Files
openclaw/src/system-agent/assistant.ts
Peter Steinberger 4273ca9dbd refactor(sessions): remove file-era transcript runtime (#113233)
* refactor(sessions): keep helper transcripts in memory

* refactor(sessions): remove file-era transcript storage

* test(sessions): use SQLite identity in attempt persistence

* test(codex): isolate legacy transcript fixtures

* fix(sessions): preserve SQLite transcript identity

* fix(sessions): harden transcript lifecycle invariants

* fix(sessions): validate transcript identities

* fix(sessions): close identity compatibility gaps

* fix(sessions): preserve leaf and plugin identities

* fix(sessions): retain dispatch transcript targets

* fix(sessions): preserve active transcript context

* fix(sessions): isolate artifact accounting

* fix(sessions): bound SQLite usage accounting

* fix(sessions): retain bounded latest usage

* fix(sessions): align rebased transcript targets

* test(sessions): align accessor scope fixture

* fix(telegram): derive SQLite transcript identity

* refactor(sessions): remove file-era compaction residue

* chore(sessions): lower max-lines baseline

* fix(sessions): preserve structured transcript identity

* test(sessions): align doctor identity assertions

* fix(sessions): isolate default SDK database

* refactor(sessions): remove dead file-era exports

* fix(sessions): reconcile SQLite transcript identity

* fix(sessions): pass checkpoint identity explicitly

* test(sessions): make entry field probe explicit

* test(sessions): satisfy transcript cleanup lint

* test(sessions): align diagnostics identity proof

* fix(sessions): finish transcript runtime teardown

* fix(sessions): preserve transcript identity invariants

* fix(sessions): harden transcript compatibility edges

* fix(sessions): preserve checkpoint transcript anchors

* fix(sessions): preserve SQLite lifecycle invariants

* fix(sessions): retarget compaction successors

* test(sessions): preserve transcript fixture semantics

* feat(plugin-sdk): add command transcript targets

* fix(sessions): serialize transcript rewrites

* fix(sessions): validate legacy successor identity

* fix(sessions): normalize compaction ownership

* fix(sessions): validate successor identity before adoption

* fix(sessions): preserve plugin transcript ownership

* fix(sessions): carry transcript identity through commands

* fix(sessions): import legacy checkpoint artifacts into SQLite

* fix(sessions): preserve successor transcript ownership

* fix(sessions): align transcript consumers with target identity

* fix(sessions): scope transcript token estimates

* fix(sessions): retain agent identity across lifecycle hooks

* fix(sessions): resolve scoped SQLite targets

* fix(sessions): isolate lifecycle transcript targets

* fix(sessions): validate compaction agent ownership

* fix(sessions): preserve reset and cleanup lifecycle

* fix(sessions): serialize prompt cleanup lifecycle

* fix(sessions): remove stale lock import

* fix(sessions): preserve reset target context

* fix(sessions): fence prompt reload takeover

* fix(sessions): unblock abort and default lifecycle reads

* fix(sessions): validate legacy successor scope

* fix(sessions): reject metadata-only runtime rows

* fix(sessions): propagate custom transcript stores

* fix(sessions): preserve adopted retry targets

* fix(sessions): allow unkeyed usage reads

* fix(sessions): harden runtime target boundaries

* fix(sessions): serialize retry transcript writes

* fix(sessions): bound prompt reload disposal

* fix(sessions): complete retry marker identity

* fix(sessions): keep legacy marker identity minimal

* test(sessions): tighten teardown fixture types

* fix(sessions): preserve compatibility target identity

* test(sessions): persist post-checkpoint boundary turn

* test(sessions): align runtime store mock contracts

* style(sessions): simplify persisted identity guard

* fix(sessions): prefer complete typed targets

* fix(sessions): recover legacy marker targets

* test(sessions): align marker lookup fixture scope

* fix(sessions): validate partial transcript targets

* fix(sessions): reconcile partial transcript identities

* fix(sessions): canonicalize compatibility identities

* test(sessions): cover compatibility aliases

* fix(sessions): adopt legacy successor identity

* fix(sessions): preserve usage read identity

* fix(sessions): preserve partial marker compatibility

* fix(sessions): validate legacy successor mappings

* fix(sessions): reconcile marker store mappings

* fix(sessions): preserve legacy fallback identity

* fix(sessions): harden marker alias resolution

* fix(sessions): prefer verified successor aliases

* fix(sessions): resolve preferred marker aliases

* fix(sessions): serialize cleanup admission

* fix(sessions): align marker lookup scopes

* fix(codex): type marker alias summaries

* style(sessions): satisfy changed lint

* test(sessions): align structured target assertions

* fix(sessions): reconcile latest identity contracts

* fix(sessions): validate transcript identity boundaries

* docs(sessions): explain stable registry keys

* fix(sessions): harden compatibility target round trips

* fix(sessions): port usage identity to split modules

* test(sessions): align subagent transcript identity

* fix(sessions): finish transcript identity migration

* fix(agents): route subagent completion capture through transcript targets

* fix(agents): settle SQLite prompt handoff during cleanup

* chore: shrink max-lines baseline after teardown

* fix(sessions): port teardown across split runtime owners

* fix(sessions): carry transcript targets through split owners

* test(agents): use SQLite compaction target in abort coverage

* chore: retain unrelated max-lines suppressions

* chore: shrink max-lines baseline after main splits

* style(agents): const compaction checkpoint locals

* fix(sessions): harden SQLite teardown boundaries

* test(sessions): use typed metadata in predicate isolation fixture

* test(agents): cover malformed settlement rejections lint-safely

* fix(sessions): close remaining SQLite identity races

* fix(agents): fail closed on incomplete successor targets

* fix(sessions): preserve transcript identity fallbacks

* fix(agents): preserve session-key abort admission

* fix(trajectory): validate incomplete export targets

* test(sessions): drop retired pricing cache imports

* fix(sessions): validate partial transcript identities

* fix(sessions): close transcript identity edge cases

* fix(plugins): reserve retired transcript locator slot

* fix(sessions): scope transcript locks by target

* style(sessions): simplify SDK initialization error

* fix(sessions): preserve initialized transcript state

* fix(codex): verify mirrored history session keys

* fix(sessions): reject stale transcript ownership

* fix(sessions): anchor asynchronous transcript ownership

* fix(sessions): measure active transcript state

* fix(sessions): preserve scoped transcript compaction

* fix(sessions): harden transcript identity and lifecycle

* fix(sessions): resolve scoped command transcript stores

* fix(sessions): make transcript appends failure-atomic

* fix(sessions): enforce scoped transcript ownership

* fix(sessions): reject cross-owner transcript handoffs

* fix(sessions): fence cleanup transcript ownership

* fix(sessions): retire stale write ownership contexts

* fix(sessions): preserve pending session migration state

* fix(sessions): validate migrated transcript ownership

* fix(sessions): validate usage transcript targets

* fix(sessions): clear predecessor transcript metadata

* fix(sessions): align durable session event targets

* fix(sessions): fence late prompt handoffs

* fix(sessions): fence lifecycle transcript fallbacks

* fix(sessions): bound zero-length memory capture

* fix(sessions): preserve transcript teardown ownership

* fix(sessions): reject duplicate cleanup ownership

* fix(sessions): serialize runtime writes with sqlite leases

* fix(sessions): close sqlite teardown concurrency gaps

* fix(sessions): preserve nested lifecycle failures

* fix(sessions): canonicalize sqlite transcript ownership

* fix(sessions): settle disposed prompt handoffs

* fix(sessions): resolve canonical attempt lock targets

* test(sessions): align canonical target fixtures

* test(sessions): retire redundant jsonl parser coverage

* refactor(sessions): split active transcript cursors

* test(memory): retire legacy marker fixture

* fix(sessions): preserve canonical transcript access after rebase

* fix(sessions): fence prompt lease and return transcript targets

* fix(sessions): colocate transcript leases with target store

* fix(sessions): canonicalize transcript lease and worker targets

* fix(sessions): preserve plugin and fork identity markers

* fix(sessions): complete sqlite transcript target migration

* fix(sessions): integrate canonical followup identity

* fix(sessions): preserve bounded transcript topology

* fix(sessions): validate transcript identity boundaries

* fix(context): separate caller and successor targets

* test(sessions): split persistence compatibility coverage

* test(sessions): preserve fixture topology efficiently

* chore(sdk): refresh plugin api baseline

* test(agents): align compaction lock target mocks

* test(sessions): seed malformed transcript fixtures directly

* fix(agents): canonicalize transcript compatibility inputs

* fix(agents): type optional tool result ids

* test(ci): stabilize loaded process timing

* test(tui): wait for collect queue admission
2026-07-27 22:33:24 -04:00

257 lines
9.2 KiB
TypeScript

// OpenClaw assistant planning converts fuzzy user text into one safe command.
import { randomUUID } from "node:crypto";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { SessionManager } from "../agents/sessions/index.js";
import {
SYSTEM_AGENT_ASSISTANT_SYSTEM_PROMPT,
SYSTEM_AGENT_GREETING_SYSTEM_PROMPT,
buildSystemAgentAssistantUserPrompt,
buildSystemAgentGreetingUserPrompt,
parseSystemAgentAssistantPlanText,
type SystemAgentAssistantPlan,
type SystemAgentAssistantTurn,
} from "./assistant-prompts.js";
import { resolveSystemAgentAssistantTimeoutMs } from "./assistant-timeout.js";
import type { SystemAgentGreetingFacts, SystemAgentGreetingPlan } from "./greeting.js";
import { SystemAgentInferenceUnavailableError } from "./inference-error.js";
import type { SystemAgentOverview } from "./overview.js";
import {
resolveSystemAgentExpectedAgentHarnessRuntimeArtifact,
resolveSystemAgentVerifiedInferenceRoute,
type SystemAgentVerifiedInferenceBinding,
type SystemAgentVerifiedInferenceDeps,
} from "./verified-inference.js";
export {
buildSystemAgentAssistantUserPrompt,
parseSystemAgentAssistantPlanText,
type SystemAgentAssistantPlan,
type SystemAgentAssistantTurn,
} from "./assistant-prompts.js";
export type SystemAgentAssistantPlanner = (params: {
input: string;
overview: SystemAgentOverview;
history?: SystemAgentAssistantTurn[];
pendingOperation?: string;
readonly verifiedInference: SystemAgentVerifiedInferenceBinding;
}) => Promise<SystemAgentAssistantPlan | null>;
type RunCliAgentFn = typeof import("../agents/cli-runner.js").runCliAgent;
type RunEmbeddedAgentFn = typeof import("../agents/embedded-agent.js").runEmbeddedAgent;
export type SystemAgentConfiguredModelPlannerDeps = SystemAgentVerifiedInferenceDeps & {
runCliAgent?: RunCliAgentFn;
runEmbeddedAgent?: RunEmbeddedAgentFn;
createTempDir?: () => Promise<string>;
removeTempDir?: (dir: string) => Promise<void>;
resolveAssistantTimeoutMs?: typeof resolveSystemAgentAssistantTimeoutMs;
};
const SYSTEM_AGENT_PLANNER_RESPONSE_SCHEMA = {
type: "object",
properties: {
reply: { type: "string" },
command: { type: "string" },
},
required: ["reply"],
additionalProperties: false,
} as const;
export async function planSystemAgentCommand(params: {
input: string;
overview: SystemAgentOverview;
history?: SystemAgentAssistantTurn[];
pendingOperation?: string;
readonly verifiedInference: SystemAgentVerifiedInferenceBinding;
deps?: SystemAgentConfiguredModelPlannerDeps;
}): Promise<SystemAgentAssistantPlan | null> {
return await planSystemAgentCommandWithConfiguredModel(params);
}
/** Plan only through the configured default agent's verified route. */
export async function planSystemAgentCommandWithConfiguredModel(params: {
input: string;
overview: SystemAgentOverview;
history?: SystemAgentAssistantTurn[];
pendingOperation?: string;
readonly verifiedInference: SystemAgentVerifiedInferenceBinding;
deps?: SystemAgentConfiguredModelPlannerDeps;
}): Promise<SystemAgentAssistantPlan | null> {
const input = params.input.trim();
if (!input) {
return null;
}
const prompt = buildSystemAgentAssistantUserPrompt({
input,
overview: params.overview,
...(params.history ? { history: params.history } : {}),
...(params.pendingOperation ? { pendingOperation: params.pendingOperation } : {}),
});
const result = await runConfiguredSystemAgentText({
prompt,
systemPrompt: SYSTEM_AGENT_ASSISTANT_SYSTEM_PROMPT,
runIdPrefix: "openclaw-planner",
verifiedInference: params.verifiedInference,
deps: params.deps,
responseFormat: SYSTEM_AGENT_PLANNER_RESPONSE_SCHEMA,
});
const parsed = parseSystemAgentAssistantPlanText(result?.text);
return parsed && result ? { ...parsed, modelLabel: result.modelLabel } : null;
}
/** One tool-free, verified inference turn for the cached caretaker greeting. */
export async function planSystemAgentGreetingWithConfiguredModel(params: {
overview: SystemAgentOverview;
facts: SystemAgentGreetingFacts;
readonly verifiedInference: SystemAgentVerifiedInferenceBinding;
deps?: SystemAgentConfiguredModelPlannerDeps;
timeoutMs: number;
}): Promise<SystemAgentGreetingPlan | null> {
const result = await runConfiguredSystemAgentText({
prompt: buildSystemAgentGreetingUserPrompt(params),
systemPrompt: SYSTEM_AGENT_GREETING_SYSTEM_PROMPT,
runIdPrefix: "openclaw-greeting",
verifiedInference: params.verifiedInference,
deps: params.deps,
timeoutMs: params.timeoutMs,
});
return result ? { text: result.text, modelRef: result.modelLabel } : null;
}
async function runConfiguredSystemAgentText(params: {
prompt: string;
systemPrompt: string;
runIdPrefix: string;
readonly verifiedInference: SystemAgentVerifiedInferenceBinding;
deps?: SystemAgentConfiguredModelPlannerDeps;
timeoutMs?: number;
responseFormat?: Record<string, unknown>;
}): Promise<{ text: string; modelLabel: string } | null> {
const route = await requireVerifiedPlannerRoute(params.verifiedInference, params.deps);
let expectedAgentHarnessRuntimeArtifact: ReturnType<
typeof resolveSystemAgentExpectedAgentHarnessRuntimeArtifact
>;
try {
expectedAgentHarnessRuntimeArtifact = resolveSystemAgentExpectedAgentHarnessRuntimeArtifact(
params.verifiedInference,
);
} catch (error) {
throw new SystemAgentInferenceUnavailableError("planner", [error]);
}
const tempDir = await (params.deps?.createTempDir ?? createTempPlannerDir)();
let text: string | undefined;
try {
const runId = `${params.runIdPrefix}-${randomUUID()}`;
const timeoutMs =
params.timeoutMs ??
(params.deps?.resolveAssistantTimeoutMs ?? resolveSystemAgentAssistantTimeoutMs)(route);
const shared = {
sessionId: `${runId}-session`,
// OpenClaw is the planner surface, but the configured roster owner supplies runtime policy.
agentId: route.agentId,
trigger: "manual" as const,
sessionFile: `in-memory:${runId}`,
sessionManager: SessionManager.inMemory(tempDir),
workspaceDir: tempDir,
cwd: tempDir,
agentDir: route.agentDir,
config: route.runConfig,
prompt: params.prompt,
provider: route.provider,
model: route.model,
timeoutMs,
thinkLevel: "off" as const,
runId,
extraSystemPrompt: params.systemPrompt,
extraSystemPromptStatic: params.systemPrompt,
messageChannel: "openclaw",
messageProvider: "openclaw",
disableTools: true,
disableTrajectory: true,
...(params.responseFormat ? { streamParams: { responseFormat: params.responseFormat } } : {}),
...(route.authProfileId ? { authProfileId: route.authProfileId } : {}),
};
const result =
route.runner === "cli"
? await (params.deps?.runCliAgent ?? (await import("../agents/cli-runner.js")).runCliAgent)(
{
...shared,
executionMode: "side-question",
cleanupCliLiveSessionOnRunEnd: true,
},
)
: await (
params.deps?.runEmbeddedAgent ??
(await import("../agents/embedded-agent.js")).runEmbeddedAgent
)({
...shared,
toolsAllow: [],
agentHarnessRuntimeOverride: route.agentHarnessRuntimeOverride,
...(expectedAgentHarnessRuntimeArtifact ? { expectedAgentHarnessRuntimeArtifact } : {}),
cleanupBundleMcpOnRunEnd: true,
...(route.authProfileId ? { authProfileIdSource: "user" as const } : {}),
});
text = extractPlannerResultText(result)?.trim();
} catch (error) {
if (error instanceof SystemAgentInferenceUnavailableError) {
throw error;
}
text = undefined;
} finally {
await (params.deps?.removeTempDir ?? removeTempPlannerDir)(tempDir);
}
if (!text) {
return null;
}
// Cleanup is the final suspension before callers can display model text, so
// authority must still match after cleanup completes.
await requireVerifiedPlannerRoute(params.verifiedInference, params.deps);
return { text, modelLabel: route.modelLabel };
}
async function requireVerifiedPlannerRoute(
binding: SystemAgentVerifiedInferenceBinding | undefined,
deps: SystemAgentConfiguredModelPlannerDeps | undefined,
) {
if (!binding) {
throw new SystemAgentInferenceUnavailableError("planner");
}
try {
const route = await resolveSystemAgentVerifiedInferenceRoute(binding, deps);
if (route) {
return route;
}
} catch (error) {
throw new SystemAgentInferenceUnavailableError("planner", [error]);
}
throw new SystemAgentInferenceUnavailableError("planner");
}
async function createTempPlannerDir(): Promise<string> {
return await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-planner-"));
}
async function removeTempPlannerDir(dir: string): Promise<void> {
await fs.rm(dir, { recursive: true, force: true });
}
function extractPlannerResultText(result: {
payloads?: Array<{ text?: string }>;
meta?: {
finalAssistantVisibleText?: string;
finalAssistantRawText?: string;
};
}): string | undefined {
return (
result.meta?.finalAssistantVisibleText ??
result.meta?.finalAssistantRawText ??
result.payloads
?.map((payload) => payload.text?.trim())
.filter(Boolean)
.join("\n")
);
}