Block oversized requests before providers hard-fail

The runtime already tracked rough token estimates for compaction, but provider-bound
requests still relied on naive model output limits and could be sent upstream even
when the selected model could not fit the estimated prompt plus requested output.

This adds a small model token/context registry in the API layer, estimates request
size from the serialized prompt payload, and fails locally with a dedicated
context-window error before Anthropic or xAI calls are made. Focused integration
coverage asserts the preflight fires before any HTTP request leaves the process.

Constraint: Keep the first pass minimal and reusable across both Anthropic and OpenAI-compatible providers
Rejected: Auto-compact-and-retry in the same patch | broader control-flow change than the requested minimal preflight
Confidence: medium
Scope-risk: narrow
Reversibility: clean
Directive: Expand the model registry before enabling preflight for additional providers or aliases
Tested: cargo build -p api -p tools -p rusty-claude-cli; cargo test -p api
Not-tested: End-to-end CLI auto-compaction or retry behavior after a local context_window_blocked failure
This commit is contained in:
Yeachan-Heo
2026-04-05 16:39:58 +00:00
parent b9c5cc118e
commit fa72cd665e
6 changed files with 264 additions and 11 deletions

View File

@@ -8,6 +8,13 @@ pub enum ApiError {
provider: &'static str,
env_vars: &'static [&'static str],
},
ContextWindowExceeded {
model: String,
estimated_input_tokens: u32,
requested_output_tokens: u32,
estimated_total_tokens: u32,
context_window_tokens: u32,
},
ExpiredOAuthToken,
Auth(String),
InvalidApiKeyEnv(VarError),
@@ -48,6 +55,7 @@ impl ApiError {
Self::Api { retryable, .. } => *retryable,
Self::RetriesExhausted { last_error, .. } => last_error.is_retryable(),
Self::MissingCredentials { .. }
| Self::ContextWindowExceeded { .. }
| Self::ExpiredOAuthToken
| Self::Auth(_)
| Self::InvalidApiKeyEnv(_)
@@ -67,6 +75,16 @@ impl Display for ApiError {
"missing {provider} credentials; export {} before calling the {provider} API",
env_vars.join(" or ")
),
Self::ContextWindowExceeded {
model,
estimated_input_tokens,
requested_output_tokens,
estimated_total_tokens,
context_window_tokens,
} => write!(
f,
"context_window_blocked for {model}: estimated input {estimated_input_tokens} + requested output {requested_output_tokens} = {estimated_total_tokens} tokens exceeds the {context_window_tokens}-token context window; compact the session or reduce request size before retrying"
),
Self::ExpiredOAuthToken => {
write!(
f,