3 Commits

Include renames

Author	SHA1	Message	Date
weichenandCursor	9f5751c205	Retry model streams only before the first delta ... Why: Buffering a whole attempt hid live output, overflow detection missed common provider errors, and a cut-off tool call could still run. Evidence: GOWORK=off go test -race -count=1 ./runtime/llm/ ./runtime/ passed. Impact: WithRetry forwards events immediately and retries only when nothing has been forwarded. Length or an unclean end drops unfinished tool calls. Loop usage keeps a billing sum and the last request separately. Refs: feature/llm-robustness Co-authored-by: Cursor <cursoragent@cursor.com>	2026-10-03 15:52:08 +00:00
weichenandCursor	694b08cdbe	Pair skipped tool calls and close the stdio and fetch gaps ... Why: a tool-budget stop left tool calls without results, host callbacks raced, a canceled MCP read stole the next response, and fetch re-resolved after the SSRF check. Evidence: GOWORK=off go vet ./... && go test -count=1 ./... && go test -race ./runtime/... ./adapters/native/... passed, including TestLoopBudgetToolCallCap, TestParallelHostCallbacksAreSerial, TestStdioSlowCancelThenEcho, TestPresetsAndClientForChatCompletions, TestFetchResolveChangesToLoopbackRejected, and TestFetchHostCheckRedirectStillRejectsPrivate. Impact: over-budget calls get an error result and no tool event; one Run serializes host callbacks; MCP dispatches by id; anthropic and google presets use OpenAI-compatible chat endpoints; fetch dials the address it just checked. deps/agent-intent is 3130190; error-code-system and logging-system are a3ee67b and 49b5d8b. Refs: N1, N2, N3, N4, N13, N14 Co-authored-by: Cursor <cursoragent@cursor.com>	2026-10-03 01:10:29 +00:00
weichen	dd2ac11b31	Extend exec.Request with capability fields and enforce budgets end to end ... Why: the frozen exec port could not express per-request model, tool allowlist, skills, budget, or identifiers, so squad roles and product profiles had no way to steer one execution; contract v0.1.0 semantics (budget/cancel) stayed unconsumed (parity-matrix #4/#10/#16). Evidence: go vet ./... clean; go test ./... all ok, including new loop budget caps (tool calls, prompt tokens, deadline), cancel propagation into a blocking tool, registry Restrict fail-closed policy tests, native adapter v2 tests (model override, allowlist, deadline-bound context, execution-id log header, skills prompt line), and settle classification marking budget_exceeded permanent. Impact: exec.Request gains optional Model/ToolAllowlist/Skills/Budget/ SessionScope/ExecutionID/Env (zero value = legacy behavior); runtime loop enforces a shared budget and emits budget_exceeded events; adapters/native consumes all new fields. Consumers on the old port keep compiling and behaving identically. Refs: docs/parity-matrix.md rows #4/#10/#16 (Batch2 scope); deps/ development-guidelines standards/agent-execution.md (shared budget across retry layers).	2026-10-01 05:26:19 +00:00