Alex b5296df8a9 feat(pricing): cached-input rates for gpt-5.4-mini and gpt-5.4-nano ...

Checked against OpenAI's pricing page: gpt-5.5 at $5 / $30 (cached $0.50)
was already right. The mini and nano models declared no cached rate, so
cached prompt tokens were billed at the full input rate.

2026-09-21 14:30:48 +01:00

..

encodings

feat: air-gapped deployment guide, no implicit downloads

2026-09-15 17:54:24 +01:00

models

feat(pricing): cached-input rates for gpt-5.4-mini and gpt-5.4-nano

2026-09-21 14:30:48 +01:00

settings

feat(pricing): per-million model rates and a cost module

2026-09-21 11:38:22 +01:00

__init__.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

db_uri.py

refactor(settings): split Settings into per-domain modules

2026-09-17 11:04:01 +01:00

json_schema_utils.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

log_context.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

logging_config.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

model_registry.py

refactor: read settings directly instead of getattr with a second default

2026-09-17 11:14:34 +01:00

model_settings.py

feat(pricing): per-million model rates and a cost module

2026-09-21 11:38:22 +01:00

model_utils.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

model_yaml.py

feat(pricing): per-million model rates and a cost module

2026-09-21 11:38:22 +01:00

optional_deps.py

fix(rename): second review pass on the package rename

2026-09-07 14:02:59 +01:00

paths.py

feat: installed package keeps its data in ~/.docsgpt/server

2026-09-15 22:45:54 +01:00

secret_key.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

shutdown.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

url_validation.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00