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

Refactor Terminal and AIAgent cleanup

2026-02-21 22:31:43 -08:00

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

fix(security): add .config/gh to read protection for @file references (#4327)

2026-03-31 12:48:30 -07:00

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

feat: add inline diff previews for write actions

2026-04-01 02:13:57 -07:00

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

fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter

2026-03-21 16:54:43 -07:00

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

Merge branch 'main' into rewbs/tool-use-charge-to-subscription

2026-04-02 11:00:35 +11:00

subdirectory_hints.py

feat: progressive subdirectory hint discovery (#5291)

2026-04-05 12:33:47 -07:00

title_generator.py

feat(agent): configurable timeouts for auxiliary LLM calls via config.yaml (#3597)

2026-03-28 14:35:28 -07:00

trajectory.py

Refactor Terminal and AIAgent cleanup

2026-02-21 22:31:43 -08:00

usage_pricing.py

fix: status bar shows 26K instead of 260K for token counts with trailing zeros (#3024)

2026-03-25 12:45:58 -07:00