mirror of
https://github.com/openclaw/openclaw.git
synced 2026-06-04 08:44:05 +00:00
* refactor: extract agent core package Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts. * refactor: extract shared llm runtime Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout. * refactor: remove pi runtime internals Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code. * refactor: tighten agent session runtime Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts. * refactor: remove static model and pi auth paths Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities. * refactor: remove legacy provider compat paths * docs: remove agent parity notes * fix: skip provider wildcard metadata parsing * refactor: share session extension sdk loading * refactor: inline acpx proxy error formatter * refactor: fold edit recovery into edit tool * fix: accept extension batch separator * test: align startup provider plugin expectations * fix: restore provider-scoped release discovery * test: align static asset packaging expectations * fix: run static provider catalogs during scoped discovery * fix: add provider entry catalogs for scoped live discovery * fix: load lightweight provider catalog entries * fix: refresh provider-scoped plugin metadata * fix: keep provider catalog entries on release live path * fix: keep static manifest models in release live checks * fix: harden release model discovery * fix: reduce OpenAI live cache probe reasoning * fix: disable OpenAI cache probe reasoning * ci: extend OpenAI gateway live timeout * fix: extend live gateway model budget * fix: stabilize release validation regressions * fix: honor provider aliases in model rows * fix: stabilize release validation lanes * fix: stabilize release memory qa * ci: stabilize release validation lanes * ci: prefer ipv4 for live docker node calls * fix: restore shared tool-call stream wrapper * ci: remove legacy pi test shard alias * fix: clean up embedded agent test drift * fix: stabilize runtime alias status * fix: clean up embedded agent ci drift * fix: restore release ci invariants * fix: clean up post-rebase runtime drift * fix: restore release ci checks * fix: restore release ci after rebase * fix: remove stale pi runtime path * test: align compaction runtime expectations * test: update plugin prerelease expectations * fix: handle claude live tool approvals * fix: stabilize release validation gates * fix: finish agent runtime import * test: finish post-rebase agent runtime mocks * fix: keep codex compaction native * fix: stabilize codex app-server hook tests * test: isolate codex diagnostic active run * test: remove codex diagnostic completion race # Conflicts: # extensions/codex/src/app-server/run-attempt.test.ts * ci: fix full release manifest performance run id * refactor: narrow llm plugin sdk boundary * chore: drop generated google boundary stamps * fix: repair rebase fallout * fix: clean up rebased runtime references * fix: decode codex jwt payloads as base64url * fix: preserve shipped pi runtime alias * fix: add scoped sdk virtual modules * fix: decode llm codex oauth jwt as base64url * fix: avoid stale vertex adc negative cache * fix: harden tool arg decoding and codeql path * fix: keep vertex adc negative checks live * refactor: consolidate codex jwt and edit helpers * fix: await codex oauth node runtime imports * fix: preserve sdk tool and notice contracts * fix: preserve shipped compat config boundaries * fix: align codex oauth callback host * fix: terminate agent-core loop streams on failure * fix: keep codex oauth callback alive during fallback * ci: include session tools in critical codeql scans * fix: keep Cloudflare Anthropic provider auth header * docs: redirect legacy pi runtime pages * fix: honor bundled web provider compat discovery * fix: protect session output spill files * fix: keep legacy agent dir env blocked * fix: contain auto-discovered skill symlinks * fix: harden agent core sdk proxy surfaces * fix: restore approval reaction sdk compat * fix: keep live docker runs bounded * fix: keep codex oauth redirect host aligned * fix: resolve post-rebase agent runtime drift * fix: redact anthropic oauth parse failures * fix: preserve responses strict tool shaping * fix: repair agent runtime rebase cleanup * docs: redirect retired parity pages * fix: bound auto-discovered resources to roots * fix: repair post-rebase agent test drift * fix: preserve bundled provider allowlist migration * fix: preserve manifest-owned provider aliases * fix: declare photon image dependency * fix: keep provider headers out of proxy body * fix: preserve shipped env aliases * fix: refresh control ui i18n generated state * fix: quote read fallback paths * fix: preview edits through configured backend * test: satisfy core test typecheck * fix: preserve ZAI usage auth fallback * test: repair codex diagnostic test * fix: repair agent runtime rebase drift * test: finish embedded runner import rename * fix: repair agent runtime rebase integrations * test: align compaction oauth fallback expectations * fix: allow sdk-auth session models * fix: update doctor tool schema import * fix: preserve bedrock plugin region * fix: stream harmony-like prose immediately * ci: include session runtime in codeql shards * fix: repair latest rebase integrations * fix: honor explicit codex websocket transport * fix: keep openai-compatible credentials provider-scoped * fix: refresh sdk api baseline after rebase * fix: route cli runtime aliases through openclaw harness * test: rename stale harness mock expectation * test: rename embedded agent overflow calls * test: clean embedded auth test wording * test: use openclaw stream types in deepinfra cache test * fix: refresh sdk api baseline on latest main * fix: honor bundled discovery compat allowlists * fix: refresh sdk api baseline after latest rebase * fix: remove stale rebase imports * test: rename stale model catalog mock * test: mock renamed doctor runtime modules * fix: map canonical kimi env auth * fix: use internal model registry in bench script * fix: migrate deepinfra provider catalog entry * fix: enforce builtin tool suppression * fix: route compaction auth and proxy payloads safely * refactor: prune unused llm registry leftovers * test: update codex hooks session import * test: fix model picker ci coverage * test: align model picker auth mock types
193 lines
5.9 KiB
TypeScript
193 lines
5.9 KiB
TypeScript
import type { CliBackendConfig } from "../config/types.js";
|
|
import type { OpenClawConfig } from "../config/types.openclaw.js";
|
|
import type { ContextEngineHostCapability } from "../context-engine/types.js";
|
|
|
|
export type PluginTextReplacement = {
|
|
from: string | RegExp;
|
|
to: string;
|
|
};
|
|
|
|
export type PluginTextTransforms = {
|
|
/** Rewrites applied to outbound prompt text before provider/CLI transport. */
|
|
input?: PluginTextReplacement[];
|
|
/** Rewrites applied to inbound assistant text before OpenClaw consumes it. */
|
|
output?: PluginTextReplacement[];
|
|
};
|
|
|
|
export type CliBundleMcpMode =
|
|
| "claude-config-file"
|
|
| "codex-config-overrides"
|
|
| "gemini-system-settings";
|
|
|
|
export type CliBackendPrepareExecutionContext = {
|
|
config?: OpenClawConfig;
|
|
workspaceDir: string;
|
|
agentDir?: string;
|
|
provider: string;
|
|
modelId: string;
|
|
authProfileId?: string;
|
|
};
|
|
|
|
export type CliBackendPreparedExecution = {
|
|
env?: Record<string, string>;
|
|
clearEnv?: string[];
|
|
cleanup?: () => Promise<void>;
|
|
};
|
|
|
|
export type CliBackendThinkingLevel =
|
|
| "off"
|
|
| "minimal"
|
|
| "low"
|
|
| "medium"
|
|
| "high"
|
|
| "xhigh"
|
|
| "adaptive"
|
|
| "max";
|
|
|
|
export type CliBackendResolveExecutionArgsContext = {
|
|
config?: OpenClawConfig;
|
|
workspaceDir: string;
|
|
provider: string;
|
|
modelId: string;
|
|
authProfileId?: string;
|
|
thinkingLevel?: CliBackendThinkingLevel;
|
|
useResume: boolean;
|
|
baseArgs: readonly string[];
|
|
};
|
|
|
|
export type CliBackendResolveExecutionArgs = (
|
|
ctx: CliBackendResolveExecutionArgsContext,
|
|
) => readonly string[] | null | undefined;
|
|
|
|
export type CliBackendAuthEpochMode = "combined" | "profile-only";
|
|
|
|
export type CliBackendNativeToolMode = "none" | "always-on";
|
|
|
|
export type CliBackendNormalizeConfigContext = {
|
|
config?: OpenClawConfig;
|
|
backendId: string;
|
|
agentId?: string;
|
|
};
|
|
|
|
/** Plugin-owned CLI backend defaults used by the text-only CLI runner. */
|
|
export type CliBackendPlugin = {
|
|
/** Provider id used in model refs, for example `claude-cli/opus`. */
|
|
id: string;
|
|
/** Canonical model provider whose models this CLI backend can execute. */
|
|
modelProvider?: string;
|
|
/** Default backend config before user overrides from `agents.defaults.cliBackends`. */
|
|
config: CliBackendConfig;
|
|
/**
|
|
* Context-engine host capabilities provided by this backend when it is
|
|
* driven through the generic CLI runner.
|
|
*/
|
|
contextEngineHostCapabilities?: readonly ContextEngineHostCapability[];
|
|
/**
|
|
* Optional live-smoke metadata owned by the backend plugin.
|
|
*
|
|
* Keep provider-specific test wiring here instead of scattering it across
|
|
* Docker wrappers, docs, and gateway live tests.
|
|
*/
|
|
liveTest?: {
|
|
defaultModelRef?: string;
|
|
defaultImageProbe?: boolean;
|
|
defaultMcpProbe?: boolean;
|
|
docker?: {
|
|
npmPackage?: string;
|
|
binaryName?: string;
|
|
};
|
|
};
|
|
/**
|
|
* Whether OpenClaw should inject bundle MCP config for this backend.
|
|
*
|
|
* Keep this opt-in. Only backends that explicitly consume OpenClaw's bundle
|
|
* MCP bridge should enable it.
|
|
*/
|
|
bundleMcp?: boolean;
|
|
/**
|
|
* Provider-owned bundle MCP integration strategy.
|
|
*
|
|
* Different CLIs wire MCP through different surfaces:
|
|
* - Claude: `--strict-mcp-config --mcp-config`
|
|
* - Codex: `-c mcp_servers=...`
|
|
* - Gemini: system-level `settings.json`
|
|
*/
|
|
bundleMcpMode?: CliBundleMcpMode;
|
|
/**
|
|
* Optional config normalizer applied after user overrides merge.
|
|
*
|
|
* Use this for backend-specific compatibility rewrites when old config
|
|
* shapes need to stay working.
|
|
*/
|
|
normalizeConfig?: (
|
|
config: CliBackendConfig,
|
|
context?: CliBackendNormalizeConfigContext,
|
|
) => CliBackendConfig;
|
|
/**
|
|
* Backend-owned final system-prompt transform.
|
|
*
|
|
* Use this for tiny CLI-specific compatibility rewrites without replacing
|
|
* the generic CLI runner or prompt builder.
|
|
*/
|
|
transformSystemPrompt?: (ctx: {
|
|
config?: OpenClawConfig;
|
|
workspaceDir?: string;
|
|
provider: string;
|
|
modelId: string;
|
|
modelDisplay: string;
|
|
agentId?: string;
|
|
systemPrompt: string;
|
|
}) => string | null | undefined;
|
|
/**
|
|
* Backend-owned bidirectional text replacements.
|
|
*
|
|
* `input` applies to the system prompt and user prompt passed to the CLI.
|
|
* `output` applies to parsed/streamed assistant text from the CLI.
|
|
*/
|
|
textTransforms?: PluginTextTransforms;
|
|
/**
|
|
* Preferred auth-profile id when the caller did not explicitly lock one.
|
|
*
|
|
* Use this when the backend should consume a canonical OpenClaw auth profile
|
|
* rather than ambient host auth by default.
|
|
*/
|
|
defaultAuthProfileId?: string;
|
|
/**
|
|
* Session/auth epoch source policy.
|
|
*
|
|
* `combined` keeps the legacy "host credential + auth profile" fingerprint.
|
|
* `profile-only` treats the selected OpenClaw auth profile as the sole auth
|
|
* owner for session invalidation when one is present.
|
|
*/
|
|
authEpochMode?: CliBackendAuthEpochMode;
|
|
/**
|
|
* Backend-owned execution bridge.
|
|
*
|
|
* Use this on async run paths when the backend needs a generated auth/config
|
|
* bridge (for example a private CLI home directory) without teaching the core
|
|
* runner about provider-specific file formats.
|
|
*/
|
|
prepareExecution?: (
|
|
ctx: CliBackendPrepareExecutionContext,
|
|
) =>
|
|
| Promise<CliBackendPreparedExecution | null | undefined>
|
|
| CliBackendPreparedExecution
|
|
| null
|
|
| undefined;
|
|
/**
|
|
* Backend-owned per-run argv rewrite.
|
|
*
|
|
* Use this for request-scoped CLI dialect flags that should not be modeled
|
|
* as static config, such as mapping OpenClaw thinking levels to a backend's
|
|
* native effort flag.
|
|
*/
|
|
resolveExecutionArgs?: CliBackendResolveExecutionArgs;
|
|
/**
|
|
* Whether this CLI backend can expose native tools outside OpenClaw's tool
|
|
* catalog. Backends that cannot provide a true no-tools mode must mark
|
|
* themselves as `always-on` so callers that require disabled tools fail
|
|
* closed instead of launching a native harness.
|
|
*/
|
|
nativeToolMode?: CliBackendNativeToolMode;
|
|
};
|