Compare commits

..

8 Commits

Author SHA1 Message Date
github-actions[bot] ee7f891698 docs: update token count to 196k tokens · 98% of context window 2026-06-16 11:15:10 +00:00
github-actions[bot] 7fde348e2b chore: bump version to 2.1.17 2026-06-16 11:15:04 +00:00
Gabi Simons 122135e6dc Merge pull request #2759 from assapin/fix/budget-error-surfaced-to-user
fix(agent-runner): deliver budget/billing error turns instead of dropping them
2026-06-16 14:14:48 +03:00
Gabi Simons 8563fb0681 Merge remote-tracking branch 'origin/main' into fix/budget-error-surfaced-to-user
# Conflicts:
#	CHANGELOG.md
2026-06-16 11:35:45 +03:00
omri-maya 0155ab1943 Merge pull request #2775 from nanocoai/docs/onecli-gateway-upgrade-notice
docs(changelog): clarify the OneCLI gateway is a separate, operator-driven upgrade
2026-06-16 09:55:25 +03:00
Gabi Simons 59c4d33adc Merge branch 'main' into fix/budget-error-surfaced-to-user 2026-06-15 17:42:01 +03:00
Gabi Simons e03c5c194a Merge branch 'main' into fix/budget-error-surfaced-to-user 2026-06-15 12:17:20 +03:00
assafpin 01433bae32 fix(agent-runner): deliver budget/billing error turns instead of dropping them
A turn that ends in a non-retryable provider error (e.g. an Anthropic
403 billing_error) comes back from the streaming SDK as a result with
is_error=true and no <message> envelope. dispatchResultText treated it
as scratchpad and dropped it, then the poll-loop pushed a re-wrap nudge
-> new turn -> same error, re-hammering the gateway until idle-kill. The
user saw silence.

- providers/claude.ts: surface is_error on the result event, and fall
  back to errors[] for the message text (error subtypes carry no result).
- poll-loop.ts: when a result has no <message> blocks and is_error, deliver
  the notice verbatim to the originating channel and skip the nudge.

Verified live (real agent image + SDK, 403 mock): the notice is delivered
to the channel and the retry loop is gone.

Refs #2751
2026-06-14 12:56:02 +03:00
7 changed files with 137 additions and 31 deletions
+1
View File
@@ -4,6 +4,7 @@ All notable changes to NanoClaw will be documented in this file.
## [Unreleased]
- **Budget/billing-exhausted LLM turns now reach the user instead of being silently dropped.** When a turn ends in a non-retryable provider error (e.g. an Anthropic `403 billing_error`) with no `<message>` wrapping, the agent-runner delivers the provider's notice to the originating channel and stops re-nudging the failing gateway. `providers/claude.ts` now surfaces the SDK's `is_error` flag (and the error subtype's `errors[]` text); `poll-loop.ts` delivers that text and skips the re-wrap retry. Fixes the case where a spend-limit notice produced silence plus a turn-after-turn retry loop.
- [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).
- **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.
+60 -1
View File
@@ -4,8 +4,9 @@ import { initTestSessionDb, closeSessionDb, getInboundDb, getOutboundDb } from '
import { getPendingMessages, markCompleted } from './db/messages-in.js';
import { getUndeliveredMessages } from './db/messages-out.js';
import { formatMessages, extractRouting } from './formatter.js';
import { isCorruptionError } from './poll-loop.js';
import { isCorruptionError, processQuery } from './poll-loop.js';
import { MockProvider } from './providers/mock.js';
import type { AgentQuery, ProviderEvent } from './providers/types.js';
beforeEach(() => {
initTestSessionDb();
@@ -379,6 +380,64 @@ describe('end-to-end with mock provider', () => {
});
});
/**
* Build a one-shot stub query that yields init + a single result event, then
* ends. `pushes` records any follow-ups the loop tried to inject (e.g. the
* re-wrap nudge), so a test can assert the loop did NOT re-hammer.
*/
function makeResultQuery(result: ProviderEvent): { query: AgentQuery; pushes: string[] } {
const pushes: string[] = [];
async function* events(): AsyncGenerator<ProviderEvent> {
yield { type: 'init', continuation: 'sess-1' };
yield result;
}
return {
pushes,
query: {
push: (m: string) => {
pushes.push(m);
},
end: () => {},
events: events(),
abort: () => {},
},
};
}
const ERR_ROUTING = {
platformId: 'chan-1',
channelType: 'discord',
threadId: null,
inReplyTo: 'm1',
};
describe('error result with no <message> envelope', () => {
it('delivers a budget/billing error to the triggering channel and does not nudge', async () => {
const budgetText = 'Spending limit reached. Add your own key at https://example.com/keys';
const { query, pushes } = makeResultQuery({ type: 'result', text: budgetText, isError: true });
await processQuery(query, ERR_ROUTING, ['m1'], 'claude', undefined, 'prompt', undefined);
const out = getUndeliveredMessages();
expect(out).toHaveLength(1);
expect(JSON.parse(out[0].content).text).toBe(budgetText);
expect(out[0].platform_id).toBe('chan-1');
expect(out[0].channel_type).toBe('discord');
// No re-wrap nudge — an error result must not re-hammer the gateway.
expect(pushes).toHaveLength(0);
});
it('still nudges (and does not deliver) a normal unwrapped result', async () => {
const { query, pushes } = makeResultQuery({ type: 'result', text: 'bare text, no envelope' });
await processQuery(query, ERR_ROUTING, ['m1'], 'claude', undefined, 'prompt', undefined);
expect(getUndeliveredMessages()).toHaveLength(0);
expect(pushes).toHaveLength(1);
expect(pushes[0]).toContain('was not delivered');
});
});
describe('isCorruptionError', () => {
it('matches the Docker Desktop macOS torn-read symptom', () => {
expect(isCorruptionError('database disk image is malformed')).toBe(true);
+57 -22
View File
@@ -323,7 +323,7 @@ interface QueryResult {
continuation?: string;
}
async function processQuery(
export async function processQuery(
query: AgentQuery,
routing: RoutingContext,
initialBatchIds: string[],
@@ -482,28 +482,43 @@ async function processQuery(
// at all — either way the turn is finished.
markCompleted(initialBatchIds);
if (event.text) {
const { hasUnwrapped } = dispatchResultText(event.text, routing);
const willRetryWrapping = hasUnwrapped && !unwrappedNudged;
notifyExchangeComplete(onExchangeComplete, {
prompt: archivePrompts[0] ?? initialPrompt,
result: event.text,
continuation: queryContinuation ?? initialContinuation,
status: hasUnwrapped ? 'undelivered' : 'completed',
});
if (willRetryWrapping) {
unwrappedNudged = true;
const destinations = getAllDestinations();
const names = destinations.map((d) => d.name).join(', ');
query.push(
`<system>Your response was not delivered — it was not wrapped in <message to="name">...</message> blocks. ` +
`All output must be wrapped: use <message to="name"> for content to send, or <internal> for scratchpad. ` +
`Your destinations: ${names}. ` +
`Please re-send your response with the correct wrapping.</system>`,
);
const { sent, hasUnwrapped } = dispatchResultText(event.text, routing);
if (sent === 0 && event.isError === true) {
// Non-retryable error turn (e.g. a 403 billing_error) with no
// <message> envelope: deliver the notice instead of dropping it as
// scratchpad, and skip the re-wrap nudge — it would just re-hammer
// the failing gateway turn after turn.
deliverErrorResult(event.text, routing);
notifyExchangeComplete(onExchangeComplete, {
prompt: archivePrompts[0] ?? initialPrompt,
result: event.text,
continuation: queryContinuation ?? initialContinuation,
status: 'error',
});
archivePrompts.shift();
} else {
const willRetryWrapping = hasUnwrapped && !unwrappedNudged;
notifyExchangeComplete(onExchangeComplete, {
prompt: archivePrompts[0] ?? initialPrompt,
result: event.text,
continuation: queryContinuation ?? initialContinuation,
status: hasUnwrapped ? 'undelivered' : 'completed',
});
if (willRetryWrapping) {
unwrappedNudged = true;
const destinations = getAllDestinations();
const names = destinations.map((d) => d.name).join(', ');
query.push(
`<system>Your response was not delivered — it was not wrapped in <message to="name">...</message> blocks. ` +
`All output must be wrapped: use <message to="name"> for content to send, or <internal> for scratchpad. ` +
`Your destinations: ${names}. ` +
`Please re-send your response with the correct wrapping.</system>`,
);
}
// The wrapping-retry result answers the SAME user prompt — keep it
// queued so the retry archives against it, not the nudge text.
if (!willRetryWrapping) archivePrompts.shift();
}
// The wrapping-retry result answers the SAME user prompt — keep it
// queued so the retry archives against it, not the nudge text.
if (!willRetryWrapping) archivePrompts.shift();
} else {
archivePrompts.shift();
}
@@ -557,6 +572,26 @@ function handleEvent(event: ProviderEvent, _routing: RoutingContext): void {
}
}
/**
* Deliver a turn's text straight to the channel the batch arrived on. Used when
* a turn ends in a provider error (e.g. a non-retryable 403 billing_error) with
* no <message> envelope: the notice would otherwise be dropped as scratchpad.
* This is the same user-facing write the outer catch block does, minus the
* `Error:` prefix — the provider's text is already a user-facing message.
*/
function deliverErrorResult(text: string, routing: RoutingContext): void {
log('Error result with no <message> envelope — delivering to channel');
writeMessageOut({
id: generateId(),
in_reply_to: routing.inReplyTo,
kind: 'chat',
platform_id: routing.platformId,
channel_type: routing.channelType,
thread_id: routing.threadId,
content: JSON.stringify({ text }),
});
}
/**
* Parse the agent's final text for <message to="name">...</message> blocks
* and dispatch each one to its resolved destination. Text outside of blocks
@@ -440,8 +440,13 @@ export class ClaudeProvider implements AgentProvider {
if (message.type === 'system' && message.subtype === 'init') {
yield { type: 'init', continuation: message.session_id };
} else if (message.type === 'result') {
const text = 'result' in message ? (message as { result?: string }).result ?? null : null;
yield { type: 'result', text };
// `result` text exists only on subtype:"success"; error subtypes
// (e.g. a non-retryable 403 billing_error) carry their message in
// `errors[]` instead. Surface either so the poll-loop can deliver a
// billing/quota notice to the user rather than dropping the turn.
const m = message as { result?: string; is_error?: boolean; errors?: string[] };
const text = m.result ?? (m.errors && m.errors.length > 0 ? m.errors.join('\n') : null);
yield { type: 'result', text, isError: m.is_error === true };
} else if (message.type === 'system' && (message as { subtype?: string }).subtype === 'api_retry') {
yield { type: 'error', message: 'API retry', retryable: true };
} else if (message.type === 'system' && (message as { subtype?: string }).subtype === 'rate_limit_event') {
@@ -125,7 +125,13 @@ export interface AgentQuery {
export type ProviderEvent =
| { type: 'init'; continuation: string }
| { type: 'result'; text: string | null }
/**
* A completed turn. `isError` is set when the underlying SDK flagged the
* turn as an error (e.g. a non-retryable Anthropic 403 billing_error). The
* poll-loop uses it to surface the result text to the user instead of
* dropping it as un-wrapped scratchpad, and to skip the re-wrap nudge.
*/
| { type: 'result'; text: string | null; isError?: boolean }
| { type: 'error'; message: string; retryable: boolean; classification?: string }
| { type: 'progress'; message: string }
/**
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "nanoclaw",
"version": "2.1.16",
"version": "2.1.17",
"description": "Personal Claude assistant. Lightweight, secure, customizable.",
"type": "module",
"packageManager": "pnpm@10.33.0",
+4 -4
View File
@@ -1,5 +1,5 @@
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="195k tokens, 98% of context window">
<title>195k tokens, 98% of context window</title>
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="196k tokens, 98% of context window">
<title>196k tokens, 98% of context window</title>
<linearGradient id="s" x2="0" y2="100%">
<stop offset="0" stop-color="#bbb" stop-opacity=".1"/>
<stop offset="1" stop-opacity=".1"/>
@@ -15,8 +15,8 @@
<g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" font-size="11">
<text aria-hidden="true" x="26" y="15" fill="#010101" fill-opacity=".3">tokens</text>
<text x="26" y="14">tokens</text>
<text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">195k</text>
<text x="71" y="14">195k</text>
<text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">196k</text>
<text x="71" y="14">196k</text>
</g>
</g>
</a>

Before

Width:  |  Height:  |  Size: 1.1 KiB

After

Width:  |  Height:  |  Size: 1.1 KiB