feat(adapters): add Claude Fable 5.2 and GPT-6.2 with CLI floors, and refresh sandbox CLI pins (Nov 18 audit) (#22222)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agents run on coding harnesses. Each adapter has a model catalog,
and sandboxes contain pinned CLIs.
> - Anthropic released Claude Fable 5.2 and OpenAI released GPT-6.2 Sol
and GPT-6.2 Astra for Codex. Both need newer CLIs than the Paperclip
Runner provider pack ships.
> - A stale catalog hides valid models. A model that needs a newer CLI
fails with an opaque backend error.
> - This pull request adds the verified model IDs with their CLI floors,
names the version gap in Paperclip Runner, and refreshes the sandbox CLI
pins.
> - The benefit is that operators can select current models and get a
named version error instead of a backend failure.

## Linked Issues or Issue Description

Refs #20774 and #21636 (both add parts of Fable 5.2 support; see
"Overlap" below).
Refs #18486 (adds GPT-6.1 Terra; this PR does not duplicate it).
Refs #16708 (adds Claude Haiku 5.5 to `claude_local`; this PR does not
duplicate it).

**What happened?**

Claude Fable 5.2 (`claude-fable-5-2`) and GPT-6.2 Sol / Astra
(`gpt-6.2-sol`, `gpt-6.2-astra`) are generally available. The
`claude_local`, `codex_local`, and OpenCode pickers do not list them.
Claude Code 2.1.321 is the first release with Fable 5.2. Codex 0.169.1
is the first release whose bundled catalog lists GPT-6.2. The Paperclip
Runner provider pack bundles Claude Code 2.1.286 and Codex 0.160.0.

**Expected behavior**

The pickers list the new models. A run on a CLI below the model minimum
stops with the detected and required versions, or falls back to a
compatible model with a visible message.

**Proposed change**

Add the models and their per-model CLI floors. Gate ACPX Claude in
Paperclip Runner on the Claude Code version that its Agent SDK bundles.
Refresh the sandbox CLI pins with verified digests. Record the audit.

## What Changed

- Claude Code (`claude_local`):
- Add `claude-fable-5-2` (label "Claude Fable 5.2") at the top of the
picker. `claude-fable-5-1` stays selectable after the current-generation
models.
- Add Bedrock `global.anthropic.claude-fable-5-2`. Anthropic documents
only this global ID for Bedrock.
  - Fable 5.2 offers all five efforts (`low` to `max`).
- `minimumClaudeCliVersionForModel("claude-fable-5-2")` returns
`2.1.321`. The existing CLI-lane Test and launch checks use this floor.
On a managed sandbox, the CLI lane installs a private Claude Code at
this version, as it does for the other floors.
- Paperclip Runner (ACPX Codex): `resolvePaperclipRunnerProviderProfile`
rejects a model whose Codex floor is above the qualified ACPX Codex
runtime (`0.160.0`). The error code is
`paperclip_runner_codex_cli_version_incompatible`, and the message gives
both versions.
- Paperclip Runner (ACPX Claude):
`resolvePaperclipRunnerProviderProfile` rejects a model whose Claude
Code floor is above the version that the qualified Agent SDK bundles.
The error code is `paperclip_runner_claude_cli_version_incompatible`.
The message gives both versions. A new helper,
`claudeCodeVersionForAgentSdk`, maps SDK `0.3.N` to Claude Code `2.1.N`
(the SDK's `claudeCodeVersion` field) and returns `null` for any other
line.
- Codex (`codex_local`):
- Add `gpt-6.2-sol` and `gpt-6.2-astra` at the top of the picker, in the
bundled catalog order.
  - Both offer Fast mode and the `low` to `ultra` efforts.
- Both have a CLI floor of `0.169.1`. On the native Codex provider with
the pinned Codex 0.160.0, the existing fallback moves `gpt-6.2-sol` to
`gpt-6.1-sol` and `gpt-6.2-astra` to `gpt-6-astra` with a visible
message.
  - The default stays `gpt-6.1-sol`.
- OpenCode fallback catalog: add `openai/gpt-6.2-sol`,
`openai/gpt-6.2-astra`, `anthropic/claude-fable-5-2`,
`google/gemini-4-carbon`, and `google/gemini-4-hydrogen`.
- Evaluation image sandbox layer (`docker/daytona-runner`):

  | CLI | Before | After |
  | --- | --- | --- |
  | Grok CLI | 1.0.70 | 1.0.89 |
  | Gemini CLI | 0.65.0 | 0.68.0 |
  | Cursor CLI | 2026.10.22-27dcf5f | 2026.11.17-f532c45 |
  | GitHub CLI | 2.103.3 | 2.105.0 |

- Add `doc/adapter-model-audit-2026-11-18.md` with sources,
compatibility findings, and deferred items. Add a note on above-window
Codex floors to `doc/architecture/paperclip-runner-compatibility.md`.

No saved agent changes model, effort, or spending settings. No picker
entry is removed.

### Managed sandboxes

On Paperclip Runner, Fable 5.2 and GPT-6.2 stay unusable until the
provider pack moves to Claude Code 2.1.321 or later and Codex 0.169.1 or
later. A sandbox image that carries that provider pack must also be
promoted. This PR does not change the provider pack (see "Deferred
items" in the audit). Native remote Codex accepts only `>=0.149.0
<0.161.0`, so GPT-6.2 also needs that window to move.

### Overlap

- #21636 sets the Fable 5.2 floor to `2.1.290`. The [Claude Code
changelog](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md)
adds Fable 5.2 in 2.1.321. `git merge-tree` merges the two without a
text conflict, but #21636's line becomes unreachable after this PR's
line, and its test then fails. Rule: keep `2.1.321`. Merge this PR
first. Then close #21636 or change its floor and test to `2.1.321`.
- #20774 (draft) lists `claude-fable-5-2`. It conflicts in
`packages/adapters/claude-local/src/index.ts` and
`server/src/__tests__/adapter-models.test.ts`. Rule: keep this PR's
catalog order and Bedrock ID.
- #18486 adds `gpt-6.1-terra`. It conflicts in
`packages/adapters/codex-local/src/index.test.ts` and
`src/server/codex-args.test.ts` (the ordered ID list and the Fast-mode
message). Rule: keep both sets of models in the bundled catalog order
(`gpt-6.2-sol`, `gpt-6.2-astra`, `gpt-6-astra`, `gpt-6.1-sol`,
`gpt-6.1-terra`, ...). Either PR can merge first; the second rebases.
- #16708 adds Claude Haiku 5.5. It conflicts in
`packages/adapters/claude-local/src/index.test.ts` (adjacent test cases)
and `doc/DEVELOPING.md`. Rule: keep both test blocks.

## Verification

Research date: November 18, 2026. Sources are listed in the audit doc.

- `vitest run src/index.test.ts src/server/model-order.test.ts
src/server/cli-capabilities.test.ts src/server/test.remote.test.ts` in
`packages/adapters/claude-local`: 40 passed. `execute.remote.test.ts`
(29), `test.probe.test.ts` (21), `sandbox-cli-version.test.ts` (15),
`acp.auth.test.ts` (25), and `acp.test.ts` (47, with
`--testTimeout=60000`) also passed when run one file at a time.
- `vitest run src/index.test.ts src/server/codex-args.test.ts
src/ui/build-config.test.ts src/server/test.remote.test.ts` in
`packages/adapters/codex-local`: all passed (155). `acp.test.ts` (49),
`acp.cli-version.test.ts` (4), and `execute.test.ts` (10) also passed
one file at a time.
- `vitest run` in `packages/adapters/opencode-local`: 94 passed.
- `vitest run src/services/native-runtime/acpx-qualification.test.ts
src/services/native-runtime/codex-model-fallback.test.ts
src/__tests__/adapter-models.test.ts
src/__tests__/heartbeat-model-fallback-warning.test.ts` in `server`: all
passed. The new cases cover the ACPX Claude and ACPX Codex version
errors and the native GPT-6.2 fallback on Codex 0.160.0.
- `vitest run src/lib/agent-setup-fields.test.ts
src/lib/codex-reasoning-effort.test.ts` in `ui`: 11 passed.
- `tsc --noEmit` in the three adapters and `pnpm typecheck` in `server`:
passed.
- Cursor archive SHA-256
`189ed41d8963cd22dcdafbbd62f072cc55ac08374c922dbd04aee525f4018ab6` is
computed from the versioned Linux x64 tarball. The extracted binary
reports `2026.11.17-f532c45`, the version that
`https://cursor.com/install` resolves.
- GitHub CLI SHA-256
`79e7ab5db738c48777b696e374f8b428f0647debfb424f44d2f426370407fe2f`
matches `gh_2.105.0_checksums.txt`.
- Grok CLI 1.0.89 and Gemini CLI 0.68.0 installed from npm report those
versions. The flags that Paperclip uses are in `--help` (`-m`,
`--effort`, `grok models`; `-m`, `-p`, `--output-format`,
`--approval-mode`, `--yolo`).
- Host baseline: tests that create an AI provider need the host's empty
`ANTHROPIC_BASE_URL` unset. Under full-package parallel runs, SSH and
sandbox fixture tests time out at 5 seconds on this host; each file
passes alone. The audit doc records both.
- Not run locally: the full `pnpm -r typecheck`, `pnpm build`, browser
suites, and the image build. CI runs these. No live model inference ran.

## Risks

- Low risk for saved agents: no default, saved model, effort, or
spending setting changes.
- The new Paperclip Runner checks reject `claude-fable-5-2` on ACPX
Claude and `gpt-6.2-*` on ACPX Codex (and any later model whose floor is
above the bundled runtime) before launch. Without this PR, the turn
would start and fail at the backend.
- The `0.3.N` → `2.1.N` mapping covers only the current SDK line. Any
other line returns `null`, and the check is skipped.
- The sandbox CLI pins change only the evaluation image. The fleet image
change is separate.
- Rollback: revert this PR. No data migration.

## Model Used

- Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, through Claude Code
with tool use (shell, web fetch, file edits).

## 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
- [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
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: devinfoley <139239+devinfoley@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
authored and GitHub committed 2026-11-18 14:27:00 -08:00
1 parent e4b119440e
commit eaac8ed0f7
17 files changed
+273 -28

No files matched your search

+107
View File
@@ -0,0 +1,107 @@
# Adapter model and harness audit: November 18, 2026
This audit follows the [October 23, 2026 audit](adapter-model-audit-2026-10-23.md).
It covers model selection in the coding-agent adapters and the CLI pins in the
evaluation sandbox image. Catalog entries identify models; provider accounts
and installed CLIs determine access. No agent defaults or saved model
selections are migrated.
## Model changes
| Adapter | Changes from the audit |
| --- | --- |
| Claude Code (direct and Bedrock) | Add Claude Fable 5.2 (`claude-fable-5-2`; Bedrock `global.anthropic.claude-fable-5-2`) at the top of the picker. Fable 5.1 stays selectable after the current-generation models. Fable 5.2 supports all five effort levels and needs Claude Code 2.1.321 or later. The CLI-lane Test and launch report that minimum. Paperclip Runner (ACPX Claude) now rejects a model whose minimum is above the Claude Code that its Agent SDK bundles, with a named version error. |
| Codex | Add `gpt-6.2-sol` and `gpt-6.2-astra` with Fast mode and the `low` to `ultra` efforts. Both need Codex 0.169.1 or later. On an older CLI, native Codex runs fall back to `gpt-6.1-sol` or `gpt-6-astra` and show a message. ACPX Codex in Paperclip Runner rejects them before launch with a named version error. The default stays `gpt-6.1-sol`. |
| OpenCode | Add `openai/gpt-6.2-sol`, `openai/gpt-6.2-astra`, `anthropic/claude-fable-5-2`, `google/gemini-4-carbon`, and `google/gemini-4-hydrogen` to the static fallback. All five IDs are in the OpenCode model registry (models.dev). |
| Gemini CLI | No change. Gemini CLI 0.68.0 still registers no Gemini 4 model. Deferred. |
| Grok Build, Kimi Code, Cursor, Pi, Hermes | No new verified model IDs. |
## Harness changes
| Harness | Before | After |
| --- | --- | --- |
| Grok CLI (`@xai-official/grok`) | 1.0.70 | 1.0.89 |
| Gemini CLI | 0.65.0 | 0.68.0 |
| Cursor CLI (sandbox layer) | 2026.10.22-27dcf5f | 2026.11.17-f532c45 |
| GitHub CLI | 2.103.3 | 2.105.0 |
| Kimi Code CLI | 2.3.3 | Unchanged; see "Deferred items" |
| Codex CLI (shared provider pack) | 0.160.0 | Unchanged; see "Deferred items" |
| Claude Agent SDK / Claude Code | 0.3.286 / 2.1.286 | Unchanged; see "Deferred items" |
| OpenCode (shared provider pack) | 1.18.34 | Unchanged; see "Deferred items" |
| Hermes | 0.19.0 | 0.19.0 (newest on PyPI) |
These pins change only the evaluation image's sandbox layer. They must stay
aligned with the fleet sandbox image definition. Native Grok uses its separate
1.0.13 prerequisite and does not use the global Grok CLI.
Fable 5.2 and GPT-6.2 do not run on Paperclip Runner in managed sandboxes
until a Paperclip release with newer provider-pack harnesses is rolled out and
a sandbox image that carries it is promoted. On Paperclip Runner, Fable 5.2
fails before launch with the named Claude Code version error, and GPT-6.2
falls back as described above. The legacy Claude CLI lane already installs a
private Claude Code at the model minimum when the sandbox can reach the npm
registry.
## Sources and verification
Research date: November 18, 2026.
- [Claude Code changelog](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md),
2.1.321: "Added Claude Fable 5.2 (`claude-fable-5-2`), now the default Fable
model". npm `latest` is 2.1.327. `@anthropic-ai/claude-agent-sdk` 0.3.N
declares `claudeCodeVersion` 2.1.N (checked for 0.3.286, 0.3.321, and 0.3.327).
- [Claude models overview](https://platform.claude.com/docs/en/about-claude/models/overview):
Fable 5.2's API ID is `claude-fable-5-2` and its Amazon Bedrock ID is
`global.anthropic.claude-fable-5-2`. Claude Mythos 5.2 has limited availability.
- [Effort](https://platform.claude.com/docs/en/build-with-claude/effort):
"Claude Fable 5.2 supports all five effort levels."
- The bundled `codex-rs/models-manager/models.json` lists `gpt-6.2-sol` and
`gpt-6.2-astra` (visibility `list`, `minimal_client_version` 0.166.0,
efforts `low` to `ultra`, `fast` tier) from
[rust-v0.169.1](https://github.com/openai/codex/releases/tag/rust-v0.169.1).
[rust-v0.169.0](https://github.com/openai/codex/releases/tag/rust-v0.169.0)
does not list them. 0.170.0 is the npm `latest`. The catalog orders
GPT-6.2 Sol before GPT-6.2 Astra.
- [models.dev](https://models.dev/api.json) lists `openai/gpt-6.2-sol`,
`openai/gpt-6.2-astra`, `anthropic/claude-fable-5-2`,
`google/gemini-4-carbon`, and `google/gemini-4-hydrogen`.
- Gemini CLI 0.68.0 `packages/core/src/config/models.ts` has no Gemini 4
entry. The 0.66.0 to 0.68.0 release notes contain fixes only for the
`-p`, `--model`, and settings paths that Paperclip uses.
- Grok CLI 1.0.89 and Gemini CLI 0.68.0 are the npm `latest` tags.
- Cursor CLI 2026.11.17-f532c45 is the version `https://cursor.com/install`
resolves. The archive SHA-256 was computed from the versioned Linux x64 tarball.
- [GitHub CLI 2.105.0](https://github.com/cli/cli/releases/tag/v2.105.0): the
pinned digest matches the release `checksums.txt`.
- [Hermes on PyPI](https://pypi.org/project/hermes-agent/) remains at 0.19.0.
## Deferred items
- **Provider-pack runtimes.** Codex 0.170.0, Claude Code 2.1.327 (Agent SDK
0.3.327), and OpenCode 1.19.6 need runner qualification. Native remote Codex
accepts only `>=0.149.0 <0.161.0`, so GPT-6.2 needs that window and the
install pin to move. The deferred Claude 2.1.286 → 2.1.308 headless-default
changes from the previous audit still apply.
- **Kimi Code 2.6.3.** The native Kimi profile binds 2.3.3 with a patched
distribution closure. A new version needs its own qualification.
- **GPT-6.1 Terra** is in the Codex catalog. [#18486](https://github.com/paperclipai/paperclip/pull/18486)
adds it; this audit does not duplicate it.
- **Claude Haiku 5.5** in the Claude Code picker is covered by
[#16708](https://github.com/paperclipai/paperclip/pull/16708).
- **Claude Mythos 5.2** has limited availability.
- **Gemini 4** (Argon, Carbon, Hydrogen) in the Gemini CLI and Cursor catalogs:
the CLI does not register them, and Cursor documents display names only.
- **GPT-6.2 API pricing.** The reviewed Codex rate card has no GPT-6.2 entry,
so direct-API receipts for it stay unpriced until the card is reviewed.
## Host-environment baseline failures
Recorded once for this audit, Node 25.9.0:
- Server tests that create an AI provider fail at import with
`AI_InvalidArgumentError: baseURL must be a non-empty string.` because the
host sets `ANTHROPIC_BASE_URL` to an empty value. They pass with it unset.
- Under full-package parallel runs, Claude and Codex adapter tests that use SSH
and sandbox fixtures exceed the 5-second test timeout on this host. The
failing set differs between runs. Each file passes when run alone or with
`--testTimeout=60000`.
@@ -70,6 +70,9 @@ release follows a backward-compatible protocol.
startup reports the supported range and the remediation.
- Runner binary contracts, required runner capabilities, artifact digests,
provider-pack manifests, and runtime permission checks are unchanged.
- A model whose Codex floor is above the window (GPT-6.2 needs `0.169.1`)
cannot run natively. A selection of it falls back to the newest same-class
model that the CLI accepts and shows a visible message.
This window does not relax the separate ACP provider-pack qualification.
When qualifying newer Codex releases, review the upper bound in
+6 -6
View File
@@ -81,8 +81,8 @@ ENV PATH=${PAPERCLIP_RUNNER_PROVIDER_PACK_ROOT}/node_modules/.bin:/usr/local/sha
# Never add a second CLI version to work around a runner compatibility pin.
RUN npm uninstall -g @anthropic-ai/claude-code @openai/codex opencode-ai \
&& npm install -g \
@xai-official/grok@1.0.70 \
@google/gemini-cli@0.65.0 \
@xai-official/grok@1.0.89 \
@google/gemini-cli@0.68.0 \
@moonshot-ai/kimi-code@2.3.3 \
&& npm cache clean --force
@@ -94,8 +94,8 @@ RUN /usr/bin/python3 -m venv /opt/hermes \
&& /opt/hermes/bin/pip install --no-cache-dir hermes-agent==0.19.0 \
&& ln -sf /opt/hermes/bin/hermes /usr/local/bin/hermes
ARG CURSOR_VERSION=2026.10.22-27dcf5f
ARG CURSOR_SHA256_AMD64=85296944e4600a83c4b764f578d1502bf9c416db200d33a593e8f3ecabfdc294
ARG CURSOR_VERSION=2026.11.17-f532c45
ARG CURSOR_SHA256_AMD64=189ed41d8963cd22dcdafbbd62f072cc55ac08374c922dbd04aee525f4018ab6
RUN set -eu; \
arch="$(dpkg --print-architecture)"; \
[ "$arch" = "amd64" ] || { echo "FATAL: cursor pin only covers amd64, not $arch" >&2; exit 1; }; \
@@ -109,8 +109,8 @@ RUN set -eu; \
ln -sf /usr/local/bin/cursor-agent /usr/local/bin/agent; \
chmod -R a+rX /opt/cursor
ARG GH_VERSION=2.103.3
ARG GH_SHA256_AMD64=4c806978ffce1cec70853302a56d70ac6da4f19bae7adca4e1a8ab00633dd91d
ARG GH_VERSION=2.105.0
ARG GH_SHA256_AMD64=79e7ab5db738c48777b696e374f8b428f0647debfb424f44d2f426370407fe2f
RUN set -eu; \
arch="$(dpkg --print-architecture)"; \
[ "$arch" = "amd64" ] || { echo "FATAL: gh pin only covers amd64, not $arch" >&2; exit 1; }; \
+8 -6
View File
@@ -24,14 +24,16 @@ The October 2026 refreshes pin Codex 0.160.0, Claude Agent SDK
0.3.286 (Claude Code 2.1.286), and OpenCode 1.18.34 in the shared provider
pack. Claude Code 2.1.280 is the minimum for
[Opus 5.5](https://code.claude.com/docs/en/model-config) and 2.1.284 is the
minimum for Sonnet 5.5; the pinned runtime also supports Fable 5.1. Codex
0.160.0 ships bundled metadata for the current
[GPT-6.1 Sol, GPT-6 Sol, and GPT-6 Luna model IDs](https://learn.chatgpt.com/docs/models).
The sandbox layer pins Grok CLI 1.0.70, Gemini CLI 0.65.0, Kimi Code 2.3.3,
Cursor CLI 2026.10.22-27dcf5f, and GitHub CLI 2.103.3 (October 2026
minimum for Sonnet 5.5; the pinned runtime also supports Fable 5.1. Fable 5.2
needs Claude Code 2.1.321, so it does not run on Paperclip Runner with this
image until the provider pack moves past that version. Codex 0.160.0 ships bundled metadata for the
[GPT-6.1 Sol, GPT-6 Sol, and GPT-6 Luna model IDs](https://learn.chatgpt.com/docs/models);
GPT-6.2 Sol and Astra need Codex 0.169.1.
The sandbox layer pins Grok CLI 1.0.89, Gemini CLI 0.68.0, Kimi Code 2.3.3,
Cursor CLI 2026.11.17-f532c45, and GitHub CLI 2.105.0 (November 2026
refresh). The native Cursor provider uses its separately verified distribution,
pinned to 2026.09.26-dd393fe; it does not use the sandbox layer’s global Cursor
executable. Grok CLI 1.0.70 supports the current
executable. Grok CLI 1.0.89 supports the current
[Grok 4.7](https://docs.x.ai/developers/grok-4-7) model family. Hermes stays
at 0.19.0, the newest release on PyPI.
@@ -1,6 +1,6 @@
import { describe, expect, it } from "vitest";
import { claudeLocalReasoningEffortsForModel, DEFAULT_CLAUDE_LOCAL_MODEL, resolveClaudeModel } from "./index.js";
import { minimumClaudeCliVersionForModel } from "./server/cli-capabilities.js";
import { claudeLocalReasoningEffortsForModel, DEFAULT_CLAUDE_LOCAL_MODEL, models, resolveClaudeModel } from "./index.js";
import { claudeCodeVersionForAgentSdk, minimumClaudeCliVersionForModel } from "./server/cli-capabilities.js";
describe("Claude model defaults", () => {
it.each([
@@ -24,6 +24,21 @@ describe("Claude model defaults", () => {
expect(claudeLocalReasoningEffortsForModel(model)).toEqual(["low", "medium", "high", "xhigh", "max"]);
});
it.each([
"claude-fable-5-2",
"claude-fable-5-2[1m]",
"global.anthropic.claude-fable-5-2",
])("requires CLI 2.1.321 and offers all efforts for %s", (model) => {
expect(minimumClaudeCliVersionForModel(model)).toBe("2.1.321");
expect(claudeLocalReasoningEffortsForModel(model)).toEqual(["low", "medium", "high", "xhigh", "max"]);
});
it("lists Fable 5.2 first and keeps Fable 5.1 selectable", () => {
const ids = models.map((model) => model.id);
expect(ids[0]).toBe("claude-fable-5-2");
expect(ids).toContain("claude-fable-5-1");
});
it("keeps model-specific Claude reasoning limits", () => {
expect(claudeLocalReasoningEffortsForModel("claude-fable-5-1")).toContain("xhigh");
expect(claudeLocalReasoningEffortsForModel("claude-sonnet-5")).toContain("max");
@@ -33,6 +48,14 @@ describe("Claude model defaults", () => {
expect(claudeLocalReasoningEffortsForModel("custom-model")).toEqual(["low", "medium", "high"]);
});
it("maps an Agent SDK 0.3.N release to the Claude Code 2.1.N it bundles", () => {
expect(claudeCodeVersionForAgentSdk("0.3.286")).toBe("2.1.286");
expect(claudeCodeVersionForAgentSdk(" 0.3.321 ")).toBe("2.1.321");
for (const version of ["0.4.1", "0.3.286-beta.1", "", null, undefined]) {
expect(claudeCodeVersionForAgentSdk(version)).toBeNull();
}
});
it.each([undefined, null, "", " "])("uses Opus 5.5 for an unset model (%j)", (model) => {
expect(DEFAULT_CLAUDE_LOCAL_MODEL).toBe("claude-opus-5-5");
expect(resolveClaudeModel(model)).toBe("claude-opus-5-5");
+4 -2
View File
@@ -26,7 +26,7 @@ export const type = "claude_local";
export function claudeLocalReasoningEffortsForModel(model: string): readonly string[] {
const id = model.trim().replace(/\[1m\]$/, "").replace(/^(?:(?:us|eu|apac|global|jp|au)\.)?anthropic\./, "");
if (/^claude-haiku-/.test(id)) return [];
if (/^claude-(?:opus-5(?:-5)?|opus-4-[78]|sonnet-5(?:-5)?|fable-5(?:-1)?)$/.test(id)) {
if (/^claude-(?:opus-5(?:-5)?|opus-4-[78]|sonnet-5(?:-5)?|fable-5(?:-[12])?)$/.test(id)) {
return ["low", "medium", "high", "xhigh", "max"];
}
if (/^claude-(?:opus|sonnet)-4-6(?:-v1)?$/.test(id)) return ["low", "medium", "high", "max"];
@@ -40,11 +40,12 @@ export const SANDBOX_INSTALL_COMMAND = "npm install -g @anthropic-ai/claude-code
// first, by decreasing capability, then older releases grouped by family. The server applies the
// same order to discovered models (server/model-order.ts); the picker keeps it.
export const models = [
{ id: "claude-fable-5-1", label: "Claude Fable 5.1" },
{ id: "claude-fable-5-2", label: "Claude Fable 5.2" },
{ id: "claude-mythos-5", label: "Claude Mythos 5" },
{ id: "claude-opus-5-5", label: "Claude Opus 5.5" },
{ id: "claude-sonnet-5-5", label: "Claude Sonnet 5.5" },
{ id: "claude-haiku-4-5", label: "Claude Haiku 4.5" },
{ id: "claude-fable-5-1", label: "Claude Fable 5.1" },
{ id: "claude-fable-5", label: "Claude Fable 5" },
{ id: "claude-opus-5", label: "Claude Opus 5" },
{ id: "claude-opus-4-8", label: "Claude Opus 4.8" },
@@ -94,6 +95,7 @@ Operational fields:
- graceSec (number, optional): SIGTERM grace period in seconds
Notes:
- Claude Fable 5.2 uses model ID \`claude-fable-5-2\` (Bedrock: \`global.anthropic.claude-fable-5-2\`) and requires Claude Code v2.1.321 or later.
- Claude Opus 5.5 uses model ID \`claude-opus-5-5\` and requires Claude Code v2.1.280 or later.
- Claude Sonnet 5.5 uses model ID \`claude-sonnet-5-5\` and requires Claude Code v2.1.284 or later.
- filesystemScope and networkScope are spawn-level confinement and are orthogonal to Claude permission flags. Both require Bubblewrap on the host and explicit engine="cli"; default or explicit ACP is rejected because ACP confinement is not yet supported. networkScope="allowlist" injects HTTP_PROXY/HTTPS_PROXY for the CLI while its private network namespace blocks direct sockets, so every required provider/API hostname must be listed explicitly.
@@ -39,6 +39,8 @@ function cacheKeyForTarget(command: string, target: AdapterExecutionTarget | nul
export function minimumClaudeCliVersionForModel(model: string): string | null {
const modelId = model.trim().replace(/\[1m\]$/, "").replace(/^(?:(?:us|eu|apac|global|jp|au)\.)?anthropic\./, "");
// Claude Code 2.1.321 changelog: "Added Claude Fable 5.2 (`claude-fable-5-2`)".
if (modelId === "claude-fable-5-2") return "2.1.321";
if (modelId === "claude-opus-5-5") return "2.1.280";
if (modelId === "claude-sonnet-5-5") return "2.1.284";
return modelId === "claude-fable-5-1"
@@ -46,6 +48,16 @@ export function minimumClaudeCliVersionForModel(model: string): string | null {
: null;
}
/**
* The Claude Code version an Agent SDK release bundles. SDK 0.3.N ships Claude Code 2.1.N
* (its package.json `claudeCodeVersion`); any other SDK line returns null so callers skip the
* comparison rather than guess.
*/
export function claudeCodeVersionForAgentSdk(sdkVersion: string | null | undefined): string | null {
const patch = /^0\.3\.(\d+)$/.exec(sdkVersion?.trim() ?? "")?.[1];
return patch ? `2.1.${patch}` : null;
}
export function parseClaudeCliVersion(output: string): string | null {
return output.match(/\b(\d+)\.(\d+)\.(\d+)\b/)?.[0] ?? null;
}
@@ -5,7 +5,10 @@ export { listClaudeSkills, syncClaudeSkills } from "./skills.js";
export { listClaudeModels, refreshClaudeModels, resetClaudeModelsCacheForTests } from "./models.js";
export { testEnvironment } from "./test.js";
export {
claudeCliVersionAtLeast,
claudeCodeVersionForAgentSdk,
claudeCommandSupportsEffortFlag,
minimumClaudeCliVersionForModel,
resetClaudeCliCapabilitiesCacheForTests,
} from "./cli-capabilities.js";
export {
@@ -14,6 +14,8 @@ const ANTHROPIC_API_VERSION = "2023-06-01";
* then older releases grouped by family.
*/
const BEDROCK_MODELS: AdapterModel[] = [
// Anthropic documents Fable 5.2 on Bedrock only by its global inference profile ID.
{ id: "global.anthropic.claude-fable-5-2", label: "Bedrock Fable 5.2" },
// Fable 5.1's documented geo inference ID carries no -v1 suffix, unlike earlier entries.
{ id: "us.anthropic.claude-fable-5-1", label: "Bedrock Fable 5.1" },
{ id: "us.anthropic.claude-opus-5-5", label: "Bedrock Opus 5.5" },
@@ -19,6 +19,9 @@ describe("codex model CLI floors", () => {
expect(minimumCodexCliVersionForModel(" gpt-6.1-sol ")).toBe("0.159.0");
expect(minimumCodexCliVersionForModel("gpt-6-sol")).toBe("0.157.0");
expect(minimumCodexCliVersionForModel("gpt-6-luna")).toBe("0.157.0");
// 0.169.1 is the first stable release whose bundled catalog lists GPT-6.2.
expect(minimumCodexCliVersionForModel("gpt-6.2-sol")).toBe("0.169.1");
expect(minimumCodexCliVersionForModel("gpt-6.2-astra")).toBe("0.169.1");
});
it("gates the default model on its CLI floor and keeps the compatibility fallback floor-free", () => {
@@ -83,7 +86,9 @@ describe("codex local adapter metadata", () => {
expect(DEFAULT_CODEX_LOCAL_MODEL).toBe("gpt-6.1-sol");
expect(CODEX_LOCAL_COMPATIBILITY_FALLBACK_MODEL).toBe("gpt-5.6-sol");
// Ordered like the ChatGPT app: newest version first, then by capability within a version (#14878).
expect(modelIds.slice(0, 13)).toEqual([
expect(modelIds.slice(0, 15)).toEqual([
"gpt-6.2-sol",
"gpt-6.2-astra",
"gpt-6.1-sol",
"gpt-6-astra",
"gpt-6-sol",
@@ -103,11 +108,13 @@ describe("codex local adapter metadata", () => {
expect(isCodexLocalFastModeSupported("gpt-6-astra")).toBe(true);
expect(isCodexLocalFastModeSupported("gpt-6.1-sol")).toBe(true);
expect(isCodexLocalFastModeSupported("gpt-6-sol")).toBe(true);
expect(isCodexLocalFastModeSupported("gpt-6.2-sol")).toBe(true);
expect(isCodexLocalFastModeSupported("gpt-6.2-astra")).toBe(true);
expect(modelIds).not.toContain("gpt-5.3-codex");
expect(modelIds).not.toContain("gpt-5.3-codex-spark");
});
it.each(["gpt-6-astra", "gpt-6.1-sol", "gpt-6-sol", " gpt-6-sol ", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6"])("uses the reasoning efforts advertised for %s", (model) => {
it.each(["gpt-6.2-sol", "gpt-6.2-astra", "gpt-6-astra", "gpt-6.1-sol", "gpt-6-sol", " gpt-6-sol ", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6"])("uses the reasoning efforts advertised for %s", (model) => {
expect(codexLocalReasoningEffortsForModel(model)).toEqual([
"low",
"medium",
+13 -2
View File
@@ -42,6 +42,8 @@ export function resolveCodexLocalCliPolicy(config: unknown, options: { networkAc
}
export const CODEX_LOCAL_FAST_MODE_SUPPORTED_MODELS = [
"gpt-6.2-sol",
"gpt-6.2-astra",
"gpt-6-astra",
"gpt-6.1-sol",
"gpt-6-sol",
@@ -100,6 +102,8 @@ export function codexLocalReasoningEffortsForModel(
): readonly CodexLocalReasoningEffort[] {
const normalizedModel = normalizeCodexModel(model);
switch (normalizedModel) {
case "gpt-6.2-sol":
case "gpt-6.2-astra":
case "gpt-6-astra":
case "gpt-6.1-sol":
case "gpt-6-sol":
@@ -119,9 +123,14 @@ export function codexLocalReasoningEffortsForModel(
// "The '<model>' model is not supported when using Codex with a ChatGPT account.", which reads
// like an account problem when it is really a stale install, typically a sandbox image baked
// before the catalog gained the model. Record the oldest stable release verified to work so the
// Test and the remote runner can name the actual gap. Omit models with no verified floor; the
// install pin in the runner and images is always at or above every floor listed here.
// Test and the remote runner can name the actual gap. Omit models with no verified floor. A floor
// above the runner's install pin keeps the model usable only where a newer CLI is installed.
const CODEX_LOCAL_MODEL_MINIMUM_CLI_VERSIONS: Readonly<Record<string, string>> = {
// 0.169.1 is the first release whose bundled catalog lists GPT-6.2 (0.169.0 does not), though
// the catalog entry declares minimal_client_version 0.166.0. The runner pin is still older, so
// remote runs fall back to gpt-6.1-sol / gpt-6-astra with a visible message until it moves.
"gpt-6.2-sol": "0.169.1",
"gpt-6.2-astra": "0.169.1",
// 0.156.1 and older are rejected (openai/codex#49396); 0.159.0 and 0.159.2 are accepted
// (openai/codex#49464). No stable release between those was verified either way.
"gpt-6.1-sol": "0.159.0",
@@ -220,6 +229,8 @@ export function isCodexLocalFastModeSupported(model: string | null | undefined):
// then by decreasing capability inside each version, older models at the end. The server
// returns this list as written and the model dropdown keeps its order.
export const models = [
{ id: "gpt-6.2-sol", label: "gpt-6.2-sol" },
{ id: "gpt-6.2-astra", label: "gpt-6.2-astra" },
{ id: "gpt-6.1-sol", label: "gpt-6.1-sol" },
{ id: "gpt-6-astra", label: "gpt-6-astra" },
{ id: "gpt-6-sol", label: "gpt-6-sol" },
@@ -163,7 +163,7 @@ describe("buildCodexExecArgs", () => {
expect(result.fastModeRequested).toBe(true);
expect(result.fastModeApplied).toBe(false);
expect(result.fastModeIgnoredReason).toContain(
"currently only supported on gpt-6-astra, gpt-6.1-sol, gpt-6-sol, gpt-6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.4 or manually configured model IDs",
"currently only supported on gpt-6.2-sol, gpt-6.2-astra, gpt-6-astra, gpt-6.1-sol, gpt-6-sol, gpt-6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.4 or manually configured model IDs",
);
expect(result.args).toEqual([
"exec",
@@ -53,6 +53,8 @@ export function isValidOpenCodeModelId(value: unknown): value is string {
export const models: Array<{ id: string; label: string }> = [
{ id: DEFAULT_OPENCODE_LOCAL_MODEL, label: DEFAULT_OPENCODE_LOCAL_MODEL },
{ id: "openai/gpt-6.2-sol", label: "openai/gpt-6.2-sol" },
{ id: "openai/gpt-6.2-astra", label: "openai/gpt-6.2-astra" },
{ id: "openai/gpt-6-astra", label: "openai/gpt-6-astra" },
{ id: "openai/gpt-6.1-sol", label: "openai/gpt-6.1-sol" },
{ id: "openai/gpt-6-sol", label: "openai/gpt-6-sol" },
@@ -62,11 +64,14 @@ export const models: Array<{ id: string; label: string }> = [
{ id: "openai/gpt-5.6-luna", label: "openai/gpt-5.6-luna" },
{ id: "anthropic/claude-opus-5-5", label: "anthropic/claude-opus-5-5" },
{ id: "anthropic/claude-opus-5", label: "anthropic/claude-opus-5" },
{ id: "anthropic/claude-fable-5-2", label: "anthropic/claude-fable-5-2" },
{ id: "anthropic/claude-fable-5-1", label: "anthropic/claude-fable-5-1" },
{ id: "anthropic/claude-sonnet-5-5", label: "anthropic/claude-sonnet-5-5" },
{ id: "anthropic/claude-sonnet-5", label: "anthropic/claude-sonnet-5" },
{ id: "anthropic/claude-haiku-5-5", label: "anthropic/claude-haiku-5-5" },
{ id: "google/gemini-4-carbon", label: "google/gemini-4-carbon" },
{ id: "google/gemini-4-argon", label: "google/gemini-4-argon" },
{ id: "google/gemini-4-hydrogen", label: "google/gemini-4-hydrogen" },
{ id: "google/gemini-3.8-flash", label: "google/gemini-3.8-flash" },
{ id: "xai/grok-4.7", label: "xai/grok-4.7" },
{ id: "openai/gpt-5.5", label: "openai/gpt-5.5" },
+8 -6
View File
@@ -65,10 +65,11 @@ describe("adapter model listing", () => {
expect(models).toEqual(claudeFallbackModels);
expect(models.some((model) => model.id === "claude-opus-4-8")).toBe(true);
// Newest release of the most capable family leads the list (#14877).
expect(models[0]?.id).toBe("claude-fable-5-1");
expect(models[0]?.id).toBe("claude-fable-5-2");
expect(models.some((model) => model.id === "claude-sonnet-5")).toBe(true);
expect(models.some((model) => model.id === "claude-opus-4-5")).toBe(true);
expect(models.some((model) => model.id === "claude-fable-5-1")).toBe(true);
expect(models.some((model) => model.id === "claude-fable-5-2")).toBe(true);
expect(models.some((model) => model.id === "claude-fable-5")).toBe(true);
expect(models.some((model) => model.id === "claude-mythos-5")).toBe(true);
// Opus 5 is a current GA flagship and must be offered even when live discovery is unavailable.
@@ -101,7 +102,7 @@ describe("adapter model listing", () => {
expect(first.some((model) => model.id === "claude-sonnet-5-5")).toBe(true);
// Discovered models take the curated order too: the API's order is not shown as-is.
const firstIds = first.map((model) => model.id);
expect(firstIds[0]).toBe("claude-fable-5-1");
expect(firstIds[0]).toBe("claude-fable-5-2");
expect(firstIds.indexOf("claude-opus-5-5")).toBeLessThan(firstIds.indexOf("claude-opus-4-8"));
expect(firstIds.indexOf("claude-opus-4-8")).toBeLessThan(firstIds.indexOf("claude-opus-4-8-20260529"));
});
@@ -143,6 +144,7 @@ describe("adapter model listing", () => {
});
it.each([
["claude-fable-5-2", "Claude Fable 5.2"],
["claude-fable-5-1", "Claude Fable 5.1"],
["claude-opus-5-5", "Claude Opus 5.5"],
["claude-sonnet-5-5", "Claude Sonnet 5.5"],
@@ -163,14 +165,14 @@ describe("adapter model listing", () => {
expect(models.some((model) => model.id === "claude-opus-4-8")).toBe(true);
});
it("exposes the Bedrock-native Fable 5.1 ID (never the direct ID) in Bedrock mode", async () => {
it("exposes Bedrock-native Fable IDs (never the direct IDs) in Bedrock mode", async () => {
process.env.CLAUDE_CODE_USE_BEDROCK = "1";
const fetchSpy = vi.spyOn(globalThis, "fetch");
const models = await listAdapterModels("claude_local");
// Fable 5.1 leads here too, using its documented dateless Bedrock ID.
expect(models[0]?.id).toBe("us.anthropic.claude-fable-5-1");
// Fable 5.2 leads here too; Anthropic documents only its global inference profile ID.
expect(models[0]?.id).toBe("global.anthropic.claude-fable-5-2");
expect(models.map((model) => model.id)).toEqual(expect.arrayContaining([
"us.anthropic.claude-opus-5-5", "us.anthropic.claude-opus-5", "us.anthropic.claude-sonnet-5-5",
"us.anthropic.claude-sonnet-5", "us.anthropic.claude-fable-5-1", "us.anthropic.claude-opus-4-7",
@@ -178,7 +180,7 @@ describe("adapter model listing", () => {
]));
expect(models.some((model) => model.id === "claude-sonnet-5-5")).toBe(false);
expect(models.map((model) => model.id)).not.toEqual(expect.arrayContaining(["us.anthropic.claude-opus-4-8-v1"]));
expect(models.some((model) => model.id === "claude-fable-5-1")).toBe(false);
expect(models.some((model) => model.id === "claude-fable-5-1" || model.id === "claude-fable-5-2")).toBe(false);
expect(fetchSpy).not.toHaveBeenCalled();
});
@@ -88,6 +88,34 @@ describe("host ACPX qualification admission", () => {
expect(resolvePaperclipRunnerNativeProviderInput({ backend: "acpx_runtime", adapterConfig }))
.toMatchObject({ acpxAgent, model: "explicit-new-model" });
});
it("names the Claude Code gap when the bundled SDK predates the model's minimum", () => {
expect(QUALIFIED_ACPX_PROFILES.claude.agentRuntimeVersion).toBe("0.3.286");
for (const model of ["claude-fable-5-2", "claude-fable-5-2[1m]"]) {
expect(() => resolvePaperclipRunnerProviderProfile({ provider: "acpx", acpxAgent: "claude", model }))
.toThrow(expect.objectContaining({
code: "paperclip_runner_claude_cli_version_incompatible",
message: expect.stringContaining("requires Claude Code 2.1.321 or newer; this Paperclip Runner bundles Claude Code 2.1.286"),
}));
}
for (const model of ["claude-opus-5-5", "claude-sonnet-5-5", "claude-fable-5-1"]) {
expect(resolvePaperclipRunnerProviderProfile({ provider: "acpx", acpxAgent: "claude", model }))
.toMatchObject({ acpxAgent: "claude", model });
}
});
it("names the Codex gap when the qualified ACPX runtime predates the model's minimum", () => {
expect(QUALIFIED_ACPX_PROFILES.codex.agentRuntimeVersion).toBe("0.160.0");
for (const model of ["gpt-6.2-sol", "gpt-6.2-astra"]) {
expect(() => resolvePaperclipRunnerProviderProfile({ provider: "acpx", acpxAgent: "codex", model }))
.toThrow(expect.objectContaining({
code: "paperclip_runner_codex_cli_version_incompatible",
message: expect.stringContaining("requires Codex 0.169.1 or newer; this Paperclip Runner bundles Codex 0.160.0"),
}));
}
for (const model of ["gpt-6.1-sol", "gpt-6-astra"]) {
expect(resolvePaperclipRunnerProviderProfile({ provider: "acpx", acpxAgent: "codex", model }))
.toMatchObject({ acpxAgent: "codex", model });
}
});
it("requires an explicit Codex ACP selection", () => {
for (const model of [undefined, "", " "]) {
expect(() => resolvePaperclipRunnerProviderProfile({ provider: "acpx", acpxAgent: "codex", model }))
@@ -24,6 +24,13 @@ describe("bounded Codex model fallback", () => {
expect(unavailable.mock.calls).toEqual([["gpt-6-sol"], ["gpt-5.6-sol"]]);
});
it("moves GPT-6.2 to the newest same-class model the pinned 0.160.0 CLI accepts", () => {
expect(codexModelFallbackCandidates("gpt-6.2-sol")).toEqual(["gpt-6.1-sol", "gpt-6-sol", "gpt-5.6-sol"]);
expect(codexModelFallbackCandidates("gpt-6.2-astra")).toEqual(["gpt-6-astra", "gpt-5.6-sol"]);
expect(compatibleCodexModel("gpt-6.2-sol", "0.160.0")).toBe("gpt-6.1-sol");
expect(compatibleCodexModel("gpt-6.2-astra", "0.160.0")).toBe("gpt-6-astra");
});
it.each([
["gpt-6.1-sol", "0.159.0"], ["gpt-6-sol", "0.157.0"], ["gpt-5.6-sol", "0.156.0"],
["team-model", "0.156.0"], [null, "0.156.0"], ["gpt-6.1-sol", null],
@@ -11,8 +11,10 @@ import {
type PaperclipRunnerProvider,
} from "@paperclipai/adapter-utils";
import {
codexCliVersionAtLeast,
codexLocalReasoningEffortsForModel,
isCodexLocalKnownModel,
minimumCodexCliVersionForModel,
} from "@paperclipai/adapter-codex-local";
import {
AGENTCORE_QUALIFIED_MODEL,
@@ -20,6 +22,11 @@ import {
} from "../provider-profile-qualification.js";
import { resolveAcpxQualification, resolveAntigravityCandidateAdmission, resolveKimiCandidateAdmission, type AcpxQualificationCandidate } from "./acpx-qualification.js";
import { compatibleCodexModel } from "./codex-model-fallback.js";
import {
claudeCliVersionAtLeast,
claudeCodeVersionForAgentSdk,
minimumClaudeCliVersionForModel,
} from "@paperclipai/adapter-claude-local/server";
import { parseNativeCursorCloudConfig, type NativeCursorCloudConfig } from "../../vendor/paperclip-runner/index.js";
export const QUALIFIED_OPENCODE_RUNNER_VERSION = "1.18.34" as const;
@@ -642,14 +649,38 @@ export function resolvePaperclipRunnerProviderProfile(
const selectedModel = acpxAgent === "grok" && model === "grok-build"
? DEFAULT_ACPX_RUNNER_MODELS.grok
: model || DEFAULT_ACPX_RUNNER_MODELS[acpxAgent] || "";
let qualifiedProfile: ReturnType<typeof resolveQualifiedAcpxProfile>;
try {
resolveQualifiedAcpxProfile(acpxAgent, selectedModel);
qualifiedProfile = resolveQualifiedAcpxProfile(acpxAgent, selectedModel);
} catch (error) {
throw new PaperclipRunnerProviderProfileError(
"paperclip_runner_acpx_model_unqualified",
error instanceof Error ? error.message : "Paperclip Runner ACPX requires an admitted model.",
);
}
if (acpxAgent === "claude") {
// The provider pack runs the Claude Code its Agent SDK bundles; name the gap instead of
// letting an older CLI fail the turn with an opaque backend error.
const minimum = minimumClaudeCliVersionForModel(selectedModel);
const bundled = claudeCodeVersionForAgentSdk(qualifiedProfile.agentRuntimeVersion);
if (minimum && bundled && !claudeCliVersionAtLeast(bundled, minimum)) {
throw new PaperclipRunnerProviderProfileError(
"paperclip_runner_claude_cli_version_incompatible",
`${selectedModel} requires Claude Code ${minimum} or newer; this Paperclip Runner bundles Claude Code ${bundled}. Choose another model or use the legacy Claude runner until the Runner is updated.`,
);
}
}
if (acpxAgent === "codex") {
// ACPX Codex runs the qualified runtime pin, so the backend would reject a newer model.
const minimum = minimumCodexCliVersionForModel(selectedModel);
const bundled = qualifiedProfile.agentRuntimeVersion;
if (minimum && bundled && !codexCliVersionAtLeast(bundled, minimum)) {
throw new PaperclipRunnerProviderProfileError(
"paperclip_runner_codex_cli_version_incompatible",
`${selectedModel} requires Codex ${minimum} or newer; this Paperclip Runner bundles Codex ${bundled}. Choose another model or use the legacy Codex runner until the Runner is updated.`,
);
}
}
return {
provider: "acpx",
backend: "acpx_runtime",