Files
PaperClipAI/server/src/services/native-runtime/native-execution-input.ts
T
da887ea3e9 fix(runner): honor Codex effort selected in composer (#14568)
## Thinking Path

> - Paperclip manages AI agents that work on assigned tasks.
> - The task composer lets a person choose an assignee, model, and
effort for the next run.
> - A Paperclip Runner agent can use Codex as its provider.
> - The composer hid Codex effort for that agent because it checked only
the older Codex adapter.
> - The native Runner input also did not carry an effort choice to
Codex.
> - This pull request carries the chosen effort from the composer to
each Codex turn.
> - People can now select a supported effort and get the effort they
selected.

## Linked Issues or Issue Description

Refs #14322

**What happened?**

The composer showed a model but no effort slider when the assignee used
Paperclip Runner with the Codex provider. A task-level model override
also did not reach the native Runner input.

**Expected behavior**

The composer shows effort choices for a known Codex model. The next
native Codex turn uses the selected model and effort.

**Steps to reproduce**

1. Open a task composer.
2. Select an agent that uses Paperclip Runner with the Codex provider.
3. Select a known Codex model such as `gpt-6-astra`.
4. Open the assignee and model picker. The effort slider is missing
before this change.

## What Changed

- Show known Codex effort levels for Paperclip Runner Codex assignees.
- Save the task effort override in the native run input and send it to
Codex on each turn.
- Apply the task's merged model and effort overrides when the native run
starts.
- Apply a task model override for OpenCode Runner without changing the
agent's provider.
- Add Runner effort tests and desktop and mobile Storybook cases.

## Verification

- `pnpm -r typecheck` passed.
- `pnpm build` passed.
- `pnpm build-storybook` passed.
- `pnpm check:token-gates` passed.
- Focused UI, server, Runner contract, and Codex driver tests passed.
- The full CI test matrix, build, typecheck, and canary dry run passed
on the latest head.

## Risks

- Native Runner inputs add an optional Codex effort field to the current
v5 input. Older inputs keep their previous behavior.
- A known model rejects an effort that its catalog does not support.
Unknown models do not show a slider.

> This fixes an existing composer bug. I checked `ROADMAP.md`; it does
not describe this bug as planned work.

## Model Used

OpenAI Codex, GPT-6. The exact deployment ID and context window are not
exposed in this session. The model used reasoning, code execution, and
repository tools.

## 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
- [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>
Co-authored-by: OpenAI GPT-6 Astra <noreply@openai.com>
2026-09-29 09:41:05 -05:00

320 lines
13 KiB
TypeScript

import type { PaperclipTurnContext } from "@paperclipai/adapter-utils/server-utils";
import { createHash } from "node:crypto";
import { buildNativeContinuationPrompt } from "./native-continuation.js";
import type {
NativeAcpxAgent,
NativeAcpxPermissionMode,
NativeCodexApprovalPolicy,
NativeExecutionInputV5,
NativeCompletionSource,
NativeInteractionResponseEnvelope,
NativeOpenCodePermissionMode,
NativePlanningContext,
NativeRuntimeContextSnapshot,
StrictCompletionContractInput,
} from "../../vendor/paperclip-runner/index.js";
import {
parseNativeExecutionInput,
resolveQualifiedAcpxProfile,
} from "../../vendor/paperclip-runner/index.js";
import {
isPaperclipExternalChatContractTurn,
isPaperclipExternalChatQuestionResponseTurn,
selectPaperclipPromptSections,
} from "@paperclipai/adapter-utils/server-utils";
const NATIVE_GITHUB_ATTACHMENT_RECOVERY_GUIDANCE = [
"## GitHub attachment recovery navigation",
"Paperclip owns recovery navigation for unavailable GitHub attachments. It may append an authenticated task link after an accepted response, only when the current source remains authorized and a safe configured Board URL is available. The model does not select or authorize that link.",
"A task URL missing from your prompt or tool results is not evidence that no task link can be provided; do not claim that a link is unavailable merely because you cannot see its URL. Do not invent a URL or promise that a link will appear. Briefly explain the unavailable input and ask the user to attach it directly to this Paperclip task or paste the needed text. Never infer the file's contents or substitute an older file.",
].join("\n");
/** Closed constructor: callers cannot spread legacy context or environment data. */
export function buildNativeExecutionInput(input: {
companyId: string;
runId: string;
issue: {
id: string;
identifier: string | null;
title: string;
description: string | null;
workMode: string;
};
taskPrompt: string;
initialCommunicationGuidance?: string | null;
/**
* The already-sanitized Paperclip wake envelope for this run. Native drivers
* receive a closed execution input rather than the legacy adapter context,
* so the constructor must deliberately project the same bounded wake delta
* that legacy adapters place in their provider prompt.
*/
wakePayload?: unknown;
/** Additive source ownership emitted by the server task/wake builders. */
turnContext?: unknown;
resumedSession?: boolean;
previousTurn?: { runId: string; task: { title: string; description: string | null } } | null;
conversationMode?: boolean;
agentId: string;
workspace: {
id: string;
cwd: string;
repoUrl: string | null;
repoRef: string | null;
branchName: string | null;
};
normalizedSessionId: string | null;
provider?: "codex" | "opencode" | "claude_managed" | "aws_agentcore" | "acpx";
acpxAgent?: NativeAcpxAgent;
codexApprovalPolicy?: NativeCodexApprovalPolicy;
codexReasoningEffort?: string;
opencodePermissionMode?: NativeOpenCodePermissionMode;
acpxPermissionMode?: NativeAcpxPermissionMode;
model?: string | null;
managedProfile?: Extract<
NativeExecutionInputV5["provider"],
{ kind: "claude_managed" }
>["managedProfile"];
maxSessionListCostUsd?: number;
agentCoreProfile?: Extract<
NativeExecutionInputV5["provider"],
{ kind: "aws_agentcore" }
>["agentCoreProfile"];
maxEstimatedSessionCostUsd?: number;
invocationLimits?: Extract<
NativeExecutionInputV5["provider"],
{ kind: "aws_agentcore" }
>["invocationLimits"];
lifecyclePolicy?: NativeExecutionInputV5["session"]["lifecyclePolicy"];
executionMode?: "default" | "plan";
planningContext?: NativePlanningContext | null;
interactionResponses?: NativeInteractionResponseEnvelope[];
completionContract: {
id: string;
sha256: string;
schemaVersion: string;
contract: StrictCompletionContractInput;
sources?: Array<{ id: string; source: NativeCompletionSource }>;
};
runtimeContext: NativeRuntimeContextSnapshot;
}): NativeExecutionInputV5 {
if (input.issue.workMode !== "standard" && input.issue.workMode !== "planning" && input.issue.workMode !== "ask") {
throw new Error("native_execution_input_invalid: issue work mode must be standard, planning, or ask");
}
const executionMode = input.executionMode
?? (input.issue.workMode === "planning" ? "plan" : "default");
const acpxProfile = input.provider === "acpx"
? resolveQualifiedAcpxProfile(
input.acpxAgent ?? "codex",
input.model ?? "",
)
: null;
// Answers are materialized from the authoritative interaction only for this
// invocation; do not persist a duplicate answer in the durable wake snapshot.
const wake =
input.wakePayload &&
typeof input.wakePayload === "object" &&
!Array.isArray(input.wakePayload)
? (input.wakePayload as Record<string, unknown>)
: null;
const question = wake?.externalChatQuestionResponse
? input.interactionResponses?.find(
(response) =>
response.interactionId === wake.interactionId &&
response.kind === "ask_user_questions" &&
response.response.status === "answered",
)
: null;
const answerResult = question?.response.result as
Record<string, unknown> | undefined;
// The server supplies only the revalidated answer chain, in source order.
// Keep prior choices available even when this continuation starts a fresh
// provider session; never recover them from model prose or a transcript.
const answerChain = question
? input.interactionResponses?.filter((response) =>
response.kind === "ask_user_questions" &&
response.response.status === "answered" &&
typeof (response.response.result as Record<string, unknown> | undefined)
?.summaryMarkdown === "string")
: null;
const answerSummary =
answerChain && answerChain.length > 1 &&
answerChain.at(-1)?.interactionId === question?.interactionId
? answerChain.map((response, index) => {
const label = index === answerChain.length - 1
? "Latest answered question" : `Earlier answer ${index + 1}`;
return `${label}:\n${(response.response.result as Record<string, unknown>).summaryMarkdown}`;
}).join("\n\n")
: answerResult?.summaryMarkdown;
const wakePayload =
question && typeof answerSummary === "string"
? {
...wake,
questionResponse: {
interactionId: question.interactionId,
summaryMarkdown: answerSummary,
},
}
: input.wakePayload;
// Build the full bootstrap through the same owner as legacy adapters.
// Verified native resume selection stays at the existing session boundary.
const { taskContextNote, wakePrompt } = selectPaperclipPromptSections({
paperclipTaskMarkdownAssignment: input.taskPrompt,
paperclipWake: wakePayload,
conversationMode: input.conversationMode,
}, {
resumedSession: false,
includeCommunicationGuidance: false,
nativeWakeReaderAvailable: true,
});
const externalChatTurn =
isPaperclipExternalChatContractTurn(wakePayload) ||
isPaperclipExternalChatQuestionResponseTurn(wakePayload);
const taskPrompt = [
wakePrompt,
// Durable task questions must survive the current provider turn.
// Keep routing visible before deferred tool discovery; usage belongs in the tool schema.
"Use Paperclip's request_human_input for durable task questions.",
externalChatTurn && wake?.externalChatProvider === "github"
? NATIVE_GITHUB_ATTACHMENT_RECOVERY_GUIDANCE
: "",
taskContextNote,
]
.filter((section) => section.length > 0)
.join("\n\n");
const completionSources = !externalChatTurn && !input.conversationMode && input.taskPrompt.trim()
? verifiedCompletionSources(input.turnContext, input.completionContract.sources ?? [])
: [];
return parseNativeExecutionInput({
schema: "paperclip.native-execution-input.v5",
...(input.initialCommunicationGuidance ? { initialCommunicationGuidance: input.initialCommunicationGuidance } : {}),
...(input.resumedSession && input.previousTurn && !input.conversationMode ? {
continuationPrompt: buildNativeContinuationPrompt({
wakePayload: input.wakePayload,
previousRunId: input.previousTurn.runId,
previousIssue: input.previousTurn.task,
allowExternalChat: true,
issue: input.issue,
}),
} : {}),
executionMode,
planningContext: input.planningContext ?? null,
binding: {
companyId: input.companyId,
runId: input.runId,
issueId: input.issue.id,
agentId: input.agentId,
executionWorkspaceId: input.workspace.id,
},
task: {
identifier: input.issue.identifier ?? input.issue.id,
// The issue title is durable background context and may itself contain an
// exact-output instruction from the thread's first message. Repeating it
// as the native turn title can override a newer provider message in small
// models. Keep the canonical title and description in task.prompt as
// explicitly labeled background, but give authenticated external-chat
// turns neutral structured fields.
title: externalChatTurn ? "External chat follow-up" : input.issue.title,
description: externalChatTurn ? null : input.issue.description,
prompt: taskPrompt,
workMode: input.issue.workMode,
},
workspace: {
cwd: input.workspace.cwd,
repoUrl: input.workspace.repoUrl,
repoRef: input.workspace.repoRef,
branchName: input.workspace.branchName,
},
session: {
normalizedSessionId: input.normalizedSessionId,
driverKind: input.provider === "opencode"
? "opencode_server"
: input.provider === "claude_managed"
? "claude_managed_agents_api"
: input.provider === "aws_agentcore"
? "aws_agentcore_harness_api"
: input.provider === "acpx"
? "acpx_runtime"
: "codex_app_server",
protocolVersion: 1,
lifecyclePolicy: input.lifecyclePolicy ?? { mode: "per_turn", idleTimeoutMs: null },
},
provider: input.provider === "claude_managed"
? {
kind: "claude_managed",
model: input.model,
managedProfile: input.managedProfile,
maxSessionListCostUsd: input.maxSessionListCostUsd,
}
: input.provider === "aws_agentcore"
? {
kind: "aws_agentcore",
model: input.model,
agentCoreProfile: input.agentCoreProfile,
maxEstimatedSessionCostUsd: input.maxEstimatedSessionCostUsd,
invocationLimits: input.invocationLimits,
}
: input.provider === "acpx"
? {
kind: "acpx",
agent: acpxProfile!.agent,
model: input.model,
permissionMode: input.acpxPermissionMode ?? "approve-all",
profile: {
driverKind: acpxProfile!.driverKind,
protocolVersion: acpxProfile!.protocolVersion,
acpxVersion: acpxProfile!.acpxVersion,
agent: acpxProfile!.agent,
agentProfileVersion: acpxProfile!.agentProfileVersion,
agentServerPackage: acpxProfile!.agentServerPackage,
agentServerVersion: acpxProfile!.agentServerVersion,
agentRuntimePackage: acpxProfile!.agentRuntimePackage,
agentRuntimeVersion: acpxProfile!.agentRuntimeVersion,
commandDigest: acpxProfile!.commandDigest,
},
}
: input.provider === "opencode"
? {
kind: "opencode",
model: input.model,
permissionMode: input.opencodePermissionMode ?? "allow",
}
: {
kind: "codex",
model: input.model ?? null,
approvalPolicy: input.codexApprovalPolicy ?? "never",
...(input.codexReasoningEffort ? { reasoningEffort: input.codexReasoningEffort } : {}),
},
completionContract: {
id: input.completionContract.id,
sha256: input.completionContract.sha256,
schemaVersion: input.completionContract.schemaVersion,
contract: input.completionContract.contract,
},
...(completionSources.length ? { completionSources: {
promptSha256: createHash("sha256").update(taskPrompt).digest("hex"),
contractRevision: input.completionContract.contract.revision,
criteria: completionSources,
} } : {}),
interactionResponses: input.interactionResponses ?? [],
credentialBindings: [],
runtimeContext: input.runtimeContext,
}) as NativeExecutionInputV5;
}
/** Verify source identities and revisions, never guess provenance from requirement text. */
function verifiedCompletionSources(
value: unknown,
sources: Array<{ id: string; source: NativeCompletionSource }>,
): Array<{ id: string; source: NativeCompletionSource }> {
if (!value || typeof value !== "object" || Array.isArray(value)) return [];
const context = value as Partial<PaperclipTurnContext>;
if (context.version !== 1) return [];
return sources.filter(({ source }) => {
if (source.kind === "description") {
return context.assignment?.owner === "task_markdown" && context.assignment.description?.id === source.id && context.assignment.description.revision === source.revision;
}
return context.events?.owner === "wake_prompt" && Array.isArray(context.events.comments) && context.events.comments.some((comment) => comment.id === source.id && comment.revision === source.revision);
});
}