mirror of
https://github.com/codewhale-hq/Codewhale.git
synced 2026-11-07 10:36:05 -10:00
A catalog row stating codewhale.protocol = "responses" now resolves to
WireFormat::Responses and dispatches to {base}/responses — the account API
serves /v1/responses natively and the wire machinery already existed; the
catalog label map was the only missing seam. Unknown protocol labels still
fall back to the namespace rule so a row this build predates stays
reachable, and the id alone never invents a Responses route.
codewhale-config --lib: 706 passed, 1 skipped. codewhale-filtered
codewhale-tui tests: 95 passed including a new end-to-end
catalog→Responses dispatch test. fmt clean.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
29 lines
982 B
Bash
29 lines
982 B
Bash
# Codewhale workspace credentials
|
|
#
|
|
# Shell-exported variables override values in this file. Codewhale loads only
|
|
# literal credential names for built-in providers from a workspace `.env`.
|
|
# Routing, model/base URL, config/profile, MCP/plugin, sandbox, approval,
|
|
# executable-path, runtime, and other control settings are ignored here; put
|
|
# those in config.toml, CLI flags, or the launching shell.
|
|
#
|
|
# Variable expansion is deliberately unsupported. Keep values literal and
|
|
# keep `.env` untracked.
|
|
|
|
# DeepSeek API (default provider)
|
|
# Get an API key from DeepSeek, then keep it local in `.env`.
|
|
# DEEPSEEK_API_KEY=
|
|
|
|
# NVIDIA NIM-hosted models
|
|
# NVIDIA_API_KEY=
|
|
# NVIDIA_NIM_API_KEY=
|
|
|
|
# AtlasCloud OpenAI-compatible endpoint
|
|
# ATLASCLOUD_API_KEY=
|
|
|
|
# Mistral AI (la Plateforme) — https://console.mistral.ai/api-keys
|
|
# MISTRAL_API_KEY=
|
|
|
|
# Codewhale API — account key (cwc_key_…) with the models:infer scope
|
|
# https://app.codewhale.net/settings?section=api
|
|
# CODEWHALE_API_KEY=
|