惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

爱范儿
爱范儿
腾讯CDC
博客园 - 司徒正美
A
About on SuperTechFans
H
Help Net Security
J
Java Code Geeks
C
Check Point Blog
B
Blog RSS Feed
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
MongoDB | Blog
MongoDB | Blog
U
Unit 42
Hugging Face - Blog
Hugging Face - Blog
Last Week in AI
Last Week in AI
MyScale Blog
MyScale Blog
V
Visual Studio Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
I
InfoQ
H
Hackread – Cybersecurity News, Data Breaches, AI and More
F
Fortinet All Blogs
博客园 - 聂微东
酷 壳 – CoolShell
酷 壳 – CoolShell
GbyAI
GbyAI
博客园 - 【当耐特】
雷峰网
雷峰网

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4
fix(amazon-bedrock): add known model context windows to d...
wirjo · 2026-04-23 · via Recent Commits to openclaw:main

@@ -21,8 +21,121 @@ import {

2121

const log = createSubsystemLogger("bedrock-discovery");

22222323

const DEFAULT_REFRESH_INTERVAL_SECONDS = 3600;

24-

const DEFAULT_CONTEXT_WINDOW = 32000;

24+

const DEFAULT_CONTEXT_WINDOW = 32_000;

2525

const DEFAULT_MAX_TOKENS = 4096;

26+27+

// ---------------------------------------------------------------------------

28+

// Known model context windows (Bedrock API does not expose token limits)

29+

// ---------------------------------------------------------------------------

30+31+

/**

32+

* Bedrock's ListFoundationModels and GetFoundationModel APIs return no token

33+

* limit information — only model ID, name, modalities, and lifecycle status.

34+

* There is currently no Bedrock API to discover context windows or max output

35+

* tokens programmatically.

36+

*

37+

* This map provides correct context window values for known models so that

38+

* session management, compaction thresholds, and context overflow detection

39+

* work correctly. If AWS adds token metadata to the API in the future, this

40+

* table should become a fallback rather than the primary source.

41+

*

42+

* Inference profile prefixes (us., eu., ap., global.) are stripped before lookup.

43+

*

44+

* Sources: https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html

45+

* https://platform.claude.com/docs/en/about-claude/models

46+

*/

47+

const KNOWN_CONTEXT_WINDOWS: Record<string, number> = {

48+

// Anthropic Claude

49+

"anthropic.claude-3-7-sonnet-20250219-v1:0": 200_000,

50+

"anthropic.claude-opus-4-7": 1_000_000,

51+

"anthropic.claude-opus-4-6-v1": 1_000_000,

52+

"anthropic.claude-opus-4-6-v1:0": 1_000_000,

53+

"anthropic.claude-sonnet-4-6": 1_000_000,

54+

"anthropic.claude-sonnet-4-6-v1:0": 1_000_000,

55+

"anthropic.claude-sonnet-4-5-20250929-v1:0": 200_000,

56+

"anthropic.claude-sonnet-4-20250514-v1:0": 200_000,

57+

"anthropic.claude-opus-4-5-20251101-v1:0": 200_000,

58+

"anthropic.claude-opus-4-1-20250805-v1:0": 200_000,

59+

"anthropic.claude-haiku-4-5-20251001-v1:0": 200_000,

60+

"anthropic.claude-3-5-haiku-20241022-v1:0": 200_000,

61+

"anthropic.claude-3-haiku-20240307-v1:0": 200_000,

62+

// Amazon Nova

63+

"amazon.nova-premier-v1:0": 1_000_000,

64+

"amazon.nova-pro-v1:0": 300_000,

65+

"amazon.nova-lite-v1:0": 300_000,

66+

"amazon.nova-micro-v1:0": 128_000,

67+

"amazon.nova-2-lite-v1:0": 300_000,

68+

// MiniMax

69+

"minimax.minimax-m2.5": 1_000_000,

70+

"minimax.minimax-m2.1": 1_000_000,

71+

"minimax.minimax-m2": 1_000_000,

72+

// Meta Llama 4

73+

"meta.llama4-maverick-17b-instruct-v1:0": 1_000_000,

74+

"meta.llama4-scout-17b-instruct-v1:0": 512_000,

75+

// Meta Llama 3

76+

"meta.llama3-3-70b-instruct-v1:0": 128_000,

77+

"meta.llama3-2-90b-instruct-v1:0": 128_000,

78+

"meta.llama3-2-11b-instruct-v1:0": 128_000,

79+

"meta.llama3-2-3b-instruct-v1:0": 128_000,

80+

"meta.llama3-2-1b-instruct-v1:0": 128_000,

81+

"meta.llama3-1-405b-instruct-v1:0": 128_000,

82+

"meta.llama3-1-70b-instruct-v1:0": 128_000,

83+

"meta.llama3-1-8b-instruct-v1:0": 128_000,

84+

// NVIDIA Nemotron

85+

"nvidia.nemotron-super-3-120b": 256_000,

86+

"nvidia.nemotron-nano-3-30b": 128_000,

87+

"nvidia.nemotron-nano-12b-v2": 128_000,

88+

"nvidia.nemotron-nano-9b-v2": 128_000,

89+

// Mistral

90+

"mistral.mistral-large-3-675b-instruct": 128_000,

91+

"mistral.mistral-large-2407-v1:0": 128_000,

92+

"mistral.mistral-small-2402-v1:0": 32_000,

93+

// DeepSeek

94+

"deepseek.r1-v1:0": 128_000,

95+

"deepseek.v3.2": 128_000,

96+

// Cohere

97+

"cohere.command-r-plus-v1:0": 128_000,

98+

"cohere.command-r-v1:0": 128_000,

99+

// AI21

100+

"ai21.jamba-1-5-large-v1:0": 256_000,

101+

"ai21.jamba-1-5-mini-v1:0": 256_000,

102+

// Google Gemma

103+

"google.gemma-3-27b-it": 128_000,

104+

"google.gemma-3-12b-it": 128_000,

105+

"google.gemma-3-4b-it": 128_000,

106+

// GLM

107+

"zai.glm-5": 128_000,

108+

"zai.glm-4.7": 128_000,

109+

"zai.glm-4.7-flash": 128_000,

110+

// Qwen

111+

"qwen.qwen3-coder-next": 256_000,

112+

"qwen.qwen3-coder-30b-a3b-v1:0": 256_000,

113+

"qwen.qwen3-32b-v1:0": 128_000,

114+

"qwen.qwen3-vl-235b-a22b": 128_000,

115+

};

116+117+

/**

118+

* Resolve the real context window for a Bedrock model ID.

119+

* Strips inference profile prefixes (us., eu., ap., global.) before lookup.

120+

*/

121+

function resolveKnownContextWindow(modelId: string): number | undefined {

122+

const stripped = modelId.replace(/^(?:us|eu|ap|apac|au|jp|global)\./, "");

123+

const candidates = [modelId, stripped];

124+

for (const candidate of candidates) {

125+

if (KNOWN_CONTEXT_WINDOWS[candidate] !== undefined) {

126+

return KNOWN_CONTEXT_WINDOWS[candidate];

127+

}

128+

const withoutVersionSuffix = candidate.replace(/:0$/, "");

129+

if (

130+

withoutVersionSuffix !== candidate &&

131+

KNOWN_CONTEXT_WINDOWS[withoutVersionSuffix] !== undefined

132+

) {

133+

return KNOWN_CONTEXT_WINDOWS[withoutVersionSuffix];

134+

}

135+

}

136+

return undefined;

137+

}

138+26139

const DEFAULT_COST = {

27140

input: 0,

28141

output: 0,

@@ -163,7 +276,7 @@ function toModelDefinition(

163276

reasoning: inferReasoningSupport(summary),

164277

input: mapInputModalities(summary),

165278

cost: DEFAULT_COST,

166-

contextWindow: defaults.contextWindow,

279+

contextWindow: resolveKnownContextWindow(id) ?? defaults.contextWindow,

167280

maxTokens: defaults.maxTokens,

168281

};

169282

}

@@ -192,7 +305,7 @@ function resolveBaseModelId(profile: InferenceProfileSummary): string | undefine

192305

}

193306

if (profile.type === "SYSTEM_DEFINED") {

194307

const id = profile.inferenceProfileId ?? "";

195-

const prefixMatch = /^(?:us|eu|ap|jp|global)\.(.+)$/i.exec(id);

308+

const prefixMatch = /^(?:us|eu|ap|apac|au|jp|global)\.(.+)$/i.exec(id);

196309

if (prefixMatch) {

197310

return prefixMatch[1];

198311

}

@@ -282,7 +395,9 @@ function resolveInferenceProfiles(

282395

reasoning: baseModel?.reasoning ?? false,

283396

input: baseModel?.input ?? ["text"],

284397

cost: baseModel?.cost ?? DEFAULT_COST,

285-

contextWindow: baseModel?.contextWindow ?? defaults.contextWindow,

398+

contextWindow: baseModel?.contextWindow

399+

?? resolveKnownContextWindow(baseModelId ?? profile.inferenceProfileId ?? "")

400+

?? defaults.contextWindow,

286401

maxTokens: baseModel?.maxTokens ?? defaults.maxTokens,

287402

});

288403

}