graff — a fast agentic coding harness in Zig: multi-provider, MCP, workflows, DGM evolution loop, TS/Python SDKs
Python
Release notes: Kimi sign-in (#1733) and the opt-in OpenAI 12h cache (#1698)
justrach67734e16561d
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex d1c83b30..381f07cc 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -13,6 +13,8 @@ current is part of cutting a release.## v0.302.69- Reading peer mail no longer rewrites history the model was already sent: only wake lines it was never sent are removed. On Claude Agent every woken turn used to start a fresh Claude Code process; on other providers the cached prefix changed after each inbox read (#1799).+- `graff login kimi` signs international accounts in on kimi.ai and mainland China accounts on kimi.com (from the saved login, or clock and locale); `graff login kimi.ai|kimi.com` choose outright and refresh returns to the issuing site. Sign-in links are copied to the clipboard, over SSH too, and no browser opens where it can't be seen (#1733).+- OpenAI Responses GPT-5.6+: `GRAFF_OPENAI_CACHE_TTL=12h` / `openai_cache_ttl` puts a 12-hour breakpoint on the stable prefix; the default stays 30m until a live probe confirms it. Usage parses cache writes by TTL (#1698, ADR 0312).- Workers can use gateway models and name their own provider: `--subagent-model` with `--subagent-provider codegraff` accepts a gateway model the built-in catalog does not list, a persona's `model: <provider>/<model>` pin runs on that provider, and its calls report cost (#1769).- `graff harness-tree show|digest|check|apply|diff` reads the instruction file, skills, subagents, scripts and hooks graff loads as one tree (#1770).- MCP over HTTP retries a cancel notice when local ports run out (#1796, #1794).diff --git a/docs/releases/v0.302.69.md b/docs/releases/v0.302.69.mdindex 23662c47..8ae16f75 100644--- a/docs/releases/v0.302.69.md+++ b/docs/releases/v0.302.69.md@@ -1,11 +1,14 @@# v0.302.69-Peer mail stops rewriting history that was already sent, workers can use gateway models, and `graff harness-tree` shows the harness as one value.+Peer mail stops rewriting history that was already sent, Kimi international accounts sign in on kimi.ai, workers can use gateway models, and `graff harness-tree` shows the harness as one value.- **Reading peer mail keeps the conversation intact.** After a turn read its inbox, graff removed every peer wake line from the whole history, including ones the model had already been sent. That rewrote history the provider had cached: on Claude Agent every woken turn started a fresh Claude Code process, and on other providers it changed the cached prefix. Only wake lines the model was never sent are removed now. (#1799)+- **Kimi sign-in works for international accounts.** `graff login kimi` signs international accounts in on kimi.ai and mainland China accounts on kimi.com, picking the site from your saved login or your clock and locale; `graff login kimi.ai` and `graff login kimi.com` choose it outright, and token refresh goes back to the site that issued the login. Earlier logins keep refreshing on kimi.com. (#1733)+- **Sign-in links are copied for you.** In a terminal, `graff login` puts the link on the clipboard (over SSH, on your own terminal's clipboard). Over SSH and with `GRAFF_NO_BROWSER`, graff no longer opens a browser you can't see. (#1733)- **Workers can use gateway models and name their own provider.** `--subagent-model <model>` with `--subagent-provider codegraff` accepts a model the gateway serves even when the built-in catalog does not list it, a persona pinned with `model: <provider>/<model>` runs on that provider, and a worker's calls on another provider report their cost. (#1769)- **`graff harness-tree show|digest|check|apply|diff`** reads the files graff loads to decide how it works (the instruction file, skills, subagents, scripts and hooks) as one tree you can inspect, compare and apply. (#1770)- **MCP over HTTP: cancelling a request retries its notice** when the machine is briefly out of local ports, instead of dropping it. (#1796, #1794)+- **OpenAI 12-hour prompt cache, opt-in.** On the direct OpenAI Responses route for GPT-5.6 and later, `GRAFF_OPENAI_CACHE_TTL=12h` (or `openai_cache_ttl` in settings) keeps the stable prompt prefix cached for 12 hours. The default is unchanged (30 minutes) until a live check confirms OpenAI accepts and keeps it. Usage now separates 12-hour and 30-minute cache writes. (#1698, ADR 0312)- ADR 0308 records that a cheaper scout worker is an opt-in persona, not a default route. (#1771)Includes all changes from v0.302.68.diff --git a/src/cli_text_source.zig b/src/cli_text_source.zigindex 53c48580..9b2e45da 100644--- a/src/cli_text_source.zig+++ b/src/cli_text_source.zig@@ -7,6 +7,7 @@ pub const changelog_text =\\──────────\\0.302.69\\ • reading peer mail no longer rewrites history the model was already sent+ \\ • graff login kimi works for kimi.ai (international) accounts; sign-in links are copied\\ • workers can use gateway models; graff harness-tree shows the harness as one tree\\\\0.302.68