Teknium 888dc1e680 fix: harden auxiliary codex adapter — dict-shaped items + tool call guard (#5734) ... Two remaining gaps from the codex empty-output spec: 1. Normalize dict-shaped streamed items: output_item.done events may yield dicts (raw/fallback paths) instead of SDK objects. The extraction loop now uses _item_get() that handles both getattr and dict .get() access. 2. Avoid plain-text synthesis when function_call events were streamed: tracks has_function_calls during streaming and skips text-delta synthesis when tool calls are present — prevents collapsing a tool-call response into a fake text message.		2026-04-06 21:35:33 -07:00
..
__init__.py
anthropic_adapter.py	fix: preserve Anthropic thinking block signatures across tool-use turns	2026-04-02 10:30:32 -07:00
auxiliary_client.py	fix: harden auxiliary codex adapter — dict-shaped items + tool call guard (#5734)	2026-04-06 21:35:33 -07:00
builtin_memory_provider.py	feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623)	2026-04-02 15:33:51 -07:00
context_compressor.py	Fix compaction summary retries for temperature-restricted models	2026-04-06 16:49:57 -07:00
context_references.py
copilot_acp_client.py	fix: bridge tool-calls in copilot-acp adapter	2026-04-06 01:47:57 -07:00
credential_pool.py	fix: sync openai-codex pool entry from ~/.codex/auth.json on exhaustion (#5610)	2026-04-06 18:16:56 -07:00
display.py
insights.py	fix(insights): show cache tokens in overview so total adds up (#4428)	2026-04-01 03:06:47 -07:00
memory_manager.py	fix: mem0 API v2 compat, prefetch context fencing, secret redaction (#5423)	2026-04-05 22:43:33 -07:00
memory_provider.py	feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623)	2026-04-02 15:33:51 -07:00
model_metadata.py	fix: update Gemini model catalog + wire models.dev as live model source	2026-04-06 10:28:03 -07:00
models_dev.py	fix: update Gemini model catalog + wire models.dev as live model source	2026-04-06 10:28:03 -07:00
prompt_builder.py	feat: add grok to TOOL_USE_ENFORCEMENT_MODELS for direct xAI usage (#5595)	2026-04-06 11:22:07 -07:00
prompt_caching.py
redact.py	fix: mem0 API v2 compat, prefetch context fencing, secret redaction (#5423)	2026-04-05 22:43:33 -07:00
skill_commands.py	feat(skills): add skill config interface + llm-wiki skill (#5635)	2026-04-06 13:49:13 -07:00
skill_utils.py	feat(skills): add skill config interface + llm-wiki skill (#5635)	2026-04-06 13:49:13 -07:00
smart_model_routing.py
subdirectory_hints.py	feat: progressive subdirectory hint discovery (#5291)	2026-04-05 12:33:47 -07:00
title_generator.py
trajectory.py
usage_pricing.py