getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-18 12:03:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix token statistics on abort for Anthropic provider

Browse source 
- Add handling for message_start event to capture initial token usage
- Fix message_delta to use assignment (=) instead of addition (+=)
  since Anthropic sends cumulative token counts, not incremental
- Add comprehensive tests for all providers (Google, OpenAI Completions,
  OpenAI Responses, Anthropic)
- Document OpenAI limitation: token stats only available at stream end

Fixes issue where aborted streams had zero token counts despite
Anthropic sending input tokens in the initial message_start event.
This commit is contained in:
Mario Zechner 2025-10-26 21:22:24 +01:00
parent 23be934a9a
commit bc8d994a7b
3 changed files with 161 additions and 73 deletions
Download patch file Download diff file Expand all files Collapse all files

136
packages/ai/src/models.generated.ts
View file

@ -3810,23 +3810,6 @@ export const MODELS = {
contextWindow: 32768,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"cohere/command-r-08-2024": {
id: "cohere/command-r-08-2024",
name: "Cohere: Command R (08-2024)",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4000,
} satisfies Model<"openai-completions">,
"cohere/command-r-plus-08-2024": {
id: "cohere/command-r-plus-08-2024",
name: "Cohere: Command R+ (08-2024)",
@ -3844,6 +3827,23 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 4000,
} satisfies Model<"openai-completions">,
"cohere/command-r-08-2024": {
id: "cohere/command-r-08-2024",
name: "Cohere: Command R (08-2024)",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4000,
} satisfies Model<"openai-completions">,
"sao10k/l3.1-euryale-70b": {
id: "sao10k/l3.1-euryale-70b",
name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@ -3912,23 +3912,6 @@ export const MODELS = {
contextWindow: 16384,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-70b-instruct": {
id: "meta-llama/llama-3.1-70b-instruct",
name: "Meta: Llama 3.1 70B Instruct",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.39999999999999997,
output: 0.39999999999999997,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-405b-instruct": {
id: "meta-llama/llama-3.1-405b-instruct",
name: "Meta: Llama 3.1 405B Instruct",
@ -3946,6 +3929,23 @@ export const MODELS = {
contextWindow: 32768,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-70b-instruct": {
id: "meta-llama/llama-3.1-70b-instruct",
name: "Meta: Llama 3.1 70B Instruct",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.39999999999999997,
output: 0.39999999999999997,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mistral-nemo": {
id: "mistralai/mistral-nemo",
name: "Mistral: Mistral Nemo",
@ -4065,23 +4065,6 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3-70b-instruct": {
id: "meta-llama/llama-3-70b-instruct",
name: "Meta: Llama 3 70B Instruct",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.3,
output: 0.39999999999999997,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 8192,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3-8b-instruct": {
id: "meta-llama/llama-3-8b-instruct",
name: "Meta: Llama 3 8B Instruct",
@ -4099,6 +4082,23 @@ export const MODELS = {
contextWindow: 8192,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3-70b-instruct": {
id: "meta-llama/llama-3-70b-instruct",
name: "Meta: Llama 3 70B Instruct",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.3,
output: 0.39999999999999997,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 8192,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"mistralai/mixtral-8x22b-instruct": {
id: "mistralai/mixtral-8x22b-instruct",
name: "Mistral: Mixtral 8x22B Instruct",
@ -4133,23 +4133,6 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mistral-tiny": {
id: "mistralai/mistral-tiny",
name: "Mistral Tiny",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.25,
output: 0.25,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mistral-small": {
id: "mistralai/mistral-small",
name: "Mistral Small",
@ -4167,6 +4150,23 @@ export const MODELS = {
contextWindow: 32768,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mistral-tiny": {
id: "mistralai/mistral-tiny",
name: "Mistral Tiny",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.25,
output: 0.25,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"mistralai/mixtral-8x7b-instruct": {
id: "mistralai/mixtral-8x7b-instruct",
name: "Mistral: Mixtral 8x7B Instruct",