Bump version to 2.0.0 and upload install-galaxy.sh in deploy script

- Update version from 1.6.3 to 2.0.0 in app/Cargo.toml and Cargo.lock
- Add install-galaxy.sh upload step to build-and-deploy-hermes script
- Include pending AI provider and agent changes
This commit is contained in:
Ryan Ward
2026-07-15 16:17:13 -05:00
parent af5315313d
commit e9a9a4c30f
19 changed files with 523 additions and 61 deletions
+14 -11
View File
@@ -3139,17 +3139,20 @@ impl BlocklistAIController {
// Check if this error is eligible for corrective retry.
// Similar to loop detection, inject a message telling the LLM
// to try a different approach rather than just failing.
// Exclude errors that are proxy/config issues (cache_control,
// BadRequestError from LiteLLM) since the LLM can't fix those.
let error_str = format!("{e}");
let is_corrective_retry_candidate = !matches!(
e.as_ref(),
AIApiError::QuotaLimit { .. }
) && (error_str.contains("ValidationException")
|| error_str.contains("validation")
|| error_str.contains("context window")
|| error_str.contains("too many tokens")
|| error_str.contains("input is too long")
|| error_str.contains("throttl")
|| error_str.contains("ThrottlingException"));
let is_proxy_config_error = error_str.contains("cache_control")
|| error_str.contains("tool_use` ids were found without")
|| error_str.contains("BadRequestError");
let is_corrective_retry_candidate = !is_proxy_config_error
&& !matches!(e.as_ref(), AIApiError::QuotaLimit { .. })
&& (error_str.contains("ValidationException")
|| error_str.contains("context window")
|| error_str.contains("too many tokens")
|| error_str.contains("input is too long")
|| error_str.contains("throttl")
|| error_str.contains("ThrottlingException"));
const MAX_ERROR_RETRIES: usize = 2;
let retry_count = self
@@ -4026,7 +4029,7 @@ impl BlocklistAIController {
let max_ctx = context_window_for_model(&active_model_id);
let new_usage =
(summary_tokens + remaining_msgs_tokens) as f32 / max_ctx as f32;
conversation.set_context_window_usage(new_usage);
conversation.set_context_window_usage(new_usage.clamp(0.0, 1.0));
conversation
.set_current_context_tokens(summary_tokens + remaining_msgs_tokens);