* fix(tools): require python3 for Box native file scripts
Unversioned `python` is still Python 2 on some host-rootfs nsjail
mounts. Falling back to it made read/write/edit scripts fail with
SyntaxError on f-strings (#2603).
Resolve only `python3`, and return a clear JSON error when it is
missing instead of invoking Python 2.
Fixes#2603
* style(tools): format Box interpreter error command
Co-authored-by: multica-agent <[email protected]>
---------
Co-authored-by: Li-john1021 <[email protected]>
Co-authored-by: Chin Rock <[email protected]>
Co-authored-by: multica-agent <[email protected]>
Use the chat provider to apply transport-specific metadata cleanup.
Keep finish_reason removal in the common message conversion path.
Verify streaming and non-streaming HTTP payloads through LiteLLM,
metadata preservation for other providers, and source message immutability.
Remove response-only finish_reason metadata when converting stored messages
into subsequent model requests.
Strip provider_specific_fields from Groq messages and tool calls to avoid
strict request validation failures after a tool response. Preserve metadata
required by other providers, including Gemini thought signatures, without
mutating the original message entities.
Cover streaming and non-streaming request construction with regression tests.
Core no longer assembles a whole trace locally. Every workflow node is uploaded
the moment it completes as its own `execution_node` record, and each execution
closes with exactly one `execution_chain` record; all records of one execution
carry the same `event_id`, so Space groups them back into a single chain.
- every execution starts at an inbound event: event-less Pipeline lanes and
WebUI/API debug runs synthesize their virtual inbound event at the boundary
and are marked debug=true, so a Runner is never a trace origin
- sampling is decided once per event from a stable hash of the event id (the
previous `int(id[:8], 16)` raised on every `platform:`-prefixed id and so
dropped every successful inbound-event chain) and is reported on each record
as sample{mode,denominator}; the default mode is now `all`
- the local trace buffer, the 120s TTL, the per-process trace cap and the shared
open-node mirror are gone, which also removes the truncated-chain upload and
the re-buffered-closed-trace leak they caused
- a broken chain is always uploaded, and its reason falls back to the first
failed node so the chain explains itself
- flush keeps records until the sender accepts them and counts what it drops;
telemetry health replaces the unused send-task queue
- heartbeat reports bound Agent / plugin-processor / event-binding counts
- bound Pipeline and Agent resources (plugins, MCP servers, knowledge bases,
tools with their Host source, skills, models and the Runner schema selectors
that picked them) are reported on the chain record
- failure text is bounded and redacted instead of passing exception text through
- the dead per-query feature counters and their call sites are removed
Wire contract: schema 2 (`execution_node` / `execution_chain`).
scan_skill_directory is disabled for Cloud-managed sandboxes, but the
register_skill tool was still advertised to the model whenever a backend was
available, so every call failed closed without a usable explanation. Advertise
register_skill only when the runtime may scan sandbox directories, and keep
activate available in both modes.
The workspace file tools (read/write/edit/glob/grep) ran a script through
`python`, which a sandbox built from a host rootfs may not provide: those hosts
ship `python3` only, and a read-only /usr prevents creating a `python` shim
inside the jail. Every file tool then failed with `/bin/sh: 1: python: not
found`. Resolve the interpreter with `command -v python3 || command -v python`,
matching the interpreter the Box service already uses for its own scripts.
* fix(runner): align SDK pin and workspace-aware integration fixtures
* fix(ci): format sources and resolve current migration head
* test(persistence): align standalone migration fixtures with current models
* test(web): align smoke fixtures with current processor UI
---------
Co-authored-by: dadachann <[email protected]>
* feat(mcp): surface OAuth-required server tests
* fix(mcp): show connection failure details in status cards
---------
Co-authored-by: RockChinQ <[email protected]>
The Ollama requester declared litellm_provider: ollama, which routes
every request through litellm's legacy /api/generate-based
OllamaConfig. That config's get_supported_openai_params() does not
include "tools"/"tool_choice" at all, so an Ollama-hosted model in a
local-agent pipeline could never receive a structured tool definition
or return a structured tool_calls response - it could only try to
express a tool call as free text (typically inside its own <think>
reasoning), which LangBot then has no way to execute.
litellm's "ollama_chat" provider targets Ollama's modern /api/chat
endpoint instead, which correctly forwards tools/tool_choice and
correctly surfaces the model's native message.tool_calls field.
Verified against a real local Ollama 0.33.2 instance with the exact
system prompt, RAG-augmented user message, and tool set a live
pipeline sends.
Two follow-on fixes needed because the Ollama requester definition is
shared by LLM and text-embedding models:
- get_reasoning_capabilities: match family in ('ollama', 'ollama_chat')
so the reasoning-level UI still works for this provider.
- scan_models: retry {base_url}/v1/models on a 404 from {base_url}/models,
since Ollama's base_url is a bare host (must not include /v1 - that
would break OllamaChatConfig.get_complete_url, which appends /api/chat
to it directly), unlike most other OpenAI-compatible providers whose
base_url already ends in /v1.
- invoke_embedding: litellm's embedding routing has no "ollama_chat"
case, only "ollama". Build the embedding model name with an explicit
custom_llm_provider="ollama" override when the requester is configured
for ollama_chat, so embedding models (e.g. bge-m3) keep working.
Co-authored-by: zx90316 <[email protected]>
execute_func_call returns list[ContentElement] for MCP tools, but the
runner assigned that list directly to the tool-message content. The
OpenAI chat-completions spec requires tool-message content to be a
string, so OpenAI-compatible endpoints return HTTP 500 when the raw
list is sent.
Serialize the list to a string before building the tool message, using
ContentElement.__str__ which returns the text payload for text elements
and a human-readable placeholder for images and files. Fixes#2457.
SessionManager clears image_base64 on past turns to save memory, and
exclude_none serialization drops the hollowed field entirely, so a
replayed history part can arrive as {'type': 'image_base64'} with no
payload. The converter accessed the missing key unconditionally and
raised KeyError on every turn after an image was sent.
Prefer the base64 payload when present, fall back to an image_url that
survived on the same element, and drop hollow parts otherwise (same
strategy as the existing file-part handling). Fixes#2469.
huanghuoguoguo