mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-16 10:50:38 +09:00
Add cheap model profiles for local adapters (#4881)
## Thinking Path > - Paperclip is a control plane for autonomous AI companies, where adapters are the boundary between the board, agents, and execution runtimes. > - Local adapters currently expose a primary runtime configuration, but operators often need a cheaper model lane for routine or low-risk work. > - That cheap lane has to stay adapter-owned: runtime profile settings should not mutate the primary adapter config or bypass existing auth/secret mediation. > - Issue creation also needs an ergonomic way to request primary, cheap, or custom model behavior for a selected assignee. > - This pull request adds a first-class `cheap` model profile contract across adapter capabilities, heartbeat config resolution, agent configuration, and issue creation. > - The benefit is cheaper task execution can be configured and requested explicitly while preserving adapter boundaries, secret handling, and audit visibility. ## What Changed - Added adapter model-profile capability metadata and a `cheap` profile contract for supported local adapters. - Applied `runtimeConfig.modelProfiles.cheap.adapterConfig` during heartbeat config resolution, including requested/applied/fallback run metadata. - Added agent configuration UI for cheap model profile settings without writing those settings into primary `adapterConfig`. - Added New Issue assignee model lane controls for Primary / Cheap / Custom and request payload handling. - Added run ledger profile badges and Storybook stories for the new cheap-lane UI states. - Added tests for validators, heartbeat model profile application, permission/secret mediation, UI payload helpers, and run ledger rendering. - Added committed UI verification screenshots under `docs/pr-screenshots/pap-2837/`. - Addressed Greptile review feedback around cheap-profile defaults, shared profile types, and fallback test data. ## Verification Local: - `pnpm exec vitest run packages/shared/src/validators/issue.test.ts server/src/__tests__/adapter-registry.test.ts server/src/__tests__/agent-permissions-routes.test.ts server/src/__tests__/heartbeat-model-profile.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/lib/agent-config-patch.test.ts ui/src/lib/issue-assignee-overrides.test.ts ui/src/lib/new-agent-runtime-config.test.ts` — passed, 8 files / 103 tests. - `pnpm exec vitest run ui/src/lib/new-agent-runtime-config.test.ts ui/src/components/IssueRunLedger.test.tsx` — passed after Greptile/rebase follow-up, 2 files / 17 tests. - `pnpm --filter @paperclipai/ui typecheck` — passed after Greptile/rebase follow-up. - `pnpm -r typecheck` — passed. - `pnpm build` — passed. - `pnpm test:run` — did not complete successfully in this local worktree: it stopped in pre-existing `@paperclipai/adapter-utils` sandbox/SSH fixture suites outside this PR diff. Failures were 5s local timeouts plus `git init -b` unsupported by this machine's Git 2.21.0. The branch-specific targeted suites above passed. - Branch was fetched/rebased onto `public-gh/master`; `git rev-list --left-right --count public-gh/master...HEAD` reports `0 9`. Remote PR checks on latest head `e30bf399146451c86cee98ed528d51d33fa5af5a`: - `policy` — passed. - `verify` — passed. - `e2e` — passed. - `Greptile Review` — passed, confidence score 5/5; Greptile review threads resolved. - `security/snyk (cryppadotta)` — passed. Screenshots: - [New issue cheap lane desktop](https://github.com/paperclipai/paperclip/blob/PAP-2837-plan-cheap-model-for-adapters-that-can-support-it/docs/pr-screenshots/pap-2837/newissue-cheap-desktop.png) - [New issue custom lane desktop](https://github.com/paperclipai/paperclip/blob/PAP-2837-plan-cheap-model-for-adapters-that-can-support-it/docs/pr-screenshots/pap-2837/newissue-custom-desktop.png) - [New issue unsupported adapter desktop](https://github.com/paperclipai/paperclip/blob/PAP-2837-plan-cheap-model-for-adapters-that-can-support-it/docs/pr-screenshots/pap-2837/newissue-unsupported-desktop.png) - [Run ledger model profile badges desktop](https://github.com/paperclipai/paperclip/blob/PAP-2837-plan-cheap-model-for-adapters-that-can-support-it/docs/pr-screenshots/pap-2837/runledger-profile-badges-desktop.png) - Mobile variants are also in `docs/pr-screenshots/pap-2837/`. ## Risks - Medium: heartbeat config mediation now merges runtime model profiles into adapter configs, so adapter secret normalization and host-command restrictions must keep covering nested config paths. - Medium: the UI adds another issue creation choice; unsupported adapters must keep hiding the cheap lane and preserve primary behavior. - Low migration risk: no database migration is included. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used OpenAI Codex coding agent using GPT-5-class reasoning with repo tool use and command execution. Exact served model/context window was not exposed by the runtime. ## 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 - [ ] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
parent
1fe1067361
commit
a3de1d764d
60 changed files with 2216 additions and 151 deletions
|
|
@ -28,6 +28,7 @@ import {
|
|||
findActiveServerAdapter,
|
||||
findServerAdapter,
|
||||
listAdapterModels,
|
||||
listAdapterModelProfiles,
|
||||
registerServerAdapter,
|
||||
requireServerAdapter,
|
||||
unregisterServerAdapter,
|
||||
|
|
@ -79,6 +80,31 @@ describe("server adapter registry", () => {
|
|||
]);
|
||||
});
|
||||
|
||||
it("exposes adapter model profiles when adapters declare them", async () => {
|
||||
const adapterWithProfiles: ServerAdapterModule = {
|
||||
...externalAdapter,
|
||||
modelProfiles: [
|
||||
{
|
||||
key: "cheap",
|
||||
label: "Cheap",
|
||||
adapterConfig: { model: "external-mini" },
|
||||
source: "adapter_default",
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
registerServerAdapter(adapterWithProfiles);
|
||||
|
||||
expect(await listAdapterModelProfiles("external_test")).toEqual([
|
||||
{
|
||||
key: "cheap",
|
||||
label: "Cheap",
|
||||
adapterConfig: { model: "external-mini" },
|
||||
source: "adapter_default",
|
||||
},
|
||||
]);
|
||||
});
|
||||
|
||||
it("removes external adapters when unregistered", () => {
|
||||
registerServerAdapter(externalAdapter);
|
||||
|
||||
|
|
@ -167,6 +193,45 @@ describe("server adapter registry", () => {
|
|||
expect(adapter!.supportsLocalAgentJwt).toBe(true);
|
||||
});
|
||||
|
||||
it("built-in local adapters declare cheap model profile defaults where supported", async () => {
|
||||
await expect(listAdapterModelProfiles("claude_local")).resolves.toEqual([
|
||||
expect.objectContaining({
|
||||
key: "cheap",
|
||||
adapterConfig: expect.objectContaining({ model: "claude-sonnet-4-6" }),
|
||||
source: "adapter_default",
|
||||
}),
|
||||
]);
|
||||
await expect(listAdapterModelProfiles("codex_local")).resolves.toEqual([
|
||||
expect.objectContaining({
|
||||
key: "cheap",
|
||||
adapterConfig: expect.objectContaining({ model: "gpt-5.3-codex-spark" }),
|
||||
source: "adapter_default",
|
||||
}),
|
||||
]);
|
||||
await expect(listAdapterModelProfiles("gemini_local")).resolves.toEqual([
|
||||
expect.objectContaining({
|
||||
key: "cheap",
|
||||
adapterConfig: expect.objectContaining({ model: "gemini-2.5-flash-lite" }),
|
||||
source: "adapter_default",
|
||||
}),
|
||||
]);
|
||||
await expect(listAdapterModelProfiles("opencode_local")).resolves.toEqual([
|
||||
expect.objectContaining({
|
||||
key: "cheap",
|
||||
adapterConfig: expect.objectContaining({ model: "openai/gpt-5.1-codex-mini" }),
|
||||
source: "adapter_default",
|
||||
}),
|
||||
]);
|
||||
await expect(listAdapterModelProfiles("cursor")).resolves.toEqual([
|
||||
expect.objectContaining({
|
||||
key: "cheap",
|
||||
adapterConfig: expect.objectContaining({ model: "gpt-5.1-codex-mini" }),
|
||||
source: "adapter_default",
|
||||
}),
|
||||
]);
|
||||
await expect(listAdapterModelProfiles("pi_local")).resolves.toEqual([]);
|
||||
});
|
||||
|
||||
it("switches active adapter behavior back to the builtin when an override is paused", async () => {
|
||||
const builtIn = findServerAdapter("claude_local");
|
||||
expect(builtIn).not.toBeNull();
|
||||
|
|
|
|||
|
|
@ -496,6 +496,165 @@ describe.sequential("agent permission routes", () => {
|
|||
expect(mockLogActivity).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("blocks agent-authenticated self-updates that set cheap-profile host-executed workspace commands", async () => {
|
||||
mockAgentService.getById.mockResolvedValue({
|
||||
...baseAgent,
|
||||
adapterType: "codex_local",
|
||||
});
|
||||
|
||||
const app = await createApp({
|
||||
type: "agent",
|
||||
agentId,
|
||||
companyId,
|
||||
source: "agent_key",
|
||||
runId: "run-1",
|
||||
});
|
||||
|
||||
const res = await requestApp(app, (baseUrl) => request(baseUrl)
|
||||
.patch(`/api/agents/${agentId}`)
|
||||
.send({
|
||||
runtimeConfig: {
|
||||
modelProfiles: {
|
||||
cheap: {
|
||||
adapterConfig: {
|
||||
workspaceStrategy: {
|
||||
type: "git_worktree",
|
||||
provisionCommand: "touch /tmp/paperclip-rce",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
}));
|
||||
|
||||
expect(res.status).toBe(403);
|
||||
expect(res.body.error).toContain("host-executed workspace commands");
|
||||
expect(res.body.error).toContain(
|
||||
"runtimeConfig.modelProfiles.cheap.adapterConfig.workspaceStrategy.provisionCommand",
|
||||
);
|
||||
expect(mockLogActivity).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("allows board updates that set cheap-profile workspace commands", async () => {
|
||||
mockAgentService.getById.mockResolvedValue({
|
||||
...baseAgent,
|
||||
adapterType: "codex_local",
|
||||
});
|
||||
|
||||
const app = await createApp({
|
||||
type: "board",
|
||||
userId: "board-user",
|
||||
source: "local_implicit",
|
||||
isInstanceAdmin: true,
|
||||
companyIds: [companyId],
|
||||
});
|
||||
|
||||
const runtimeConfig = {
|
||||
modelProfiles: {
|
||||
cheap: {
|
||||
adapterConfig: {
|
||||
workspaceStrategy: {
|
||||
type: "git_worktree",
|
||||
provisionCommand: "bash ./scripts/provision-worktree.sh",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
const res = await requestApp(app, (baseUrl) => request(baseUrl)
|
||||
.patch(`/api/agents/${agentId}`)
|
||||
.send({ runtimeConfig }));
|
||||
|
||||
expect(res.status, JSON.stringify(res.body)).toBe(200);
|
||||
expect(mockAgentService.update).toHaveBeenCalledWith(
|
||||
agentId,
|
||||
expect.objectContaining({ runtimeConfig }),
|
||||
expect.anything(),
|
||||
);
|
||||
expect(mockLogActivity).toHaveBeenCalledWith(expect.anything(), expect.objectContaining({
|
||||
action: "agent.updated",
|
||||
}));
|
||||
});
|
||||
|
||||
it("normalizes cheap-profile env bindings through the adapter config secret pipeline", async () => {
|
||||
mockAgentService.getById.mockResolvedValue({
|
||||
...baseAgent,
|
||||
adapterType: "codex_local",
|
||||
});
|
||||
mockSecretService.normalizeAdapterConfigForPersistence.mockImplementation(async (_companyId, config) => ({
|
||||
...config,
|
||||
env: {
|
||||
API_TOKEN: {
|
||||
type: "secret_ref",
|
||||
secretId: "33333333-3333-4333-8333-333333333333",
|
||||
version: "latest",
|
||||
},
|
||||
},
|
||||
}));
|
||||
|
||||
const app = await createApp({
|
||||
type: "board",
|
||||
userId: "board-user",
|
||||
source: "local_implicit",
|
||||
isInstanceAdmin: true,
|
||||
companyIds: [companyId],
|
||||
});
|
||||
|
||||
const res = await requestApp(app, (baseUrl) => request(baseUrl)
|
||||
.patch(`/api/agents/${agentId}`)
|
||||
.send({
|
||||
runtimeConfig: {
|
||||
modelProfiles: {
|
||||
cheap: {
|
||||
adapterConfig: {
|
||||
model: "gpt-5.3-codex-spark",
|
||||
env: {
|
||||
API_TOKEN: {
|
||||
type: "secret_ref",
|
||||
secretId: "33333333-3333-4333-8333-333333333333",
|
||||
version: "latest",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
}));
|
||||
|
||||
expect(res.status, JSON.stringify(res.body)).toBe(200);
|
||||
expect(mockSecretService.normalizeAdapterConfigForPersistence).toHaveBeenCalledWith(
|
||||
companyId,
|
||||
expect.objectContaining({
|
||||
model: "gpt-5.3-codex-spark",
|
||||
env: expect.any(Object),
|
||||
}),
|
||||
{ strictMode: false },
|
||||
);
|
||||
expect(mockAgentService.update).toHaveBeenCalledWith(
|
||||
agentId,
|
||||
expect.objectContaining({
|
||||
runtimeConfig: {
|
||||
modelProfiles: {
|
||||
cheap: {
|
||||
adapterConfig: {
|
||||
model: "gpt-5.3-codex-spark",
|
||||
env: {
|
||||
API_TOKEN: {
|
||||
type: "secret_ref",
|
||||
secretId: "33333333-3333-4333-8333-333333333333",
|
||||
version: "latest",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
}),
|
||||
expect.anything(),
|
||||
);
|
||||
});
|
||||
|
||||
it("blocks agent-authenticated self-updates that set instructions bundle roots", async () => {
|
||||
const app = await createApp({
|
||||
type: "agent",
|
||||
|
|
|
|||
123
server/src/__tests__/heartbeat-model-profile.test.ts
Normal file
123
server/src/__tests__/heartbeat-model-profile.test.ts
Normal file
|
|
@ -0,0 +1,123 @@
|
|||
import { describe, expect, it } from "vitest";
|
||||
import type { AdapterModelProfileDefinition } from "../adapters/index.js";
|
||||
import {
|
||||
mergeModelProfileAdapterConfig,
|
||||
normalizeModelProfileWakeContext,
|
||||
resolveModelProfileApplication,
|
||||
} from "../services/heartbeat.ts";
|
||||
|
||||
const cheapProfile: AdapterModelProfileDefinition = {
|
||||
key: "cheap",
|
||||
label: "Cheap",
|
||||
adapterConfig: {
|
||||
model: "adapter-cheap",
|
||||
modelReasoningEffort: "low",
|
||||
},
|
||||
source: "adapter_default",
|
||||
};
|
||||
|
||||
describe("heartbeat model profile application", () => {
|
||||
it("applies cheap profile patches before explicit issue adapter config overrides", () => {
|
||||
const modelProfile = resolveModelProfileApplication({
|
||||
adapterModelProfiles: [cheapProfile],
|
||||
agentRuntimeConfig: {},
|
||||
issueModelProfile: "cheap",
|
||||
contextSnapshot: {},
|
||||
});
|
||||
|
||||
const merged = mergeModelProfileAdapterConfig({
|
||||
baseConfig: {
|
||||
model: "primary",
|
||||
modelReasoningEffort: "high",
|
||||
approvalPolicy: "strict",
|
||||
},
|
||||
modelProfile,
|
||||
issueAdapterConfig: {
|
||||
model: "issue-explicit",
|
||||
},
|
||||
});
|
||||
|
||||
expect(modelProfile).toMatchObject({
|
||||
requested: "cheap",
|
||||
requestedBy: "issue_override",
|
||||
applied: "cheap",
|
||||
configSource: "adapter_default",
|
||||
fallbackReason: null,
|
||||
});
|
||||
expect(merged).toEqual({
|
||||
model: "issue-explicit",
|
||||
modelReasoningEffort: "low",
|
||||
approvalPolicy: "strict",
|
||||
});
|
||||
});
|
||||
|
||||
it("lets agent runtime profile config customize adapter defaults", () => {
|
||||
const modelProfile = resolveModelProfileApplication({
|
||||
adapterModelProfiles: [cheapProfile],
|
||||
agentRuntimeConfig: {
|
||||
modelProfiles: {
|
||||
cheap: {
|
||||
adapterConfig: {
|
||||
model: "agent-cheap",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
issueModelProfile: null,
|
||||
contextSnapshot: { modelProfile: "cheap" },
|
||||
});
|
||||
|
||||
expect(modelProfile).toMatchObject({
|
||||
requested: "cheap",
|
||||
requestedBy: "wake_context",
|
||||
applied: "cheap",
|
||||
configSource: "agent_runtime",
|
||||
adapterConfig: {
|
||||
model: "agent-cheap",
|
||||
modelReasoningEffort: "low",
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it("falls back to the primary config when the adapter does not support the requested profile", () => {
|
||||
const modelProfile = resolveModelProfileApplication({
|
||||
adapterModelProfiles: [],
|
||||
agentRuntimeConfig: {
|
||||
modelProfiles: {
|
||||
cheap: {
|
||||
adapterConfig: {
|
||||
model: "agent-cheap",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
issueModelProfile: null,
|
||||
contextSnapshot: { modelProfile: "cheap" },
|
||||
});
|
||||
|
||||
const merged = mergeModelProfileAdapterConfig({
|
||||
baseConfig: {
|
||||
model: "primary",
|
||||
},
|
||||
modelProfile,
|
||||
issueAdapterConfig: null,
|
||||
});
|
||||
|
||||
expect(modelProfile).toMatchObject({
|
||||
requested: "cheap",
|
||||
applied: null,
|
||||
fallbackReason: "adapter_profile_not_supported",
|
||||
adapterConfig: null,
|
||||
});
|
||||
expect(merged).toEqual({ model: "primary" });
|
||||
});
|
||||
|
||||
it("normalizes a wake payload model profile into run context", () => {
|
||||
const contextSnapshot = normalizeModelProfileWakeContext({
|
||||
contextSnapshot: {},
|
||||
payload: { modelProfile: "cheap" },
|
||||
});
|
||||
|
||||
expect(contextSnapshot).toMatchObject({ modelProfile: "cheap" });
|
||||
});
|
||||
});
|
||||
Loading…
Add table
Add a link
Reference in a new issue