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.mdindex 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 (ahand-written `docs/releases/<tag>.md` wins if present), so keeping this filecurrent 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### Modelsdiff --git a/docs/releases/v0.0.302.15.md b/docs/releases/v0.0.302.15.mdnew file mode 100644index 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.jsonindex 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.zigindex 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