mirror of
https://github.com/MoonshotAI/kimi-code.git
synced 2026-07-09 17:29:12 +00:00
* feat(agent-core): record llm request trace in wire.jsonl Add three observability record types so every request sent to the model can be reconstructed from the wire log at the logical-request level: - llm.tools_snapshot: content-addressed snapshot of the top-level tools table as sent (post deferred-strip), written once per unique table - llm.request: one record per outbound request (retries, strict resends, and compaction rounds included) carrying the effective request params and hash links to the system prompt and tools snapshot - mcp.tools_discovered: the server's verbatim tools/list result plus the agent's gating (allow-list, collisions), deduplicated by content hash Observability records never feed state rebuild; replay only restores the write-dedup cursors. The records/types.ts contract now documents the two record classes explicitly (persisted is not the same as replayed). Recording happens at the single Agent.generate choke point. The LLMRequestLogFields side channel gains kind/projection/maxTokens/ droppedCount, chatWithRetry preserves caller-set fields, and compaction tags its requests. The vis wire view renders the new record kinds. * fix(agent-core): record the provider-clamped completion cap in the request trace The llm.request trace recorded the client-requested budget cap, but chat-completions providers tighten the actual wire value inside withMaxCompletionTokens (remaining-context sizing, transport ceilings, model-default resolution) — with the default budget the clamp is active on nearly every non-empty-context request, so the recorded value did not match what was sent. Providers now expose the effective cap they computed as a readonly maxCompletionTokens field on the clone, and the recorder reads it from the effective provider at the Agent.generate choke point. This replaces the side-channel recomputation, which is removed along with the appliedCompletionBudgetCap helper. * fix(agent-core): park pre-replay MCP discovery records and hash the collision outcome Two wire-hygiene fixes for the mcp.tools_discovered trace: Parking: the real Session ordering connects MCP servers concurrently with agent construction, so ToolManager can observe a connected server before agent.resume() has replayed the wire. Recording at that point bypassed the restored dedup cursor (duplicating a 1-50KB record on every resume) and appended a stray metadata record ahead of replay. AgentRecords now exposes a one-shot opened latch — set when replay completes (after the migration rewrite flushes) or when the first live record is logged — and ToolManager parks discoveries until then, re-running the dedup check at drain time. A frozen range-limited replay never opens; those agents are transient previews. Collision hashing: the dedup hash now covers the collision outcome, not just the raw list and allow-list. Collisions depend on which other servers hold a sanitized qualified name at registration time, so a server can re-register with identical tools but a flipped outcome; that gating change must produce a new record instead of being suppressed. * fix(agent-core): skip the request trace for pre-flight-aborted calls Mirror kosong generate()'s pre-flight abort check at the Agent.generate choke point: a call whose signal is already aborted never reaches the wire (generate throws before dispatching), so it must not leave an llm.request/llm.tools_snapshot trace or a diagnostic log line claiming a request was sent. Recording stays before dispatch for every call that passes the gate, preserving the crash-safety of the trace. * chore(agent-core): remove a leftover adaptive-thinking override hook The adaptiveThinkingOverride option was a temporary local hook explicitly marked for removal before commit. Nothing passes it, so resolution falls back to the alias-level adaptiveThinking value in all cases; drop the option and the dead indirection. * fix(kosong): derive the exposed completion cap from generation kwargs maxCompletionTokens was a field stored only by withMaxCompletionTokens, so caps that reach the wire through other paths were invisible to the request trace: with completion budgeting disabled via env, Anthropic still sends the constructor-resolved max_tokens (required by the Messages API), and constructor-level kwargs like OpenAILegacyOptions maxTokens were likewise unreported. Replace the stored field with a getter derived from each provider's generation kwargs — the single source the request body reads — covering constructor defaults, direct withGenerationKwargs configuration, and budget application in one place. Kimi mirrors its request-time legacy max_tokens alias normalization; openai-legacy reuses the same normalizeGenerationKwargs the request path uses. * feat(agent-core): add thinkingKeep passthrough for Kimi providers and update tests
159 lines
5.2 KiB
TypeScript
159 lines
5.2 KiB
TypeScript
import { APIConnectionError, emptyUsage, isRetryableGenerateError } from '@moonshot-ai/kosong';
|
|
import { describe, expect, it } from 'vitest';
|
|
|
|
import type { KimiConfig } from '#/config';
|
|
import { ErrorCodes, KimiError } from '#/errors';
|
|
import type { LLM, LLMChatParams, LLMChatResponse } from '#/loop/llm';
|
|
import { chatWithRetry } from '#/loop/retry';
|
|
import { ProviderManager } from '#/session/provider-manager';
|
|
|
|
function okResponse(): LLMChatResponse {
|
|
return { toolCalls: [], usage: emptyUsage() };
|
|
}
|
|
|
|
function makeInput(
|
|
llm: LLM,
|
|
signal: AbortSignal,
|
|
): Parameters<typeof chatWithRetry>[0] {
|
|
return {
|
|
llm,
|
|
params: { messages: [], tools: [], signal },
|
|
dispatchEvent: async () => {},
|
|
turnId: 't',
|
|
currentStep: 1,
|
|
stepUuid: 'u',
|
|
};
|
|
}
|
|
|
|
describe('chatWithRetry: terminated stream drops', () => {
|
|
it('preserves caller-set requestLogFields across attempts while owning turnStep/attempt', async () => {
|
|
// The strict-resend path marks its params with `projection: 'strict'`;
|
|
// the per-attempt rebuild must merge that marker instead of replacing
|
|
// the whole fields object.
|
|
let calls = 0;
|
|
const seenFields: Array<LLMChatParams['requestLogFields']> = [];
|
|
const llm: LLM = {
|
|
systemPrompt: '',
|
|
modelName: 'mock',
|
|
isRetryableError: (e) => isRetryableGenerateError(e),
|
|
async chat(params: LLMChatParams): Promise<LLMChatResponse> {
|
|
calls += 1;
|
|
seenFields.push(params.requestLogFields);
|
|
if (calls === 1) throw new APIConnectionError('terminated');
|
|
return okResponse();
|
|
},
|
|
};
|
|
const input = makeInput(llm, new AbortController().signal);
|
|
|
|
await chatWithRetry({
|
|
...input,
|
|
params: { ...input.params, requestLogFields: { projection: 'strict' } },
|
|
});
|
|
|
|
expect(seenFields).toEqual([
|
|
{ projection: 'strict', turnStep: 't.1' },
|
|
{ projection: 'strict', turnStep: 't.1', attempt: '2/3' },
|
|
]);
|
|
});
|
|
|
|
it('retries an APIConnectionError("terminated") and succeeds on a later attempt', async () => {
|
|
// A mid-stream `terminated` is classified as a retryable APIConnectionError,
|
|
// so an intermittent connection drop should be recovered transparently.
|
|
let calls = 0;
|
|
const llm: LLM = {
|
|
systemPrompt: '',
|
|
modelName: 'mock',
|
|
isRetryableError: (e) => isRetryableGenerateError(e),
|
|
async chat(_params: LLMChatParams): Promise<LLMChatResponse> {
|
|
calls += 1;
|
|
if (calls === 1) throw new APIConnectionError('terminated');
|
|
return okResponse();
|
|
},
|
|
};
|
|
|
|
const response = await chatWithRetry(makeInput(llm, new AbortController().signal));
|
|
|
|
expect(calls).toBe(2);
|
|
expect(response).toEqual(okResponse());
|
|
});
|
|
|
|
it('does NOT retry when the signal is aborted (user ESC), surfacing a clean AbortError', async () => {
|
|
// Even though `terminated` is retryable, a user-aborted request must never
|
|
// be retried: the abort signal is checked before any retry, so it surfaces
|
|
// as an AbortError rather than a provider error.
|
|
let calls = 0;
|
|
const ac = new AbortController();
|
|
ac.abort();
|
|
|
|
const llm: LLM = {
|
|
systemPrompt: '',
|
|
modelName: 'mock',
|
|
isRetryableError: (e) => isRetryableGenerateError(e),
|
|
async chat(_params: LLMChatParams): Promise<LLMChatResponse> {
|
|
calls += 1;
|
|
throw new APIConnectionError('terminated');
|
|
},
|
|
};
|
|
|
|
await expect(chatWithRetry(makeInput(llm, ac.signal))).rejects.toMatchObject({
|
|
name: 'AbortError',
|
|
});
|
|
expect(calls).toBe(1);
|
|
});
|
|
|
|
it('does not retry OAuth token fetch connection errors (already retried internally)', async () => {
|
|
let tokenCalls = 0;
|
|
const manager = new ProviderManager({
|
|
config: oauthConfig(),
|
|
resolveOAuthTokenProvider: () => ({
|
|
async getAccessToken() {
|
|
tokenCalls += 1;
|
|
throw new KimiError(
|
|
ErrorCodes.PROVIDER_CONNECTION_ERROR,
|
|
'OAuth provider "managed:kimi-code" failed to fetch an access token: fetch failed',
|
|
);
|
|
},
|
|
}),
|
|
});
|
|
const resolveAuth = manager.resolveAuth('kimi-code/kimi-for-coding');
|
|
if (resolveAuth === undefined) throw new Error('expected OAuth auth resolver');
|
|
|
|
let chatCalls = 0;
|
|
const llm: LLM = {
|
|
systemPrompt: '',
|
|
modelName: 'mock',
|
|
isRetryableError: (e) => isRetryableGenerateError(e),
|
|
async chat(_params: LLMChatParams): Promise<LLMChatResponse> {
|
|
chatCalls += 1;
|
|
return resolveAuth(async () => okResponse());
|
|
},
|
|
};
|
|
|
|
await expect(chatWithRetry(makeInput(llm, new AbortController().signal))).rejects.toMatchObject({
|
|
code: ErrorCodes.PROVIDER_CONNECTION_ERROR,
|
|
});
|
|
expect(chatCalls).toBe(1);
|
|
expect(tokenCalls).toBe(1);
|
|
});
|
|
});
|
|
|
|
function oauthConfig(): KimiConfig {
|
|
return {
|
|
defaultModel: 'kimi-code/kimi-for-coding',
|
|
providers: {
|
|
'managed:kimi-code': {
|
|
type: 'kimi',
|
|
apiKey: '',
|
|
baseUrl: 'https://api.example/v1',
|
|
oauth: { storage: 'file', key: 'oauth/kimi-code' },
|
|
},
|
|
},
|
|
models: {
|
|
'kimi-code/kimi-for-coding': {
|
|
provider: 'managed:kimi-code',
|
|
model: 'kimi-for-coding',
|
|
maxContextSize: 1_000_000,
|
|
},
|
|
},
|
|
};
|
|
}
|