fix(agent-chat): streaming state leak, document parser magic bytes, HITL flow
### Bugfixes — Agent Chat 'Думаю' State Leak - fix(agent-chat): loadHistory() now resets streamingState/idle + cancels stale submission — prevents 'Думаю' state leak across conversation switches - fix(agent-chat): onDisconnected/onDisconnectedPermanent cascade to streamingState — prevents permanent hang on connection loss during stream - fix(agent-chat): guard on isLoadingHistory — prevents false commit of 'agent unavailable' fallback when switching conversations - fix(agent-chat): remove race in _sendNow empty-response check vs Svelte microtask (duplicate logic removed, handles correctly) - fix(stream-processor): confirm_resolved now appends msg.text to partialText instead of dropping it ### Bugfixes — Backend PDF Upload - fix(document-parser): _detect_format_by_magic() — reads file header magic bytes as fallback when Gradio loses filename - fix(document-parser): improved name extraction — tries orig_name, path stem - fix(document-parser): @RELATION AgentChatTypes -> AgentChat.Types ### HITL Flow & Agent Chat Improvements - feat(agent): HITL resume confirm/deny with userId/userJwt/envId propagation - feat(agent): confirm_required metadata fallback via aget_state() after 'Event loop is closed' error during interrupt - feat(agent): interrupt_before re-enabled via AGENT_CONFIRM_TOOLS env var - feat(frontend): debug panel with connection/stream state monitoring - feat(frontend): AgentChatModel constructor options + onBeforeSend callback - feat(frontend): crypto.randomUUID() for local conversation ID on first send ### Backend Agent Refactoring - refactor(agent): langgraph_setup — monkey-patch for PydanticSerializationError - refactor(agent): tools.py — dual identity headers, expanded tool set - refactor(agent): run.py — _find_free_port, Gradio server port fallback - refactor(agent): app.py — file size validation, message truncation, HITL path ### Frontend - feat(dashboard-hub): DashboardHubModel with filters, pagination, git actions - feat(ui): DateRangeFilter component - feat(i18n): new dashboard keys; cache tooltips fix - fix(i18n): full run tooltips — cache is NOT ignored ### Semantic Protocol - chore(agents): update all agents with canonical format - chore(skills): sync semantics-core, semantics-contracts, molecular-cot-logging ### Housekeeping - chore: remove stale semantic reports (10 files, Jan 2026) - chore: update 033-gradio-agent-chat specs, contracts, UX, tasks, tests - chore: add .agents/ directory (mirrors .opencode/ agent layouts) - chore: update run.sh with DEV_MODE, port management
This commit is contained in:
@@ -61,8 +61,27 @@ def parse_xlsx(file_path: str) -> str:
|
||||
raise ParseError(f"Failed to parse XLSX: {e}") from e
|
||||
|
||||
|
||||
def _detect_format_by_magic(path: str) -> str | None:
|
||||
"""Detect file format by reading magic bytes. Returns extension or None."""
|
||||
try:
|
||||
with open(path, "rb") as f:
|
||||
header = f.read(8)
|
||||
except OSError:
|
||||
return None
|
||||
|
||||
if header[:4] == b"%PDF":
|
||||
return ".pdf"
|
||||
if header[:4] == b"PK\x03\x04":
|
||||
# ZIP-based: XLSX, DOCX, etc. Try XLSX first.
|
||||
return ".xlsx"
|
||||
if header[:1] in (b"{", b"["):
|
||||
return ".json"
|
||||
# CSV often starts with text characters; safe fallback
|
||||
return None
|
||||
|
||||
|
||||
def parse_upload(file_data) -> str:
|
||||
"""Parse an uploaded file based on its extension.
|
||||
"""Parse an uploaded file based on its extension with magic-byte fallback.
|
||||
|
||||
Args:
|
||||
file_data: str (file path) or dict with "name" and "path"/"file_path" keys.
|
||||
@@ -71,9 +90,19 @@ def parse_upload(file_data) -> str:
|
||||
path = file_data
|
||||
name = Path(path).name
|
||||
else:
|
||||
name = file_data.get("name", "")
|
||||
path = file_data.get("path", file_data.get("file_path", ""))
|
||||
name = file_data.get("name") or file_data.get("orig_name", "")
|
||||
path = file_data.get("path") or file_data.get("file_path", "")
|
||||
# Gradio sometimes sends files without 'name' key — fall back to path stem
|
||||
if not name and path:
|
||||
name = Path(path).name
|
||||
ext = Path(name).suffix.lower()
|
||||
# Double fallback: if name has no extension, try the physical file path
|
||||
if not ext and path:
|
||||
ext = Path(path).suffix.lower()
|
||||
|
||||
# Triple fallback: detect by magic bytes (Gradio ChatInterface loses filename)
|
||||
if not ext and path:
|
||||
ext = _detect_format_by_magic(path)
|
||||
|
||||
if ext == ".pdf":
|
||||
return parse_pdf(path)
|
||||
@@ -82,6 +111,19 @@ def parse_upload(file_data) -> str:
|
||||
elif ext in (".json", ".csv", ".txt"):
|
||||
with open(path, encoding="utf-8", errors="replace") as f:
|
||||
return f.read(100_000) # truncate at ~100k chars
|
||||
elif ext is None:
|
||||
# Magic bytes detection returned None — unknown binary, try as text
|
||||
try:
|
||||
with open(path, encoding="utf-8", errors="replace") as f:
|
||||
return f.read(100_000)
|
||||
except Exception as e:
|
||||
raise ParseError(
|
||||
f"Could not detect file format for '{name}'. "
|
||||
f"Supported: PDF, XLSX, JSON, CSV, TXT"
|
||||
) from e
|
||||
else:
|
||||
raise ParseError(f"Unsupported format: {ext}. Supported: PDF, XLSX, JSON, CSV, TXT")
|
||||
raise ParseError(
|
||||
f"Unsupported format: '{ext}' (file: {name}). "
|
||||
f"Supported: PDF, XLSX, JSON, CSV, TXT"
|
||||
)
|
||||
# #endregion AgentChat.Document.Parser
|
||||
|
||||
Reference in New Issue
Block a user