mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-22 11:54:35 +01:00
## 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>
149 lines
11 KiB
TypeScript
149 lines
11 KiB
TypeScript
import { afterEach, describe, expect, it, vi } from "vitest";
|
|
import { readFileSync } from "node:fs";
|
|
import { ACPX_QUALIFICATION_ENV, ANTIGRAVITY_CANDIDATE_ADMISSION_ENV, resolveAcpxQualification, resolveKimiCandidateAdmission } from "./acpx-qualification.js";
|
|
import { QUALIFIED_ACPX_PROFILES, KIMI_DISTRIBUTION_CLOSURE_SHA256 } from "../../vendor/paperclip-runner/index.js";
|
|
import type { NativeExecutionInput } from "../../vendor/paperclip-runner/index.js";
|
|
import { resolvePaperclipRunnerProviderProfile, resolvePaperclipRunnerNativeProviderInput } from "./provider-profile.js";
|
|
|
|
const provider = { kind: "acpx", agent: "copilot", model: "exact-model", permissionMode: "approve-all" } as Extract<NativeExecutionInput["provider"], { kind: "acpx" }>;
|
|
const authorize = (value: unknown) => ({ [ACPX_QUALIFICATION_ENV]: JSON.stringify(value) });
|
|
describe("host ACPX qualification admission", () => {
|
|
afterEach(() => vi.unstubAllEnvs());
|
|
|
|
it.each([undefined, "malformed", JSON.stringify(kimiAdmission("linux", "x64"))])("admits released Kimi without candidate authority (%s)", authority => {
|
|
vi.stubEnv(ANTIGRAVITY_CANDIDATE_ADMISSION_ENV, authority);
|
|
vi.stubEnv(ACPX_QUALIFICATION_ENV, "malformed-unrelated-authority");
|
|
const config = { provider: "acpx", acpxAgent: "kimi", model: "kimi-for-coding" };
|
|
expect(QUALIFIED_ACPX_PROFILES.kimi.agentProfileVersion).toBe(17);
|
|
expect(QUALIFIED_ACPX_PROFILES.kimi.qualificationStatus).not.toBe("pending");
|
|
expect(resolveKimiCandidateAdmission({ companyId: "candidate-company", model: config.model })).toBeUndefined();
|
|
expect(resolvePaperclipRunnerProviderProfile(config, { companyId: "candidate-company" })).toMatchObject(config);
|
|
expect(resolvePaperclipRunnerNativeProviderInput({ companyId: "candidate-company", backend: "acpx_runtime", adapterConfig: config }))
|
|
.toMatchObject({ ...config, acpxPermissionMode: "approve-all" });
|
|
expect(() => resolvePaperclipRunnerProviderProfile({ ...config, model: "" }))
|
|
.toThrow(expect.objectContaining({ code: "paperclip_runner_acpx_model_required" }));
|
|
});
|
|
|
|
it.each([undefined, "malformed", JSON.stringify([{ agent: "antigravity", model: "exact-model" }])])(
|
|
"keeps pending Antigravity closed despite host authorization (%s)", host => {
|
|
vi.stubEnv(ACPX_QUALIFICATION_ENV, host);
|
|
const config = { provider: "acpx", acpxAgent: "antigravity", model: "exact-model",
|
|
env: { [ACPX_QUALIFICATION_ENV]: JSON.stringify([{ agent: "antigravity", model: "exact-model" }]) } };
|
|
for (const resolve of [() => resolvePaperclipRunnerProviderProfile(config),
|
|
() => resolvePaperclipRunnerNativeProviderInput({ backend: "acpx_runtime", adapterConfig: config })]) {
|
|
expect(resolve).toThrow(expect.objectContaining({ code: "paperclip_runner_acpx_agent_unavailable" }));
|
|
expect(resolve).toThrow("Google Antigravity is awaiting native Runner acceptance");
|
|
}
|
|
},
|
|
);
|
|
|
|
it("admits only the exact Pi model without host authorization and preserves permission modes", () => {
|
|
const config = { provider: "acpx", acpxAgent: "pi", model: "openrouter/deepseek/deepseek-v4-flash-0731" };
|
|
for (const authorization of [undefined, "malformed unrelated candidate authorization"]) {
|
|
vi.stubEnv(ACPX_QUALIFICATION_ENV, authorization);
|
|
expect(resolvePaperclipRunnerProviderProfile(config)).toMatchObject(config);
|
|
for (const acpxPermissionMode of [undefined, "approve-all", "approve-paperclip", "approve-reads", "deny-all"]) {
|
|
expect(resolvePaperclipRunnerNativeProviderInput({ backend: "acpx_runtime", adapterConfig: { ...config, acpxPermissionMode } }))
|
|
.toMatchObject({ ...config, acpxPermissionMode: acpxPermissionMode ?? "approve-all" });
|
|
}
|
|
for (const model of [undefined, ""]) {
|
|
expect(() => resolvePaperclipRunnerProviderProfile({ ...config, model }))
|
|
.toThrow(expect.objectContaining({ code: "paperclip_runner_acpx_model_required" }));
|
|
}
|
|
}
|
|
});
|
|
|
|
it.each([[], {}, [{ agent: "cursor", model: "" }], [{ agent: "cursor", model: " exact-model" }],
|
|
[{ agent: "cursor", model: "exact-model", allowAll: true }], [{ agent: "claude", model: "exact-model" }],
|
|
[{ agent: "cursor", model: "exact-model" }, { agent: "cursor", model: "exact-model" }],
|
|
])("rejects malformed or broad authorization %j", entries => {
|
|
expect(() => resolveAcpxQualification({ ...provider, agent: "pi" }, authorize(entries))).toThrow("Invalid ACPX");
|
|
});
|
|
it("admits Cursor through ordinary configuration and ignores unrelated qualification authority", () => {
|
|
const config = { provider: "acpx", acpxAgent: "cursor", model: "exact-cursor-model" };
|
|
vi.stubEnv(ACPX_QUALIFICATION_ENV, JSON.stringify([{ agent: "pi", model: "pi-model" }]));
|
|
expect(resolvePaperclipRunnerProviderProfile(config)).toMatchObject({ acpxAgent: "cursor", model: config.model });
|
|
expect(resolvePaperclipRunnerNativeProviderInput({ backend: "acpx_runtime", adapterConfig: config })).toMatchObject({ acpxAgent: "cursor", model: config.model });
|
|
expect(resolveAcpxQualification({ ...provider, agent: "cursor" } as typeof provider, authorize([]))).toBeUndefined();
|
|
expect(() => resolvePaperclipRunnerProviderProfile({ ...config, model: "" })).toThrow(expect.objectContaining({ code: "paperclip_runner_acpx_model_required" }));
|
|
});
|
|
it.each([undefined, "malformed", JSON.stringify([{agent:"pi",model:"pi-model"}])])("admits ordinary Copilot without host overrides (%s)", host => {
|
|
vi.stubEnv(ACPX_QUALIFICATION_ENV,host);
|
|
const config={provider:"acpx",acpxAgent:"copilot",model:"gpt-5.6-luna"};
|
|
expect(resolvePaperclipRunnerProviderProfile(config)).toMatchObject({acpxAgent:"copilot",model:config.model});
|
|
expect(resolvePaperclipRunnerNativeProviderInput({backend:"acpx_runtime",adapterConfig:config})).toMatchObject({acpxAgent:"copilot",model:config.model});
|
|
expect(resolveAcpxQualification({...provider,model:config.model},{})).toBe("copilot");
|
|
});
|
|
it.each(["", " ", "auto", "default"])("refuses implicit Copilot model %s",model=>{
|
|
expect(()=>resolvePaperclipRunnerProviderProfile({provider:"acpx",acpxAgent:"copilot",model})).toThrow(expect.objectContaining({code:"paperclip_runner_acpx_model_required"}));
|
|
expect(()=>resolveAcpxQualification({...provider,model},{})).toThrow("explicit available model");
|
|
});
|
|
it("does not alter existing qualified providers", () => {
|
|
expect(resolveAcpxQualification({ ...provider, agent: "codex" } as typeof provider, authorize([]))).toBeUndefined();
|
|
});
|
|
it.each(["claude", "codex", "grok", "cursor", "pi"])("keeps %s model selection open to native verification", (acpxAgent) => {
|
|
const adapterConfig = { provider: "acpx", acpxAgent, model: "explicit-new-model" };
|
|
expect(resolvePaperclipRunnerProviderProfile(adapterConfig))
|
|
.toMatchObject({ acpxAgent, model: "explicit-new-model" });
|
|
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 }))
|
|
.toThrow(expect.objectContaining({ code: "paperclip_runner_acpx_model_unqualified" }));
|
|
}
|
|
});
|
|
it("preserves product defaults separately from qualification examples", () => {
|
|
for (const [acpxAgent, model] of [["claude", "claude-opus-5-5"], ["grok", "grok-4.7"]]) {
|
|
expect(resolvePaperclipRunnerProviderProfile({ provider: "acpx", acpxAgent }))
|
|
.toMatchObject({ acpxAgent, model });
|
|
}
|
|
});
|
|
it("binds the executor to host process environment rather than agent configuration", () => {
|
|
const source = readFileSync(new URL("./native-session-executor.ts", import.meta.url), "utf8");
|
|
expect(source).toContain("resolveAcpxQualification(input.execution.provider, process.env)");
|
|
expect(source).not.toContain("resolveAcpxQualification(input.execution.provider, effectiveRunnerEnvironment)");
|
|
});
|
|
});
|
|
|
|
it.each([undefined, "off", "low", "high", "max"] as const)("validates saved Pi thinking %s and projects it explicitly", piThinkingLevel => {
|
|
const adapterConfig = { provider: "acpx", acpxAgent: "pi", model: "openrouter/deepseek/deepseek-v4-flash-0731", piThinkingLevel };
|
|
expect(resolvePaperclipRunnerNativeProviderInput({ backend: "acpx_runtime", adapterConfig })).toMatchObject({ piThinkingLevel: piThinkingLevel ?? "low" });
|
|
for (const alias of ["medium", "minimal", "xhigh"]) expect(() => resolvePaperclipRunnerProviderProfile({ ...adapterConfig, piThinkingLevel: alias })).toThrow(expect.objectContaining({ code: "paperclip_runner_pi_thinking_invalid" }));
|
|
});
|
|
|
|
function kimiAdmission(platform: "darwin" | "linux", architecture: "arm64" | "x64") {
|
|
return { schema: "paperclip.acpx-candidate-admission.v1", companyId: "candidate-company", agent: "kimi", model: "kimi-for-coding",
|
|
platform, architecture, expiresAt: Date.now() + 60_000, profileDigest: QUALIFIED_ACPX_PROFILES.kimi.commandDigest,
|
|
nativeClosureDigest: `sha256:${KIMI_DISTRIBUTION_CLOSURE_SHA256[`${platform}-${architecture}` as "darwin-arm64" | "linux-x64"]}` };
|
|
}
|