation()
lines = docs.split("\n")
tool_lines = [line for line in lines if line.strip().startswith("- **`")]
# Should have multiple tools (at least 20 from TOOL_REGISTRY)
assert len(tool_lines) >= 20
# Each tool line should have proper markdown format
for line in tool_lines:
assert line.startswith("- **`"), f"Bad format: {line}"
assert "`**:" in line, f"Missing description separator: {line}"
def test_tool_documentation_includes_workflows(self):
"""Test that key workflow patterns are documented."""
docs = _generate_tool_documentation()
# Check workflow sections
assert "MCP Integration Workflow" in docs
assert "Agent Creation Workflow" in docs
assert "Folder Management" in docs
# Check workflow details
assert "suggested_goal" in docs # Agent creation feedback loop
assert "clarifying_questions" in docs # Agent creation feedback loop
assert "run_mcp_tool(server_url)" in docs # MCP discovery pattern
def test_tool_documentation_completeness(self):
"""Test that all tools from TOOL_REGISTRY appear in documentation."""
from backend.copilot.tools import TOOL_REGISTRY
docs = _generate_tool_documentation()
# Verify each registered tool is documented
for tool_name in TOOL_REGISTRY.keys():
assert (
f"`{tool_name}`" in docs
), f"Tool '{tool_name}' missing from auto-generated documentation"
def test_tool_documentation_no_duplicate_tools(self):
"""Test that no tool appears multiple times in the list."""
from backend.copilot.tools import TOOL_REGISTRY
docs = _generate_tool_documentation()
# Extract the tools section (before KEY WORKFLOWS)
tools_section = docs.split("## KEY WORKFLOWS")[0]
# Count occurrences of each tool
for tool_name in TOOL_REGISTRY.keys():
# Count how many times this tool appears as a bullet point
count = tools_section.count(f"- **`{tool_name}`**")
assert count == 1, f"Tool '{tool_name}' appears {count} times (should be 1)"

View File

@@ -10,13 +10,14 @@ Storage is handled via ``WorkspaceStorageBackend`` (GCS in prod, local
filesystem for self-hosted) — no DB column needed.
"""
import json
import logging
import os
import re
import time
from dataclasses import dataclass
from backend.util import json
logger = logging.getLogger(__name__)
# UUIDs are hex + hyphens; strip everything else to prevent path injection.
@@ -58,41 +59,37 @@ def strip_progress_entries(content: str) -> str:
Removes entries whose ``type`` is in ``STRIPPABLE_TYPES`` and reparents
any remaining child entries so the ``parentUuid`` chain stays intact.
Typically reduces transcript size by ~30%.
Entries that are not stripped or reparented are kept as their original
raw JSON line to avoid unnecessary re-serialization that changes
whitespace or key ordering.
"""
lines = content.strip().split("\n")
entries: list[dict] = []
# Parse entries, keeping the original line alongside the parsed dict.
parsed: list[tuple[str, dict | None]] = []
for line in lines:
try:
entries.append(json.loads(line))
except json.JSONDecodeError:
# Keep unparseable lines as-is (safety)
entries.append({"_raw": line})
parsed.append((line, json.loads(line, fallback=None)))
# First pass: identify stripped UUIDs and build parent map.
stripped_uuids: set[str] = set()
uuid_to_parent: dict[str, str] = {}
kept: list[dict] = []
for entry in entries:
if "_raw" in entry:
kept.append(entry)
for _line, entry in parsed:
if not isinstance(entry, dict):
continue
uid = entry.get("uuid", "")
parent = entry.get("parentUuid", "")
entry_type = entry.get("type", "")
if uid:
uuid_to_parent[uid] = parent
if entry.get("type", "") in STRIPPABLE_TYPES and uid:
stripped_uuids.add(uid)
if entry_type in STRIPPABLE_TYPES:
if uid:
stripped_uuids.add(uid)
else:
kept.append(entry)
# Reparent: walk up chain through stripped entries to find surviving ancestor
for entry in kept:
if "_raw" in entry:
# Second pass: keep non-stripped entries, reparenting where needed.
# Preserve original line when no reparenting is required.
reparented: set[str] = set()
for _line, entry in parsed:
if not isinstance(entry, dict):
continue
parent = entry.get("parentUuid", "")
original_parent = parent
@@ -100,63 +97,32 @@ def strip_progress_entries(content: str) -> str:
parent = uuid_to_parent.get(parent, "")
if parent != original_parent:
entry["parentUuid"] = parent
uid = entry.get("uuid", "")
if uid:
reparented.add(uid)
result_lines: list[str] = []
for entry in kept:
if "_raw" in entry:
result_lines.append(entry["_raw"])
else:
for line, entry in parsed:
if not isinstance(entry, dict):
result_lines.append(line)
continue
if entry.get("type", "") in STRIPPABLE_TYPES:
continue
uid = entry.get("uuid", "")
if uid in reparented:
# Re-serialize only entries whose parentUuid was changed.
result_lines.append(json.dumps(entry, separators=(",", ":")))
else:
result_lines.append(line)
return "\n".join(result_lines) + "\n"
# ---------------------------------------------------------------------------
# Local file I/O (read from CLI's JSONL, write temp file for --resume)
# Local file I/O (write temp file for --resume)
# ---------------------------------------------------------------------------
def read_transcript_file(transcript_path: str) -> str | None:
"""Read a JSONL transcript file from disk.
Returns the raw JSONL content, or ``None`` if the file is missing, empty,
or only contains metadata (≤2 lines with no conversation messages).
"""
if not transcript_path or not os.path.isfile(transcript_path):
logger.debug(f"[Transcript] File not found: {transcript_path}")
return None
try:
with open(transcript_path) as f:
content = f.read()
if not content.strip():
logger.debug("[Transcript] File is empty: %s", transcript_path)
return None
lines = content.strip().split("\n")
# Validate that the transcript has real conversation content
# (not just metadata like queue-operation entries).
if not validate_transcript(content):
logger.debug(
"[Transcript] No conversation content (%d lines) in %s",
len(lines),
transcript_path,
)
return None
logger.info(
f"[Transcript] Read {len(lines)} lines, "
f"{len(content)} bytes from {transcript_path}"
)
return content
except (json.JSONDecodeError, OSError) as e:
logger.warning(f"[Transcript] Failed to read {transcript_path}: {e}")
return None
def _sanitize_id(raw_id: str, max_len: int = 36) -> str:
"""Sanitize an ID for safe use in file paths.
@@ -171,14 +137,6 @@ def _sanitize_id(raw_id: str, max_len: int = 36) -> str:
_SAFE_CWD_PREFIX = os.path.realpath("/tmp/copilot-")
def _encode_cwd_for_cli(cwd: str) -> str:
"""Encode a working directory path the same way the Claude CLI does.
The CLI replaces all non-alphanumeric characters with ``-``.
"""
return re.sub(r"[^a-zA-Z0-9]", "-", os.path.realpath(cwd))
def cleanup_cli_project_dir(sdk_cwd: str) -> None:
"""Remove the CLI's project directory for a specific working directory.
@@ -188,7 +146,8 @@ def cleanup_cli_project_dir(sdk_cwd: str) -> None:
"""
import shutil
cwd_encoded = _encode_cwd_for_cli(sdk_cwd)
# Encode cwd the same way CLI does (replaces non-alphanumeric with -)
cwd_encoded = re.sub(r"[^a-zA-Z0-9]", "-", os.path.realpath(sdk_cwd))
config_dir = os.environ.get("CLAUDE_CONFIG_DIR") or os.path.expanduser("~/.claude")
projects_base = os.path.realpath(os.path.join(config_dir, "projects"))
project_dir = os.path.realpath(os.path.join(projects_base, cwd_encoded))
@@ -248,32 +207,29 @@ def write_transcript_to_tempfile(
def validate_transcript(content: str | None) -> bool:
"""Check that a transcript has actual conversation messages.
A valid transcript for resume needs at least one user message and one
assistant message (not just queue-operation / file-history-snapshot
metadata).
A valid transcript needs at least one assistant message (not just
queue-operation / file-history-snapshot metadata). We do NOT require
a ``type: "user"`` entry because with ``--resume`` the user's message
is passed as a CLI query parameter and does not appear in the
transcript file.
"""
if not content or not content.strip():
return False
lines = content.strip().split("\n")
if len(lines) < 2:
return False
has_user = False
has_assistant = False
for line in lines:
try:
entry = json.loads(line)
msg_type = entry.get("type")
if msg_type == "user":
has_user = True
elif msg_type == "assistant":
has_assistant = True
except json.JSONDecodeError:
if not line.strip():
continue
entry = json.loads(line, fallback=None)
if not isinstance(entry, dict):
return False
if entry.get("type") == "assistant":
has_assistant = True
return has_user and has_assistant
return has_assistant
# ---------------------------------------------------------------------------
@@ -328,26 +284,41 @@ async def upload_transcript(
session_id: str,
content: str,
message_count: int = 0,
log_prefix: str = "[Transcript]",
) -> None:
"""Strip progress entries and upload transcript to bucket storage.
"""Strip progress entries and upload complete transcript.
The transcript represents the FULL active context (atomic).
Each upload REPLACES the previous transcript entirely.
The executor holds a cluster lock per session, so concurrent uploads for
the same session cannot happen. We always overwrite — with ``--resume``
the CLI may compact old tool results, so neither byte size nor line count
is a reliable proxy for "newer".
the same session cannot happen.
Args:
message_count: ``len(session.messages)`` at upload time — used by
the next turn to detect staleness and compress only the gap.
content: Complete JSONL transcript (from TranscriptBuilder).
message_count: ``len(session.messages)`` at upload time.
"""
from backend.util.workspace_storage import get_workspace_storage
# Strip metadata entries (progress, file-history-snapshot, etc.)
# Note: SDK-built transcripts shouldn't have these, but strip for safety
stripped = strip_progress_entries(content)
if not validate_transcript(stripped):
# Log entry types for debugging — helps identify why validation failed
entry_types: list[str] = []
for line in stripped.strip().split("\n"):
entry = json.loads(line, fallback={"type": "INVALID_JSON"})
entry_types.append(entry.get("type", "?"))
logger.warning(
f"[Transcript] Skipping upload — stripped content not valid "
f"for session {session_id}"
"%s Skipping upload — stripped content not valid "
"(types=%s, stripped_len=%d, raw_len=%d)",
log_prefix,
entry_types,
len(stripped),
len(content),
)
logger.debug("%s Raw content preview: %s", log_prefix, content[:500])
logger.debug("%s Stripped content: %s", log_prefix, stripped[:500])
return
storage = await get_workspace_storage()
@@ -373,17 +344,18 @@ async def upload_transcript(
content=json.dumps(meta).encode("utf-8"),
)
except Exception as e:
logger.warning(f"[Transcript] Failed to write metadata for {session_id}: {e}")
logger.warning(f"{log_prefix} Failed to write metadata: {e}")
logger.info(
f"[Transcript] Uploaded {len(encoded)}B "
f"(stripped from {len(content)}B, msg_count={message_count}) "
f"for session {session_id}"
f"{log_prefix} Uploaded {len(encoded)}B "
f"(stripped from {len(content)}B, msg_count={message_count})"
)
async def download_transcript(
user_id: str, session_id: str
user_id: str,
session_id: str,
log_prefix: str = "[Transcript]",
) -> TranscriptDownload | None:
"""Download transcript and metadata from bucket storage.
@@ -399,10 +371,10 @@ async def download_transcript(
data = await storage.retrieve(path)
content = data.decode("utf-8")
except FileNotFoundError:
logger.debug(f"[Transcript] No transcript in storage for {session_id}")
logger.debug(f"{log_prefix} No transcript in storage")
return None
except Exception as e:
logger.warning(f"[Transcript] Failed to download transcript: {e}")
logger.warning(f"{log_prefix} Failed to download transcript: {e}")
return None
# Try to load metadata (best-effort — old transcripts won't have it)
@@ -419,16 +391,13 @@ async def download_transcript(
meta_path = f"local://{mwid}/{mfid}/{mfname}"
meta_data = await storage.retrieve(meta_path)
meta = json.loads(meta_data.decode("utf-8"))
meta = json.loads(meta_data.decode("utf-8"), fallback={})
message_count = meta.get("message_count", 0)
uploaded_at = meta.get("uploaded_at", 0.0)
except (FileNotFoundError, json.JSONDecodeError, Exception):
except (FileNotFoundError, Exception):
pass # No metadata — treat as unknown (msg_count=0 → always fill gap)
logger.info(
f"[Transcript] Downloaded {len(content)}B "
f"(msg_count={message_count}) for session {session_id}"
)
logger.info(f"{log_prefix} Downloaded {len(content)}B (msg_count={message_count})")
return TranscriptDownload(
content=content,
message_count=message_count,

View File

@@ -0,0 +1,150 @@
"""Build complete JSONL transcript from SDK messages.
The transcript represents the FULL active context at any point in time.
Each upload REPLACES the previous transcript atomically.
Flow:
Turn 1: Upload [msg1, msg2]
Turn 2: Download [msg1, msg2] → Upload [msg1, msg2, msg3, msg4] (REPLACE)
Turn 3: Download [msg1, msg2, msg3, msg4] → Upload [all messages] (REPLACE)
The transcript is never incremental - always the complete atomic state.
"""
import logging
from typing import Any
from uuid import uuid4
from pydantic import BaseModel
from backend.util import json
from .transcript import STRIPPABLE_TYPES
logger = logging.getLogger(__name__)
class TranscriptEntry(BaseModel):
"""Single transcript entry (user or assistant turn)."""
type: str
uuid: str
parentUuid: str | None
message: dict[str, Any]
class TranscriptBuilder:
"""Build complete JSONL transcript from SDK messages.
This builder maintains the FULL conversation state, not incremental changes.
The output is always the complete active context.
"""
def __init__(self) -> None:
self._entries: list[TranscriptEntry] = []
self._last_uuid: str | None = None
def load_previous(self, content: str, log_prefix: str = "[Transcript]") -> None:
"""Load complete previous transcript.
This loads the FULL previous context. As new messages come in,
we append to this state. The final output is the complete context
(previous + new), not just the delta.
"""
if not content or not content.strip():
return
lines = content.strip().split("\n")
for line_num, line in enumerate(lines, 1):
if not line.strip():
continue
data = json.loads(line, fallback=None)
if data is None:
logger.warning(
"%s Failed to parse transcript line %d/%d",
log_prefix,
line_num,
len(lines),
)
continue
# Load all non-strippable entries (user/assistant/system/etc.)
# Skip only STRIPPABLE_TYPES to match strip_progress_entries() behavior
entry_type = data.get("type", "")
if entry_type in STRIPPABLE_TYPES:
continue
entry = TranscriptEntry(
type=data["type"],
uuid=data.get("uuid") or str(uuid4()),
parentUuid=data.get("parentUuid"),
message=data.get("message", {}),
)
self._entries.append(entry)
self._last_uuid = entry.uuid
logger.info(
"%s Loaded %d entries from previous transcript (last_uuid=%s)",
log_prefix,
len(self._entries),
self._last_uuid[:12] if self._last_uuid else None,
)
def add_user_message(
self, content: str | list[dict], uuid: str | None = None
) -> None:
"""Add user message to the complete context."""
msg_uuid = uuid or str(uuid4())
self._entries.append(
TranscriptEntry(
type="user",
uuid=msg_uuid,
parentUuid=self._last_uuid,
message={"role": "user", "content": content},
)
)
self._last_uuid = msg_uuid
def add_assistant_message(
self, content_blocks: list[dict], model: str = ""
) -> None:
"""Add assistant message to the complete context."""
msg_uuid = str(uuid4())
self._entries.append(
TranscriptEntry(
type="assistant",
uuid=msg_uuid,
parentUuid=self._last_uuid,
message={
"role": "assistant",
"model": model,
"content": content_blocks,
},
)
)
self._last_uuid = msg_uuid
def to_jsonl(self) -> str:
"""Export complete context as JSONL.
Returns the FULL conversation state (all entries), not incremental.
This output REPLACES any previous transcript.
"""
if not self._entries:
return ""
lines = [entry.model_dump_json(exclude_none=True) for entry in self._entries]
return "\n".join(lines) + "\n"
@property
def entry_count(self) -> int:
"""Total number of entries in the complete context."""
return len(self._entries)
@property
def is_empty(self) -> bool:
"""Whether this builder has any entries."""
return len(self._entries) == 0

View File

@@ -1,11 +1,11 @@
"""Unit tests for JSONL transcript management utilities."""
import json
import os
from backend.util import json
from .transcript import (
STRIPPABLE_TYPES,
read_transcript_file,
strip_progress_entries,
validate_transcript,
write_transcript_to_tempfile,
@@ -38,49 +38,6 @@ PROGRESS_ENTRY = {
VALID_TRANSCRIPT = _make_jsonl(METADATA_LINE, FILE_HISTORY, USER_MSG, ASST_MSG)
# --- read_transcript_file ---
class TestReadTranscriptFile:
def test_returns_content_for_valid_file(self, tmp_path):
path = tmp_path / "session.jsonl"
path.write_text(VALID_TRANSCRIPT)
result = read_transcript_file(str(path))
assert result is not None
assert "user" in result
def test_returns_none_for_missing_file(self):
assert read_transcript_file("/nonexistent/path.jsonl") is None
def test_returns_none_for_empty_path(self):
assert read_transcript_file("") is None
def test_returns_none_for_empty_file(self, tmp_path):
path = tmp_path / "empty.jsonl"
path.write_text("")
assert read_transcript_file(str(path)) is None
def test_returns_none_for_metadata_only(self, tmp_path):
content = _make_jsonl(METADATA_LINE, FILE_HISTORY)
path = tmp_path / "meta.jsonl"
path.write_text(content)
assert read_transcript_file(str(path)) is None
def test_returns_none_for_invalid_json(self, tmp_path):
path = tmp_path / "bad.jsonl"
path.write_text("not json\n{}\n{}\n")
assert read_transcript_file(str(path)) is None
def test_no_size_limit(self, tmp_path):
"""Large files are accepted — bucket storage has no size limit."""
big_content = {"type": "user", "uuid": "u9", "data": "x" * 1_000_000}
content = _make_jsonl(METADATA_LINE, FILE_HISTORY, big_content, ASST_MSG)
path = tmp_path / "big.jsonl"
path.write_text(content)
result = read_transcript_file(str(path))
assert result is not None
# --- write_transcript_to_tempfile ---
@@ -155,12 +112,56 @@ class TestValidateTranscript:
assert validate_transcript(content) is False
def test_assistant_only_no_user(self):
"""With --resume the user message is a CLI query param, not a transcript entry.
A transcript with only assistant entries is valid."""
content = _make_jsonl(METADATA_LINE, FILE_HISTORY, ASST_MSG)
assert validate_transcript(content) is False
assert validate_transcript(content) is True
def test_resume_transcript_without_user_entry(self):
"""Simulates a real --resume stop hook transcript: the CLI session file
has summary + assistant entries but no user entry."""
summary = {"type": "summary", "uuid": "s1", "text": "context..."}
asst1 = {
"type": "assistant",
"uuid": "a1",
"message": {"role": "assistant", "content": "Hello!"},
}
asst2 = {
"type": "assistant",
"uuid": "a2",
"parentUuid": "a1",
"message": {"role": "assistant", "content": "Sure, let me help."},
}
content = _make_jsonl(summary, asst1, asst2)
assert validate_transcript(content) is True
def test_single_assistant_entry(self):
"""A transcript with just one assistant line is valid — the CLI may
produce short transcripts for simple responses with no tool use."""
content = json.dumps(ASST_MSG) + "\n"
assert validate_transcript(content) is True
def test_invalid_json_returns_false(self):
assert validate_transcript("not json\n{}\n{}\n") is False
def test_malformed_json_after_valid_assistant_returns_false(self):
"""Validation must scan all lines - malformed JSON anywhere should fail."""
valid_asst = json.dumps(ASST_MSG)
malformed = "not valid json"
content = valid_asst + "\n" + malformed + "\n"
assert validate_transcript(content) is False
def test_blank_lines_are_skipped(self):
"""Transcripts with blank lines should be valid if they contain assistant entries."""
content = (
json.dumps(USER_MSG)
+ "\n\n" # blank line
+ json.dumps(ASST_MSG)
+ "\n"
+ "\n" # another blank line
)
assert validate_transcript(content) is True
# --- strip_progress_entries ---
@@ -253,3 +254,31 @@ class TestStripProgressEntries:
assert "queue-operation" not in result_types
assert "user" in result_types
assert "assistant" in result_types
def test_preserves_original_line_formatting(self):
"""Non-reparented entries keep their original JSON formatting."""
# orjson produces compact JSON - test that we preserve the exact input
# when no reparenting is needed (no re-serialization)
original_line = json.dumps(USER_MSG)
content = original_line + "\n" + json.dumps(ASST_MSG) + "\n"
result = strip_progress_entries(content)
result_lines = result.strip().split("\n")
# Original line should be byte-identical (not re-serialized)
assert result_lines[0] == original_line
def test_reparented_entries_are_reserialized(self):
"""Entries whose parentUuid changes must be re-serialized."""
progress = {"type": "progress", "uuid": "p1", "parentUuid": "u1"}
asst = {
"type": "assistant",
"uuid": "a1",
"parentUuid": "p1",
"message": {"role": "assistant", "content": "done"},
}
content = _make_jsonl(USER_MSG, progress, asst)
result = strip_progress_entries(content)
lines = result.strip().split("\n")
asst_entry = json.loads(lines[-1])
assert asst_entry["parentUuid"] == "u1" # reparented

View File

@@ -34,8 +34,9 @@ client = LangfuseAsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
langfuse = get_client()
# Default system prompt used when Langfuse is not configured
# This is a snapshot of the "CoPilot Prompt" from Langfuse (version 11)
DEFAULT_SYSTEM_PROMPT = """You are **Otto**, an AI Co-Pilot for AutoGPT and a Forward-Deployed Automation Engineer serving small business owners. Your mission is to help users automate business tasks with AI by delivering tangible value through working automations—not through documentation or lengthy explanations.
# Provides minimal baseline tone and personality - all workflow, tools, and
# technical details are provided via the supplement.
DEFAULT_SYSTEM_PROMPT = """You are an AI automation assistant helping users build and run automations.
Here is everything you know about the current user from previous interactions:
@@ -43,113 +44,12 @@ Here is everything you know about the current user from previous interactions:
{users_information}
</users_information>
## YOUR CORE MANDATE
Your goal is to help users automate tasks by:
- Understanding their needs and business context
- Building and running working automations
- Delivering tangible value through action, not just explanation
You are action-oriented. Your success is measured by:
- **Value Delivery**: Does the user think "wow, that was amazing" or "what was the point"?
- **Demonstrable Proof**: Show working automations, not descriptions of what's possible
- **Time Saved**: Focus on tangible efficiency gains
- **Quality Output**: Deliver results that meet or exceed expectations
## YOUR WORKFLOW
Adapt flexibly to the conversation context. Not every interaction requires all stages:
1. **Explore & Understand**: Learn about the user's business, tasks, and goals. Use `add_understanding` to capture important context that will improve future conversations.
2. **Assess Automation Potential**: Help the user understand whether and how AI can automate their task.
3. **Prepare for AI**: Provide brief, actionable guidance on prerequisites (data, access, etc.).
4. **Discover or Create Agents**:
- **Always check the user's library first** with `find_library_agent` (these may be customized to their needs)
- Search the marketplace with `find_agent` for pre-built automations
- Find reusable components with `find_block`
- **For live integrations** (read a GitHub repo, query a database, post to Slack, etc.) consider `run_mcp_tool` — it connects directly to external services without building a full agent
- Create custom solutions with `create_agent` if nothing suitable exists
- Modify existing library agents with `edit_agent`
- **When `create_agent` returns `suggested_goal`**: Present the suggestion to the user and ask "Would you like me to proceed with this refined goal?" If they accept, call `create_agent` again with the suggested goal.
- **When `create_agent` returns `clarifying_questions`**: After the user answers, call `create_agent` again with the original description AND the answers in the `context` parameter.
5. **Execute**: Run automations immediately, schedule them, or set up webhooks using `run_agent`. Test specific components with `run_block`.
6. **Show Results**: Display outputs using `agent_output`.
## AVAILABLE TOOLS
**Understanding & Discovery:**
- `add_understanding`: Create a memory about the user's business or use cases for future sessions
- `search_docs`: Search platform documentation for specific technical information
- `get_doc_page`: Retrieve full text of a specific documentation page
**Agent Discovery:**
- `find_library_agent`: Search the user's existing agents (CHECK HERE FIRST—these may be customized)
- `find_agent`: Search the marketplace for pre-built automations
- `find_block`: Find pre-written code units that perform specific tasks (agents are built from blocks)
**Agent Creation & Editing:**
- `create_agent`: Create a new automation agent
- `edit_agent`: Modify an agent in the user's library
**Execution & Output:**
- `run_agent`: Run an agent now, schedule it, or set up a webhook trigger
- `run_block`: Test or run a specific block independently
- `agent_output`: View results from previous agent runs
**MCP (Model Context Protocol) Servers:**
- `run_mcp_tool`: Connect to any MCP server to discover and run its tools
**Two-step flow:**
1. `run_mcp_tool(server_url)` → returns a list of available tools. Each tool has `name`, `description`, and `input_schema` (JSON Schema). Read `input_schema.properties` to understand what arguments are needed.
2. `run_mcp_tool(server_url, tool_name, tool_arguments)` → executes the tool. Build `tool_arguments` as a flat `{{key: value}}` object matching the tool's `input_schema.properties`.
**Authentication:** If the MCP server requires credentials, the UI will show an OAuth connect button. Once the user connects and clicks Proceed, they will automatically send you a message confirming credentials are ready (e.g. "I've connected the MCP server credentials. Please retry run_mcp_tool..."). When you receive that confirmation, **immediately** call `run_mcp_tool` again with the exact same `server_url` — and the same `tool_name`/`tool_arguments` if you were already mid-execution. Do not ask the user what to do next; just retry.
**Finding server URLs (fastest → slowest):**
1. **Known hosted servers** — use directly, no lookup:
- Notion: `https://mcp.notion.com/mcp`
- Linear: `https://mcp.linear.app/mcp`
- Stripe: `https://mcp.stripe.com`
- Intercom: `https://mcp.intercom.com/mcp`
- Cloudflare: `https://mcp.cloudflare.com/mcp`
- Atlassian (Jira/Confluence): `https://mcp.atlassian.com/mcp`
2. **`web_search`** — use `web_search("{{service}} MCP server URL")` for any service not in the list above. This is the fastest way to find unlisted servers.
3. **Registry API** — `web_fetch("https://registry.modelcontextprotocol.io/v0.1/servers?search={{query}}&limit=10")` to browse what's available. Returns names + GitHub repo URLs but NOT the endpoint URL; follow up with `web_search` to find the actual endpoint.
- **Never** `web_fetch` the registry homepage — it is JavaScript-rendered and returns a blank page.
**When to use:** Use `run_mcp_tool` when the user wants to interact with an external service (GitHub, Slack, a database, a SaaS tool, etc.) via its MCP integration. Unlike `web_fetch` (which just retrieves a raw URL), MCP servers expose structured typed tools — prefer `run_mcp_tool` for any service with an MCP server, and `web_fetch` only for plain URL retrieval with no MCP server involved.
**CRITICAL**: `run_mcp_tool` is **always available** in your tool list. If the user explicitly provides an MCP server URL or asks you to call `run_mcp_tool`, you MUST use it — never claim it is unavailable, and never substitute `web_fetch` for an explicit MCP request.
## BEHAVIORAL GUIDELINES
**Be Concise:**
- Target 2-5 short lines maximum
- Make every word count—no repetition or filler
- Use lightweight structure for scannability (bullets, numbered lists, short prompts)
- Avoid jargon (blocks, slugs, cron) unless the user asks
**Be Proactive:**
- Suggest next steps before being asked
- Anticipate needs based on conversation context and user information
- Look for opportunities to expand scope when relevant
- Reveal capabilities through action, not explanation
**Use Tools Effectively:**
- Select the right tool for each task
- **Always check `find_library_agent` before searching the marketplace**
- Use `add_understanding` to capture valuable business context
- When tool calls fail, try alternative approaches
- **For MCP integrations**: Known URL (see list) or `web_search("{{service}} MCP server URL")` → `run_mcp_tool(server_url)` → `run_mcp_tool(server_url, tool_name, tool_arguments)`. If credentials needed, UI prompts automatically; when user confirms, retry immediately with same arguments.
**Handle Feedback Loops:**
- When a tool returns a suggested alternative (like a refined goal), present it clearly and ask the user for confirmation before proceeding
- When clarifying questions are answered, immediately re-call the tool with the accumulated context
- Don't ask redundant questions if the user has already provided context in the conversation
## CRITICAL REMINDER
You are NOT a chatbot. You are NOT documentation. You are a partner who helps busy business owners get value quickly by showing proof through working automations. Bias toward action over explanation."""
Be concise, proactive, and action-oriented. Bias toward showing working solutions over lengthy explanations."""
# ---------------------------------------------------------------------------

View File

@@ -81,7 +81,6 @@ MODEL_COST: dict[LlmModel, int] = {
LlmModel.CLAUDE_4_OPUS: 21,
LlmModel.CLAUDE_4_SONNET: 5,
LlmModel.CLAUDE_4_6_OPUS: 14,
LlmModel.CLAUDE_4_6_SONNET: 9,
LlmModel.CLAUDE_4_5_HAIKU: 4,
LlmModel.CLAUDE_4_5_OPUS: 14,
LlmModel.CLAUDE_4_5_SONNET: 9,

View File

@@ -211,22 +211,6 @@ class AgentRejectionData(BaseNotificationData):
return value
class WaitlistLaunchData(BaseNotificationData):
"""Notification data for when an agent from a waitlist is launched."""
agent_name: str
waitlist_name: str
store_url: str
launched_at: datetime
@field_validator("launched_at")
@classmethod
def validate_timezone(cls, value: datetime):
if value.tzinfo is None:
raise ValueError("datetime must have timezone information")
return value
NotificationData = Annotated[
Union[
AgentRunData,
@@ -239,7 +223,6 @@ NotificationData = Annotated[
DailySummaryData,
RefundRequestData,
BaseSummaryData,
WaitlistLaunchData,
],
Field(discriminator="type"),
]
@@ -290,7 +273,6 @@ def get_notif_data_type(
NotificationType.REFUND_PROCESSED: RefundRequestData,
NotificationType.AGENT_APPROVED: AgentApprovalData,
NotificationType.AGENT_REJECTED: AgentRejectionData,
NotificationType.WAITLIST_LAUNCH: WaitlistLaunchData,
}[notification_type]
@@ -336,7 +318,6 @@ class NotificationTypeOverride:
NotificationType.REFUND_PROCESSED: QueueType.ADMIN,
NotificationType.AGENT_APPROVED: QueueType.IMMEDIATE,
NotificationType.AGENT_REJECTED: QueueType.IMMEDIATE,
NotificationType.WAITLIST_LAUNCH: QueueType.IMMEDIATE,
}
return BATCHING_RULES.get(self.notification_type, QueueType.IMMEDIATE)
@@ -356,7 +337,6 @@ class NotificationTypeOverride:
NotificationType.REFUND_PROCESSED: "refund_processed.html",
NotificationType.AGENT_APPROVED: "agent_approved.html",
NotificationType.AGENT_REJECTED: "agent_rejected.html",
NotificationType.WAITLIST_LAUNCH: "waitlist_launch.html",
}[self.notification_type]
@property
@@ -374,7 +354,6 @@ class NotificationTypeOverride:
NotificationType.REFUND_PROCESSED: "Refund for ${{data.amount / 100}} to {{data.user_name}} has been processed",
NotificationType.AGENT_APPROVED: "🎉 Your agent '{{data.agent_name}}' has been approved!",
NotificationType.AGENT_REJECTED: "Your agent '{{data.agent_name}}' needs some updates",
NotificationType.WAITLIST_LAUNCH: "🚀 {{data.agent_name}} is now available!",
}[self.notification_type]

View File

@@ -15,6 +15,7 @@ from backend.data import graph as graph_db
from backend.data import human_review as human_review_db
from backend.data import onboarding as onboarding_db
from backend.data import user as user_db
from backend.data import workspace as workspace_db
# Import dynamic field utilities from centralized location
from backend.data.block import BlockInput, BlockOutputEntry
@@ -32,7 +33,6 @@ from backend.data.execution import (
from backend.data.graph import GraphModel, Node
from backend.data.model import USER_TIMEZONE_NOT_SET, CredentialsMetaInput, GraphInput
from backend.data.rabbitmq import Exchange, ExchangeType, Queue, RabbitMQConfig
from backend.data.workspace import get_or_create_workspace
from backend.util.clients import (
get_async_execution_event_bus,
get_async_execution_queue,
@@ -831,8 +831,9 @@ async def add_graph_execution(
udb = user_db
gdb = graph_db
odb = onboarding_db
wdb = workspace_db
else:
edb = udb = gdb = odb = get_database_manager_async_client()
edb = udb = gdb = odb = wdb = get_database_manager_async_client()
# Get or create the graph execution
if graph_exec_id:
@@ -892,7 +893,7 @@ async def add_graph_execution(
if execution_context is None:
user = await udb.get_user_by_id(user_id)
settings = await gdb.get_graph_settings(user_id=user_id, graph_id=graph_id)
workspace = await get_or_create_workspace(user_id)
workspace = await wdb.get_or_create_workspace(user_id)
execution_context = ExecutionContext(
# Execution identity

View File

@@ -368,12 +368,10 @@ async def test_add_graph_execution_is_repeatable(mocker: MockerFixture):
mock_get_event_bus = mocker.patch(
"backend.executor.utils.get_async_execution_event_bus"
)
mock_wdb = mocker.patch("backend.executor.utils.workspace_db")
mock_workspace = mocker.MagicMock()
mock_workspace.id = "test-workspace-id"
mocker.patch(
"backend.executor.utils.get_or_create_workspace",
new=mocker.AsyncMock(return_value=mock_workspace),
)
mock_wdb.get_or_create_workspace = mocker.AsyncMock(return_value=mock_workspace)
# Setup mock returns
# The function returns (graph, starting_nodes_input, compiled_nodes_input_masks, nodes_to_skip)
@@ -649,12 +647,10 @@ async def test_add_graph_execution_with_nodes_to_skip(mocker: MockerFixture):
mock_get_event_bus = mocker.patch(
"backend.executor.utils.get_async_execution_event_bus"
)
mock_wdb = mocker.patch("backend.executor.utils.workspace_db")
mock_workspace = mocker.MagicMock()
mock_workspace.id = "test-workspace-id"
mocker.patch(
"backend.executor.utils.get_or_create_workspace",
new=mocker.AsyncMock(return_value=mock_workspace),
)
mock_wdb.get_or_create_workspace = mocker.AsyncMock(return_value=mock_workspace)
# Setup returns - include nodes_to_skip in the tuple
mock_validate.return_value = (

View File

@@ -1,59 +0,0 @@
{# Waitlist Launch Notification Email Template #}
{#
Template variables:
data.agent_name: the name of the launched agent
data.waitlist_name: the name of the waitlist the user joined
data.store_url: URL to view the agent in the store
data.launched_at: when the agent was launched
Subject: {{ data.agent_name }} is now available!
#}
{% block content %}
<h1 style="color: #7c3aed; font-size: 32px; font-weight: 700; margin: 0 0 24px 0; text-align: center;">
The wait is over!
</h1>
<p style="color: #586069; font-size: 18px; text-align: center; margin: 0 0 24px 0;">
<strong>'{{ data.agent_name }}'</strong> is now live in the AutoGPT Store!
</p>
<div style="height: 32px; background: transparent;"></div>
<div style="background: #f3e8ff; border: 1px solid #d8b4fe; border-radius: 8px; padding: 20px; margin: 0;">
<h3 style="color: #6b21a8; font-size: 16px; font-weight: 600; margin: 0 0 12px 0;">
You're one of the first to know!
</h3>
<p style="color: #6b21a8; margin: 0; font-size: 16px; line-height: 1.5;">
You signed up for the <strong>{{ data.waitlist_name }}</strong> waitlist, and we're excited to let you know that this agent is now ready for you to use.
</p>
</div>
<div style="height: 32px; background: transparent;"></div>
<div style="text-align: center; margin: 24px 0;">
<a href="{{ data.store_url }}" style="display: inline-block; background: linear-gradient(135deg, #7c3aed 0%, #5b21b6 100%); color: white; text-decoration: none; padding: 14px 28px; border-radius: 6px; font-weight: 600; font-size: 16px;">
Get {{ data.agent_name }} Now
</a>
</div>
<div style="height: 32px; background: transparent;"></div>
<div style="background: #d1ecf1; border: 1px solid #bee5eb; border-radius: 8px; padding: 20px; margin: 0;">
<h3 style="color: #0c5460; font-size: 16px; font-weight: 600; margin: 0 0 12px 0;">
What can you do now?
</h3>
<ul style="color: #0c5460; margin: 0; padding-left: 18px; font-size: 16px; line-height: 1.6;">
<li>Visit the store to learn more about what this agent can do</li>
<li>Install and start using the agent right away</li>
<li>Share it with others who might find it useful</li>
</ul>
</div>
<div style="height: 32px; background: transparent;"></div>
<p style="color: #6a737d; font-size: 14px; text-align: center; margin: 24px 0;">
Thank you for helping us prioritize what to build! Your interest made this happen.
</p>
{% endblock %}

View File

@@ -72,19 +72,58 @@ def dumps(
T = TypeVar("T")
@overload
def loads(data: str | bytes, *args, target_type: Type[T], **kwargs) -> T: ...
# Sentinel value to detect when fallback is not provided
_NO_FALLBACK = object()
@overload
def loads(data: str | bytes, *args, **kwargs) -> Any: ...
def loads(
data: str | bytes, *args, target_type: Type[T], fallback: T | None = None, **kwargs
) -> T:
pass
@overload
def loads(data: str | bytes, *args, fallback: Any = None, **kwargs) -> Any:
pass
def loads(
data: str | bytes, *args, target_type: Type[T] | None = None, **kwargs
data: str | bytes,
*args,
target_type: Type[T] | None = None,
fallback: Any = _NO_FALLBACK,
**kwargs,
) -> Any:
parsed = orjson.loads(data)
"""Parse JSON with optional fallback on decode errors.
Args:
data: JSON string or bytes to parse
target_type: Optional type to validate/cast result to
fallback: Value to return on JSONDecodeError. If not provided, raises.
**kwargs: Additional arguments (unused, for compatibility)
Returns:
Parsed JSON data, or fallback value if parsing fails
Raises:
orjson.JSONDecodeError: Only if fallback is not provided
Examples:
>>> loads('{"valid": "json"}')
{'valid': 'json'}
>>> loads('invalid json', fallback=None)
None
>>> loads('invalid json', fallback={})
{}
>>> loads('invalid json') # raises orjson.JSONDecodeError
"""
try:
parsed = orjson.loads(data)
except orjson.JSONDecodeError:
if fallback is not _NO_FALLBACK:
return fallback
raise
if target_type:
return type_match(parsed, target_type)

View File

@@ -1,53 +0,0 @@
-- CreateEnum
CREATE TYPE "WaitlistExternalStatus" AS ENUM ('DONE', 'NOT_STARTED', 'CANCELED', 'WORK_IN_PROGRESS');
-- AlterEnum
ALTER TYPE "NotificationType" ADD VALUE 'WAITLIST_LAUNCH';
-- CreateTable
CREATE TABLE "WaitlistEntry" (
"id" TEXT NOT NULL,
"createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
"updatedAt" TIMESTAMP(3) NOT NULL,
"storeListingId" TEXT,
"owningUserId" TEXT NOT NULL,
"slug" TEXT NOT NULL,
"search" tsvector DEFAULT ''::tsvector,
"name" TEXT NOT NULL,
"subHeading" TEXT NOT NULL,
"videoUrl" TEXT,
"agentOutputDemoUrl" TEXT,
"imageUrls" TEXT[],
"description" TEXT NOT NULL,
"categories" TEXT[],
"status" "WaitlistExternalStatus" NOT NULL DEFAULT 'NOT_STARTED',
"votes" INTEGER NOT NULL DEFAULT 0,
"unaffiliatedEmailUsers" TEXT[] DEFAULT ARRAY[]::TEXT[],
"isDeleted" BOOLEAN NOT NULL DEFAULT false,
CONSTRAINT "WaitlistEntry_pkey" PRIMARY KEY ("id")
);
-- CreateTable
CREATE TABLE "_joinedWaitlists" (
"A" TEXT NOT NULL,
"B" TEXT NOT NULL
);
-- CreateIndex
CREATE UNIQUE INDEX "_joinedWaitlists_AB_unique" ON "_joinedWaitlists"("A", "B");
-- CreateIndex
CREATE INDEX "_joinedWaitlists_B_index" ON "_joinedWaitlists"("B");
-- AddForeignKey
ALTER TABLE "WaitlistEntry" ADD CONSTRAINT "WaitlistEntry_storeListingId_fkey" FOREIGN KEY ("storeListingId") REFERENCES "StoreListing"("id") ON DELETE SET NULL ON UPDATE CASCADE;
-- AddForeignKey
ALTER TABLE "WaitlistEntry" ADD CONSTRAINT "WaitlistEntry_owningUserId_fkey" FOREIGN KEY ("owningUserId") REFERENCES "User"("id") ON DELETE RESTRICT ON UPDATE CASCADE;
-- AddForeignKey
ALTER TABLE "_joinedWaitlists" ADD CONSTRAINT "_joinedWaitlists_A_fkey" FOREIGN KEY ("A") REFERENCES "User"("id") ON DELETE CASCADE ON UPDATE CASCADE;
-- AddForeignKey
ALTER TABLE "_joinedWaitlists" ADD CONSTRAINT "_joinedWaitlists_B_fkey" FOREIGN KEY ("B") REFERENCES "WaitlistEntry"("id") ON DELETE CASCADE ON UPDATE CASCADE;

View File

@@ -71,10 +71,6 @@ model User {
OAuthAuthorizationCodes OAuthAuthorizationCode[]
OAuthAccessTokens OAuthAccessToken[]
OAuthRefreshTokens OAuthRefreshToken[]
// Waitlist relations
WaitlistEntries WaitlistEntry[]
JoinedWaitlists WaitlistEntry[] @relation("joinedWaitlists")
}
enum OnboardingStep {
@@ -349,7 +345,6 @@ enum NotificationType {
REFUND_PROCESSED
AGENT_APPROVED
AGENT_REJECTED
WAITLIST_LAUNCH
}
model NotificationEvent {
@@ -992,8 +987,7 @@ model StoreListing {
OwningUser User @relation(fields: [owningUserId], references: [id])
// Relations
Versions StoreListingVersion[] @relation("ListingVersions")
WaitlistEntries WaitlistEntry[]
Versions StoreListingVersion[] @relation("ListingVersions")
// Unique index on agentId to ensure only one listing per agent, regardless of number of versions the agent has.
@@unique([agentGraphId])
@@ -1125,47 +1119,6 @@ model StoreListingReview {
@@index([reviewByUserId])
}
enum WaitlistExternalStatus {
DONE
NOT_STARTED
CANCELED
WORK_IN_PROGRESS
}
model WaitlistEntry {
id String @id @default(uuid())
createdAt DateTime @default(now())
updatedAt DateTime @updatedAt
storeListingId String?
StoreListing StoreListing? @relation(fields: [storeListingId], references: [id], onDelete: SetNull)
owningUserId String
OwningUser User @relation(fields: [owningUserId], references: [id])
slug String
search Unsupported("tsvector")? @default(dbgenerated("''::tsvector"))
// Content fields
name String
subHeading String
videoUrl String?
agentOutputDemoUrl String?
imageUrls String[]
description String
categories String[]
//Waitlist specific fields
status WaitlistExternalStatus @default(NOT_STARTED)
votes Int @default(0) // Hide from frontend api
JoinedUsers User[] @relation("joinedWaitlists")
// NOTE: DO NOT DOUBLE SEND TO THESE USERS, IF THEY HAVE SIGNED UP SINCE THEY MAY HAVE ALREADY RECEIVED AN EMAIL
// DOUBLE CHECK WHEN SENDING THAT THEY ARE NOT IN THE JOINED USERS LIST ALSO
unaffiliatedEmailUsers String[] @default([])
isDeleted Boolean @default(false)
}
enum SubmissionStatus {
DRAFT // Being prepared, not yet submitted
PENDING // Submitted, awaiting review

View File

@@ -1,5 +1,5 @@
import { Sidebar } from "@/components/__legacy__/Sidebar";
import { Users, DollarSign, UserSearch, FileText, Clock } from "lucide-react";
import { Users, DollarSign, UserSearch, FileText } from "lucide-react";
import { IconSliders } from "@/components/__legacy__/ui/icons";
@@ -11,11 +11,6 @@ const sidebarLinkGroups = [
href: "/admin/marketplace",
icon: <Users className="h-6 w-6" />,
},
{
text: "Waitlist Management",
href: "/admin/waitlist",
icon: <Clock className="h-6 w-6" />,
},
{
text: "User Spending",
href: "/admin/spending",

View File

@@ -1,217 +0,0 @@
"use client";
import { useState } from "react";
import { useQueryClient } from "@tanstack/react-query";
import { Button } from "@/components/atoms/Button/Button";
import { Input } from "@/components/atoms/Input/Input";
import { Dialog } from "@/components/molecules/Dialog/Dialog";
import {
usePostV2CreateWaitlist,
getGetV2ListAllWaitlistsQueryKey,
} from "@/app/api/__generated__/endpoints/admin/admin";
import { useToast } from "@/components/molecules/Toast/use-toast";
import { Plus } from "@phosphor-icons/react";
export function CreateWaitlistButton() {
const [open, setOpen] = useState(false);
const { toast } = useToast();
const queryClient = useQueryClient();
const createWaitlistMutation = usePostV2CreateWaitlist({
mutation: {
onSuccess: (response) => {
if (response.status === 200) {
toast({
title: "Success",
description: "Waitlist created successfully",
});
setOpen(false);
setFormData({
name: "",
slug: "",
subHeading: "",
description: "",
categories: "",
imageUrls: "",
videoUrl: "",
agentOutputDemoUrl: "",
});
queryClient.invalidateQueries({
queryKey: getGetV2ListAllWaitlistsQueryKey(),
});
} else {
toast({
variant: "destructive",
title: "Error",
description: "Failed to create waitlist",
});
}
},
onError: (error) => {
console.error("Error creating waitlist:", error);
toast({
variant: "destructive",
title: "Error",
description: "Failed to create waitlist",
});
},
},
});
const [formData, setFormData] = useState({
name: "",
slug: "",
subHeading: "",
description: "",
categories: "",
imageUrls: "",
videoUrl: "",
agentOutputDemoUrl: "",
});
function handleInputChange(id: string, value: string) {
setFormData((prev) => ({
...prev,
[id]: value,
}));
}
function generateSlug(name: string) {
return name
.toLowerCase()
.replace(/[^a-z0-9]+/g, "-")
.replace(/^-|-$/g, "");
}
function handleSubmit(e: React.FormEvent) {
e.preventDefault();
createWaitlistMutation.mutate({
data: {
name: formData.name,
slug: formData.slug || generateSlug(formData.name),
subHeading: formData.subHeading,
description: formData.description,
categories: formData.categories
? formData.categories.split(",").map((c) => c.trim())
: [],
imageUrls: formData.imageUrls
? formData.imageUrls.split(",").map((u) => u.trim())
: [],
videoUrl: formData.videoUrl || null,
agentOutputDemoUrl: formData.agentOutputDemoUrl || null,
},
});
}
return (
<>
<Button onClick={() => setOpen(true)}>
<Plus size={16} className="mr-2" />
Create Waitlist
</Button>
<Dialog
title="Create New Waitlist"
controlled={{
isOpen: open,
set: async (isOpen) => setOpen(isOpen),
}}
onClose={() => setOpen(false)}
styling={{ maxWidth: "600px" }}
>
<Dialog.Content>
<p className="mb-4 text-sm text-zinc-500">
Create a new waitlist for an upcoming agent. Users can sign up to be
notified when it launches.
</p>
<form onSubmit={handleSubmit} className="flex flex-col gap-2">
<Input
id="name"
label="Name"
value={formData.name}
onChange={(e) => handleInputChange("name", e.target.value)}
placeholder="SEO Analysis Agent"
required
/>
<Input
id="slug"
label="Slug"
value={formData.slug}
onChange={(e) => handleInputChange("slug", e.target.value)}
placeholder="seo-analysis-agent (auto-generated if empty)"
/>
<Input
id="subHeading"
label="Subheading"
value={formData.subHeading}
onChange={(e) => handleInputChange("subHeading", e.target.value)}
placeholder="Analyze your website's SEO in minutes"
required
/>
<Input
id="description"
label="Description"
type="textarea"
value={formData.description}
onChange={(e) => handleInputChange("description", e.target.value)}
placeholder="Detailed description of what this agent does..."
rows={4}
required
/>
<Input
id="categories"
label="Categories (comma-separated)"
value={formData.categories}
onChange={(e) => handleInputChange("categories", e.target.value)}
placeholder="SEO, Marketing, Analysis"
/>
<Input
id="imageUrls"
label="Image URLs (comma-separated)"
value={formData.imageUrls}
onChange={(e) => handleInputChange("imageUrls", e.target.value)}
placeholder="https://example.com/image1.jpg, https://example.com/image2.jpg"
/>
<Input
id="videoUrl"
label="Video URL (optional)"
value={formData.videoUrl}
onChange={(e) => handleInputChange("videoUrl", e.target.value)}
placeholder="https://youtube.com/watch?v=..."
/>
<Input
id="agentOutputDemoUrl"
label="Output Demo URL (optional)"
value={formData.agentOutputDemoUrl}
onChange={(e) =>
handleInputChange("agentOutputDemoUrl", e.target.value)
}
placeholder="https://example.com/demo-output.mp4"
/>
<Dialog.Footer>
<Button
type="button"
variant="secondary"
onClick={() => setOpen(false)}
>
Cancel
</Button>
<Button type="submit" loading={createWaitlistMutation.isPending}>
Create Waitlist
</Button>
</Dialog.Footer>
</form>
</Dialog.Content>
</Dialog>
</>
);
}

View File

@@ -1,221 +0,0 @@
"use client";
import { useState } from "react";
import { Button } from "@/components/atoms/Button/Button";
import { Input } from "@/components/atoms/Input/Input";
import { Select } from "@/components/atoms/Select/Select";
import { Dialog } from "@/components/molecules/Dialog/Dialog";
import { useToast } from "@/components/molecules/Toast/use-toast";
import { usePutV2UpdateWaitlist } from "@/app/api/__generated__/endpoints/admin/admin";
import type { WaitlistAdminResponse } from "@/app/api/__generated__/models/waitlistAdminResponse";
import type { WaitlistUpdateRequest } from "@/app/api/__generated__/models/waitlistUpdateRequest";
import { WaitlistExternalStatus } from "@/app/api/__generated__/models/waitlistExternalStatus";
type EditWaitlistDialogProps = {
waitlist: WaitlistAdminResponse;
onClose: () => void;
onSave: () => void;
};
const STATUS_OPTIONS = [
{ value: WaitlistExternalStatus.NOT_STARTED, label: "Not Started" },
{ value: WaitlistExternalStatus.WORK_IN_PROGRESS, label: "Work In Progress" },
{ value: WaitlistExternalStatus.DONE, label: "Done" },
{ value: WaitlistExternalStatus.CANCELED, label: "Canceled" },
];
export function EditWaitlistDialog({
waitlist,
onClose,
onSave,
}: EditWaitlistDialogProps) {
const { toast } = useToast();
const updateWaitlistMutation = usePutV2UpdateWaitlist();
const [formData, setFormData] = useState({
name: waitlist.name,
slug: waitlist.slug,
subHeading: waitlist.subHeading,
description: waitlist.description,
categories: waitlist.categories.join(", "),
imageUrls: waitlist.imageUrls.join(", "),
videoUrl: waitlist.videoUrl || "",
agentOutputDemoUrl: waitlist.agentOutputDemoUrl || "",
status: waitlist.status,
storeListingId: waitlist.storeListingId || "",
});
function handleInputChange(id: string, value: string) {
setFormData((prev) => ({
...prev,
[id]: value,
}));
}
function handleStatusChange(value: string) {
setFormData((prev) => ({
...prev,
status: value as WaitlistExternalStatus,
}));
}
async function handleSubmit(e: React.FormEvent) {
e.preventDefault();
const updateData: WaitlistUpdateRequest = {
name: formData.name,
slug: formData.slug,
subHeading: formData.subHeading,
description: formData.description,
categories: formData.categories
? formData.categories.split(",").map((c) => c.trim())
: [],
imageUrls: formData.imageUrls
? formData.imageUrls.split(",").map((u) => u.trim())
: [],
videoUrl: formData.videoUrl || null,
agentOutputDemoUrl: formData.agentOutputDemoUrl || null,
status: formData.status,
storeListingId: formData.storeListingId || null,
};
updateWaitlistMutation.mutate(
{ waitlistId: waitlist.id, data: updateData },
{
onSuccess: (response) => {
if (response.status === 200) {
toast({
title: "Success",
description: "Waitlist updated successfully",
});
onSave();
} else {
toast({
variant: "destructive",
title: "Error",
description: "Failed to update waitlist",
});
}
},
onError: () => {
toast({
variant: "destructive",
title: "Error",
description: "Failed to update waitlist",
});
},
},
);
}
return (
<Dialog
title="Edit Waitlist"
controlled={{
isOpen: true,
set: async (open) => {
if (!open) onClose();
},
}}
onClose={onClose}
styling={{ maxWidth: "600px" }}
>
<Dialog.Content>
<p className="mb-4 text-sm text-zinc-500">
Update the waitlist details. Changes will be reflected immediately.
</p>
<form onSubmit={handleSubmit} className="flex flex-col gap-2">
<Input
id="name"
label="Name"
value={formData.name}
onChange={(e) => handleInputChange("name", e.target.value)}
required
/>
<Input
id="slug"
label="Slug"
value={formData.slug}
onChange={(e) => handleInputChange("slug", e.target.value)}
/>
<Input
id="subHeading"
label="Subheading"
value={formData.subHeading}
onChange={(e) => handleInputChange("subHeading", e.target.value)}
required
/>
<Input
id="description"
label="Description"
type="textarea"
value={formData.description}
onChange={(e) => handleInputChange("description", e.target.value)}
rows={4}
required
/>
<Select
id="status"
label="Status"
value={formData.status}
onValueChange={handleStatusChange}
options={STATUS_OPTIONS}
/>
<Input
id="categories"
label="Categories (comma-separated)"
value={formData.categories}
onChange={(e) => handleInputChange("categories", e.target.value)}
/>
<Input
id="imageUrls"
label="Image URLs (comma-separated)"
value={formData.imageUrls}
onChange={(e) => handleInputChange("imageUrls", e.target.value)}
/>
<Input
id="videoUrl"
label="Video URL"
value={formData.videoUrl}
onChange={(e) => handleInputChange("videoUrl", e.target.value)}
/>
<Input
id="agentOutputDemoUrl"
label="Output Demo URL"
value={formData.agentOutputDemoUrl}
onChange={(e) =>
handleInputChange("agentOutputDemoUrl", e.target.value)
}
/>
<Input
id="storeListingId"
label="Store Listing ID (for linking)"
value={formData.storeListingId}
onChange={(e) =>
handleInputChange("storeListingId", e.target.value)
}
placeholder="Leave empty if not linked"
/>
<Dialog.Footer>
<Button type="button" variant="secondary" onClick={onClose}>
Cancel
</Button>
<Button type="submit" loading={updateWaitlistMutation.isPending}>
Save Changes
</Button>
</Dialog.Footer>
</form>
</Dialog.Content>
</Dialog>
);
}

View File

@@ -1,156 +0,0 @@
"use client";
import { Button } from "@/components/atoms/Button/Button";
import { Dialog } from "@/components/molecules/Dialog/Dialog";
import { User, Envelope, DownloadSimple } from "@phosphor-icons/react";
import { useGetV2GetWaitlistSignups } from "@/app/api/__generated__/endpoints/admin/admin";
type WaitlistSignupsDialogProps = {
waitlistId: string;
onClose: () => void;
};
export function WaitlistSignupsDialog({
waitlistId,
onClose,
}: WaitlistSignupsDialogProps) {
const {
data: signupsResponse,
isLoading,
isError,
} = useGetV2GetWaitlistSignups(waitlistId);
const signups = signupsResponse?.status === 200 ? signupsResponse.data : null;
function exportToCSV() {
if (!signups) return;
const headers = ["Type", "Email", "User ID", "Username"];
const rows = signups.signups.map((signup) => [
signup.type,
signup.email || "",
signup.userId || "",
signup.username || "",
]);
const escapeCell = (cell: string) => `"${cell.replace(/"/g, '""')}"`;
const csvContent = [
headers.join(","),
...rows.map((row) => row.map(escapeCell).join(",")),
].join("\n");
const blob = new Blob([csvContent], { type: "text/csv" });
const url = window.URL.createObjectURL(blob);
const a = document.createElement("a");
a.href = url;
a.download = `waitlist-${waitlistId}-signups.csv`;
a.click();
window.URL.revokeObjectURL(url);
}
function renderContent() {
if (isLoading) {
return <div className="py-10 text-center">Loading signups...</div>;
}
if (isError) {
return (
<div className="py-10 text-center text-red-500">
Failed to load signups. Please try again.
</div>
);
}
if (!signups || signups.signups.length === 0) {
return (
<div className="py-10 text-center text-gray-500">
No signups yet for this waitlist.
</div>
);
}
return (
<>
<div className="flex justify-end">
<Button variant="secondary" size="small" onClick={exportToCSV}>
<DownloadSimple className="mr-2 h-4 w-4" size={16} />
Export CSV
</Button>
</div>
<div className="max-h-[400px] overflow-y-auto rounded-md border">
<table className="w-full">
<thead className="bg-gray-50 dark:bg-gray-800">
<tr>
<th className="px-4 py-3 text-left text-sm font-medium">
Type
</th>
<th className="px-4 py-3 text-left text-sm font-medium">
Email / Username
</th>
<th className="px-4 py-3 text-left text-sm font-medium">
User ID
</th>
</tr>
</thead>
<tbody className="divide-y">
{signups.signups.map((signup, index) => (
<tr key={index}>
<td className="px-4 py-3">
{signup.type === "user" ? (
<span className="flex items-center gap-1 text-blue-600">
<User className="h-4 w-4" size={16} /> User
</span>
) : (
<span className="flex items-center gap-1 text-gray-600">
<Envelope className="h-4 w-4" size={16} /> Email
</span>
)}
</td>
<td className="px-4 py-3">
{signup.type === "user"
? signup.username || signup.email
: signup.email}
</td>
<td className="px-4 py-3 font-mono text-sm">
{signup.userId || "-"}
</td>
</tr>
))}
</tbody>
</table>
</div>
</>
);
}
return (
<Dialog
title="Waitlist Signups"
controlled={{
isOpen: true,
set: async (open) => {
if (!open) onClose();
},
}}
onClose={onClose}
styling={{ maxWidth: "700px" }}
>
<Dialog.Content>
<p className="mb-4 text-sm text-zinc-500">
{signups
? `${signups.totalCount} total signups`
: "Loading signups..."}
</p>
{renderContent()}
<Dialog.Footer>
<Button variant="secondary" onClick={onClose}>
Close
</Button>
</Dialog.Footer>
</Dialog.Content>
</Dialog>
);
}

View File

@@ -1,214 +0,0 @@
"use client";
import { useState } from "react";
import { useQueryClient } from "@tanstack/react-query";
import {
Table,
TableBody,
TableCell,
TableHead,
TableHeader,
TableRow,
} from "@/components/__legacy__/ui/table";
import { Button } from "@/components/atoms/Button/Button";
import {
useGetV2ListAllWaitlists,
useDeleteV2DeleteWaitlist,
getGetV2ListAllWaitlistsQueryKey,
} from "@/app/api/__generated__/endpoints/admin/admin";
import type { WaitlistAdminResponse } from "@/app/api/__generated__/models/waitlistAdminResponse";
import { EditWaitlistDialog } from "./EditWaitlistDialog";
import { WaitlistSignupsDialog } from "./WaitlistSignupsDialog";
import { Trash, PencilSimple, Users, Link } from "@phosphor-icons/react";
import { useToast } from "@/components/molecules/Toast/use-toast";
export function WaitlistTable() {
const [editingWaitlist, setEditingWaitlist] =
useState<WaitlistAdminResponse | null>(null);
const [viewingSignups, setViewingSignups] = useState<string | null>(null);
const { toast } = useToast();
const queryClient = useQueryClient();
const { data: response, isLoading, error } = useGetV2ListAllWaitlists();
const deleteWaitlistMutation = useDeleteV2DeleteWaitlist({
mutation: {
onSuccess: (response) => {
if (response.status === 200) {
toast({
title: "Success",
description: "Waitlist deleted successfully",
});
queryClient.invalidateQueries({
queryKey: getGetV2ListAllWaitlistsQueryKey(),
});
} else {
toast({
variant: "destructive",
title: "Error",
description: "Failed to delete waitlist",
});
}
},
onError: (error) => {
console.error("Error deleting waitlist:", error);
toast({
variant: "destructive",
title: "Error",
description: "Failed to delete waitlist",
});
},
},
});
function handleDelete(waitlistId: string) {
if (!confirm("Are you sure you want to delete this waitlist?")) return;
deleteWaitlistMutation.mutate({ waitlistId });
}
function handleWaitlistSaved() {
setEditingWaitlist(null);
queryClient.invalidateQueries({
queryKey: getGetV2ListAllWaitlistsQueryKey(),
});
}
function formatStatus(status: string) {
const statusColors: Record<string, string> = {
NOT_STARTED: "bg-gray-100 text-gray-800",
WORK_IN_PROGRESS: "bg-blue-100 text-blue-800",
DONE: "bg-green-100 text-green-800",
CANCELED: "bg-red-100 text-red-800",
};
return (
<span
className={`rounded-full px-2 py-1 text-xs font-medium ${statusColors[status] || "bg-gray-100 text-gray-700"}`}
>
{status.replace(/_/g, " ")}
</span>
);
}
function formatDate(dateStr: string) {
if (!dateStr) return "-";
return new Intl.DateTimeFormat("en-US", {
month: "short",
day: "numeric",
year: "numeric",
}).format(new Date(dateStr));
}
if (isLoading) {
return <div className="py-10 text-center">Loading waitlists...</div>;
}
if (error) {
return (
<div className="py-10 text-center text-red-500">
Error loading waitlists. Please try again.
</div>
);
}
const waitlists = response?.status === 200 ? response.data.waitlists : [];
if (waitlists.length === 0) {
return (
<div className="py-10 text-center text-gray-500">
No waitlists found. Create one to get started!
</div>
);
}
return (
<>
<div className="rounded-md border bg-white">
<Table>
<TableHeader className="bg-gray-50">
<TableRow>
<TableHead className="font-medium">Name</TableHead>
<TableHead className="font-medium">Status</TableHead>
<TableHead className="font-medium">Signups</TableHead>
<TableHead className="font-medium">Votes</TableHead>
<TableHead className="font-medium">Created</TableHead>
<TableHead className="font-medium">Linked Agent</TableHead>
<TableHead className="font-medium">Actions</TableHead>
</TableRow>
</TableHeader>
<TableBody>
{waitlists.map((waitlist) => (
<TableRow key={waitlist.id}>
<TableCell>
<div>
<div className="font-medium">{waitlist.name}</div>
<div className="text-sm text-gray-500">
{waitlist.subHeading}
</div>
</div>
</TableCell>
<TableCell>{formatStatus(waitlist.status)}</TableCell>
<TableCell>{waitlist.signupCount}</TableCell>
<TableCell>{waitlist.votes}</TableCell>
<TableCell>{formatDate(waitlist.createdAt)}</TableCell>
<TableCell>
{waitlist.storeListingId ? (
<span className="text-green-600">
<Link size={16} className="inline" /> Linked
</span>
) : (
<span className="text-gray-400">Not linked</span>
)}
</TableCell>
<TableCell>
<div className="flex gap-2">
<Button
variant="ghost"
size="small"
onClick={() => setViewingSignups(waitlist.id)}
title="View signups"
>
<Users size={16} />
</Button>
<Button
variant="ghost"
size="small"
onClick={() => setEditingWaitlist(waitlist)}
title="Edit"
>
<PencilSimple size={16} />
</Button>
<Button
variant="ghost"
size="small"
onClick={() => handleDelete(waitlist.id)}
title="Delete"
disabled={deleteWaitlistMutation.isPending}
>
<Trash size={16} className="text-red-500" />
</Button>
</div>
</TableCell>
</TableRow>
))}
</TableBody>
</Table>
</div>
{editingWaitlist && (
<EditWaitlistDialog
waitlist={editingWaitlist}
onClose={() => setEditingWaitlist(null)}
onSave={handleWaitlistSaved}
/>
)}
{viewingSignups && (
<WaitlistSignupsDialog
waitlistId={viewingSignups}
onClose={() => setViewingSignups(null)}
/>
)}
</>
);
}

View File

@@ -1,52 +0,0 @@
import { withRoleAccess } from "@/lib/withRoleAccess";
import { Suspense } from "react";
import { WaitlistTable } from "./components/WaitlistTable";
import { CreateWaitlistButton } from "./components/CreateWaitlistButton";
import { Warning } from "@phosphor-icons/react/dist/ssr";
function WaitlistDashboard() {
return (
<div className="mx-auto p-6">
<div className="flex flex-col gap-4">
<div className="flex items-center justify-between">
<div>
<h1 className="text-3xl font-bold">Waitlist Management</h1>
<p className="text-gray-500">
Manage upcoming agent waitlists and track signups
</p>
</div>
<CreateWaitlistButton />
</div>
<div className="flex items-start gap-3 rounded-lg border border-amber-300 bg-amber-50 p-4 dark:border-amber-700 dark:bg-amber-950">
<Warning
className="mt-0.5 h-5 w-5 flex-shrink-0 text-amber-600 dark:text-amber-400"
weight="fill"
/>
<div className="text-sm text-amber-800 dark:text-amber-200">
<p className="font-medium">TODO: Email-only signup notifications</p>
<p className="mt-1 text-amber-700 dark:text-amber-300">
Notifications for email-only signups (users who weren&apos;t
logged in) have not been implemented yet. Currently only
registered users will receive launch emails.
</p>
</div>
</div>
<Suspense
fallback={
<div className="py-10 text-center">Loading waitlists...</div>
}
>
<WaitlistTable />
</Suspense>
</div>
</div>
);
}
export default async function WaitlistDashboardPage() {
const withAdminAccess = await withRoleAccess(["admin"]);
const ProtectedWaitlistDashboard = await withAdminAccess(WaitlistDashboard);
return <ProtectedWaitlistDashboard />;
}

View File

@@ -8,7 +8,6 @@ import { useMainMarketplacePage } from "./useMainMarketplacePage";
import { FeaturedCreators } from "../FeaturedCreators/FeaturedCreators";
import { MainMarketplacePageLoading } from "../MainMarketplacePageLoading";
import { ErrorCard } from "@/components/molecules/ErrorCard/ErrorCard";
import { WaitlistSection } from "../WaitlistSection/WaitlistSection";
export const MainMarkeplacePage = () => {
const { featuredAgents, topAgents, featuredCreators, isLoading, hasError } =
@@ -47,10 +46,6 @@ export const MainMarkeplacePage = () => {
{/* 100px margin because our featured sections button are placed 40px below the container */}
<Separator className="mb-6 mt-24" />
{/* Waitlist Section - "Help Shape What's Next" */}
<WaitlistSection />
<Separator className="mb-6 mt-12" />
{topAgents && (
<AgentsSection sectionTitle="Top Agents" agents={topAgents.agents} />
)}

View File

@@ -1,105 +0,0 @@
"use client";
import Image from "next/image";
import { Button } from "@/components/atoms/Button/Button";
import { Check } from "@phosphor-icons/react";
interface WaitlistCardProps {
name: string;
subHeading: string;
description: string;
imageUrl: string | null;
isMember?: boolean;
onCardClick: () => void;
onJoinClick: (e: React.MouseEvent) => void;
}
export function WaitlistCard({
name,
subHeading,
description,
imageUrl,
isMember = false,
onCardClick,
onJoinClick,
}: WaitlistCardProps) {
function handleJoinClick(e: React.MouseEvent) {
e.stopPropagation();
onJoinClick(e);
}
return (
<div
className="flex h-[24rem] w-full max-w-md cursor-pointer flex-col items-start rounded-3xl bg-white transition-all duration-300 hover:shadow-lg dark:bg-zinc-900 dark:hover:shadow-gray-700"
onClick={onCardClick}
data-testid="waitlist-card"
role="button"
tabIndex={0}
aria-label={`${name} waitlist card`}
onKeyDown={(e) => {
if (e.key === "Enter" || e.key === " ") {
onCardClick();
}
}}
>
{/* Image Section */}
<div className="relative aspect-[2/1.2] w-full overflow-hidden rounded-large md:aspect-[2.17/1]">
{imageUrl ? (
<Image
src={imageUrl}
alt={`${name} preview image`}
fill
className="object-cover"
/>
) : (
<div className="flex h-full w-full items-center justify-center bg-gradient-to-br from-neutral-200 to-neutral-300 dark:from-neutral-700 dark:to-neutral-800">
<span className="text-4xl font-bold text-neutral-400 dark:text-neutral-500">
{name.charAt(0)}
</span>
</div>
)}
</div>
<div className="mt-3 flex w-full flex-1 flex-col px-4">
{/* Name and Subheading */}
<div className="flex w-full flex-col">
<h3 className="line-clamp-1 font-poppins text-xl font-semibold text-[#272727] dark:text-neutral-100">
{name}
</h3>
<p className="mt-1 line-clamp-1 text-sm text-neutral-500 dark:text-neutral-400">
{subHeading}
</p>
</div>
{/* Description */}
<div className="mt-2 flex w-full flex-col">
<p className="line-clamp-5 text-sm font-normal leading-relaxed text-neutral-600 dark:text-neutral-400">
{description}
</p>
</div>
<div className="flex-grow" />
{/* Join Waitlist Button */}
<div className="mt-4 w-full pb-4">
{isMember ? (
<Button
disabled
className="w-full rounded-full bg-green-600 text-white hover:bg-green-600 dark:bg-green-700 dark:hover:bg-green-700"
>
<Check className="mr-2" size={16} weight="bold" />
On the waitlist
</Button>
) : (
<Button
onClick={handleJoinClick}
className="w-full rounded-full bg-zinc-800 text-white hover:bg-zinc-700 dark:bg-zinc-700 dark:hover:bg-zinc-600"
>
Join waitlist
</Button>
)}
</div>
</div>
</div>
);
}

View File

@@ -1,356 +0,0 @@
"use client";
import { useState } from "react";
import Image from "next/image";
import { Button } from "@/components/atoms/Button/Button";
import { Dialog } from "@/components/molecules/Dialog/Dialog";
import { Input } from "@/components/atoms/Input/Input";
import {
Carousel,
CarouselContent,
CarouselItem,
CarouselNext,
CarouselPrevious,
} from "@/components/__legacy__/ui/carousel";
import type { StoreWaitlistEntry } from "@/app/api/__generated__/models/storeWaitlistEntry";
import { Check, Play } from "@phosphor-icons/react";
import { useSupabaseStore } from "@/lib/supabase/hooks/useSupabaseStore";
import { useToast } from "@/components/molecules/Toast/use-toast";
import { usePostV2AddSelfToTheAgentWaitlist } from "@/app/api/__generated__/endpoints/store/store";
interface MediaItem {
type: "image" | "video";
url: string;
label?: string;
}
// Extract YouTube video ID from various URL formats
function getYouTubeVideoId(url: string): string | null {
const regExp =
/^.*((youtu.be\/)|(v\/)|(\/u\/\w\/)|(embed\/)|(watch\?))\??v?=?([^#&?]*).*/;
const match = url.match(regExp);
return match && match[7].length === 11 ? match[7] : null;
}
// Validate video URL for security
function isValidVideoUrl(url: string): boolean {
if (url.startsWith("data:video")) {
return true;
}
const videoExtensions = /\.(mp4|webm|ogg)$/i;
const youtubeRegex = /^(https?:\/\/)?(www\.)?(youtube\.com|youtu\.?be)\/.+$/;
const validUrl = /^(https?:\/\/)/i;
const cleanedUrl = url.split("?")[0];
return (
(validUrl.test(url) && videoExtensions.test(cleanedUrl)) ||
youtubeRegex.test(url)
);
}
// Video player with YouTube embed support
function VideoPlayer({
url,
autoPlay = false,
className = "",
}: {
url: string;
autoPlay?: boolean;
className?: string;
}) {
const youtubeId = getYouTubeVideoId(url);
if (youtubeId) {
return (
<iframe
src={`https://www.youtube.com/embed/${youtubeId}${autoPlay ? "?autoplay=1" : ""}`}
title="YouTube video player"
className={className}
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
sandbox="allow-same-origin allow-scripts allow-presentation"
allowFullScreen
/>
);
}
if (!isValidVideoUrl(url)) {
return (
<div
className={`flex items-center justify-center bg-zinc-800 ${className}`}
>
<span className="text-sm text-zinc-400">Invalid video URL</span>
</div>
);
}
return <video src={url} controls autoPlay={autoPlay} className={className} />;
}
function MediaCarousel({ waitlist }: { waitlist: StoreWaitlistEntry }) {
const [activeVideo, setActiveVideo] = useState<string | null>(null);
// Build media items array: videos first, then images
const mediaItems: MediaItem[] = [
...(waitlist.videoUrl
? [{ type: "video" as const, url: waitlist.videoUrl, label: "Video" }]
: []),
...(waitlist.agentOutputDemoUrl
? [
{
type: "video" as const,
url: waitlist.agentOutputDemoUrl,
label: "Demo",
},
]
: []),
...waitlist.imageUrls.map((url) => ({ type: "image" as const, url })),
];
if (mediaItems.length === 0) return null;
// Single item - no carousel needed
if (mediaItems.length === 1) {
const item = mediaItems[0];
return (
<div className="relative aspect-[350/196] w-full overflow-hidden rounded-large">
{item.type === "image" ? (
<Image
src={item.url}
alt={`${waitlist.name} preview`}
fill
className="object-cover"
/>
) : (
<VideoPlayer url={item.url} className="h-full w-full object-cover" />
)}
</div>
);
}
// Multiple items - use carousel
return (
<Carousel className="w-full">
<CarouselContent>
{mediaItems.map((item, index) => (
<CarouselItem key={index}>
<div className="relative aspect-[350/196] w-full overflow-hidden rounded-large">
{item.type === "image" ? (
<Image
src={item.url}
alt={`${waitlist.name} preview ${index + 1}`}
fill
className="object-cover"
/>
) : activeVideo === item.url ? (
<VideoPlayer
url={item.url}
autoPlay
className="h-full w-full object-cover"
/>
) : (
<button
onClick={() => setActiveVideo(item.url)}
className="group relative h-full w-full bg-zinc-900"
>
<div className="absolute inset-0 flex items-center justify-center">
<div className="flex h-16 w-16 items-center justify-center rounded-full bg-white/90 transition-transform group-hover:scale-110">
<Play size={32} weight="fill" className="text-zinc-800" />
</div>
</div>
<span className="absolute bottom-3 left-3 text-sm text-white">
{item.label}
</span>
</button>
)}
</div>
</CarouselItem>
))}
</CarouselContent>
<CarouselPrevious className="left-2 top-1/2 -translate-y-1/2" />
<CarouselNext className="right-2 top-1/2 -translate-y-1/2" />
</Carousel>
);
}
interface WaitlistDetailModalProps {
waitlist: StoreWaitlistEntry;
isMember?: boolean;
onClose: () => void;
onJoinSuccess?: (waitlistId: string) => void;
}
export function WaitlistDetailModal({
waitlist,
isMember = false,
onClose,
onJoinSuccess,
}: WaitlistDetailModalProps) {
const { user } = useSupabaseStore();
const [email, setEmail] = useState("");
const [success, setSuccess] = useState(false);
const { toast } = useToast();
const joinWaitlistMutation = usePostV2AddSelfToTheAgentWaitlist();
function handleJoin() {
joinWaitlistMutation.mutate(
{
waitlistId: waitlist.waitlistId,
data: { email: user ? undefined : email },
},
{
onSuccess: (response) => {
if (response.status === 200) {
setSuccess(true);
toast({
title: "You're on the waitlist!",
description: `We'll notify you when ${waitlist.name} goes live.`,
});
onJoinSuccess?.(waitlist.waitlistId);
} else {
toast({
variant: "destructive",
title: "Error",
description: "Failed to join waitlist. Please try again.",
});
}
},
onError: () => {
toast({
variant: "destructive",
title: "Error",
description: "Failed to join waitlist. Please try again.",
});
},
},
);
}
// Success state
if (success) {
return (
<Dialog
title=""
controlled={{
isOpen: true,
set: async (open) => {
if (!open) onClose();
},
}}
onClose={onClose}
styling={{ maxWidth: "500px" }}
>
<Dialog.Content>
<div className="flex flex-col items-center justify-center py-4 text-center">
{/* Party emoji */}
<span className="mb-2 text-5xl">🎉</span>
{/* Title */}
<h2 className="mb-2 font-poppins text-[22px] font-medium leading-7 text-zinc-900 dark:text-zinc-100">
You&apos;re on the waitlist
</h2>
{/* Subtitle */}
<p className="text-base leading-[26px] text-zinc-600 dark:text-zinc-400">
Thanks for helping us prioritize which agents to build next.
We&apos;ll notify you when this agent goes live in the
marketplace.
</p>
</div>
{/* Close button */}
<Dialog.Footer className="flex justify-center pb-2 pt-4">
<Button
variant="secondary"
onClick={onClose}
className="rounded-full border border-zinc-700 bg-white px-4 py-3 text-zinc-900 hover:bg-zinc-100 dark:border-zinc-500 dark:bg-zinc-800 dark:text-zinc-100 dark:hover:bg-zinc-700"
>
Close
</Button>
</Dialog.Footer>
</Dialog.Content>
</Dialog>
);
}
// Main modal - handles both member and non-member states
return (
<Dialog
title="Join the waitlist"
controlled={{
isOpen: true,
set: async (open) => {
if (!open) onClose();
},
}}
onClose={onClose}
styling={{ maxWidth: "500px" }}
>
<Dialog.Content>
{/* Subtitle */}
<p className="mb-6 text-center text-base text-zinc-600 dark:text-zinc-400">
Help us decide what to build next and get notified when this agent
is ready
</p>
{/* Media Carousel */}
<MediaCarousel waitlist={waitlist} />
{/* Agent Name */}
<h3 className="mt-4 font-poppins text-[22px] font-medium leading-7 text-zinc-800 dark:text-zinc-100">
{waitlist.name}
</h3>
{/* Agent Description */}
<p className="mt-2 line-clamp-5 text-sm leading-[22px] text-zinc-500 dark:text-zinc-400">
{waitlist.description}
</p>
{/* Email input for non-logged-in users who haven't joined */}
{!isMember && !user && (
<div className="mt-4 pr-1">
<Input
id="email"
label="Email address"
type="email"
placeholder="you@example.com"
value={email}
onChange={(e) => setEmail(e.target.value)}
required
/>
</div>
)}
{/* Footer buttons */}
<Dialog.Footer className="sticky bottom-0 mt-6 flex justify-center gap-3 bg-white pb-2 pt-4 dark:bg-zinc-900">
{isMember ? (
<Button
disabled
className="rounded-full bg-green-600 px-4 py-3 text-white hover:bg-green-600 dark:bg-green-700 dark:hover:bg-green-700"
>
<Check size={16} className="mr-2" />
You&apos;re on the waitlist
</Button>
) : (
<>
<Button
onClick={handleJoin}
loading={joinWaitlistMutation.isPending}
disabled={!user && !email}
className="rounded-full bg-zinc-800 px-4 py-3 text-white hover:bg-zinc-700 dark:bg-zinc-700 dark:hover:bg-zinc-600"
>
Join waitlist
</Button>
<Button
type="button"
variant="secondary"
onClick={onClose}
className="rounded-full bg-zinc-200 px-4 py-3 text-zinc-900 hover:bg-zinc-300 dark:bg-zinc-700 dark:text-zinc-100 dark:hover:bg-zinc-600"
>
Not now
</Button>
</>
)}
</Dialog.Footer>
</Dialog.Content>
</Dialog>
);
}

View File

@@ -1,102 +0,0 @@
"use client";
import { useState } from "react";
import {
Carousel,
CarouselContent,
CarouselItem,
} from "@/components/__legacy__/ui/carousel";
import { WaitlistCard } from "../WaitlistCard/WaitlistCard";
import { WaitlistDetailModal } from "../WaitlistDetailModal/WaitlistDetailModal";
import type { StoreWaitlistEntry } from "@/app/api/__generated__/models/storeWaitlistEntry";
import { useWaitlistSection } from "./useWaitlistSection";
export function WaitlistSection() {
const { waitlists, joinedWaitlistIds, isLoading, hasError, markAsJoined } =
useWaitlistSection();
const [selectedWaitlist, setSelectedWaitlist] =
useState<StoreWaitlistEntry | null>(null);
function handleOpenModal(waitlist: StoreWaitlistEntry) {
setSelectedWaitlist(waitlist);
}
function handleJoinSuccess(waitlistId: string) {
markAsJoined(waitlistId);
}
// Don't render if loading, error, or no waitlists
if (isLoading || hasError || !waitlists || waitlists.length === 0) {
return null;
}
return (
<div className="flex flex-col items-center justify-center">
<div className="w-full max-w-[1360px]">
{/* Section Header */}
<div className="mb-6">
<h2 className="font-poppins text-2xl font-semibold text-[#282828] dark:text-neutral-200">
Help Shape What&apos;s Next
</h2>
<p className="mt-2 text-base text-neutral-600 dark:text-neutral-400">
These agents are in development. Your interest helps us prioritize
what gets built and we&apos;ll notify you when they&apos;re ready.
</p>
</div>
{/* Mobile Carousel View */}
<Carousel
className="md:hidden"
opts={{
loop: true,
}}
>
<CarouselContent>
{waitlists.map((waitlist) => (
<CarouselItem
key={waitlist.waitlistId}
className="min-w-64 max-w-71"
>
<WaitlistCard
name={waitlist.name}
subHeading={waitlist.subHeading}
description={waitlist.description}
imageUrl={waitlist.imageUrls[0] || null}
isMember={joinedWaitlistIds.has(waitlist.waitlistId)}
onCardClick={() => handleOpenModal(waitlist)}
onJoinClick={() => handleOpenModal(waitlist)}
/>
</CarouselItem>
))}
</CarouselContent>
</Carousel>
{/* Desktop Grid View */}
<div className="hidden grid-cols-1 place-items-center gap-6 md:grid md:grid-cols-2 lg:grid-cols-3">
{waitlists.map((waitlist) => (
<WaitlistCard
key={waitlist.waitlistId}
name={waitlist.name}
subHeading={waitlist.subHeading}
description={waitlist.description}
imageUrl={waitlist.imageUrls[0] || null}
isMember={joinedWaitlistIds.has(waitlist.waitlistId)}
onCardClick={() => handleOpenModal(waitlist)}
onJoinClick={() => handleOpenModal(waitlist)}
/>
))}
</div>
</div>
{/* Single Modal for both viewing and joining */}
{selectedWaitlist && (
<WaitlistDetailModal
waitlist={selectedWaitlist}
isMember={joinedWaitlistIds.has(selectedWaitlist.waitlistId)}
onClose={() => setSelectedWaitlist(null)}
onJoinSuccess={handleJoinSuccess}
/>
)}
</div>
);
}

View File

@@ -1,58 +0,0 @@
"use client";
import { useMemo } from "react";
import { useSupabaseStore } from "@/lib/supabase/hooks/useSupabaseStore";
import {
useGetV2GetTheAgentWaitlist,
useGetV2GetWaitlistIdsTheCurrentUserHasJoined,
getGetV2GetWaitlistIdsTheCurrentUserHasJoinedQueryKey,
} from "@/app/api/__generated__/endpoints/store/store";
import type { StoreWaitlistEntry } from "@/app/api/__generated__/models/storeWaitlistEntry";
import { useQueryClient } from "@tanstack/react-query";
export function useWaitlistSection() {
const { user } = useSupabaseStore();
const queryClient = useQueryClient();
// Fetch waitlists
const {
data: waitlistsResponse,
isLoading: waitlistsLoading,
isError: waitlistsError,
} = useGetV2GetTheAgentWaitlist();
// Fetch memberships if logged in
const { data: membershipsResponse, isLoading: membershipsLoading } =
useGetV2GetWaitlistIdsTheCurrentUserHasJoined({
query: {
enabled: !!user,
},
});
const waitlists: StoreWaitlistEntry[] = useMemo(() => {
if (waitlistsResponse?.status === 200) {
return waitlistsResponse.data.listings;
}
return [];
}, [waitlistsResponse]);
const joinedWaitlistIds: Set<string> = useMemo(() => {
if (membershipsResponse?.status === 200) {
return new Set(membershipsResponse.data);
}
return new Set();
}, [membershipsResponse]);
const isLoading = waitlistsLoading || (!!user && membershipsLoading);
const hasError = waitlistsError;
// Function to add a waitlist ID to joined set (called after successful join)
function markAsJoined(_waitlistId: string) {
// Invalidate the memberships query to refetch
queryClient.invalidateQueries({
queryKey: getGetV2GetWaitlistIdsTheCurrentUserHasJoinedQueryKey(),
});
}
return { waitlists, joinedWaitlistIds, isLoading, hasError, markAsJoined };
}

View File

@@ -53,8 +53,6 @@ export function getPaginationNextPageNumber(
if (!hasValidPaginationInfo(lastPage)) return undefined;
const { pagination } = lastPage.data;
if (!pagination) return undefined;
const hasMore =
pagination.current_page * pagination.page_size < pagination.total_items;
return hasMore ? pagination.current_page + 1 : undefined;

View File

@@ -5696,301 +5696,6 @@
}
}
},
"/api/store/admin/waitlist": {
"get": {
"tags": ["v2", "admin", "store", "admin", "waitlist"],
"summary": "List All Waitlists",
"description": "Get all waitlists with admin details (admin only).\n\nReturns:\n WaitlistAdminListResponse with all waitlists",
"operationId": "getV2List all waitlists",
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/WaitlistAdminListResponse"
}
}
}
},
"401": {
"$ref": "#/components/responses/HTTP401NotAuthenticatedError"
}
},
"security": [{ "HTTPBearerJWT": [] }]
},
"post": {
"tags": ["v2", "admin", "store", "admin", "waitlist"],
"summary": "Create Waitlist",
"description": "Create a new waitlist (admin only).\n\nArgs:\n request: Waitlist creation details\n user_id: Authenticated admin user creating the waitlist\n\nReturns:\n WaitlistAdminResponse with the created waitlist details",
"operationId": "postV2Create waitlist",
"requestBody": {
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/WaitlistCreateRequest" }
}
},
"required": true
},
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/WaitlistAdminResponse"
}
}
}
},
"401": {
"$ref": "#/components/responses/HTTP401NotAuthenticatedError"
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/HTTPValidationError" }
}
}
}
},
"security": [{ "HTTPBearerJWT": [] }]
}
},
"/api/store/admin/waitlist/{waitlist_id}": {
"delete": {
"tags": ["v2", "admin", "store", "admin", "waitlist"],
"summary": "Delete Waitlist",
"description": "Soft delete a waitlist (admin only).\n\nArgs:\n waitlist_id: ID of the waitlist to delete\n\nReturns:\n Success message",
"operationId": "deleteV2Delete waitlist",
"security": [{ "HTTPBearerJWT": [] }],
"parameters": [
{
"name": "waitlist_id",
"in": "path",
"required": true,
"schema": {
"type": "string",
"description": "The ID of the waitlist",
"title": "Waitlist Id"
},
"description": "The ID of the waitlist"
}
],
"responses": {
"200": {
"description": "Successful Response",
"content": { "application/json": { "schema": {} } }
},
"401": {
"$ref": "#/components/responses/HTTP401NotAuthenticatedError"
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/HTTPValidationError" }
}
}
}
}
},
"get": {
"tags": ["v2", "admin", "store", "admin", "waitlist"],
"summary": "Get Waitlist Details",
"description": "Get a single waitlist with admin details (admin only).\n\nArgs:\n waitlist_id: ID of the waitlist to retrieve\n\nReturns:\n WaitlistAdminResponse with waitlist details",
"operationId": "getV2Get waitlist details",
"security": [{ "HTTPBearerJWT": [] }],
"parameters": [
{
"name": "waitlist_id",
"in": "path",
"required": true,
"schema": {
"type": "string",
"description": "The ID of the waitlist",
"title": "Waitlist Id"
},
"description": "The ID of the waitlist"
}
],
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/WaitlistAdminResponse"
}
}
}
},
"401": {
"$ref": "#/components/responses/HTTP401NotAuthenticatedError"
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/HTTPValidationError" }
}
}
}
}
},
"put": {
"tags": ["v2", "admin", "store", "admin", "waitlist"],
"summary": "Update Waitlist",
"description": "Update a waitlist (admin only).\n\nArgs:\n waitlist_id: ID of the waitlist to update\n request: Fields to update\n\nReturns:\n WaitlistAdminResponse with updated waitlist details",
"operationId": "putV2Update waitlist",
"security": [{ "HTTPBearerJWT": [] }],
"parameters": [
{
"name": "waitlist_id",
"in": "path",
"required": true,
"schema": {
"type": "string",
"description": "The ID of the waitlist",
"title": "Waitlist Id"
},
"description": "The ID of the waitlist"
}
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/WaitlistUpdateRequest" }
}
}
},
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/WaitlistAdminResponse"
}
}
}
},
"401": {
"$ref": "#/components/responses/HTTP401NotAuthenticatedError"
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/HTTPValidationError" }
}
}
}
}
}
},
"/api/store/admin/waitlist/{waitlist_id}/link": {
"post": {
"tags": ["v2", "admin", "store", "admin", "waitlist"],
"summary": "Link Waitlist to Store Listing",
"description": "Link a waitlist to a store listing (admin only).\n\nWhen the linked store listing is approved/published, waitlist users\nwill be automatically notified.\n\nArgs:\n waitlist_id: ID of the waitlist\n store_listing_id: ID of the store listing to link\n\nReturns:\n WaitlistAdminResponse with updated waitlist details",
"operationId": "postV2Link waitlist to store listing",
"security": [{ "HTTPBearerJWT": [] }],
"parameters": [
{
"name": "waitlist_id",
"in": "path",
"required": true,
"schema": {
"type": "string",
"description": "The ID of the waitlist",
"title": "Waitlist Id"
},
"description": "The ID of the waitlist"
}
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Body_postV2Link_waitlist_to_store_listing"
}
}
}
},
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/WaitlistAdminResponse"
}
}
}
},
"401": {
"$ref": "#/components/responses/HTTP401NotAuthenticatedError"
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/HTTPValidationError" }
}
}
}
}
}
},
"/api/store/admin/waitlist/{waitlist_id}/signups": {
"get": {
"tags": ["v2", "admin", "store", "admin", "waitlist"],
"summary": "Get Waitlist Signups",
"description": "Get all signups for a waitlist (admin only).\n\nArgs:\n waitlist_id: ID of the waitlist\n\nReturns:\n WaitlistSignupListResponse with all signups",
"operationId": "getV2Get waitlist signups",
"security": [{ "HTTPBearerJWT": [] }],
"parameters": [
{
"name": "waitlist_id",
"in": "path",
"required": true,
"schema": {
"type": "string",
"description": "The ID of the waitlist",
"title": "Waitlist Id"
},
"description": "The ID of the waitlist"
}
],
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/WaitlistSignupListResponse"
}
}
}
},
"401": {
"$ref": "#/components/responses/HTTP401NotAuthenticatedError"
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/HTTPValidationError" }
}
}
}
}
}
},
"/api/store/agents": {
"get": {
"tags": ["v2", "store", "public"],
@@ -6838,101 +6543,6 @@
}
}
},
"/api/store/waitlist": {
"get": {
"tags": ["v2", "store", "public"],
"summary": "Get the agent waitlist",
"description": "Get all active waitlists for public display.",
"operationId": "getV2Get the agent waitlist",
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/StoreWaitlistsAllResponse"
}
}
}
}
}
}
},
"/api/store/waitlist/my-memberships": {
"get": {
"tags": ["v2", "store", "private"],
"summary": "Get waitlist IDs the current user has joined",
"description": "Returns list of waitlist IDs the authenticated user has joined.",
"operationId": "getV2Get waitlist ids the current user has joined",
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"items": { "type": "string" },
"type": "array",
"title": "Response Getv2Get Waitlist Ids The Current User Has Joined"
}
}
}
},
"401": {
"$ref": "#/components/responses/HTTP401NotAuthenticatedError"
}
},
"security": [{ "HTTPBearerJWT": [] }]
}
},
"/api/store/waitlist/{waitlist_id}/join": {
"post": {
"tags": ["v2", "store", "public"],
"summary": "Add self to the agent waitlist",
"description": "Add the current user to the agent waitlist.",
"operationId": "postV2Add self to the agent waitlist",
"security": [{ "HTTPBearer": [] }],
"parameters": [
{
"name": "waitlist_id",
"in": "path",
"required": true,
"schema": {
"type": "string",
"description": "The ID of the waitlist to join",
"title": "Waitlist Id"
},
"description": "The ID of the waitlist to join"
}
],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Body_postV2Add_self_to_the_agent_waitlist"
}
}
}
},
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/StoreWaitlistEntry" }
}
}
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": { "$ref": "#/components/schemas/HTTPValidationError" }
}
}
}
}
}
},
"/api/workspace/files/upload": {
"post": {
"tags": ["workspace"],
@@ -8293,20 +7903,6 @@
"required": ["store_listing_version_id"],
"title": "Body_postV2Add marketplace agent"
},
"Body_postV2Add_self_to_the_agent_waitlist": {
"properties": {
"email": {
"anyOf": [
{ "type": "string", "format": "email" },
{ "type": "null" }
],
"title": "Email",
"description": "Email address for unauthenticated users"
}
},
"type": "object",
"title": "Body_postV2Add self to the agent waitlist"
},
"Body_postV2Execute_a_preset": {
"properties": {
"inputs": {
@@ -8325,18 +7921,6 @@
"type": "object",
"title": "Body_postV2Execute a preset"
},
"Body_postV2Link_waitlist_to_store_listing": {
"properties": {
"store_listing_id": {
"type": "string",
"title": "Store Listing Id",
"description": "The ID of the store listing"
}
},
"type": "object",
"required": ["store_listing_id"],
"title": "Body_postV2Link waitlist to store listing"
},
"Body_postV2Upload_submission_media": {
"properties": {
"file": { "type": "string", "format": "binary", "title": "File" }
@@ -11001,8 +10585,7 @@
"REFUND_REQUEST",
"REFUND_PROCESSED",
"AGENT_APPROVED",
"AGENT_REJECTED",
"WAITLIST_LAUNCH"
"AGENT_REJECTED"
],
"title": "NotificationType"
},
@@ -12710,57 +12293,6 @@
"required": ["submissions", "pagination"],
"title": "StoreSubmissionsResponse"
},
"StoreWaitlistEntry": {
"properties": {
"waitlistId": { "type": "string", "title": "Waitlistid" },
"slug": { "type": "string", "title": "Slug" },
"name": { "type": "string", "title": "Name" },
"subHeading": { "type": "string", "title": "Subheading" },
"videoUrl": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Videourl"
},
"agentOutputDemoUrl": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Agentoutputdemourl"
},
"imageUrls": {
"items": { "type": "string" },
"type": "array",
"title": "Imageurls"
},
"description": { "type": "string", "title": "Description" },
"categories": {
"items": { "type": "string" },
"type": "array",
"title": "Categories"
}
},
"type": "object",
"required": [
"waitlistId",
"slug",
"name",
"subHeading",
"imageUrls",
"description",
"categories"
],
"title": "StoreWaitlistEntry",
"description": "Public waitlist entry - no PII fields exposed."
},
"StoreWaitlistsAllResponse": {
"properties": {
"listings": {
"items": { "$ref": "#/components/schemas/StoreWaitlistEntry" },
"type": "array",
"title": "Listings"
}
},
"type": "object",
"required": ["listings"],
"title": "StoreWaitlistsAllResponse"
},
"StreamChatRequest": {
"properties": {
"message": { "type": "string", "title": "Message" },
@@ -14656,203 +14188,6 @@
"required": ["loc", "msg", "type"],
"title": "ValidationError"
},
"WaitlistAdminListResponse": {
"properties": {
"waitlists": {
"items": { "$ref": "#/components/schemas/WaitlistAdminResponse" },
"type": "array",
"title": "Waitlists"
},
"totalCount": { "type": "integer", "title": "Totalcount" }
},
"type": "object",
"required": ["waitlists", "totalCount"],
"title": "WaitlistAdminListResponse",
"description": "Response model for listing all waitlists (admin view)."
},
"WaitlistAdminResponse": {
"properties": {
"id": { "type": "string", "title": "Id" },
"createdAt": { "type": "string", "title": "Createdat" },
"updatedAt": { "type": "string", "title": "Updatedat" },
"slug": { "type": "string", "title": "Slug" },
"name": { "type": "string", "title": "Name" },
"subHeading": { "type": "string", "title": "Subheading" },
"description": { "type": "string", "title": "Description" },
"categories": {
"items": { "type": "string" },
"type": "array",
"title": "Categories"
},
"imageUrls": {
"items": { "type": "string" },
"type": "array",
"title": "Imageurls"
},
"videoUrl": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Videourl"
},
"agentOutputDemoUrl": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Agentoutputdemourl"
},
"status": { "$ref": "#/components/schemas/WaitlistExternalStatus" },
"votes": { "type": "integer", "title": "Votes" },
"signupCount": { "type": "integer", "title": "Signupcount" },
"storeListingId": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Storelistingid"
},
"owningUserId": { "type": "string", "title": "Owninguserid" }
},
"type": "object",
"required": [
"id",
"createdAt",
"updatedAt",
"slug",
"name",
"subHeading",
"description",
"categories",
"imageUrls",
"status",
"votes",
"signupCount",
"owningUserId"
],
"title": "WaitlistAdminResponse",
"description": "Admin response model with full waitlist details including internal data."
},
"WaitlistCreateRequest": {
"properties": {
"name": { "type": "string", "title": "Name" },
"slug": { "type": "string", "title": "Slug" },
"subHeading": { "type": "string", "title": "Subheading" },
"description": { "type": "string", "title": "Description" },
"categories": {
"items": { "type": "string" },
"type": "array",
"title": "Categories",
"default": []
},
"imageUrls": {
"items": { "type": "string" },
"type": "array",
"title": "Imageurls",
"default": []
},
"videoUrl": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Videourl"
},
"agentOutputDemoUrl": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Agentoutputdemourl"
}
},
"type": "object",
"required": ["name", "slug", "subHeading", "description"],
"title": "WaitlistCreateRequest",
"description": "Request model for creating a new waitlist."
},
"WaitlistExternalStatus": {
"type": "string",
"enum": ["DONE", "NOT_STARTED", "CANCELED", "WORK_IN_PROGRESS"],
"title": "WaitlistExternalStatus"
},
"WaitlistSignup": {
"properties": {
"type": { "type": "string", "title": "Type" },
"userId": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Userid"
},
"email": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Email"
},
"username": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Username"
}
},
"type": "object",
"required": ["type"],
"title": "WaitlistSignup",
"description": "Individual signup entry for a waitlist."
},
"WaitlistSignupListResponse": {
"properties": {
"waitlistId": { "type": "string", "title": "Waitlistid" },
"signups": {
"items": { "$ref": "#/components/schemas/WaitlistSignup" },
"type": "array",
"title": "Signups"
},
"totalCount": { "type": "integer", "title": "Totalcount" }
},
"type": "object",
"required": ["waitlistId", "signups", "totalCount"],
"title": "WaitlistSignupListResponse",
"description": "Response model for listing waitlist signups."
},
"WaitlistUpdateRequest": {
"properties": {
"name": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Name"
},
"slug": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Slug"
},
"subHeading": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Subheading"
},
"description": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Description"
},
"categories": {
"anyOf": [
{ "items": { "type": "string" }, "type": "array" },
{ "type": "null" }
],
"title": "Categories"
},
"imageUrls": {
"anyOf": [
{ "items": { "type": "string" }, "type": "array" },
{ "type": "null" }
],
"title": "Imageurls"
},
"videoUrl": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Videourl"
},
"agentOutputDemoUrl": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Agentoutputdemourl"
},
"status": {
"anyOf": [
{ "$ref": "#/components/schemas/WaitlistExternalStatus" },
{ "type": "null" }
]
},
"storeListingId": {
"anyOf": [{ "type": "string" }, { "type": "null" }],
"title": "Storelistingid"
}
},
"type": "object",
"title": "WaitlistUpdateRequest",
"description": "Request model for updating a waitlist."
},
"Webhook": {
"properties": {
"id": { "type": "string", "title": "Id" },

View File

@@ -183,7 +183,7 @@ body[data-google-picker-open="true"] [data-dialog-content] {
/* Streamdown external link dialog: "Open link" button */
[data-streamdown="link-safety-modal"] button:last-of-type {
color: white;
color: black;
}
/* CoPilot chat table styling — remove left/right borders, increase padding */

View File

@@ -65,7 +65,7 @@ The result routes data to yes_output or no_output, enabling intelligent branchin
| condition | A plaintext English description of the condition to evaluate | str | Yes |
| yes_value | (Optional) Value to output if the condition is true. If not provided, input_value will be used. | Yes Value | No |
| no_value | (Optional) Value to output if the condition is false. If not provided, input_value will be used. | No Value | No |
| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
### Outputs
@@ -103,7 +103,7 @@ The block sends the entire conversation history to the chosen LLM, including sys
|-------|-------------|------|----------|
| prompt | The prompt to send to the language model. | str | No |
| messages | List of messages in the conversation. | List[Any] | Yes |
| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
| ollama_host | Ollama host for local models | str | No |
@@ -257,7 +257,7 @@ The block formulates a prompt based on the given focus or source data, sends it
|-------|-------------|------|----------|
| focus | The focus of the list to generate. | str | No |
| source_data | The data to generate the list from. | str | No |
| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| max_retries | Maximum number of retries for generating a valid list. | int | No |
| force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No |
| max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
@@ -424,7 +424,7 @@ The block sends the input prompt to a chosen LLM, along with any system prompts
| prompt | The prompt to send to the language model. | str | Yes |
| expected_format | Expected format of the response. If provided, the response will be validated against this format. The keys should be the expected fields in the response, and the values should be the description of the field. | Dict[str, str] | Yes |
| list_result | Whether the response should be a list of objects in the expected format. | bool | No |
| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No |
| sys_prompt | The system prompt to provide additional context to the model. | str | No |
| conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |
@@ -464,7 +464,7 @@ The block sends the input prompt to a chosen LLM, processes the response, and re
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| prompt | The prompt to send to the language model. You can use any of the {keys} from Prompt Values to fill in the prompt with values from the prompt values dictionary by putting them in curly braces. | str | Yes |
| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| sys_prompt | The system prompt to provide additional context to the model. | str | No |
| retry | Number of times to retry the LLM call if the response does not match the expected format. | int | No |
| prompt_values | Values used to fill in the prompt. The values can be used in the prompt by putting them in a double curly braces, e.g. {{variable_name}}. | Dict[str, str] | No |
@@ -501,7 +501,7 @@ The block splits the input text into smaller chunks, sends each chunk to an LLM
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| text | The text to summarize. | str | Yes |
| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| focus | The topic to focus on in the summary | str | No |
| style | The style of the summary to generate. | "concise" \| "detailed" \| "bullet points" \| "numbered list" | No |
| max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
@@ -763,7 +763,7 @@ Configure agent_mode_max_iterations to control loop behavior: 0 for single decis
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| prompt | The prompt to send to the language model. | str | Yes |
| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
| multiple_tool_calls | Whether to allow multiple tool calls in a single response. | bool | No |
| sys_prompt | The system prompt to provide additional context to the model. | str | No |
| conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |

View File

@@ -20,7 +20,7 @@ Configure timeouts for DOM settlement and page loading. Variables can be passed
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| browserbase_project_id | Browserbase project ID (required if using Browserbase) | str | Yes |
| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" \| "claude-sonnet-4-6" | No |
| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" | No |
| url | URL to navigate to. | str | Yes |
| action | Action to perform. Suggested actions are: click, fill, type, press, scroll, select from dropdown. For multi-step actions, add an entry for each step. | List[str] | Yes |
| variables | Variables to use in the action. Variables contains data you want the action to use. | Dict[str, str] | No |
@@ -65,7 +65,7 @@ Supports searching within iframes and configurable timeouts for dynamic content
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| browserbase_project_id | Browserbase project ID (required if using Browserbase) | str | Yes |
| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" \| "claude-sonnet-4-6" | No |
| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" | No |
| url | URL to navigate to. | str | Yes |
| instruction | Natural language description of elements or actions to discover. | str | Yes |
| iframes | Whether to search within iframes. If True, Stagehand will search for actions within iframes. | bool | No |
@@ -106,7 +106,7 @@ Use this to explore a page's interactive elements before building automated work
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| browserbase_project_id | Browserbase project ID (required if using Browserbase) | str | Yes |
| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" \| "claude-sonnet-4-6" | No |
| model | LLM to use for Stagehand (provider is inferred) | "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "claude-sonnet-4-5-20250929" | No |
| url | URL to navigate to. | str | Yes |
| instruction | Natural language description of elements or actions to discover. | str | Yes |
| iframes | Whether to search within iframes. If True, Stagehand will search for actions within iframes. | bool | No |