Compare commits

..

2 Commits

Author SHA1 Message Date
Zamil Majdy
3cfe2f384a fix(copilot): remove redundant success-path transcript upload
The success path always uploaded the resume file (old downloaded data),
then the finally block overwrote with the stop hook (new turn data).
With always-upload, this caused the smaller stop hook to overwrite
larger (but stale) data from the resume file. Remove the success path
upload — the finally block handles it correctly by preferring stop hook
content and falling back to the resume file when empty.
2026-03-06 12:45:12 +07:00
Zamil Majdy
fea6711ae7 fix(copilot): always upload transcript instead of size-based skip
The size comparison (existing >= new) prevented transcript uploads when
the CLI compacted old tool results via --resume, causing the stored
transcript to become permanently stale. Since the executor holds a
cluster lock per session, concurrent uploads cannot race — just always
overwrite.
2026-03-06 02:16:36 +07:00
6 changed files with 19 additions and 146 deletions

View File

@@ -187,11 +187,9 @@ class ClaudeCodeBlock(Block):
)
files: list[SandboxFileOutput] = SchemaField(
description=(
"List of files created/modified by Claude Code during this execution. "
"Includes text files and binary files (images, PDFs, etc.). "
"List of text files created/modified by Claude Code during this execution. "
"Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. "
"workspace_ref contains a workspace:// URI for workspace storage. "
"For binary files, content contains a placeholder; use workspace_ref to access the file."
"workspace_ref contains a workspace:// URI if the file was stored to workspace."
)
)
conversation_history: str = SchemaField(
@@ -454,15 +452,13 @@ class ClaudeCodeBlock(Block):
else:
new_conversation_history = turn_entry
# Extract files created/modified during this run and store to workspace.
# Binary files (images, PDFs, etc.) are stored via store_media_file
# which handles virus scanning and workspace storage.
# Extract files created/modified during this run and store to workspace
sandbox_files = await extract_and_store_sandbox_files(
sandbox=sandbox,
working_directory=working_directory,
execution_context=execution_context,
since_timestamp=start_timestamp,
text_only=False,
text_only=True,
)
return (

View File

@@ -1408,46 +1408,11 @@ 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
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),
)
)
# Transcript upload is handled in the finally block below — it
# correctly prefers the stop hook content (new turn data) over the
# resume file (old downloaded data). Uploading here would write
# stale data that the finally block then overwrites with potentially
# smaller (but newer) stop hook content.
logger.info(
"[SDK] [%s] Stream completed successfully with %d messages",

View File

@@ -74,50 +74,8 @@ TEXT_EXTENSIONS = {
".tex",
".csv",
".log",
".svg", # SVG is XML-based text
}
# Binary file extensions we explicitly support extracting
BINARY_EXTENSIONS = {
# Images
".png",
".jpg",
".jpeg",
".gif",
".webp",
".ico",
".bmp",
".tiff",
".tif",
# Documents
".pdf",
# Archives
".zip",
".tar",
".gz",
".7z",
# Audio
".mp3",
".wav",
".ogg",
".flac",
# Video
".mp4",
".webm",
".mov",
".avi",
# Fonts
".woff",
".woff2",
".ttf",
".otf",
".eot",
}
# Maximum file size for binary extraction (50MB)
# Prevents OOM from accidentally extracting huge files
MAX_BINARY_FILE_SIZE = 50 * 1024 * 1024
class SandboxFileOutput(BaseModel):
"""A file extracted from a sandbox and optionally stored in workspace."""
@@ -162,8 +120,7 @@ async def extract_sandbox_files(
sandbox: The E2B sandbox instance
working_directory: Directory to search for files
since_timestamp: ISO timestamp - only return files modified after this time
text_only: If True, only extract text files. If False, also extract
supported binary files (images, PDFs, etc.).
text_only: If True, only extract text files (default). If False, extract all files.
Returns:
List of ExtractedFile objects with path, content, and metadata
@@ -192,48 +149,15 @@ async def extract_sandbox_files(
if not file_path:
continue
# Check file type (case-insensitive for extensions)
file_path_lower = file_path.lower()
is_text = any(
file_path_lower.endswith(ext.lower()) for ext in TEXT_EXTENSIONS
)
is_binary = any(
file_path_lower.endswith(ext.lower()) for ext in BINARY_EXTENSIONS
)
# Check if it's a text file
is_text = any(file_path.endswith(ext) for ext in TEXT_EXTENSIONS)
# Skip files with unrecognized extensions
if not is_text and not is_binary:
continue
# In text_only mode, skip binary files
# Skip non-text files if text_only mode
if text_only and not is_text:
continue
try:
# Check file size before reading to prevent OOM
stat_result = await sandbox.commands.run(
f"stat -c %s {shlex.quote(file_path)} 2>/dev/null"
)
if stat_result.exit_code != 0 or not stat_result.stdout:
logger.debug(f"Skipping {file_path}: could not determine file size")
continue
try:
file_size = int(stat_result.stdout.strip())
except ValueError:
logger.debug(
f"Skipping {file_path}: unexpected stat output "
f"{stat_result.stdout.strip()!r}"
)
continue
if file_size > MAX_BINARY_FILE_SIZE:
logger.info(
f"Skipping {file_path}: size {file_size} bytes "
f"exceeds limit {MAX_BINARY_FILE_SIZE}"
)
continue
# Read file content as bytes
content = await sandbox.files.read(file_path, format="bytes")
if isinstance(content, str):
content = content.encode("utf-8")

View File

@@ -1,11 +1,10 @@
"use server";
import { postV1GetOrCreateUser } from "@/app/api/__generated__/endpoints/auth/auth";
import { getOnboardingStatus, resolveResponse } from "@/app/api/helpers";
import { getServerSupabase } from "@/lib/supabase/server/getServerSupabase";
import { signupFormSchema } from "@/types/auth";
import * as Sentry from "@sentry/nextjs";
import { isWaitlistError, logWaitlistError } from "../../api/auth/utils";
import { getOnboardingStatus } from "../../api/helpers";
export async function signup(
email: string,
@@ -58,17 +57,6 @@ export async function signup(
await supabase.auth.setSession(data.session);
}
try {
await resolveResponse(postV1GetOrCreateUser());
} catch (createUserError) {
console.error("Error creating user during signup:", createUserError);
Sentry.captureException(createUserError);
return {
success: false,
error: "Failed to complete account setup. Please try again.",
};
}
// Get onboarding status from backend (includes chat flag evaluated for this user)
const { shouldShowOnboarding } = await getOnboardingStatus();
const next = shouldShowOnboarding ? "/onboarding" : "/";

View File

@@ -16,7 +16,7 @@ When activated, the block:
- Install dependencies (npm, pip, etc.)
- Run terminal commands
- Build and test applications
5. Extracts all files created/modified during execution (text files and binary files like images, PDFs, etc.)
5. Extracts all text files created/modified during execution
6. Returns the response and files, optionally keeping the sandbox alive for follow-up tasks
The block supports conversation continuation through three mechanisms:
@@ -42,7 +42,7 @@ The block supports conversation continuation through three mechanisms:
| Output | Description |
|--------|-------------|
| Response | The output/response from Claude Code execution |
| Files | List of files (text and binary) created/modified during execution. Includes images, PDFs, and other supported formats. Each file has path, relative_path, name, content, and workspace_ref fields. Binary files are stored in workspace and accessible via workspace_ref |
| Files | List of text files created/modified during execution. Each file includes path, relative_path, name, and content fields |
| Conversation History | Full conversation history including this turn. Use to restore context on a fresh sandbox |
| Session ID | Session ID for this conversation. Pass back with sandbox_id to continue the conversation |
| Sandbox ID | ID of the sandbox instance (null if disposed). Pass back with session_id to continue the conversation |

View File

@@ -535,7 +535,7 @@ When activated, the block:
2. Installs the latest version of Claude Code in the sandbox
3. Optionally runs setup commands to prepare the environment
4. Executes your prompt using Claude Code, which can create/edit files, install dependencies, run terminal commands, and build applications
5. Extracts all files created/modified during execution (text files and binary files like images, PDFs, etc.)
5. Extracts all text files created/modified during execution
6. Returns the response and files, optionally keeping the sandbox alive for follow-up tasks
The block supports conversation continuation through three mechanisms:
@@ -563,7 +563,7 @@ The block supports conversation continuation through three mechanisms:
|--------|-------------|------|
| error | Error message if execution failed | str |
| response | The output/response from Claude Code execution | str |
| files | List of files created/modified by Claude Code during this execution. Includes text files and binary files (images, PDFs, etc.). Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. workspace_ref contains a workspace:// URI for workspace storage. For binary files, content contains a placeholder; use workspace_ref to access the file. | List[SandboxFileOutput] |
| files | List of text files created/modified by Claude Code during this execution. Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. workspace_ref contains a workspace:// URI if the file was stored to workspace. | List[SandboxFileOutput] |
| conversation_history | Full conversation history including this turn. Pass this to conversation_history input to continue on a fresh sandbox if the previous sandbox timed out. | str |
| session_id | Session ID for this conversation. Pass this back along with sandbox_id to continue the conversation. | str |
| sandbox_id | ID of the sandbox instance. Pass this back along with session_id to continue the conversation. This is None if dispose_sandbox was True (sandbox was disposed). | str |