feat(runner): refresh shared coding harness runtimes (#13838)

## Thinking Path

> - Paperclip runs agents through local adapters and the native runner.
> - Both paths must use the same installed provider CLI.
> - New models require current harness releases.
> - The runner still pins Codex 0.153.4, Claude SDK 0.3.263, and
OpenCode 1.18.29.
> - Changing the image alone would fail the runner's exact version and
executable checks.
> - This pull request updates those dependencies, integrity checks,
controller checks, and image pins together.
> - Shared installations can then run the current models without a
task-time download.

## Linked Issues or Issue Description

Refs #13829, which updates model choices and reasoning controls.
Searches found no open PR that updates these runtime pins.

**Current behavior**

The shared provider pack ships old CLIs. Claude Code 2.1.263 cannot run
Opus 5.5, which requires 2.1.280. Remote controllers reject provider
packs whose versions differ from their declared pins.

**Proposed behavior**

Use Codex 0.156.0, Claude Agent SDK 0.3.280 / Claude Code 2.1.280, and
OpenCode 1.18.32 throughout the runner. Keep the reviewed ACP bridge
patches and one shared CLI installation per provider.

**Reason and benefit**

Current harnesses support the new model IDs while preserving executable
verification and remote provider-pack compatibility checks.

## What Changed

- Update dependency overrides, the Codex ACP package patch, runtime
profiles, and remote controller pins.
- Verify the new Claude Linux x64 and macOS arm64/x64 executables and
Codex Linux x64 executable against integrity-verified npm archives.
- Refresh OpenCode version checks, fixtures, and the runner
configuration label.
- Refresh the eval image's Grok, Gemini, Kimi, Cursor, and GitHub CLI
pins and archive hashes. Hermes remains current at 0.19.0.
- Refresh the build-time lock digest from clean pnpm 9.15.4 resolution.
Leave lockfile commits to repository automation.
- Document model compatibility and the separation between CLI runtimes
and patched ACP bridges.

## Verification

- `pnpm -r typecheck` and `pnpm build` passed.
- Rust workspace release tests passed.
- Package/patch and OpenCode binary-materialization contract tests: 11
passed.
- Real Codex 0.156.0 startup-ownership and paginated session-resume
probes passed with isolated synthetic homes and no model turn.
- Codex app-server `thread/start` preserved `gpt-6-sol` and
`gpt-6-luna`; no `turn/start` was sent. An unauthenticated built-in
catalog does not include those account-served entries.
- Installed Claude integrity probes passed for `claude-opus-5-5` and
`claude-fable-5-1`.
- `pnpm --filter @paperclipai/paperclip-runner
test:opencode:qualification` passed with the actual OpenCode 1.18.32
executable under Node 24 and Node 25. The loopback provider exercise
covers health/version, session creation/read/delete, SSE, and a
completed async prompt.
- `pnpm check:token-gates` passed.
- The targeted runner suite passed 130 tests. Three macOS failures in
snapshot module lookup and OpenCode final-message selection also
reproduce on the unchanged base; Linux CI will provide the platform
check.
- [Final Linux
CI](https://github.com/paperclipai/paperclip/actions/runs/35798076399):
all gates passed. Four jobs needed one retry after their CI workers
received shutdown signals. The PR has 55 successful checks, two skipped
checks, Greptile 5/5, and no unresolved review threads.
- Changed runner configuration UI tests: 5 passed.
- Full macOS `pnpm test:run` reached 13,094 passing server tests, 84
skipped, and 18 failures before the wrapper stopped. Failures involved
skill-cache publication permissions, missing bundled connector skills in
the worktree, and a conversation-reset timing case. The 10 cache
permission failures reproduce on the unchanged base; both
conversation-reset cases passed on a targeted retry. The wrapper did not
reach its later workspace/serialized groups locally; Linux CI covers
those groups.
- The local Docker daemon did not respond, so no local Docker build was
run. No billable model requests were made.

## Risks

- Deploy the matching controller and provider pack together. Older
controllers enforce their previous exact pins.
- Current upstream CLIs can change behavior. Existing protocol tests and
isolated real Codex probes cover the integration boundaries;
authenticated model inference is not part of these checks.
- ACP bridge package versions and executable digests stay unchanged
because their executable bytes are unchanged. Only the underlying
CLI/SDK dependencies move.
- No schema migration. Revert the runtime and image pins together to
roll back.

## Model Used

OpenAI GPT-6 via Codex, with repository tools, code execution, and web
research. The exact serving model ID and context window were not exposed
by this session.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass for the changed surfaces
and real-executable probes; full macOS-suite limitations are listed
above
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>

server/src/__tests__/adapter-registry.test.ts

@@ -336,8 +336,8 @@ describe("server adapter registry", () => {
     const expectedCodexInstall = `if ! command -v 'codex' >/dev/null 2>&1; then ${buildSandboxNpmInstallCommand("@openai/codex")}; fi`;
     const expectedGeminiInstall = `if ! command -v 'gemini' >/dev/null 2>&1; then ${buildSandboxNpmInstallCommand("@google/gemini-cli")}; fi`;
     const expectedOpenCodeInstall = `if ! command -v 'opencode' >/dev/null 2>&1; then ${buildSandboxNpmInstallCommand("opencode-ai")}; fi`;
-    const expectedRunnerCodexInstall = `if ! command -v 'codex' >/dev/null 2>&1; then ${buildSandboxNpmInstallCommand("@openai/codex@0.153.4")}; fi`;
-    const expectedRunnerOpenCodeInstall = `if ! command -v 'opencode' >/dev/null 2>&1; then ${buildSandboxNpmInstallCommand("opencode-ai@1.18.29")}; fi`;
+    const expectedRunnerCodexInstall = `if ! command -v 'codex' >/dev/null 2>&1; then ${buildSandboxNpmInstallCommand("@openai/codex@0.156.0")}; fi`;
+    const expectedRunnerOpenCodeInstall = `if ! command -v 'opencode' >/dev/null 2>&1; then ${buildSandboxNpmInstallCommand("opencode-ai@1.18.32")}; fi`;
 
     expect(findActiveServerAdapter("claude_local")?.getRuntimeCommandSpec?.({})).toEqual({
       command: "claude",

server/src/adapters/registry.ts

@@ -508,7 +508,7 @@ const paperclipRunnerAdapter: ServerAdapterModule = {
           "opencode",
           `opencode-ai@${QUALIFIED_OPENCODE_RUNNER_VERSION}`,
         )
-      : buildNpmRuntimeCommandSpec(config, "codex", "@openai/codex@0.153.4"),
+      : buildNpmRuntimeCommandSpec(config, "codex", "@openai/codex@0.156.0"),
   agentConfigurationDoc:
     "# Paperclip Runner\n\nAdapter: paperclip_runner\n\nRuns Codex, OpenCode, Claude Managed, AWS AgentCore, or ACPX Claude through the Rust Paperclip runner and authenticated PRP transport. Pi is not available through the qualified ACPX profile. Managed providers use company-scoped qualified profiles, explicit retention acknowledgement, and spend limits.\n",
   getConfigSchema: () => ({

server/src/services/native-runtime/native-session-executor.test.ts

@@ -995,8 +995,8 @@ describe("remote provider pack manifest", () => {
     const payload = {
       pins: {
         nodeMinimum: "24.11.0",
-        codex: "0.153.4",
-        opencode: "1.18.29",
+        codex: "0.156.0",
+        opencode: "1.18.32",
         acpx: "0.13.1",
         claudeAcp: "0.73.0",
         codexAcp: "1.6.2",
@@ -1053,7 +1053,7 @@ describe("remote provider pack manifest", () => {
       );
     await writeManifest();
     expect(readRemoteProviderPackManifest(root).payload.pins.opencode).toBe(
-      "1.18.29",
+      "1.18.32",
     );
     for (const [artifactName, substituteName] of [
       ["nodeCommand", "productionLock"],
@@ -1983,7 +1983,7 @@ describe("remote preinstalled executable discovery", () => {
       const shim =
         '#!/bin/sh\ncat "$(dirname "$0")/version.txt"\nprintf "%s\\n" "$@"\n';
       await writeFile(source, shim, { mode: 0o755 });
-      await writeFile(join(installation, "version.txt"), "codex-cli 0.153.4\n");
+      await writeFile(join(installation, "version.txt"), "codex-cli 0.156.0\n");
       // Existing deployments may already have the old symlink. Never write
       // through it into the shared installation while upgrading the launcher.
       await symlink(source, target);
@@ -1996,7 +1996,7 @@ describe("remote preinstalled executable discovery", () => {
           execFileSync(target, ["--version", "argument with 'quotes'"], {
             encoding: "utf8",
           }),
-        ).toBe("codex-cli 0.153.4\n--version\nargument with 'quotes'\n");
+        ).toBe("codex-cli 0.156.0\n--version\nargument with 'quotes'\n");
         expect(await readFile(source, "utf8")).toBe(shim);
       }
       expect(await readdir(join(root, "workspace", "bin"))).toEqual(["codex"]);
@@ -10252,7 +10252,7 @@ describe("runnerd provider runtime wiring", () => {
         }), stderr: "",
       };
       if (command.args?.[0] === "--version") return {
-        exitCode: 0, timedOut: false, stdout: "codex-cli 0.153.4", stderr: "",
+        exitCode: 0, timedOut: false, stdout: "codex-cli 0.156.0", stderr: "",
       };
       if (command.args?.[2] === "paperclip-runner-launch") {
         throw new Error("fixture_stop_after_launch_staging");
@@ -10373,7 +10373,7 @@ describe("runnerd provider runtime wiring", () => {
           ) {
             throw new Error("reached-preinstalled-codex-verification");
           }
-          stdout = "codex-cli 0.153.4";
+          stdout = "codex-cli 0.156.0";
         } else if (script === "uname -s; uname -m") {
           stdout = `${process.platform === "darwin" ? "Darwin" : "Linux"}\n${process.arch === "arm64" ? "arm64" : "x86_64"}\n`;
         } else if (script.includes("command -v paperclip-runnerd")) {

server/src/services/native-runtime/native-session-executor.ts

@@ -9127,8 +9127,8 @@ const RUNNERD_BINARY_CONTRACT_VERSION = 2;
 const REMOTE_PROVIDER_PACK_SCHEMA = "paperclip-runner/remote-provider-pack/v1";
 const REMOTE_PROVIDER_PACK_PINS = {
   nodeMinimum: "24.11.0",
-  codex: "0.153.4",
-  opencode: "1.18.29",
+  codex: "0.156.0",
+  opencode: "1.18.32",
   acpx: "0.13.1",
   claudeAcp: "0.73.0",
   codexAcp: "1.6.2",

server/src/services/native-runtime/provider-profile.ts

@@ -9,7 +9,7 @@ import {
   CLAUDE_MANAGED_QUALIFIED_MODEL,
 } from "../provider-profile-qualification.js";
 
-export const QUALIFIED_OPENCODE_RUNNER_VERSION = "1.18.29" as const;
+export const QUALIFIED_OPENCODE_RUNNER_VERSION = "1.18.32" as const;
 export const DEFAULT_OPENCODE_RUNNER_MODEL =
   "openrouter/deepseek/deepseek-v4-flash-0731" as const;
 export const CLAUDE_MANAGED_BETA_VERSION = "managed-agents-2026-04-01" as const;