chengyongru reviewed #4367 and identified that the cloud branch
created a bare httpx.AsyncClient that lacked the SDK's default settings
(follow_redirects, connection pool limits). Since the SDK's
DefaultAsyncHttpxClient already has trust_env=True and proper defaults,
the simplest fix is to let http_client stay None for cloud endpoints.
Also updated the test to match the new behavior (http_client is None).
When the host has HTTP_PROXY / HTTPS_PROXY / ALL_PROXY set, httpx routes
all traffic through the proxy — including requests to localhost or LAN
addresses that the proxy typically cannot reach. This breaks local model
servers (Ollama, llama.cpp, vLLM) silently.
- Local endpoints: pass transport=httpx.AsyncHTTPTransport(proxy=None)
so proxy env vars are ignored for local traffic.
- Cloud endpoints: pass trust_env=True so corporate/VPN proxies work
without explicit configuration.
Fixes#4366
maintainer edit: preserve provider-prefix CLI routing for named custom providers by stripping only the matched dynamic route prefix before sending the model id to OpenAI-compatible endpoints. This keeps ordinary namespaced model ids intact when the provider is selected explicitly.
Maintainer edit: keep the GPT-5/o-series fallback on slug-boundary matching so unrelated model names are not caught by substring checks, and include o1 alongside o3/o4 because it is also an o-series chat model.
Adds ProviderConfig.extra_query, threaded into AsyncOpenAI(default_query)
so that Azure-style gateways requiring query params like api-version can
be configured without URL hacks.
Also updates provider_signature to track extra_query changes so per-turn
refresh rebuilds the provider when the value changes.
Addresses the extra_query portion of #4204. The max_completion_tokens
model-awareness enhancement is intentionally left separate.
Custom providers (e.g. DeepSeek) may return reasoning_content as an
empty string "" to explicitly indicate no reasoning occurred. The
previous truthiness checks (, ) treated "" as falsy
and converted it to None, which caused the field to be dropped from
the message history entirely. Providers that require reasoning_content
on all assistant messages then rejected subsequent requests.
Replace truthiness checks with identity checks () so that
empty-string reasoning_content is preserved as-is. The streaming path
is unchanged since an empty join genuinely means no chunks received.
Fixes#4105
Moonshot's API rejects requests that carry both 'reasoning_effort'
(top-level kwarg) and 'thinking' (extra_body) at the same time.
After the unified thinking-style injection loop injects the native
'thinking' param for kimi models, pop 'reasoning_effort' from kwargs
since it is redundant and causes a 400 error.
Uses _model_slug() + _KIMI_THINKING_MODELS lookup to stay consistent
with the refactored code (the old _is_kimi_thinking_model helper was
removed in 4f895e63).
Existing kimi tests updated to assert 'reasoning_effort' is absent.
Xiaomi MiMo models are unaffected — their API accepts both params.
Closes#3939
Follow-up to #3851: that PR added `extra_body.thinking={type: disabled}`
for MiMo via OpenRouter, but OR doesn't forward provider-specific
thinking shapes to upstream — it strips unknown extra_body fields and
uses its own unified `reasoning` parameter. So MiMo via OR kept
thinking despite the injection (reproduced by @ClearPlume on #3851
with identical kwargs but provider switched from openrouter → xiaomi_mimo).
For known thinking-capable models (Kimi, MiMo) routed via the
openrouter spec, also inject `extra_body.reasoning = {effort: <effort>}`
in OR's documented enum ("none"|"minimal"|"low"|"medium"|"high"|"xhigh").
OR translates this to the upstream model's native shape.
Existing tests updated to expect both fields on the OR path. The direct
xiaomi_mimo and moonshot paths are unchanged (the new branch is gated
on spec.name == "openrouter"). Flash and non-MiMo models on OR continue
to receive no injection.
Channel lazy load: discover_enabled() only imports enabled channel
modules instead of all 18 modules with heavy SDKs (telegram, discord,
slack, etc). discover_all() now delegates to discover_enabled().
Lazy OpenAI client: defer AsyncOpenAI() + httpx construction to
_ensure_client() with asyncio.Lock double-checked locking. openai
and httpx imports moved from module-level into _ensure_client().
Minor: lazy Nanobot/RunResult and CronService exports via __getattr__.
Benchmark: 6910ms → 460ms (-93.3%)
The xiaomi_mimo ProviderSpec carries thinking_style="thinking_type", but
gateway providers (OpenRouter etc.) route MiMo under their own spec
which has no thinking_style. As a result, `reasoning_effort="none"` was
silently ignored: `{"thinking": {"type": "disabled"}}` was never
injected and responses still contained reasoning_content.
Mirror the Kimi pattern that already handles the same problem: add an
explicit _MIMO_THINKING_MODELS allowlist (mimo-v2.5-pro, mimo-v2.5,
mimo-v2-pro, mimo-v2-omni — per Xiaomi docs), an _is_mimo_thinking_model
helper that strips publisher prefixes ("xiaomi/mimo-v2.5-pro" matches),
and a sibling branch in _build_kwargs that injects the thinking payload
by model name. mimo-v2-flash is intentionally excluded — it has no
thinking mode.
Also include MiMo in the explicit_thinking predicate so the
reasoning_content backfill (#3554, #3584) covers the gateway path
consistently with the direct path.
Tests cover the gateway disable/enable signals, bare-slug fallback,
flash exclusion, and a non-MiMo sanity check.
* feat(long-task): add LongTaskTool for multi-step agent tasks
Implements a meta-ReAct loop where long-running tasks are broken into
sequential subagent steps, each starting fresh with the original goal
and progress from the previous step. This prevents context drift when
agents work on complex, multi-step tasks.
- Extract build_tool_registry() from SubagentManager for reuse
- Add run_step() for synchronous subagent execution (no bus announcement)
- Add HandoffTool and CompleteTool as signal mechanisms via shared dict
- Add LongTaskTool orchestrator with simplified prompt (8 iterations/step)
- Register LongTaskTool in main agent loop
- Add _extract_handoff_from_messages fallback for robustness
* fix(long-task): add debug logging for step-level observability
* feat(long-task): major overhaul with structured handoffs, validation, and observability
- Structured HandoffState: HandoffTool now accepts files_created,
files_modified, next_step_hint, and verification fields instead of
a plain string. Progress is passed between steps as structured data.
- Completion validation round: After complete() is called, a dedicated
validator step runs to verify the claim against the original goal.
If validation fails, the task continues rather than returning
a false completion.
- Dynamic prompt system: 3 Jinja2 templates (step_start, step_middle,
step_final) selected based on step number. Final steps get tighter
budget and stronger "wrap up" guidance.
- Automatic file change tracking: Extracts write_file/edit_file events
from tool_events and injects them into the next step's context if
the subagent forgot to report them explicitly.
- Budget tracking & adaptive strategy: Cumulative token usage is tracked
across steps. Per-step tool budget drops from 8 to 4 in the last
two steps to force handoff/completion.
- Crash retry with graceful degradation: A step that crashes is retried
once. Persistent crashes terminate the task and return partial progress.
- Full observability hooks for future WebUI integration:
- set_hooks() with on_step_start, on_step_complete, on_handoff,
on_validation_started, on_validation_passed, on_validation_failed,
on_task_complete, on_task_error, and catch-all on_event.
- Readable state properties: current_step, total_steps, status,
last_handoff, cumulative_usage, goal.
- inject_correction() allows external code to send user corrections
that are injected into the next step's prompt.
- run_step() accepts optional max_iterations for dynamic budget control.
All 27 long-task tests and 11 subagent tests pass.
* test(long-task): add boundary tests and fix race conditions
- Add 7 edge-case tests: validation crash resilience, hook exception safety, mid-run correction injection, FIFO correction ordering, explicit file changes overriding auto-detection, final budget for max_steps=1, and dynamic budget switching boundaries
- Fix assertion in test_long_task_completes_after_multiple_handoffs to match exact prompt format
- Remove asyncio timing hack from test_state_exposure
- Add asyncio.sleep(0) yield in test_inject_correction_during_execution to prevent race between signal injection and step continuation
- All 34 tests passing
* fix(long-task): address code review findings
- Declare _scopes = {"core"} explicitly to prevent recursive nesting in subagent scope
- Document fragile coupling in _extract_file_changes: path extraction depends on
write_file/edit_file detail format; add debug log for unexpected formats
- Align final-template threshold (max_steps - 2) with budget switch threshold
- Eliminate hasattr(self, "_state") in _reset_state by initializing in __init__
* fix(long-task): honor final signal and file tracking
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(long-task): improve prompt structure and agent contract
- Expand LongTaskTool.description to instruct parent agent on goal
construction, return value semantics, and how to handle results.
- Expand CompleteTool.description to emphasize that the summary IS the
final answer returned to the parent agent.
- Prefix validated return value with an explicit "final answer" directive
to stop parent agent from re-running work.
- Redesign step_start.md: Step 1 is now explicitly for exploration,
planning, and skeleton-building. complete() is discouraged.
- Remove bulky payload debug logging from _emit(); add targeted
info/warning/error logs at key state transitions instead.
- Add signal_type to HandoffState for cleaner signal detection.
* test(long-task): expect wrapped completion message after validation
Align assertions with LongTaskTool final return shape on main.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(webui): turn timing strip, latency, and session-switch restore
- Agent loop: publish goal_status run/idle for WebSocket turns; attach
wall-clock latency_ms on turn_end and persisted assistant metadata.
- WebSocket channel: forward goal_status and latency fields to clients.
- NanobotClient: track goal_status started_at per chat without requiring
onChat; useNanobotStream restores run strip when returning to a chat.
- Thread UI: composer/shell viewport hooks for run duration and latency;
format helpers and i18n strings.
- MessageBubble: drop trailing StreamCursor (layout artifact vs block markdown).
- Builtin / tests: model command coverage, websocket and loop tests.
Covers multi-session UX and round-trip timing visibility for the WebUI.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix: keep message-tool file attachments after canonical history hydrate
- MessageTool records per-turn media paths delivered to the active chat.
- nanobot.utils.session_attachments stages out-of-media-root files and
merges into the last assistant message before save (loop stays a thin call).
- WebUI MediaCell: use a signed URL as a real download link when present.
Fixes attachments flashing then vanishing on turn_end when paths lived
outside get_media_dir (e.g. workspace files).
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(webui): agent activity cluster, stable keys, LTR sheen labels
- Group reasoning and tool traces in AgentActivityCluster with i18n summaries
- Stabilize React list keys for activity clusters (first message id anchor)
- Replace background-clip shimmer with overlay sheen for streaming labels
- ThreadMessages/MessageList integration and locale strings
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(webui): render assistant reasoning with Markdown + deferred stream
- Use MarkdownText for ReasoningBubble body (same GFM/KaTeX path as replies)
- Apply muted/italic prose tokens so thinking stays visually subordinate
- useDeferredValue while reasoningStreaming to ease parser work during deltas
- Preload markdown chunk when trace opens; add regression test with preloaded renderer
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(webui): default-collapse agent activity cluster while Working
Outer fold no longer auto-expands during isTurnStreaming; user opens to see traces.
Header sheen and live summary unchanged.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(long_task): cumulative run history, file union, and prompt tuning
Inject cross-step summaries and merged file paths into middle/final step
templates so chains do not lose early context. Strip the last run-history
block when it duplicates Previous Progress to save tokens. Add optional
cumulative_prompt_max_chars and cumulative_step_body_max_chars parameters
with clamped defaults.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(webui): session switch keeps in-flight thread and replays buffered WS
Save the prior chat message list to the per-chat cache in a layout effect
when chatId changes (before stale writes could corrupt another chat).
Skip one post-switch layout cache tick so we do not snapshot the wrong tab.
Buffer inbound events per chat_id when no onChat subscriber is registered
(e.g. user focused another session) and drain on resubscribe up to a cap,
so streaming deltas are not lost while off-tab.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(webui): snap thread scroll to bottom on session open (no smooth glide)
Use scroll-behavior auto on the viewport, instant programmatic scroll when
following new messages and on scrollToBottomSignal. Keep smooth only for
the explicit scroll-to-bottom button.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(webui): respect manual scroll-up after opening a session
Track when the user leaves the bottom with a ref and skip ResizeObserver
and deferred bottom snaps until they return or the conversation is reset.
Remove the time-based force-bottom window that overrode atBottom.
Multi-frame scrollToBottom honours the same guard unless force (scroll button).
Co-authored-by: Cursor <cursoragent@cursor.com>
* Publish long_task UI snapshots on outbound metadata
- Add OUTBOUND_META_AGENT_UI (_agent_ui) for channel-agnostic structured state
- LongTaskTool publishes {kind: long_task, data: snapshot} on the bus with _progress
- WebSocket send forwards metadata as agent_ui for WebUI clients
- Tests for bus payload, WS frame, and progress assertions
- Fix loop progress tests: ignore _goal_status in streaming final filter and
avoid brittle outbound[-1] ordering after goal status idle messages
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat: WebUI long_task activity card and resilient history merge
Add optional ui_summary to the long_task tool for one-line UI labels. Stream
long_task agent_ui into a dedicated message row with timeline, markdown peek,
and a right sheet for details. Merge canonical history after turn_end while
re-inserting long_task rows before the final assistant reply. Collapse
duplicate task_start/step_start steps in the timeline and extend i18n.
Co-authored-by: Cursor <cursoragent@cursor.com>
* refactor: align long_task with thread_goal and drop orchestrator UI
- Persist sustained objectives via session metadata (long_task / complete_goal); no subagent wiring or tool-driven agent_ui payloads.\n- Remove WebUI long-task activity UI, types, and translations; history merge preserves trace replay only, with legacy long_task rows normalized to traces.\n- Drop long_task prompt templates and get_long_task_run_dir; add webui thread disk helper for gateway persistence tests.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(agent): thread goal runtime context, tools, and skill
- Add thread_goal_state helper and mirror active objectives into Runtime Context
- Wire loop/context/memory/events as needed for goal metadata in turns
- Expand long_task / complete_goal semantics (pivot/cancel/honest recap)
- Add always-on thread-goal SKILL.md; align /goal command prompt
- Tests for context builder and thread goal state
- Remove unused webui ChatPane component
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(thread-goal): add websocket snapshot helper and publish goal updates from long_task
Introduce thread_goal_ws_blob for bounded JSON snapshots, attach snapshots to
websocket turn_end metadata in AgentLoop, and let long_task fan-out dedicated
thread_goal frames on the websocket channel after persisting session metadata.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(channels): websocket thread_goal frames, turn_end replay, and session API scrub for subagent inject
Emit thread_goal events and optional thread_goal on turn_end; scrub persisted
subagent announce blobs on GET /api/sessions/.../messages and shorten session
list previews so WebUI does not surface full Task/Summarize scaffolding.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(webui): merge ephemeral traces per user turn when reconciling canonical history
Preserve disk/live trace rows inside the matching user–assistant segment instead
of stacking every trace before the final assistant reply (fixes inflated tool
counts after refresh or session switch).
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(webui): show assistant reply copy only on the last slice before the next user turn
Avoid duplicate copy affordances on intermediate assistant bubbles that precede
more agent activity in the same turn (tools or further assistant text).
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(webui): thread_goal stream plumbing, composer goal strip, sky glow, and client-side subagent scrub projection
Track thread_goal and turn_goal snapshots in NanobotClient, hydrate React state
from thread_goal frames and turn_end, surface objective/elapsed in the composer,
add breathing sky halo CSS while goals are active, mirror server scrub logic on
history hydration and webui_thread snapshots, and extend tests/client mocks.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(channels): add Slack Socket Mode connect timeout with actionable timeout errors
Abort hung websockets.connect handshakes after a bounded wait, log REST-vs-WSS
guidance, surface RuntimeError to channel startup, and log successful WSS setup.
Co-authored-by: Cursor <cursoragent@cursor.com>
* webui: expand thread goal in composer bottom sheet
Add ChevronUp control on the run/goal strip that opens a bottom Sheet
with full ui_summary and objective. Inline preview logic in RunElapsedStrip,
add i18n strings across locales, and a composer unit test.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(webui): widen dedupeToolCallsForUi input for session API typing
fetchSessionMessages types tool_calls as unknown; accept unknown so tsc
build passes when passing message.tool_calls through.
Co-authored-by: Cursor <cursoragent@cursor.com>
* refactor(agent): extract WebSocket turn run status to webui_turn_helpers
* refactor(skills): rename thread-goal to long-task and document idempotent goals
* feat(skills): rename sustained-goal skill to long-goal and tighten long_task guidance
* chore: remove unused subagent/context/router helpers
* feat(session): rename sustained goal to goal_state and align WS/WebUI
- Move helpers from agent/thread_goal_state to session/goal_state:
GOAL_STATE_KEY, goal_state_runtime_lines, goal_state_ws_blob, parse_goal_state.
- Session metadata now uses "goal_state"; still read legacy "thread_goal";
long_task writes drop the legacy key after save.
- WebSocket: event/field goal_state, _goal_state_sync; turn_end carries goal_state;
accept legacy _thread_goal_sync/thread_goal inbound metadata for dispatch.
- WebUI: GoalStateWsPayload, goalState hook/client props, i18n keys goalState*.
- Runtime Context copy uses "Goal (active):" instead of "Thread goal".
* feat(agent): stream Anthropic thinking deltas and fix stream idle timeout
* refactor(webui): transcript jsonl as sole timeline source
* fix(agent): reject mismatched WS message chat_id and stream reasoning deltas
* feat(webui): hydrate sustained goal and run timer after websocket subscribe
* chore(webui,websocket): remove unused fetch helpers and legacy thread_goal WS paths
* Raise default max_tokens and context window in agent schema.
Align AgentDefaults and ModelPresetConfig with typical Claude-scale usage
(32k completion budget, 256k context window) and update migration tests.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(gateway): bootstrap prefers in-memory model; clarify websocket naming
* fix(websocket): websocket _handle_message passes is_dm; refresh /status test expectations
---------
Co-authored-by: chengyongru <2755839590@qq.com>
Co-authored-by: chengyongru <chengyongru.ai@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Follow-up to PR #3651:
- Replace logger.error with logger.exception inside except blocks
so stack traces are no longer lost:
- providers/transcription.py (5 occurrences)
- agent/tools/mcp.py (1 occurrence)
- Replace stdlib logging.getLogger with loguru logger in
providers/openai_compat_provider.py for consistency.
- Do not send reasoning_effort="none" to APIs (prevents 400 on gemma/Gemini)
- Treat "none" as thinking disabled in thinking_style, Kimi, and reasoning_content backfill paths
- Fix Anthropic extended thinking not respecting "none"
- Fix Azure OpenAI temperature suppression and reasoning body for "none"
- Fix Codex reasoning body for "none"
- Add "gemma" keyword to Gemini ProviderSpec for correct auto routing
Add an `extra_body` field to `ProviderConfig` that merges arbitrary
key-value pairs into every OpenAI-compatible request body. This is the
escape hatch for provider-specific features that nanobot does not have
first-class fields for.
Real-world use cases this unblocks via config alone (no code changes):
- vLLM/TGI `chat_template_kwargs` (e.g. `enable_thinking: false`)
- vLLM guided decoding (`guided_json`, `guided_regex`)
- Local model sampling params (`repetition_penalty`, `top_k`, `min_p`)
- Any future provider-specific param without a new PR each time
The config extra_body is applied last via recursive deep-merge, so it
can extend or override provider-specific defaults (e.g. thinking
params) without clobbering sibling keys set by internal logic.
Changes:
- Add `extra_body: dict[str, Any] | None` to `ProviderConfig`
- Pass it through `factory.py` to `OpenAICompatProvider.__init__`
- Deep-merge into `_build_kwargs` after all internal extra_body entries
- Add `_deep_merge` helper (recursive dict merge, does not mutate inputs)
- 21 tests: deep-merge semantics, provider init, _build_kwargs
integration, thinking coexistence, real-world patterns (guided_json,
repetition_penalty), and schema validation
The non-streaming parse path unconditionally promoted the `reasoning`
response field to `content` when content was empty. This was intended
for StepFun (whose API returns the actual answer in `reasoning`), but
it applied to every OpenAI-compatible provider — causing internal
thinking chains from models like Xiaomi MIMO to be leaked as formal
replies.
Add `reasoning_as_content: bool` to ProviderSpec (default False) and
set it only for StepFun. The fallback now requires this flag rather
than running globally.
Fixes#3443
Parse the endpoint host before disabling keepalive so public hostnames that merely contain private-network substrings keep the default connection pool behavior.
Made-with: Cursor
Local model servers (Ollama, llama.cpp, vLLM) often close idle HTTP
connections before the client-side keepalive timer expires. When two
LLM calls happen seconds apart — for example the heartbeat _decide()
phase followed immediately by process_direct() — the second call grabs
a now-dead pooled connection, causing a transient APIConnectionError
on every first attempt.
The fix detects local endpoints via:
- ProviderSpec.is_local (Ollama, LM Studio, vLLM, OVMS)
- Private-network URL patterns (localhost, 127.x, 192.168.x, 10.x,
172.16-31.x, host.docker.internal, [::1])
For these endpoints, the AsyncOpenAI client is created with a custom
httpx.AsyncClient that sets keepalive_expiry=0, forcing a fresh TCP
connection for each request. This is cheap on LAN (sub-5ms connect)
and eliminates the stale-connection retry tax entirely.
Cloud providers (OpenAI, Anthropic, OpenRouter, etc.) keep the default
5-second keepalive, which is fine for high-frequency API usage.
The private-network heuristic also covers the common case where users
configure provider='openai' but point apiBase at a LAN IP running
llama.cpp — the spec says is_local=False, but the URL clearly is.
Two issues with DeepSeek V4 thinking mode support:
1. Missing thinking parameter injection.
DeepSeek V4 requires `extra_body: {"thinking": {"type": "enabled/disabled"}}`
— identical to VolcEngine/BytePlus. The code had this for volcengine,
byteplus, dashscope, minimax, and kimi but not DeepSeek. This means
`reasoning_effort=minimal` (thinking off) silently has no effect.
Root cause: the thinking-style→wire-format mapping was an if/elif chain
on provider *names*. DeepSeek was forgotten.
Fix: make the mapping declarative via `ProviderSpec.thinking_style`:
- "thinking_type" → {"thinking": {"type": "..."}} (DeepSeek, Volc, BytePlus)
- "enable_thinking" → {"enable_thinking": bool} (DashScope)
- "reasoning_split" → {"reasoning_split": bool} (MiniMax)
`_build_kwargs` now does a single dict lookup. Adding a new provider
with an existing wire format requires zero changes to the function.
2. Legacy session messages crash thinking-mode requests.
When a session was started without thinking mode (or with a different
model), assistant messages lack reasoning_content. DeepSeek V4 in
thinking mode rejects these with 400:
"The reasoning_content in the thinking mode must be passed back to the API."
This affects ALL assistant messages, not just those with tool_calls
(despite the docs only mentioning the tool_calls case).
Fix: `_build_kwargs` backfills `reasoning_content: ""` on every
assistant message missing it, but only when thinking mode is active.
This is semantically neutral — the model treats empty reasoning_content
as "no thinking happened on that turn". The backfill only touches the
in-memory request copy; session files on disk are untouched.
Tests: +5 (3 thinking toggle, 2 backfill). Full suite: 2377 passed.
Made-with: Cursor
Calling GitHub Copilot with `gpt-5.*` / `o*` models (e.g.
`github_copilot/gpt-5.4`, `github_copilot/gpt-5.4-mini`) failed with a
chain of misleading errors:
1. `Unsupported parameter: 'max_tokens' is not supported with this
model. Use 'max_completion_tokens' instead.`
2. `model "gpt-5.4-mini" is not accessible via the /chat/completions
endpoint` (`unsupported_api_for_model`).
3. `The requested model is not supported.` (`model_not_supported`)
even after routing to /responses.
Root causes (each one masked the next):
* The `github_copilot` ProviderSpec did not opt into
`supports_max_completion_tokens`, so `_build_kwargs` always sent the
legacy `max_tokens` parameter that GPT-5/o-series reject.
* `_should_use_responses_api` was hard-gated to
`spec.name == "openai"` plus a direct-OpenAI base URL, so the
GitHub Copilot backend always went through /chat/completions even
for models the Copilot gateway exposes only via /responses
(e.g. `gpt-5.4-mini`).
* When /responses did fail on github_copilot, the existing
"compatibility marker" heuristic silently fell back to
/chat/completions — which can never succeed for these models — so
the real upstream error was hidden.
* `_build_responses_body` did not honour `spec.strip_model_prefix`,
so the request body sent `model="github_copilot/gpt-5.4-mini"`
(with the routing prefix), which the Copilot gateway rejects with
`model_not_supported`. (`_build_kwargs` already stripped it; this
branch was missed.)
Fix:
* registry.py: set `supports_max_completion_tokens=True` on the
`github_copilot` spec so requests use `max_completion_tokens`.
* openai_compat_provider.py:
- `_should_use_responses_api` now also allows the
`github_copilot` spec, and skips the direct-OpenAI base check
for it (the Copilot gateway is its own base URL).
- `_build_responses_body` now strips the model routing prefix
when `spec.strip_model_prefix` is set, matching `_build_kwargs`.
- `chat` / `chat_stream` no longer fall back from /responses to
/chat/completions on the `github_copilot` spec: the fallback
cannot succeed for GPT-5/o-series and would mask the real
gateway error.
Tests:
* tests/cli/test_commands.py: switched the
`test_github_copilot_provider_refreshes_client_api_key_before_chat`
fixture model from `gpt-5.1` to `gpt-4` so it continues to exercise
the /chat/completions code path it was designed for (gpt-5.1 now
correctly routes to /responses on github_copilot).
* `pytest tests/providers/ tests/cli/test_commands.py` — 314 passed.
* Verified end-to-end against the live Copilot gateway with both
`github_copilot/gpt-5.4` and `github_copilot/gpt-5.4-mini`.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
DashScope rejects the OpenAI-style value "minimal" with
`'reasoning_effort.effort' must be one of: 'none', 'minimum', 'low',
'medium', 'high', 'xhigh'`, but nanobot was passing the string through
verbatim. Users who tried the documented "minimal" to disable thinking
got a 400; users who tried the DashScope-native "minimum" to work
around it got `enable_thinking=True` because the internal comparison
was a hard string match on "minimal".
Introduce a semantic/wire split in `_build_kwargs`:
- `semantic_effort` is the internal canonical form (OpenAI vocabulary).
"minimum" on the way in is normalized to "minimal" here so both
spellings share one meaning.
- `wire_effort` is what we actually serialize. For DashScope with
semantic_effort == "minimal" we translate to "minimum" on the way
out; other providers are unchanged.
- `thinking_enabled` and the Kimi thinking branch now compare on
`semantic_effort`, so either user spelling correctly disables
provider-side thinking.
Tests:
- Strengthen `test_dashscope_thinking_disabled_for_minimal` to assert
the wire value is "minimum" in addition to the extra_body signal;
the original version only checked extra_body and let the
invalid-value bug slip through.
- Add `test_dashscope_thinking_disabled_for_minimum_alias` so a user
who read the DashScope docs and configured "minimum" still gets
thinking off.
- Add `test_non_dashscope_minimal_not_retranslated` to pin down that
the DashScope-specific translation does not leak to OpenAI et al.
When the Responses API fails repeatedly (3 consecutive compatibility
errors), skip it and fall back directly to Chat Completions. Unlike a
permanent disable, the circuit re-probes after 5 minutes so recovery
is automatic when the API comes back. Success resets the counter.
Keyed per (model, reasoning_effort) so a failure with one model does
not affect others.
- Inject `thinking={"type": "enabled|disabled"}` via extra_body for
Kimi thinking-capable models (kimi-k2.5, k2.6-code-preview).
- Add _is_kimi_thinking_model helper to handle both bare slugs and
OpenRouter-style prefixed names (e.g. moonshotai/kimi-k2.5).
- reasoning_effort="minimal" maps to disabled; any other value enables it.
- Add tests for enabled/disabled states and OpenRouter prefix handling.
Ensure assistant tool-call function.arguments is always emitted as valid JSON text so strict OpenAI-compatible backends (including Alibaba code models) do not reject requests. Add regressions for dict and malformed-string argument payloads in message sanitization.
Made-with: Cursor
michaelxerandXubin Ren
yu-xin-candXubin Ren
chengyongruandXubin Ren
chengyongruandXubin Ren
04cbandXubin Ren
chengyongruandGitHub
axelray-devandXubin Ren
outlook84andXubin Ren
Yuxin LouandXubin Ren
A.G. BocsardiandXubin Ren
olgagagaandXubin Ren
Xubin RenandXubin Ren
Jiajun XieandXubin Ren
masterlyjandXubin Ren
hussein1362andXubin Ren
hanyuanlingandXubin Ren
Peixian GongandCopilot
hlgandXubin Ren
kandXubin Ren
Mohamed ElkholyandXubin Ren
razzhandXubin Ren
Michael-lhhandXubin Ren
haosenwang1018andXubin Ren