- Add curly braces to all if/else/for/while statements
- Fix indentation and trailing spaces
- Auto-fixed 372 linting errors using eslint --fix
- Remaining issues are warnings only (non-null assertions, explicit any types)
- ollama.ts: add normalizeMessagesForOllama() converting Anthropic-style
tool_use/tool_result blocks to Ollama's native tool_calls + role:tool format
- llamacpp.ts: add normalizeMessagesForLlamaCpp() with hybrid approach —
assistant tool_calls in native format, but tool results as structured user
messages (many GGUF templates silently drop role:tool messages)
- llamacpp.ts: add configurable requestTimeout with AbortController (default 3min)
- Both use fast-path when no tool blocks are present (zero overhead)
- Full test coverage for both normalizers: plain text passthrough, tool_use
conversion, tool_result mapping, multi-tool round trips, error results
Local backends using strict chat templates (e.g. Mistral 3) rejected
Flynn's Anthropic-style tool_use/tool_result content blocks, causing
'roles must alternate' errors. Added getMessageTextWithTools() and
normalizeMessagesForLocal() to serialize structured blocks to plain
text, drop empty messages, and merge consecutive same-role messages.
Also fixed compaction to ensure kept messages start with user role.
Check model capabilities via /api/show before sending tools.
Models without 'tools' capability get requests without tools
(they can still answer, just without tool use). Result is cached
per client instance. Defense-in-depth: 'does not support' added
to retry nonRetryablePatterns to avoid wasting retries on
permanent errors.
- Ollama: pass tools to API, parse tool_calls responses, handle thinking field from reasoning models (deepseek-r1, glm-4.7-flash)
- llama.cpp: pass tools via OpenAI-compatible endpoint, parse tool_calls, accumulate streaming tool call deltas
- Both clients now set stopReason to 'tool_use' when tool calls are present
- Tests: 12 new tests (8 Ollama + 5 llama.cpp, total 983→995)
Widen Message.content from string to string | MessageContentPart[] to support
multimodal content. Add Attachment type to channel layer, media conversion
utilities, and image extraction to all channel adapters (Telegram, Discord,
Slack, WhatsApp). Update all model clients (Anthropic, OpenAI, Gemini, Bedrock)
to convert structured content to provider-specific formats. Fix downstream
consumers (tokens, compaction, TUI, local models) to handle the widened type
via getMessageText() helper.
William Valentin