graff — a fast agentic coding harness in Zig: multi-provider, MCP, workflows, DGM evolution loop, TS/Python SDKs
Python
Prepare v0.302.66 release
justrachdbd264e4120e
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 42598e51..9eea1573 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -10,6 +10,11 @@ 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.+## v0.302.66++- A one-shot (`-p`) answer built on the provider's hosted search is kept. Hosted search runs inside the model call and never counted as a local tool call, so graff took a search-backed answer for a described change, printed "[described a change with no tool call — asking once more]", and the follow-up reply replaced the answer (#1786, #1787).+- Retains all changes from v0.302.65.+## v0.302.65- Claude Agent models report and use their 1M context window. Claude Code runs the current Claude models at 1M natively, but graff listed every `claude-agent` model at 200k, so it compacted at a fifth of the window and clients showed "200k context". A `<id>[1m]` name now resolves to 1M as well (#1783).diff --git a/docs/releases/v0.302.66.md b/docs/releases/v0.302.66.mdnew file mode 100644index 00000000..099685a9--- /dev/null+++ b/docs/releases/v0.302.66.md@@ -0,0 +1,7 @@+# v0.302.66++A one-shot answer built on hosted search is kept.++- **No false bounce.** In a one-shot `-p` run, graff re-asks once when the first reply describes a change without calling a tool. Hosted search runs inside the model call, so it never counted as a tool call, and a search-backed answer was taken for a described change. graff printed "[described a change with no tool call — asking once more]", and the follow-up reply replaced the answer. A reply whose model call ran a hosted search now stands. (#1786, #1787)++Includes all changes from v0.302.65.diff --git a/scripts/eval/tier1-manifest.json b/scripts/eval/tier1-manifest.jsonindex 3a42ba68..52cdd60b 100644--- a/scripts/eval/tier1-manifest.json+++ b/scripts/eval/tier1-manifest.json@@ -14,7 +14,7 @@"src/main.zig","src/repl.zig"],- "test_count_baseline": 3581,+ "test_count_baseline": 3583,"test_count_slack": 25,"required_invariants": [{diff --git a/src/cli_text_source.zig b/src/cli_text_source.zigindex a204b1fc..115e77b9 100644--- a/src/cli_text_source.zig+++ b/src/cli_text_source.zig@@ -5,6 +5,9 @@pub const changelog_text =\\What's new\\──────────+ \\0.302.66+ \\ • a one-shot answer built on hosted search is kept, not bounced and replaced+ \\\\0.302.65\\ • Claude Agent models use their full 1M context window (was listed as 200k)\\