teknium1 75f523f5c0 fix: unknown/custom models get zero cost instead of fake estimates ...

Custom OAI endpoints, self-hosted models, and local inference should NOT
show fabricated cost estimates. Changed default pricing from $3/$12 per
million tokens to $0/$0 for unrecognized models.

- Added _has_known_pricing() to distinguish commercial vs custom models
- Models with known pricing show $ amounts; unknown models show 'N/A'
- Overview shows asterisk + note when some models lack pricing data
- Gateway format adds '(excludes custom/self-hosted models)' note
- Added 7 new tests for custom model cost handling

2026-03-06 14:18:19 -08:00

..

__init__.py

Refactor Terminal and AIAgent cleanup

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

auxiliary_client.py

fix: handle None message content across codebase (fixes #276)

2026-03-02 02:23:53 -08:00

context_compressor.py

feat: smart context length probing with persistent caching + banner display

2026-03-05 16:09:57 -08:00

display.py

feat: show detailed tool call args in gateway based on config

2026-03-02 05:23:15 -08:00

insights.py

fix: unknown/custom models get zero cost instead of fake estimates

2026-03-06 14:18:19 -08:00

model_metadata.py

test: comprehensive tests for model metadata + firecrawl config

2026-03-05 18:22:39 -08:00

prompt_builder.py

Merge PR #292: feat(whatsapp): native media attachments for images, videos and documents

2026-03-05 08:35:13 -08:00

prompt_caching.py

Refactor Terminal and AIAgent cleanup

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

redact.py

refactor(cli, auth): Add Codex/OpenAI OAuth Support - finalized

2026-02-28 21:56:27 -08:00

skill_commands.py

fix: use Path.parts for hidden directory filter in skill listing

2026-03-04 18:34:16 +03:00

trajectory.py

Refactor Terminal and AIAgent cleanup

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