v0.0.19

New Features

• Set default non-thinking temp=None, add kimi-k2.7-code (#52)

Bugs Squashed

• Filter top level gemini tool schema fields such as $refs, $defs... (#51)

v0.0.18

New Features

• Add mimo-v2.5-pro-ultraspeed (#50)

v0.0.17

New Features

• Add claude-fable-5 model and stream stop-reason warnings (#49)
• fastspec dict2obj -> obj2dict handling (#43), thanks to @KeremTurgutlu

Bugs Squashed

• FullResponse/Safe tool results are truncated (#47)

v0.0.16

New Features

• fastspec dict2obj -> obj2dict handling (#43), thanks to @KeremTurgutlu

v0.0.15

New Features

• Resize images returned from tool call (Anthropic) (#41)

Bugs Squashed

• Anthropic messages: text content blocks must be non-empty (#44)
• Invalid 'input[95].call_id': string too long. Expected a string with maximum length 64, but got a string with length 116 instead. (#45)
• Fireworks generates tool_call.ids that result in Anthropic API calls failing (#42)
• Claude server tool_result yield bug (#40)
• fix truncation (#39), thanks to @RensDimmendaal

v0.0.14

New Features

• Resize images returned from tool call (Anthropic) (#41)

Bugs Squashed

• Anthropic messages: text content blocks must be non-empty (#44)

• Invalid 'input[95].call_id': string too long. Expected a string with maximum length 64, but got a string with length 116 instead. (#45)

• Fireworks generates tool_call.ids that result in Anthropic API calls failing (#42)

• Claude server tool_result yield bug (#40)

  • 

• fix truncation (#39), thanks to @RensDimmendaal

v0.0.12

New Features

• Add CODEX_AUTH_PATH (#38)

v0.0.11

New Features

• rename tools to be as safepyrun/safecmd expects (#36), thanks to @RensDimmendaal

• Add Mimo vendor, Opus 4-8, modern_llm preset, and fix Anthropic cache cost fallback (#35)

Bugs Squashed

• Wrong roles in mk_msgs when fmt2hist ends with tool (#37)

• Update 'gpt-5.3-codex-spark' meta to support tools (#34)

  • 

• Model name changes from the server response invalidates model meta patches (#33)

  • 

v0.0.10

New Features

• MediaUrl for direct url handling without byte reading (#31)

• Add timeout to mk_client (#26)

• Add retry logic with exponential backoff to acomplete (#25), thanks to @ncoop57

• Yield tool calls JIT (#19)

Bugs Squashed

• force enable web_search for codex models (#22), thanks to @jackhogan
  • The litellm metadata file is missing supports_web_search for GPT-5.4 so the Codex version wasn't getting it. Explicitly set it to True like we do for non-codex gpt models.

v0.0.9

New Features

• Add approx_pricing helper and fix Fireworks Kimi k2p6 model registration with pricing (#21)

• Refactor model info into registry; add get_model_pricing; add new gemini models (#20)

Bugs Squashed

• Fix accounts/fireworks/models/kimi-k2p5 registration (#23)

• force enable web_search for codex models (#22), thanks to @jackhogan

  • The litellm metadata file is missing supports_web_search for GPT-5.4 so the Codex version wasn't getting it. Explicitly set it to True like we do for non-codex gpt models.