* fix(agents): recognize flat JSON billing payloads and snake_case error codes
Two independent fixes for billing error detection:
1. isErrorPayloadObject/parseApiErrorInfo now recognize flat JSON like
{"error":"string_code","message":"..."} where error is a string code
at the top level, not just nested {"error":{"type":"...","message":"..."}}
envelopes.
2. isBillingErrorMessage now matches "insufficient_balance" (underscore)
and "Insufficient MBT balance" (one word between insufficient/balance)
via two new patterns in the billing pattern list.
Together these prevent raw JSON from leaking to user-facing chat when
providers return 402-style flat payloads.
Fixes#74079
* fix(agents): remove redundant billing pattern and fix misleading regex comment
Polishes the basic config identity layout, aligns assistant avatar rendering with chat, and adds a Control UI assistant avatar override with IDENTITY.md fallback.
The HTML challenge fix already keeps standalone CDN block pages out of the DNS transport path. This follow-up caches the HTML classification so status-prefixed non-HTML failures do not pay for the same scan twice and the control flow stays simpler.
Constraint: Keep behavior identical for both status-prefixed HTML pages and standalone HTML challenge pages
Rejected: Inline the helper into the status branch only | would duplicate the standalone HTML branch logic
Confidence: high
Scope-risk: narrow
Directive: If this formatter grows more branches, keep a single HTML classification result and reuse it through the decision tree
Tested: oxfmt --check src/shared/assistant-error-format.ts
Tested: node scripts/test-projects.mjs src/agents/pi-embedded-helpers.formatassistanterrortext.test.ts src/agents/pi-embedded-helpers.isbillingerrormessage.test.ts
Cloudflare challenge pages from chatgpt.com/backend-api can arrive as raw HTML without an HTTP status prefix. The transport sanitizer scanned for generic "dns" substrings before HTML detection, so these pages could surface as DNS lookup failures instead of the existing HTML/CDN block message.
Constraint: Must preserve DNS transport classification for real ENOTFOUND/getaddrinfo failures
Rejected: Treat every bare HTML document as an upstream HTML error | too broad for arbitrary model text/errors
Confidence: high
Scope-risk: narrow
Directive: Keep standalone HTML challenge detection ahead of generic transport keyword matching so CDN block pages do not regress into DNS copy
Tested: oxfmt --check on changed files; targeted node --import tsx verification for standalone Cloudflare HTML classification and DNS control case
Not-tested: Full Vitest shard run in this environment
* fix: strip standalone <function> tool call tags from visible text (#67093)
Models like Gemma emit tool calls as standalone <function> blocks with
nested <parameter> XML instead of wrapping them in <tool_call>. The
existing stripToolCallXmlTags only recognized tool_call, tool_result,
function_call, function_calls, and tool_calls — so bare <function> and
</function> tags leaked through to the user as raw syntax on Discord
and other channels.
Add "function" to TOOL_CALL_TAG_NAMES and extend the payload detection
for <function> tags to check XML payloads (not just JSON), matching the
same behavior already applied to <tool_call>. Other tag types keep the
more conservative JSON-only check to avoid stripping prose examples.
Made-with: Cursor
* Text: harden standalone <function> stripping
* fix: strip standalone <function> tool call tags from visible text (#67318) (thanks @joelnishanth)
---------
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
