graff — a fast agentic coding harness in Zig: multi-provider, MCP, workflows, DGM evolution loop, TS/Python SDKs
Python
ADR index: 0222
justrach50c733a91ad1
diff --git a/docs/adr/README.md b/docs/adr/README.mdindex 5d0705cc..7f53c6ee 100644--- a/docs/adr/README.md+++ b/docs/adr/README.md@@ -248,6 +248,7 @@ record only when you need the evidence or the edge cases.| [0219](0219-claude-5-5-era-request-contract.md) | Claude Opus 5.5, Sonnet 5.5 and Fable 5.1 are never forced to a tool, get `drop_block` thinking binding (with its beta header), take `/effort` as `output_config.effort` (left off at graff's default), and get 64K/128K `max_tokens`. Claude errors take the same retry-without ladder as other providers; a refusal ends the turn outside history. Default model `claude-opus-5-5`, ladder opus-5-5 → sonnet-5-5. || [0220](0220-claude-prompt-cache-forks-and-pricing.md) | On the Anthropic API, compaction's note and summary fork the conversation while its cache is warm. They use the same tools, system prompt and history, with the instruction appended, so they read the history instead of rewriting it. Otherwise the old shape runs without breakpoints. A turn-opening request keeps the TTL of the last gap inside a turn. 1-hour writes bill at 2x. 5.5-era models get graff's effort as shown; titles and recaps run at low. A second breakpoint marks where the previous request wrote. || [0221](0221-chatgpt-new-sign-in.md) | The ChatGPT plan's sign-in for open-source apps is its own opt-in `chatgpt-new` provider (dynamic registration, per-machine host id, RS256-verified ID token, the public Responses endpoint and WebSocket, billed flat-rate); Codex stays the primary ChatGPT route until OpenAI requires the new method. |+| [0222](0222-gpt-6-follow-ups-steer-the-running-reply.md) | A follow-up typed while a GPT-6 reply streams over the Codex WebSocket is sent as `response.steer`: accepted, the reply continues or the steer rides the next chained request; refused, it waits for the next turn. The root turn leaves server compaction off while well below its threshold, because the backend will not steer those requests. || [0223](0223-codex-cache-partition-is-the-account.md) | Codex with a ChatGPT account id partitions the prompt cache by account, not repo: the system+tools prefix carries no cwd, so turn 1 in any repo reads the prefix another repo warmed. Children keep their role lanes on the account base; other providers keep the project key (ADR 0069). || [0224](0224-six-rare-natives-join-the-fold.md) | `render_html`, `agent_message`, `install_agent_tool`, `read_tool_result`, `subagent_resume` and `schedule_task` join `native_fold.folded`: listed by `load_tool_schemas`, auto-loaded on a confident call, no longer paid on every request. || [0225](0225-mcp-load-result-states-the-slim-rule.md) | Every MCP load/search/select result says how large list results are slimmed (identity fields; comment lists become `{n, latest_author}`), so a fresh project does not code against dropped fields. A direct call's slimmed result keeps the full payload as a `read_tool_result` handle; rlm binds stay plain slim JSON. |