Skip to content

graff — a fast agentic coding harness in Zig: multi-provider, MCP, workflows, DGM evolution loop, TS/Python SDKs

Python

Note the Kimi fixes for v0.302.51

Rach Pradhan807e3215f3e0
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 65668c71..bfb552ef 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,8 @@ current is part of cutting a release.
## v0.302.51
+- Kimi works again with an API key or `graff login kimi`. Every Kimi request had been failing with `network error: RstStream` (or a 400 over HTTP/1.1) because graff sent a corrupted device-id header; graff no longer sends a device id or keeps `~/.kimi/device_id`.
+- A used-up Kimi plan window (`exceeded_current_quota_error`) stops at once as a quota cap instead of being retried as throttling.
- Retrying the same prompt after a connection failure works again, including after loading the failed conversation. Earlier work stays in history; reconnecting does not require a new chat.
- Includes independent conversation forks for subagents and workflow fan-out (`fork_from`), with optional retained workers for later continuation.
- Includes bounded workflow synthesis that returns earlier findings when the final report cannot complete.
diff --git a/src/cli.zig b/src/cli.zig
index 7ea5680d..454918ab 100644
--- a/src/cli.zig
+++ b/src/cli.zig
@@ -24,6 +24,12 @@ const update_target = @import("update_target.zig");
pub const changelog_text =
\\What's new
\\──────────
+ \\0.302.51
+ \\ • Kimi API keys and logins work again (no more RstStream)
+ \\ • a used-up Kimi plan window stops instead of retrying
+ \\ • retrying a prompt after a connection failure works again
+ \\ • subagents and workflows can fork the conversation
+ \\
\\0.302.48
\\ • oMLX is a built-in local provider: --model omlx
\\ • compaction counts opaque state by the provider's own measure