3de2d19
chore: add gemini 3.1 pro (#187)
Andrey Nering created
3de2d19
chore: add gemini 3.1 pro (#187)
Andrey Nering created
817a37c
chore(huggingface): update default small model
Andrey Nering created
d269cd1
chore: auto-update generated files
Charm created
22918d4
ci: use right access token on update action
Andrey Nering created
2613a0f
chore(taskfile): add all generators to `gen:all`
Andrey Nering created
5cf984c
chore(taskfile): add task to update vercel
Andrey Nering created
8ece734
ci: update huggingface automatically
Andrey Nering created
8a3709a
chore: update copilot models
Andrey Nering created
cb08c8e
chore: remove old anthropic models that no longer work (#186)
* Claude Haiku 3.5 * Claude Sonnet 4.5
Andrey Nering created
7927c75
v0.20.0
Andrey Nering created
1560a21
feat(cerebras): remove deprecated llama-3.3-70b and qwen-3-32b models
These models have been deprecated from the Cerebras inference platform. - Remove llama-3.3-70b and qwen-3-32b from the Cerebras provider config - Update default_small_model_id from qwen-3-32b to qwen-3-235b-a22b-instruct-2507 - Remaining models: gpt-oss-120b, qwen-3-235b-a22b-instruct-2507, zai-glm-4.7
Seb Duerr created
7d7e3c3
Add temperature=0.9 and top_p=0.95 to zai-glm-4.7 model
Seb Duerr created
32297fa
v0.19.3
Andrey Nering created
6e4904e
fix: grok 4 does not support reasoning levels (#181)
It was returning an error if you selected one. The documentations says it's not supported: https://docs.x.ai/developers/models
Andrey Nering created
dc620c4
v0.19.2
Andrey Nering created
19fc086
chore: `task gen:copilot`, add gpt 5.3 codex via copilot
Andrey Nering created
85ba2f3
v0.19.1
Andrey Nering created
bea6d5d
Add Minimax-M2.5 as new default model (#180)
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
maxffarrell and Copilot created
678c392
v0.19.0
Andrey Nering created
8e14cf4
feat: add io.net provider (#179)
Assisted-by: Kimi K2.5 via Crush <crush@charm.land>
Andrey Nering created
b45b006
chore(synthetic): update default small model
The previous one was removed from the list.
Andrey Nering created
3d87bc6
chore: update generated files
Signed-off-by: Carlos Alexandro Becker <caarlos0@users.noreply.github.com>
Carlos Alexandro Becker created
3b147c8
v0.18.0
Andrey Nering created
8f07cef
chore: release glm-5 via z.ai (#176)
Andrey Nering created
d60d148
feat(synthetic): kimi k2.5 (#178)
Signed-off-by: Carlos Alexandro Becker <caarlos0@users.noreply.github.com>
Carlos Alexandro Becker created
371906f
ci: update golangci-lint version (#177)
Andrey Nering created
7963ec9
chore(openrouter): same to temp file for debugging
Andrey Nering created
71a817c
v0.17.4
Christian Rocha created
65de73c
chore(openrouter): bump openrouter for Aurora Alpha (#175)
Christian Rocha created
d0bc586
v0.17.3
Andrey Nering created
e5471ab
chore(copilot): add claude opus 4.6
Andrey Nering created
1dbb29e
v0.17.2
Andrey Nering created
38b17ec
chore:(aws-bedrock): add claude opus 4.6 (#173)
Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>
Jan Steinke and Andrey Nering created
378e4ec
v0.17.1
Andrey Nering created
f8e2080
chore: add minimax provider (#98)
Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>
Kujtim Hoxha and Andrey Nering created
f9b6c27
fix: temporarely lower max tokens
refs https://github.com/charmbracelet/fantasy/pull/131 Signed-off-by: Carlos Alexandro Becker <caarlos0@users.noreply.github.com>
Carlos Alexandro Becker created
40cc613
feat: add opus 4.6 on anthropic and openrouter (#171)
* feat: add opus 4.6 on anthropic and openrouter Signed-off-by: Carlos Alexandro Becker <caarlos0@users.noreply.github.com> * fix: adjust Signed-off-by: Carlos Alexandro Becker <caarlos0@users.noreply.github.com> * Revert "fix: adjust" This reverts commit 4c89f5655647b86d26ee38bcca84e51db76914b2. --------- Signed-off-by: Carlos Alexandro Becker <caarlos0@users.noreply.github.com>
Carlos Alexandro Becker created
9371209
fix(synthetic): update pricing, add minimax-m2.1/gpt-oss meta (#165)
* fix(synthetic): update k2.5 pricing * fix(synthetic): enable reasoning for gpt-oss-120b * fix(synthetic): add minimax-m2.1 override Synthetic stopped self-hosting MiniMax M2.1 and are now proxying it through Fireworks. Proxied models don't include the supported_features metadata, so we need overrides for tools and reasoning support.
Amolith created
65659e2
v0.16.1
Andrey Nering created
08b0318
chore: update the vercel config to use the vercel provider (#170)
Kujtim Hoxha created
d6690d5
v0.16.0
Andrey Nering created
a8abd9b
chore!: migrate go module to `charm.land/catwalk` (#166)
BREAKING CHANGE: This will need users to update the import path.
Andrey Nering created
72c03a5
feat(copilot): implement token-based api for fresh model data (#167)
GitHub Copilot now requires a token-based flow to access the actual API endpoint: - Added token request to https://api.github.com/copilot_internal/v2/token - Parse dynamic API endpoint from token response - Use dynamic endpoint to fetch models with fresh data - Added required headers: Copilot-Integration-Id and User-Agent Result: fetches ~38 models with updated context windows including newer models like gpt-5 series with 264K-400K context windows. Update generates copilot.json with refreshed model capabilities. 💘 Generated with Crush Assisted-by: Kimi K2 Thinking via Crush <crush@charm.land>
Andrey Nering created
66e542a
chore: auto-update generated files
Charm created
a736daa
chore: auto-update generated files
Charm created
7742d0b
v0.15.1
Kujtim Hoxha created
e6ce54a
chore:handle kimi k2.5 correctly for synthetic
Kujtim Hoxha created
07dc0f8
chore: auto-update generated files
Charm created
bf6200e
chore: auto-update generated files
Charm created
3f14e08
chore: auto-update generated files
Charm created