A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Rust
add initial attempt (#306)
az2b2da9a49c74
diff --git a/packages/coding-agent/src/core/prompts/index.ts b/packages/coding-agent/src/core/prompts/index.tsindex 58a23ab1f0..157a75346d 100644--- a/packages/coding-agent/src/core/prompts/index.ts+++ b/packages/coding-agent/src/core/prompts/index.ts@@ -1 +1 @@-export { buildRlmPrompt, type RlmPromptOptions } from "./rlm.js";+export { buildRlmPrompt, buildSubagentGuidance, type RlmPromptOptions } from "./rlm.js";diff --git a/packages/coding-agent/src/core/prompts/rlm.ts b/packages/coding-agent/src/core/prompts/rlm.tsindex 6f614f1135..ee04b12a93 100644--- a/packages/coding-agent/src/core/prompts/rlm.ts+++ b/packages/coding-agent/src/core/prompts/rlm.ts@@ -87,3 +87,48 @@ export function buildRlmPrompt(options: RlmPromptOptions): string {return parts.join("\n");}++/**+ * Supplemental sub-agent delegation guidance, appended AFTER the trained+ * `buildRlmPrompt` prefix (see system-prompt.ts). This is intentionally NOT part of+ * `buildRlmPrompt`'s `parts` array: the text that function emits is frozen as the v1+ * training prefix and must stay byte-identical. The trained recursion block already+ * covers the mechanics (`await rlm(...)`, `asyncio.gather`, `asyncio.create_task`);+ * this block adds the *when* and *why* — the decision guidance the trained prefix+ * lacks — in the same When -> Why -> (menu) order Claude Code's Agent tool uses. The+ * subagent-spec "menu" itself renders just after this, inside the harness-state block.+ */+export function buildSubagentGuidance(): string {+ return [+ "# Delegating to sub-agents",+ "",+ "You already have `rlm` in scope. This is about *when* to spawn one — which matters as much as how.",+ "",+ "Reach for `await rlm(...)` when:",+ "- you have independent sub-tasks that can run in parallel — fan them out with `await asyncio.gather(rlm('task1'), rlm('task2'))` rather than working them one after another;",+ "- a sub-task would mean reading across many files, outputs, or sources you don't need to keep — delegate it and you keep the answer, not the raw material;",+ "- the sub-task matches one of your saved subagent specs (listed in the harness state below) — turn the spec into a concise task prompt and call `rlm` with it.",+ "",+ "Do it inline instead when the step is a single known lookup, edit, or command — there, a sub-agent just adds latency. Once you've delegated a sub-task, await its handle and use the result instead of redoing the work yourself.",+ "",+ "For example:",+ "```python",+ "# Independent sub-tasks in parallel — each returns just its conclusion, not the files it read",+ "auth, api = await asyncio.gather(",+ " rlm('Summarize how authentication works in this repo: entrypoints, token flow, and key files.'),",+ " rlm('Summarize the HTTP API layer: routes, middleware, and error handling.'),",+ ")",+ "",+ "# Context isolation — a sub-agent digests a large file and hands back only the answer",+ "res = await rlm('Read build.log, find the failing step and its root cause, and report it in 3 lines.')",+ "print(res.answer)",+ "",+ "# Background — kick off a slow sub-task, keep working, collect it later",+ "task = asyncio.create_task(rlm('Run the full test suite and report any failures with root causes.'))",+ "# ... continue with other work while it runs ...",+ "failures = (await task).answer",+ "```",+ "",+ "These are illustrations, not a fixed menu: delegate any self-contained sub-task that fits the cases above.",+ ].join("\n");+}diff --git a/packages/coding-agent/src/core/refinement/refinement.ts b/packages/coding-agent/src/core/refinement/refinement.tsindex 3791eb5131..f4b1ad481d 100644--- a/packages/coding-agent/src/core/refinement/refinement.ts+++ b/packages/coding-agent/src/core/refinement/refinement.ts@@ -415,7 +415,16 @@ export function formatHarnessStateForPrompt([a.path, a.title, a.id].join("\0").localeCompare([b.path, b.title, b.id].join("\0")),);totalEntries += entries.length;- lines.push(`${kind}: ${entries.length}`);+ // Render subagent specs as a task-shaped roster the model can match against — the+ // analogue of Claude Code's agent-type menu — rather than a bare count. The+ // invocation hint makes clear each spec is reached through the single `rlm` entrypoint.+ if (kind === "subagent" && entries.length > 0) {+ lines.push(+ `${kind}: ${entries.length} (invoke a spec by turning it into a concise task prompt and calling \`await rlm('<task>')\`)`,+ );+ } else {+ lines.push(`${kind}: ${entries.length}`);+ }for (const entry of entries.slice(0, maxEntriesPerKind)) {const argumentsText =entry.kind === "skill" && Object.keys(entry.arguments).length > 0diff --git a/packages/coding-agent/src/core/system-prompt.ts b/packages/coding-agent/src/core/system-prompt.tsindex ad3e0a0033..f3d573015c 100644--- a/packages/coding-agent/src/core/system-prompt.ts+++ b/packages/coding-agent/src/core/system-prompt.ts@@ -2,7 +2,7 @@* System prompt construction and project context loading*/-import { buildRlmPrompt } from "./prompts/index.js";+import { buildRlmPrompt, buildSubagentGuidance } from "./prompts/index.js";import { formatHarnessStateForPrompt, type HarnessState } from "./refinement/index.js";import { formatSkillsForPrompt, getPythonSkillRuntimeInfo, type Skill } from "./skills.js";@@ -103,6 +103,13 @@ export function buildSystemPrompt(options: BuildSystemPromptOptions): string {allowRecursion,});+ // Appended AFTER the trained buildRlmPrompt prefix, and before the harness-state+ // menu, so the model reads when/why to delegate and then sees the concrete subagent+ // specs it can match against — the same ordering as Claude Code's Agent tool.+ if (allowRecursion ?? true) {+ prompt += `\n\n${buildSubagentGuidance()}`;+ }+if (harnessState) {prompt += `\n\n${formatHarnessStateForPrompt(harnessState)}`;}