Files
openclaw/src/agents/execution-contract.ts
Peter Steinberger bb46b79d3c refactor: internalize OpenClaw agent runtime (#85341)
* 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
2026-05-27 19:24:04 +01:00

124 lines
5.3 KiB
TypeScript

import type { OpenClawConfig } from "../config/types.openclaw.js";
import { normalizeLowercaseStringOrEmpty } from "../shared/string-coerce.js";
import { resolveAgentExecutionContract, resolveSessionAgentIds } from "./agent-scope.js";
/**
* Strip any leading `provider/` or `provider:` prefix from a model id so the
* bare-name regex matching below works against `openai/gpt-5.4` and
* `openai:gpt-5.4` the same way it does against `gpt-5.4`. Returns the bare
* model id lowercased for comparison.
*
* Without this, auto-activation silently failed on prefixed model ids — a
* user who configured `model: "openai/gpt-5.4"` in their agent config would
* get the pre-PR-H looser default behavior because the regex only matched
* bare names. The adversarial review in #64227 flagged this as a quality
* gap on completion-gate criterion 1.
*/
export function stripProviderPrefix(modelId: string): string {
const normalizedModelId = modelId.trim();
const match = /^([^/:]+)[/:](.+)$/.exec(normalizedModelId);
return (match?.[2] ?? normalizedModelId).toLowerCase();
}
/**
* Regex that matches the full set of GPT-5 variants the strict-agentic
* contract should auto-activate for. Intentionally permissive: every
* model id in the gpt-5 family should opt in by default, not just the
* canonical `gpt-5.4`.
*
* Covers:
* - `gpt-5`, `gpt-5o`, `gpt-5o-mini` (no separator after `5`)
* - `gpt-5.4`, `gpt-5.4-alt`, `gpt-5.0` (dot separator)
* - `gpt-5-preview`, `gpt-5-turbo`, `gpt-5-2025-03` (dash separator)
*
* Does NOT cover `gpt-4.5`, `gpt-6`, or any non-gpt-5 family member.
*/
const STRICT_AGENTIC_MODEL_ID_PATTERN = /^gpt-5(?:[.o-]|$)/i;
/**
* Supported provider + model combinations where strict-agentic is the intended
* runtime contract. Kept as a narrow helper so both the execution-contract
* resolver and the `update_plan` auto-enable gate converge on the same
* definition of "GPT-5-family openai/openai-codex run". The embedded
* `mock-openai` QA lane intentionally piggybacks on that contract so repo QA
* can exercise the same incomplete-turn recovery rules end to end.
*/
export function isStrictAgenticSupportedProviderModel(params: {
provider?: string | null;
modelId?: string | null;
}): boolean {
const provider = normalizeLowercaseStringOrEmpty(params.provider ?? "");
if (provider !== "openai" && provider !== "openai-codex" && provider !== "mock-openai") {
return false;
}
const modelId = typeof params.modelId === "string" ? params.modelId : "";
const bareModelId = stripProviderPrefix(modelId);
return STRICT_AGENTIC_MODEL_ID_PATTERN.test(bareModelId);
}
/**
* Returns the effective execution contract for an embedded OpenClaw run.
*
* strict-agentic is a GPT-5-family openai/openai-codex-only runtime contract,
* so an unsupported provider/model pair always collapses to `"default"`
* regardless of what the caller passed or what config says — the contract
* is inert off-provider. Within the supported lane, the behavior matrix is:
*
* - Supported provider/model + explicit `"strict-agentic"` in config
* (defaults or per-agent override) ⇒ `"strict-agentic"`.
* - Supported provider/model + explicit `"default"` in config ⇒ `"default"`
* (opt-out honored).
* - Supported provider/model + unspecified ⇒ `"strict-agentic"` so the
* no-stall completion-gate criterion applies to out-of-the-box GPT-5 runs
* without requiring every user to set the flag.
* - Unsupported provider/model (anything that is not openai or openai-codex
* with a gpt-5-family model id) ⇒ `"default"`, even when the config
* explicitly sets `"strict-agentic"`. The retry guard and blocked-exit
* helpers all check this lane again, so an explicit `"strict-agentic"`
* on an unsupported lane is a no-op rather than a hard failure.
*
* This means explicit opt-out still works, but the gate criterion
* "GPT-5.4 no longer stalls after planning" now covers unconfigured
* installations, not only users who opted in manually.
*/
export function resolveEffectiveExecutionContract(params: {
config?: OpenClawConfig;
sessionKey?: string;
agentId?: string | null;
provider?: string | null;
modelId?: string | null;
}): "default" | "strict-agentic" {
const { sessionAgentId } = resolveSessionAgentIds({
sessionKey: params.sessionKey,
config: params.config,
agentId: params.agentId ?? undefined,
});
const explicit = resolveAgentExecutionContract(params.config, sessionAgentId);
// strict-agentic is a GPT-5-family openai/openai-codex runtime contract
// regardless of whether it was set explicitly or auto-activated. On an
// unsupported provider/model pair the contract is inert either way, so
// the effective value collapses to "default".
const supported = isStrictAgenticSupportedProviderModel({
provider: params.provider,
modelId: params.modelId,
});
if (!supported) {
return "default";
}
if (explicit === "default") {
return "default";
}
// Explicit strict-agentic OR unspecified-but-supported → strict-agentic.
return "strict-agentic";
}
export function isStrictAgenticExecutionContractActive(params: {
config?: OpenClawConfig;
sessionKey?: string;
agentId?: string | null;
provider?: string | null;
modelId?: string | null;
}): boolean {
return resolveEffectiveExecutionContract(params) === "strict-agentic";
}