Compare commits

..

1 Commits

Author SHA1 Message Date
Koshkoshinsk a6a46621dd fix(codex): deliver harness file events + add file to ProviderEvent
Codex's built-in image generation yields { type: 'file', path } that the
ProviderEvent union didn't declare (breaks tsc once codex.ts lands on
trunk) and the poll-loop never consumed (the image was dropped and never
reached chat). Adding the type alone clears the build but leaves delivery
broken — this fixes both.

- add { type: 'file'; path: string } to ProviderEvent
- extract enqueueFileOut() owning the outbox-staging + messages_out
  {files:[]} contract so send_file and the poll-loop can't drift apart
- poll-loop delivers file events to the batch's reply destination,
  best-effort (missing dest / unreadable file logs, never fails the turn)
- tests for enqueueFileOut

Refs CDX-001.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-15 01:50:32 +03:00
8 changed files with 205 additions and 40 deletions
-18
View File
@@ -89,22 +89,6 @@ pnpm exec tsc -p container/agent-runner/tsconfig.json --noEmit
./container/build.sh
```
### Restart the host
The image rebuild does not reload the **host**. Codex's host contribution
(`src/providers/codex.ts`) registers the `/home/node/.codex` bind mount + env
passthrough, and the running host only picks it up on restart. Skip this and the
first Codex turn fails with `EACCES` writing `/home/node/.codex/config.toml`
with no mount, Docker auto-creates the dir root-owned and the non-root container
user can't write to it.
```bash
# macOS (launchd)
launchctl kickstart -k gui/$(id -u)/com.nanoclaw
# Linux (systemd)
systemctl --user restart nanoclaw
```
### Validate
```bash
@@ -116,8 +100,6 @@ The registration tests import only the real barrels — they go red if a barrel
## Authenticate
> **Run this in a separate, real terminal — it is interactive.** It prompts for ChatGPT-subscription vs OpenAI-API-key and then drives a browser/device login, so it needs a TTY to answer prompts.
```bash
pnpm exec tsx setup/index.ts --step provider-auth codex
```
-6
View File
@@ -121,7 +121,6 @@ Bucket the upstream changed files:
- **Host source** (`src/`): may conflict if user modified the same files
- **Container** (`container/`): triggers container rebuild (+ typecheck if `agent-runner/src/` changed)
- **Build/config** (`package.json`, `pnpm-lock.yaml`, `tsconfig*.json`): lockfile changes trigger dep install
- **Version pins** (`versions.json`): a changed `onecli-gateway` / `onecli-cli` value requires upgrading the OneCLI gateway/CLI to match — see Step 5.5
- **Other**: docs, tests, setup scripts, misc
**Large drift check:** If the upstream commit count and age suggest the user has a lot of catching up to do, mention that `/migrate-nanoclaw` might be a better fit — it extracts customizations and reapplies them on clean upstream instead of merging. Offer it as an option but don't push.
@@ -216,11 +215,6 @@ If build fails:
- Do not refactor unrelated code.
- If unclear, ask the user before making changes.
# Step 5.5: OneCLI upgrade (if pins moved)
The OneCLI gateway and CLI are external components pinned in `versions.json`; when a pin moves, the running version must be upgraded to match or the new code may fail against it.
If `git diff <backup-tag-from-step-1>..HEAD -- versions.json` shows the `onecli-gateway` or `onecli-cli` value changed, follow `docs/onecli-upgrades.md` before the service restart (Step 8). Otherwise skip.
# Step 6: Breaking changes check
After validation succeeds, check if the update introduced any breaking changes.
+1 -1
View File
@@ -4,7 +4,7 @@ All notable changes to NanoClaw will be documented in this file.
## [Unreleased]
- [BREAKING] **`@onecli-sh/sdk` 0.5.0 -> 2.2.1 — requires a OneCLI server with the `/v1` API** (older servers 404 every SDK call). The sanctioned gateway and CLI versions are pinned in `versions.json`. **The gateway is a separate component — updating NanoClaw does not upgrade it for you:** `/update-nanoclaw` upgrades it when the pin moves, otherwise upgrade manually. **Migration:** [docs/onecli-upgrades.md](docs/onecli-upgrades.md).
- [BREAKING] **`@onecli-sh/sdk` 0.5.0 -> 2.2.1 — requires a OneCLI server with the `/v1` API** (older servers 404 every SDK call). The sanctioned gateway and CLI versions are pinned in `versions.json`; the `onecli` setup step enforces them. **Migration:** [docs/onecli-upgrades.md](docs/onecli-upgrades.md).
- **New agent provider: Codex (OpenAI) — run `/add-codex`.** Full runtime via `codex app-server` (planning, MCP tools, server-side history, resume). Trunk ships the seams and the skill; the payload installs from the `providers` branch (the skill, the setup picker, or `--step provider-auth codex`). Auth is vault-only — no credential ever enters a container.
- **Setup can now select, install, and authenticate a non-default agent provider.** A provider registry feeds the setup picker, an installer pulls the provider's payload from its branch, a vault auth walkthrough runs (`--step provider-auth`), and the picked provider is set on the first agent (a DB property) before its first spawn. Default (Claude) installs are unaffected — picking Claude changes nothing.
- **Provider choice is explicit per group — no install-wide default.** Provider is a DB property set via `ncl groups config update --provider` + restart; creation is provider-agnostic.
+11 -15
View File
@@ -13,6 +13,7 @@ import { getCurrentInReplyTo } from '../current-batch.js';
import { findByName, getAllDestinations } from '../destinations.js';
import { getMessageIdBySeq, getRoutingBySeq, writeMessageOut } from '../db/messages-out.js';
import { getSessionRouting } from '../db/session-routing.js';
import { enqueueFileOut } from '../outbox.js';
import { registerTools } from './server.js';
import type { McpToolDefinition } from './types.js';
@@ -156,21 +157,16 @@ export const sendFile: McpToolDefinition = {
const resolvedPath = path.isAbsolute(filePath) ? filePath : path.resolve('/workspace/agent', filePath);
if (!fs.existsSync(resolvedPath)) return err(`File not found: ${filePath}`);
const id = generateId();
const filename = (args.filename as string) || path.basename(resolvedPath);
const outboxDir = path.join('/workspace/outbox', id);
fs.mkdirSync(outboxDir, { recursive: true });
fs.copyFileSync(resolvedPath, path.join(outboxDir, filename));
writeMessageOut({
id,
in_reply_to: getCurrentInReplyTo(),
kind: 'chat',
platform_id: routing.platform_id,
channel_type: routing.channel_type,
thread_id: routing.thread_id,
content: JSON.stringify({ text: (args.text as string) || '', files: [filename] }),
const { id, filename } = enqueueFileOut({
srcPath: resolvedPath,
routing: {
platform_id: routing.platform_id,
channel_type: routing.channel_type,
thread_id: routing.thread_id,
in_reply_to: getCurrentInReplyTo(),
},
text: (args.text as string) || '',
filename: (args.filename as string) || undefined,
});
log(`send_file: ${id}${routing.resolvedName} (${filename})`);
+87
View File
@@ -0,0 +1,87 @@
import { describe, it, expect, beforeEach, afterEach } from 'bun:test';
import fs from 'fs';
import os from 'os';
import path from 'path';
import { initTestSessionDb, closeSessionDb } from './db/connection.js';
import { getUndeliveredMessages } from './db/messages-out.js';
import { enqueueFileOut } from './outbox.js';
let outboxDir: string;
let srcDir: string;
beforeEach(() => {
initTestSessionDb();
outboxDir = fs.mkdtempSync(path.join(os.tmpdir(), 'nanoclaw-outbox-'));
srcDir = fs.mkdtempSync(path.join(os.tmpdir(), 'nanoclaw-src-'));
process.env.NANOCLAW_OUTBOX_DIR = outboxDir;
});
afterEach(() => {
closeSessionDb();
delete process.env.NANOCLAW_OUTBOX_DIR;
fs.rmSync(outboxDir, { recursive: true, force: true });
fs.rmSync(srcDir, { recursive: true, force: true });
});
function writeSrc(name: string, bytes: string): string {
const p = path.join(srcDir, name);
fs.writeFileSync(p, bytes);
return p;
}
describe('enqueueFileOut', () => {
it('stages the file under the outbox and enqueues a messages_out row with files[]', () => {
const src = writeSrc('ig_abc.png', 'PNGDATA');
const { id, filename } = enqueueFileOut({
srcPath: src,
routing: { platform_id: 'chan-1', channel_type: 'discord', thread_id: 'thr-9', in_reply_to: 'm1' },
text: 'here you go',
});
// Bytes staged at <outbox>/<id>/<filename> for the host to read.
const staged = path.join(outboxDir, id, filename);
expect(fs.existsSync(staged)).toBe(true);
expect(fs.readFileSync(staged, 'utf8')).toBe('PNGDATA');
// Exactly one outbound row, carrying the file reference + routing.
const out = getUndeliveredMessages();
expect(out).toHaveLength(1);
const row = out[0];
expect(row.platform_id).toBe('chan-1');
expect(row.channel_type).toBe('discord');
expect(row.thread_id).toBe('thr-9');
expect(row.in_reply_to).toBe('m1');
const content = JSON.parse(row.content);
expect(content.files).toEqual(['ig_abc.png']);
expect(content.text).toBe('here you go');
});
it('defaults filename to the basename and text to empty', () => {
const src = writeSrc('chart.png', 'X');
const { filename } = enqueueFileOut({
srcPath: src,
routing: { platform_id: 'C-1', channel_type: 'slack', thread_id: null },
});
expect(filename).toBe('chart.png');
const row = getUndeliveredMessages()[0];
expect(row.in_reply_to).toBeNull();
const content = JSON.parse(row.content);
expect(content.text).toBe('');
expect(content.files).toEqual(['chart.png']);
});
it('throws when the source file is missing — callers decide how to surface it', () => {
expect(() =>
enqueueFileOut({
srcPath: path.join(srcDir, 'does-not-exist.png'),
routing: { platform_id: 'C-1', channel_type: 'slack', thread_id: null },
}),
).toThrow();
// Nothing enqueued on failure.
expect(getUndeliveredMessages()).toHaveLength(0);
});
});
+68
View File
@@ -0,0 +1,68 @@
/**
* File delivery via the outbox.
*
* A file is delivered in two parts that must stay in lockstep: the bytes are
* staged under `/workspace/outbox/<id>/<filename>` (the host reads them from
* there after polling), and a `messages_out` row carries `{ files: [name] }`
* so the host knows to attach them. This helper owns that contract so the two
* callers — the `send_file` MCP tool (model-driven) and the poll-loop's `file`
* event consumer (harness-generated images) — can't drift apart.
*/
import fs from 'fs';
import path from 'path';
import { writeMessageOut } from './db/messages-out.js';
/** Where staged files live. Overridable for tests; production is always the mount. */
function outboxBase(): string {
return process.env.NANOCLAW_OUTBOX_DIR ?? '/workspace/outbox';
}
function generateId(): string {
return `msg-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`;
}
export interface FileOutRouting {
platform_id: string;
channel_type: string;
thread_id: string | null;
in_reply_to?: string | null;
}
export interface EnqueueFileOut {
/** Absolute or already-resolved path to the file to deliver. Must exist. */
srcPath: string;
routing: FileOutRouting;
/** Optional accompanying message text. */
text?: string;
/** Display name; defaults to the basename of `srcPath`. */
filename?: string;
}
/**
* Stage a file into the outbox and enqueue its `messages_out` row.
*
* Throws if `srcPath` cannot be read/copied — callers decide whether that
* should surface to the user (the MCP tool validates existence first; the
* poll-loop consumer logs and moves on so one bad image can't fail the turn).
*/
export function enqueueFileOut(opts: EnqueueFileOut): { id: string; filename: string; seq: number } {
const id = generateId();
const filename = opts.filename ?? path.basename(opts.srcPath);
const outboxDir = path.join(outboxBase(), id);
fs.mkdirSync(outboxDir, { recursive: true });
fs.copyFileSync(opts.srcPath, path.join(outboxDir, filename));
const seq = writeMessageOut({
id,
in_reply_to: opts.routing.in_reply_to ?? null,
kind: 'chat',
platform_id: opts.routing.platform_id,
channel_type: opts.routing.channel_type,
thread_id: opts.routing.thread_id,
content: JSON.stringify({ text: opts.text ?? '', files: [filename] }),
});
return { id, filename, seq };
}
+31
View File
@@ -14,6 +14,7 @@ import {
type RoutingContext,
} from './formatter.js';
import { isUploadTraceCommand, uploadTrace } from './upload-trace.js';
import { enqueueFileOut } from './outbox.js';
import type { AgentProvider, AgentQuery, ProviderEvent, ProviderExchange } from './providers/types.js';
const POLL_INTERVAL_MS = 1000;
@@ -507,6 +508,8 @@ async function processQuery(
} else {
archivePrompts.shift();
}
} else if (event.type === 'file') {
deliverHarnessFile(event.path, routing);
}
}
} catch (err) {
@@ -557,6 +560,34 @@ function handleEvent(event: ProviderEvent, _routing: RoutingContext): void {
}
}
/**
* Deliver a harness-generated file (e.g. a Codex-rendered image) to the
* batch's reply destination. The model never sends these itself — its native
* client already rendered them — so the loop delivers them via the same outbox
* path send_file uses. Best-effort: a missing reply destination or an
* unreadable file logs and is skipped rather than failing the whole turn.
*/
function deliverHarnessFile(filePath: string, routing: RoutingContext): void {
if (!routing.platformId || !routing.channelType) {
log(`Dropping harness file ${filePath}: batch has no reply destination`);
return;
}
try {
const { filename, seq } = enqueueFileOut({
srcPath: filePath,
routing: {
platform_id: routing.platformId,
channel_type: routing.channelType,
thread_id: routing.threadId,
in_reply_to: routing.inReplyTo,
},
});
log(`Delivered harness file #${seq}${routing.channelType}:${routing.platformId} (${filename})`);
} catch (err) {
log(`Failed to deliver harness file ${filePath}: ${err instanceof Error ? err.message : String(err)}`);
}
}
/**
* Parse the agent's final text for <message to="name">...</message> blocks
* and dispatch each one to its resolved destination. Text outside of blocks
@@ -128,6 +128,13 @@ export type ProviderEvent =
| { type: 'result'; text: string | null }
| { type: 'error'; message: string; retryable: boolean; classification?: string }
| { type: 'progress'; message: string }
/**
* A file the harness produced that the model won't deliver itself (e.g.
* Codex's built-in image generation renders to its native client, so the
* model believes delivery already happened). The poll-loop delivers it to
* the batch's reply destination. `path` is absolute inside the container.
*/
| { type: 'file'; path: string }
/**
* Liveness signal. Providers MUST yield this on every underlying SDK
* event (tool call, thinking, partial message, anything) so the