graff — a fast agentic coding harness in Zig: multi-provider, MCP, workflows, DGM evolution loop, TS/Python SDKs
Python
Merge tag 'v0.302.42' into fix/sol-subscription-context
justrach202109e990f1
diff --cc docs/adr/README.mdindex 0da42470,36024219..a73e8294--- a/docs/adr/README.md+++ b/docs/adr/README.md@@@ -294,9 -295,19 +295,21 @@@ record only when you need the evidence| [0281](0281-anthropic-console-sign-in-reads-the-sdk-profile.md) | Anthropic Console sign-in: graff reads the `user_oauth` profile Anthropic's CLI writes (`ant auth login`), in the SDK's precedence (API key wins), sends it as Bearer, and refreshes through `ant auth print-credentials`; `graff login anthropic` runs `ant auth login`. No claude.ai subscription login. || [0282](0282-claude-system-breakpoint-closes-before-the-repo-context.md) | On Claude, the system prompt is two text blocks with the same bytes: the cache breakpoint closes the static instructions, before the project instructions and layout, so every repo shares the tools + instructions prefix. || [0283](0283-agents-prepare-and-linked.md) | New task worktrees symlink the gitignored paths `.agents/linked` lists from the main checkout and run `.agents/prepare` when `.graff/workspace.toml` names no setup script. |+ | [0284](0284-output-limits-are-recovery-not-completion.md) | Output limits continue with bounded recovery; empty replies back off; one-shots expose a saved-session handle and classified result without claiming unknown costs or exactly-once replay. |+ | [0271](0271-gemini-interactions-continue-the-stored-interaction.md) | Direct Gemini (Interactions) requests are stored and continue the last Interaction with `previous_interaction_id` plus only the new steps while a content hash proves graff's history extends it; any rewrite, model switch or rejected id falls back to a full replay; usage meters the whole prompt from the per-invocation counts. Tool choice is `validated`, `minimal` thinking maps to `low`, thought summaries stream, and Gemini 3.1 Pro with tools uses its custom-tools variant. `GRAFF_INTERACTIONS_STORE=0` keeps it stateless. |+ | [0272](0272-compaction-never-summarizes-unread-tool-results.md) | A compaction never summarizes tool results the model has not read: the cut keeps the newest model turn and its results verbatim, and the pre-send gate sends a batch that dominates the context and compacts after the model reads it. Summaries copy exact values. Interactions `user_input` steps are turn boundaries. Gemini compacts by default at 80% capped at 300k tokens. |+ | [0285](0285-acp-reauth-is-route-specific.md) | Terminal ChatGPT auth rejection carries fixed route-specific recovery metadata: ACP v1 `-32000` + `error.data`, v2 failed idle `_meta["graff/reauth"]`; `graff login chatgpt-new` repairs the new store, `codex login` the legacy one. Retry and non-auth error behavior stay unchanged. |+ | [0252](0252-hosted-compaction-with-a-codegraff-login.md) | With a Codegraff login and `GRAFF_CLEF_COMPACT=1` (default-off per 0261), `compact()` asks the gateway first: per-call keep/trim/drop decisions applied to graff's own history by call id, plus a spliced summary when pruning frees too little. Live-turn calls stay; a reply must check out and free a tenth of the context. Refused key or exhausted credits: local for the session; other failures: local for that compaction. |++ | [0286](0286-mcp-run-task-takes-caller-context.md) | `run_task` accepts bounded text context and preserves task metadata across the shared engine and ACP. |+ | [0287](0287-loopback-inference-has-request-local-deadlines.md) | Loopback inference receives request-local default deadlines; explicit limits and remote recovery budgets remain unchanged. |+ | [0288](0288-anthropic-native-login-is-source-aware.md) | Native subscription PKCE login is shared across CLI, REPL and ACP; subscription wire compatibility stays credential-source-aware. |+ | [0289](0289-mcp-results-preserve-typed-and-display-content.md) | Preserve typed MCP results independently of display content, show resource references without fetching them and answer pings during shared waits. |+ | [0290](0290-mcp-task-replies-outlive-child-deadlines.md) | HTTP task calls wait for validated child and required preprocessing budgets plus reply cleanup; other requests keep their deadlines. |+ | [0291](0291-release-builds-use-declared-task-caching.md) | Pin nanocompile and cache complete release build tasks with explicit inputs, tool resources, and a verified byte-identical restore before packaging. |+| [0292](0292-sol-subscription-context-is-500k.md) | GPT-6.1 Sol uses a 500k subscription window on Codex and ChatGPT sign-in; smaller catalog windows still win, other models retain their conservative caps, and API maxima do not widen subscription defaults. |+## When to write oneWrite an ADR when a decision is load-bearing and non-obvious: it was reached