fix: handle array content format in message conversion#17
Open
lukedd312 wants to merge 1 commit intoatalovesyou:mainfrom
Open
fix: handle array content format in message conversion#17lukedd312 wants to merge 1 commit intoatalovesyou:mainfrom
lukedd312 wants to merge 1 commit intoatalovesyou:mainfrom
Conversation
The OpenAI Chat API accepts `content` as either a plain string or an
array of content parts (`[{ type: "text", text: "..." }]`). Many
upstream callers — including OpenClaw, LiteLLM, and other OpenAI-
compatible routers — send the array form even for text-only messages.
Without this fix, `messagesToPrompt()` passes the raw array object
into template literals, producing `[object Object]` as the prompt
text instead of the actual user message.
Changes:
- Add `OpenAIContentPart` type and widen `OpenAIChatMessage.content`
to accept `string | OpenAIContentPart[]`
- Add `extractContent()` helper that normalises both representations
- Apply `extractContent()` to all message roles in `messagesToPrompt()`
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
bwiedmann
added a commit
to bwiedmann/claude-max-api-proxy
that referenced
this pull request
Feb 15, 2026
… message conversion # Conflicts: # src/adapter/openai-to-cli.ts # src/types/openai.ts
3 tasks
Grivn
added a commit
to mnemon-dev/claude-max-api-proxy
that referenced
this pull request
Feb 20, 2026
Fixes applied (from upstream PRs atalovesyou#7, atalovesyou#11, atalovesyou#12, atalovesyou#13, atalovesyou#17, atalovesyou#20): - fix: normalizeModelName crash on undefined model (issue atalovesyou#21) - fix: [object Object] serialization for array content parts - fix: E2BIG error by passing prompt via stdin instead of CLI arg - fix: ensureString on result.result to prevent non-string output - feat: CLAUDE_DANGEROUSLY_SKIP_PERMISSIONS env var for headless mode - feat: OPENCLAW_PROXY=1 env injection for hook isolation - feat: model aliases for claude-*-4-5, claude-*-4-6 generations - feat: claude-proxy/ provider prefix support - feat: developer role support in message conversion - perf: increase subprocess timeout from 5min to 15min Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
contentas either a plain string or an array of content parts ([{ type: "text", text: "..." }])messagesToPrompt()produces[object Object]as the prompt instead of the actual user messageChanges
OpenAIContentParttype and widenOpenAIChatMessage.contenttostring | OpenAIContentPart[]extractContent()helper that normalises both representations to a plain stringextractContent()to all message roles inmessagesToPrompt()Test plan
tsc --noEmitpassescontent: [{ type: "text", text: "..." }]— messages now display correctlycontentstill works as before🤖 Generated with Claude Code