mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-06-12 00:36:03 +00:00
feat(models): add provider model scanning (#2106)
* feat(models): add provider model scanning * fix: double close button * feat: update plugin module * fix(monitoring): WeChat Work feedback recording bugs (#2108) * fix(monitoring): fix WeChat Work feedback recording bugs - Fix feedback events silently dropped when stream session expires: dispatch feedback handlers regardless of session availability - Fix IntegrityError on repeated feedback (like→dislike) for same message: implement UPSERT logic in record_feedback() - Fix cancel feedback (type=3) not removing records: add delete logic - Fix inaccurate_reasons validation error: convert int reason codes to strings before creating FeedbackEvent (Pydantic expects List[str]) - Fix feedback timestamps 8 hours off in frontend: use parseUTCTimestamp instead of new Date() for UTC timestamp parsing - Fix StreamSessionManager.cleanup missing _feedback_index cleanup Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(monitoring): apply ruff format to wecom feedback files Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: 6mvp6 <13727783693@163.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * feat: add feat for receive files in wecombot * fix: ruff error * fix: always show sidebar plus buttons on touch/mobile devices (#2115) Agent-Logs-Url: https://github.com/langbot-app/LangBot/sessions/e27a4886-fbad-4a7a-8558-67a387852753 Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * fix: SPA fallback for all frontend routes, not just /home/* After migrating from Next.js to Vite SPA, routes like /auth/space/callback returned 404 because the static file server only had SPA fallback for /home/*. Now all non-API routes fall back to index.html for React Router to handle. * style: ruff format main.py * feat: add marketplace link when no parser available for file upload Links to /home/market?category=Parser, same pattern as knowledge engine selector. * fix: lint error * fix(user): allow password login and password change for Space accounts with local password set Previously, Space accounts were unconditionally blocked from password login and password change based on account_type. Now the check verifies whether the user actually has a local password set, allowing Space users who have set a local password to authenticate and change it normally. * feat: add edition field to telemetry payload Sends constants.edition (community/saas) with each telemetry event so Space can distinguish between community and SaaS instances. * style: ruff format telemetry.py * fix(dingtalk): use voice recognition text instead of raw audio binary When DingTalk sends a voice message to the bot, the callback JSON contains a 'recognition' field with the speech-to-text result (powered by Qwen). Previously, LangBot only extracted the 'downloadCode' to download the raw audio binary and passed it as 'file_base64' to LLM APIs, which caused 400 errors since most models don't support this content type. This patch: - Extracts the 'recognition' field from DingTalk audio message content - Uses it as plain text input to the LLM instead of raw audio - Falls back to audio binary only when no recognition text is available - Fixes duplicate text issue for audio messages with recognition Fixes voice messages returning 'Request failed' on all LLM models. * feat: integrate Alembic for database migrations Replace manual if-sqlite/if-postgres branching with Alembic: - Add alembic dependency - Create programmatic alembic env (no CLI/alembic.ini needed) - Support async engines via run_sync passthrough - render_as_batch=True for SQLite ALTER TABLE compatibility - Auto-stamp baseline on first run (existing DB at version 25) - Run alembic upgrade head after legacy migrations - Include sample migration showing schema + data migration patterns - Add alembic dir to package-data for distribution * ci: add migration test workflow for SQLite and PostgreSQL Tests alembic upgrade on both databases: - Stamp baseline on existing schema - Upgrade to head - Idempotent re-upgrade - Fresh DB upgrade from scratch * feat: add autogenerate support and CLI entrypoint for alembic - autogenerate: compare ORM models vs DB schema to generate migrations - CLI: python -m langbot.pkg.persistence.alembic_runner <command> - autogenerate, upgrade, stamp, current - Reads data/config.yaml for DB connection * fix: add filereader for dingtalk,lark (#2122) * fix: add filereader for dingtalk * feat: add lark * feat: update uv.lock * chore: update version to 4.9.6 in pyproject.toml, __init__.py, and uv.lock * fix: update langbot-plugin version to 0.3.8 * fix: update langbot-plugin version to 0.3.8 * docs: update database migration instructions in AGENTS.md * fix(dashscopeapi): fix null value check in reasoning content processing logic (#2128) * fix(n8n-runner): fix output_key not applied when n8n returns plain JSON (#2119) * fix: bump dependencies to resolve Dependabot security alerts (#2130) * fix: bump dependencies to resolve Dependabot security alerts Python: - aiohttp: >=3.11.18 → >=3.13.4 (duplicate Host headers, header injection, redirect leak, multipart DoS) - cryptography: >=44.0.3 → >=46.0.7 (buffer overflow with non-contiguous buffers) - pillow: >=11.2.1 → >=12.2.0 (FITS GZIP decompression bomb, HIGH) - langchain-text-splitters: >=0.0.1 → >=1.1.2 (SSRF redirect bypass) - langchain-core: add >=1.2.28 (incomplete f-string validation) - langsmith: add >=0.7.31 (streaming token redaction bypass) - python-multipart: add >=0.0.26 (multipart DoS) - Mako: add >=1.3.11 (path traversal) - pytest: >=8.4.1 → >=9.0.3 (tmpdir handling) - uv: >=0.7.11 → >=0.11.6 (arbitrary file deletion) JavaScript (web/): - vite: ^8.0.3 → ^8.0.5 (fs.deny bypass, WebSocket file read, path traversal, HIGH) - axios: ^1.13.5 → ^1.15.0 (cloud metadata exfiltration) - lodash: ^4.17.23 → ^4.18.0 (code injection via _.template, prototype pollution, HIGH) * fix: update pnpm-lock.yaml for bumped dependencies * feat(ci): add i18n key consistency check for frontend locales (#2133) * feat(ci): add i18n key consistency check workflow Agent-Logs-Url: https://github.com/langbot-app/LangBot/sessions/c7bf50da-189b-49a5-9671-dbe8e70ff9d0 Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * feat(ci): replace eval with line-by-line parser, add permissions block Agent-Logs-Url: https://github.com/langbot-app/LangBot/sessions/c7bf50da-189b-49a5-9671-dbe8e70ff9d0 Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * feat(models): add provider model scanning * feat(models): add 'select all' functionality and enrich model abilities * fix:ruff * fix:ruff --------- Co-authored-by: WangCham <651122857@qq.com> Co-authored-by: 6mvp6 <119733319+6mvp6@users.noreply.github.com> Co-authored-by: 6mvp6 <13727783693@163.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Guanchao Wang <wangcham233@gmail.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> Co-authored-by: RockChinQ <rockchinq@gmail.com> Co-authored-by: haiyangbg <zhouhaiyangaa@gmail.com> Co-authored-by: Rock Chin <1010553892@qq.com> Co-authored-by: Amadeus <115918672+AmadeusKurisu1@users.noreply.github.com> Co-authored-by: hzhhong <hung.z.h916@gmail.com> Co-authored-by: fdc310 <2213070223@qq.com>
This commit is contained in:
sheetung
@@ -31,6 +31,175 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
|
||||
http_client=httpx.AsyncClient(trust_env=True, timeout=self.requester_cfg['timeout']),
|
||||
)
|
||||
|
||||
def _mask_api_key(self, api_key: str | None) -> str:
|
||||
if not api_key:
|
||||
return ''
|
||||
if len(api_key) <= 8:
|
||||
return '****'
|
||||
return f'{api_key[:4]}...{api_key[-4:]}'
|
||||
|
||||
def _infer_model_type(self, model_id: str) -> str:
|
||||
normalized_model_id = (model_id or '').lower()
|
||||
embedding_keywords = (
|
||||
'embedding',
|
||||
'embed',
|
||||
'bge-',
|
||||
'e5-',
|
||||
'm3e',
|
||||
'gte-',
|
||||
'multilingual-e5',
|
||||
'text-embedding',
|
||||
)
|
||||
return 'embedding' if any(keyword in normalized_model_id for keyword in embedding_keywords) else 'llm'
|
||||
|
||||
def _infer_model_abilities(self, item: dict[str, typing.Any], model_id: str) -> list[str]:
|
||||
normalized_model_id = (model_id or '').lower()
|
||||
abilities: set[str] = set()
|
||||
|
||||
def _flatten(value: typing.Any) -> list[str]:
|
||||
if value is None:
|
||||
return []
|
||||
if isinstance(value, str):
|
||||
return [value.lower()]
|
||||
if isinstance(value, dict):
|
||||
flattened: list[str] = []
|
||||
for nested_value in value.values():
|
||||
flattened.extend(_flatten(nested_value))
|
||||
return flattened
|
||||
if isinstance(value, (list, tuple, set)):
|
||||
flattened: list[str] = []
|
||||
for nested_value in value:
|
||||
flattened.extend(_flatten(nested_value))
|
||||
return flattened
|
||||
return [str(value).lower()]
|
||||
|
||||
capability_tokens = _flatten(item.get('capabilities'))
|
||||
capability_tokens.extend(_flatten(item.get('modalities')))
|
||||
capability_tokens.extend(_flatten(item.get('input_modalities')))
|
||||
capability_tokens.extend(_flatten(item.get('output_modalities')))
|
||||
capability_tokens.extend(_flatten(item.get('supported_generation_methods')))
|
||||
capability_tokens.extend(_flatten(item.get('supported_parameters')))
|
||||
capability_tokens.extend(_flatten(item.get('architecture')))
|
||||
|
||||
combined_tokens = capability_tokens + [normalized_model_id]
|
||||
|
||||
vision_keywords = ('vision', 'image', 'file', 'video', 'multimodal', 'vl', 'ocr', 'omni')
|
||||
function_call_keywords = ('function', 'tool', 'tools', 'tool_choice', 'tool_call', 'tool-use', 'tool_use')
|
||||
|
||||
if any(any(keyword in token for keyword in vision_keywords) for token in combined_tokens):
|
||||
abilities.add('vision')
|
||||
|
||||
if any(any(keyword in token for keyword in function_call_keywords) for token in combined_tokens):
|
||||
abilities.add('func_call')
|
||||
|
||||
return sorted(abilities)
|
||||
|
||||
def _normalize_modalities(self, value: typing.Any) -> list[str]:
|
||||
normalized: list[str] = []
|
||||
|
||||
def _collect(item: typing.Any):
|
||||
if item is None:
|
||||
return
|
||||
if isinstance(item, str):
|
||||
for part in item.replace('->', ',').replace('+', ',').split(','):
|
||||
token = part.strip().lower()
|
||||
if token and token not in normalized:
|
||||
normalized.append(token)
|
||||
return
|
||||
if isinstance(item, dict):
|
||||
for nested in item.values():
|
||||
_collect(nested)
|
||||
return
|
||||
if isinstance(item, (list, tuple, set)):
|
||||
for nested in item:
|
||||
_collect(nested)
|
||||
return
|
||||
|
||||
_collect(value)
|
||||
return normalized
|
||||
|
||||
def _extract_scan_metadata(self, item: dict[str, typing.Any], model_id: str) -> dict[str, typing.Any]:
|
||||
display_name = item.get('name')
|
||||
if not isinstance(display_name, str) or not display_name.strip() or display_name == model_id:
|
||||
display_name = ''
|
||||
|
||||
description = item.get('description')
|
||||
if not isinstance(description, str) or not description.strip():
|
||||
description = ''
|
||||
|
||||
context_length = item.get('context_length')
|
||||
if context_length is None and isinstance(item.get('top_provider'), dict):
|
||||
context_length = item['top_provider'].get('context_length')
|
||||
|
||||
if not isinstance(context_length, int):
|
||||
try:
|
||||
context_length = int(context_length) if context_length is not None else None
|
||||
except (TypeError, ValueError):
|
||||
context_length = None
|
||||
|
||||
input_modalities = self._normalize_modalities(item.get('input_modalities'))
|
||||
output_modalities = self._normalize_modalities(item.get('output_modalities'))
|
||||
|
||||
if isinstance(item.get('architecture'), dict):
|
||||
if not input_modalities:
|
||||
input_modalities = self._normalize_modalities(item['architecture'].get('input_modalities'))
|
||||
if not output_modalities:
|
||||
output_modalities = self._normalize_modalities(item['architecture'].get('output_modalities'))
|
||||
|
||||
owned_by = item.get('owned_by')
|
||||
if not isinstance(owned_by, str) or not owned_by.strip():
|
||||
owned_by = ''
|
||||
|
||||
return {
|
||||
'display_name': display_name or None,
|
||||
'description': description or None,
|
||||
'context_length': context_length,
|
||||
'owned_by': owned_by or None,
|
||||
'input_modalities': input_modalities,
|
||||
'output_modalities': output_modalities,
|
||||
}
|
||||
|
||||
async def scan_models(self, api_key: str | None = None) -> dict[str, typing.Any]:
|
||||
headers = {}
|
||||
if api_key:
|
||||
headers['Authorization'] = f'Bearer {api_key}'
|
||||
|
||||
models_url = f'{self.requester_cfg["base_url"].rstrip("/")}/models'
|
||||
async with httpx.AsyncClient(trust_env=True, timeout=self.requester_cfg['timeout']) as client:
|
||||
response = await client.get(models_url, headers=headers)
|
||||
response.raise_for_status()
|
||||
payload = response.json()
|
||||
|
||||
models = []
|
||||
for item in payload.get('data', []):
|
||||
model_id = item.get('id')
|
||||
if not model_id:
|
||||
continue
|
||||
models.append(
|
||||
{
|
||||
'id': model_id,
|
||||
'name': model_id,
|
||||
'type': self._infer_model_type(model_id),
|
||||
'abilities': self._infer_model_abilities(item, model_id),
|
||||
**self._extract_scan_metadata(item, model_id),
|
||||
}
|
||||
)
|
||||
|
||||
models.sort(key=lambda item: (item['type'] != 'llm', item['name'].lower()))
|
||||
return {
|
||||
'models': models,
|
||||
'debug': {
|
||||
'request': {
|
||||
'method': 'GET',
|
||||
'url': models_url,
|
||||
'headers': {
|
||||
'Authorization': f'Bearer {self._mask_api_key(api_key)}' if api_key else '',
|
||||
},
|
||||
},
|
||||
'response': payload,
|
||||
},
|
||||
}
|
||||
|
||||
async def _req(
|
||||
self,
|
||||
query: pipeline_query.Query,
|
||||
|
||||
Reference in New Issue
Block a user