Blue-B 5f58248016 fix(claude): clamp max_tokens to model limit in normalizeClaudeBudget ...

When adjustedBudget < minBudget, the previous fix blindly set
max_tokens = budgetTokens+1 which could exceed MaxCompletionTokens.

Now: cap max_tokens at MaxCompletionTokens, recalculate budget, and
disable thinking entirely if constraints are unsatisfiable.

Add unit tests covering raise, clamp, disable, and no-op scenarios.

2026-03-09 22:10:30 +09:00

..

provider

fix(claude): clamp max_tokens to model limit in normalizeClaudeBudget

2026-03-09 22:10:30 +09:00

apply.go

feat(thinking): rename isBudgetBasedProvider to isBudgetCapableProvider and update logic for provider checks

2026-03-03 19:49:51 +08:00

convert.go

feat(thinking): add HasLevel and MapToClaudeEffort functions for adaptive thinking support

2026-03-03 14:16:36 +08:00

errors.go

refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation

2026-01-18 10:30:15 +08:00

strip.go

feat(thinking): add adaptive thinking support for Claude models

2026-03-03 09:05:31 +08:00

suffix.go

feat(thinking): add adaptive thinking support for Claude models

2026-03-03 09:05:31 +08:00

text.go

fix(thinking): map reasoning_effort to thinkingConfig

2026-01-15 13:06:40 +08:00

types.go

feat(thinking): add adaptive thinking support for Claude models

2026-03-03 09:05:31 +08:00

validate.go

feat(thinking): rename isBudgetBasedProvider to isBudgetCapableProvider and update logic for provider checks

2026-03-03 19:49:51 +08:00