Skip to content

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

Python

Release v0.0.302.15

justrach272576c282d5
diff --git a/CHANGELOG.md b/CHANGELOG.md
index dc6705dd..aa5ea93a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,16 @@ The release workflow uses a tag's section here as its release notes (a
hand-written `docs/releases/<tag>.md` wins if present), so keeping this file
current is part of cutting a release.
+## v0.0.302.15
+
+### Models
+
+- DeepSeek's default effort thinks at DeepSeek's `low` level (ADR 0237). graff's default (`medium`) used to send `reasoning_effort: medium` with thinking on, and on DeepSeek V4 Pro the first request of a turn planned the whole job before its first tool call. The default now sends `low` with thinking still enabled. `/effort low` still turns thinking off (ADR 0054), `high` and above are unchanged, and the flash models' default stays thinking off. The picker, status line and ACP still call the default Medium. (#1456)
+
+### Evals
+
+- DeepSeek V4 Pro at graff's default effort: v0.0.302.14 against this release, with thinking off and deepseek-harness alongside, in `evals/graff-vs-deepseek-harness/DEFAULT-EFFORT.md`. See [docs/releases/v0.0.302.15.md](docs/releases/v0.0.302.15.md).
+
## v0.0.302.14
### Models
diff --git a/docs/releases/v0.0.302.15.md b/docs/releases/v0.0.302.15.md
new file mode 100644
index 00000000..906cfd54
--- /dev/null
+++ b/docs/releases/v0.0.302.15.md
@@ -0,0 +1,44 @@
+# Codegraff v0.0.302.15
+
+DeepSeek now thinks at its `low` level at graff's default effort, so a
+default turn gets to its first tool call sooner. Measured on DeepSeek V4 Pro
+against the previous release:
+
+## Evals
+
+### DeepSeek V4 Pro at the default effort
+
+v0.0.302.14 and this release on DeepSeek's own API with one key, interleaved
+over 11 coding and 10 MCP tasks, 2 runs each:
+
+| | Pass | Wall per task | Coding tasks | MCP tasks | Output tokens per task |
+| --- | ---: | ---: | ---: | ---: | ---: |
+| v0.0.302.14 | 42/42 | 21.6s | 6.8s | 37.8s | 1,941 |
+| **v0.0.302.15** | 41/42 | **15.9s** | **6.2s** | **26.5s** | **1,235** |
+
+This release took 26% less time per task and wrote 36% fewer output tokens,
+most of it on the MCP tasks. It missed one run: on `regex-count` it counted
+lines with `grep -c '^ERROR'`, which also matches the `ERRORS_TOTAL` line the
+prompt rules out. An earlier round, with a build that sends the same request,
+measured 11.9s against 24.2s per task.
+
+On the sub-agent suites both passed 20 of 20 runs, in 37.7s per task against
+61.9s: 52.9s against 85.7s when the tasks ask for sub-agents and 22.6s against
+38.0s when they do not.
+
+Turning thinking off altogether was faster again but missed more: one coding
+run and 5 of 20 sub-agent runs, against none and 2 of 20 for `low` in the
+same rounds. `/effort low` still sends thinking off for anyone who wants that
+trade, and `/effort high` thinks longer.
+[Full results](https://github.com/justrach/codegraff/blob/v0.0.302.15/evals/graff-vs-deepseek-harness/DEFAULT-EFFORT.md).
+
+## DeepSeek thinks at its low level by default
+
+graff's default effort is `medium`, and graff sent it to DeepSeek as
+`reasoning_effort: medium` with thinking on. DeepSeek documents `low`, `high`
+and `max`, and on V4 Pro the first request of a turn planned the whole job
+before its first tool call. The default now sends `low` with thinking still
+enabled. `/effort low` still turns thinking off, `high` and above are
+unchanged, and the flash models' default stays thinking off. The picker,
+status line and ACP still call the default Medium
+([ADR 0237](https://github.com/justrach/codegraff/blob/v0.0.302.15/docs/adr/0237-deepseek-thinks-at-its-low-level-by-default.md), #1456).
diff --git a/scripts/eval/tier1-manifest.json b/scripts/eval/tier1-manifest.json
index 56ed229a..edb8c9b3 100644
--- a/scripts/eval/tier1-manifest.json
+++ b/scripts/eval/tier1-manifest.json
@@ -15,7 +15,7 @@
"src/repl.zig",
"TUI/root.zig"
],
- "test_count_baseline": 3154,
+ "test_count_baseline": 3155,
"test_count_slack": 25,
"required_invariants": [
{
diff --git a/src/cli.zig b/src/cli.zig
index d0b373da..61b4b65a 100644
--- a/src/cli.zig
+++ b/src/cli.zig
@@ -23,6 +23,9 @@ const update_target = @import("update_target.zig");
pub const changelog_text =
\\What's new
\\──────────
+ \\0.0.302.15
+ \\ • DeepSeek's default effort thinks at its low level (/effort high for more)
+ \\
\\0.0.302.14
\\ • MiMo answers without thinking unless effort is high (/effort high)
\\ • MCP servers connect in the background; the first message never waits