feat(rsi): add controlled proof demonstration protocol

docker/OpenShell-RSI.Dockerfile

@@ -12,6 +12,12 @@ RUN apt-get update \
     && find /opt/headlesscode/src -type d -name __tests__ -prune -exec rm -rf {} + \
     && find /opt/headlesscode/src -type f \( -name '*.test.ts' -o -name '*.spec.ts' \) -delete \
     && rm -rf /opt/headlesscode/scripts/eval-suite \
+    && rm -rf /opt/headlesscode/scripts/rsi-benchmark \
+    && rm -rf /opt/headlesscode/fixtures/rsi-benchmark \
     && test ! -e /opt/headlesscode/src/rsi
 
+RUN test ! -e /opt/headlesscode/scripts/rsi-benchmark/task-spec.mjs \
+    && test ! -e /opt/headlesscode/fixtures/rsi-benchmark \
+    && test ! -e /opt/headlesscode/.git
+
 USER sandbox

docker/OpenShell.Dockerfile

@@ -19,6 +19,10 @@ COPY src ./src
 COPY shared ./shared
 COPY scripts/spawn-parallel-worktrees.sh scripts/run-worker.sh scripts/headlesscode-answer.sh ./scripts/
 RUN chmod -R a+rX /opt/headlesscode/src /opt/headlesscode/shared /opt/headlesscode/scripts
+RUN test ! -e /opt/headlesscode/scripts/rsi-benchmark/task-spec.mjs \
+    && test ! -e /opt/headlesscode/scripts/rsi-benchmark/manual-tests \
+    && test ! -e /opt/headlesscode/fixtures/rsi-benchmark \
+    && test ! -e /opt/headlesscode/.git
 RUN printf '%s\n' "$HEADLESSCODE_HARNESS_COMMIT" > /opt/headlesscode/.headlesscode-harness-commit
 LABEL org.capsize.headlesscode.harness-commit="$HEADLESSCODE_HARNESS_COMMIT"
 RUN chmod +x scripts/spawn-parallel-worktrees.sh scripts/run-worker.sh scripts/headlesscode-answer.sh

docs/recursive-self-improvement.md

@@ -246,7 +246,10 @@ OpenRouter is available for RSI fleet mutations and the development benchmark
 when the worker role is configured with
 `HEADLESSCODE_RSI_ROLE_WORKER_PROVIDER=openrouter` and
 `HEADLESSCODE_RSI_ROLE_WORKER_MODEL=deepseek/deepseek-v4-flash-0731`. The model
-is pinned to DeepSeek's OpenRouter endpoint with fallback routing disabled.
+is routed through OpenRouter's available DeepInfra fp8 endpoint
+(`deepinfra/fp8`) with fallback routing disabled. The broker checks endpoint
+metadata and requires the returned selected-provider metadata to identify
+DeepInfra before qualifying usage.
 Include `REMOTE_API` in `HEADLESSCODE_RSI_WORKER_RESOURCE_CLASSES` for workers
 that claim brokered calls; Ollama workers continue to claim `LOCAL_GPU`.
 Workers need the host-side `HEADLESSCODE_OPENROUTER_API_KEY` and
@@ -311,15 +314,66 @@ benchmark inference use distinct broker campaign IDs derived from the shared
 proof campaign ID, so their allocation caps remain separate while their
 reservations count against the one PostgreSQL proof-campaign root ceiling.
 
-The current controller completes only the development phase. It records the
-arm as `evaluated` and releases its lease without finishing the proof campaign.
-A later confirmation phase can reacquire the same arm and use only the
-predeclared cells. Every selected final candidate and each root-control
-comparison must complete; each unused final candidate slot must be recorded
-with the zero-spend `not-selected` disposition. Only then may `finishArm`
-mark that arm terminal. Confirmation execution is not yet wired into the
-controller; until that work is added, these campaigns remain development-only
-and are not complete proof results.
+The demonstration launcher separates engineering from holdout planning. The
+engineering run freezes development-only cells and runs both arms for two
+generations. It must record an accepted generation-zero self-hosted candidate
+and an accepted generation-one child whose worker execution used that exact
+parent commit. The fixed-control arm must also reach a terminal generation-one
+decision. Only after these checks pass may the operator create the final plan;
+that plan binds the engineering evidence and freezes the three confirmation
+campaigns. Engineering-only manifests contain no confirmation task IDs or
+confirmation schedule cells.
+
+Use the staged commands below from a clean checkout with the exact fixed and
+self-hosted harness image identities configured. Estimate and plan fetch only
+the pinned endpoint's read-only price metadata. Execution requires PostgreSQL,
+OpenShell, the broker, the model key on the supervisor, finite per-role
+allocations, and a separately reviewed operator cap. No production inference
+has been run as part of this implementation.
+
+```sh
+# Review the engineering-only schedule and live price before choosing a cap.
+npm run rsi:proof-demonstration -- engineering --repo "$PWD" --seed "$ENGINEERING_SEED"
+
+# Run the two-generation engineering pair. The cap must cover this root's
+# frozen reservation and fit the configured mutation + benchmark allocations.
+npm run rsi:proof-demonstration -- engineering --repo "$PWD" --seed "$ENGINEERING_SEED" \
+  --operator-cap-usd "$ENGINEERING_CAP_USD" --execute
+
+# Freeze three new campaign seeds only after the engineering evidence passes.
+npm run rsi:proof-demonstration -- plan --repo "$PWD" \
+  --engineering-evidence .headlesscode/rsi-proof/engineering-evidence.json \
+  --operator-cap-usd "$CAMPAIGN_CAP_USD" --seed "$ENGINEERING_SEED" \
+  --campaign-seed "$CAMPAIGN_SEED_A" --campaign-seed "$CAMPAIGN_SEED_B" \
+  --campaign-seed "$CAMPAIGN_SEED_C" --out .headlesscode/rsi-proof/frozen-plan.json
+
+# Verify the frozen identities and cap, execute all three paired development
+# and confirmation campaigns, then write JSON and Markdown analysis reports.
+npm run rsi:proof-demonstration -- verify --repo "$PWD" --plan .headlesscode/rsi-proof/frozen-plan.json
+npm run rsi:proof-demonstration -- execute --repo "$PWD" --plan .headlesscode/rsi-proof/frozen-plan.json \
+  --operator-cap-usd "$CAMPAIGN_CAP_USD" --execute
+npm run rsi:proof-demonstration -- analyze --repo "$PWD" --plan .headlesscode/rsi-proof/frozen-plan.json \
+  --archive .headlesscode/rsi
+```
+
+The engineering command binds each campaign arm to a deterministic
+campaign-and-arm run ID. A restart reuses a finished arm's verified archive
+record or resumes the same active identity; an archived incomplete arm is
+rejected. Final campaign execution likewise reuses terminal arm records and
+will not dispatch a second attempt for an already completed cell. A crash
+after broker dispatch but before a verified result artifact remains uncertain
+and fails closed under the PostgreSQL ledger; it is not retried automatically.
+Each final campaign's cap is checked against its frozen root reservation, and
+the command's supplied cap must exactly match the value in the plan. The
+engineering cap is separate from the final plan's cap for the three campaigns.
+
+Analysis verifies the three paired terminal campaign records, frozen
+manifest/config/model/runtime identities, each confirmation schedule cell,
+the selected-parent lineage, broker receipts, artifact digests, and PostgreSQL
+root accounting. Missing, unqualified, or altered evidence yields
+`inconclusive`; a completed set that misses the frozen improvement gates yields
+`not-demonstrated`. A demonstration verdict is not a release or promotion
+action.
 
 To exercise the worker image and guest network boundary without a production
 provider credential or paid request, build the exact current harness image

package.json

@@ -43,6 +43,7 @@
 		"cli": "tsx src/cli.ts",
 		"monitor:pilot": "tsx scripts/monitor-pilot/run.ts",
 		"rsi:promote-curriculum": "tsx src/rsi/promote-curriculum.ts",
+		"rsi:proof-demonstration": "tsx scripts/rsi-proof-demonstration.ts",
 		"test": "node scripts/run-tests.mjs",
 		"prepublishOnly": "npm ci && npm test"
 	},

scripts/rsi-benchmark/mock-openrouter-guest-smoke.ts

@@ -5,7 +5,7 @@ import * as os from "node:os"
 import * as path from "node:path"
 import { createServer } from "node:http"
 import { OpenShellBenchmarkAgent, initializeTaskRepository } from "../../src/rsi/benchmark/openshell-agent.js"
-import { RSI_OPENROUTER_MODEL, startOpenRouterBroker } from "../../src/rsi/inference-broker.js"
+import { RSI_OPENROUTER_ENDPOINT_PROVIDER, RSI_OPENROUTER_ENDPOINT_TAG, RSI_OPENROUTER_MODEL, startOpenRouterBroker } from "../../src/rsi/inference-broker.js"
 import { OpenShellSessionProvider } from "../../src/cloud/openshell-provider.js"
 
 const repoRoot = path.resolve(process.argv[2] ?? process.cwd())
@@ -60,7 +60,7 @@ try {
 		upstreamFetch: async (input, init) => {
 			const url = String(input)
 			if (url.endsWith(`/models/${RSI_OPENROUTER_MODEL}/endpoints`)) {
-				return new Response(JSON.stringify({ data: { endpoints: [{ provider_slug: "deepseek", pricing: { prompt: "0.000001", completion: "0.000001" } }] } }), { status: 200, headers: { "content-type": "application/json" } })
+				return new Response(JSON.stringify({ data: { endpoints: [{ provider_name: "DeepInfra", tag: RSI_OPENROUTER_ENDPOINT_TAG, quantization: "fp8", status: 0, supported_parameters: ["tools", "tool_choice", "temperature", "seed", "max_tokens"], supports_tool_choice: { auto: true, required: true, function: true }, pricing: { prompt: "0.000001", completion: "0.000001" } }] } }), { status: 200, headers: { "content-type": "application/json" } })
 			}
 			assert.equal(url, "https://openrouter.ai/api/v1/chat/completions")
 			assert.equal(new Headers(init?.headers).get("authorization"), `Bearer ${key}`)
@@ -76,6 +76,7 @@ try {
 			assert.ok(body.messages?.length)
 			return new Response(JSON.stringify({
 				id: `mock-response-${upstreamCalls}`, model: RSI_OPENROUTER_MODEL,
+				openrouter_metadata: { endpoints: { available: [{ provider: RSI_OPENROUTER_ENDPOINT_PROVIDER, selected: true }] } },
 				choices: [{ message, finish_reason: "tool_calls" }],
 				usage: { prompt_tokens: 400, completion_tokens: 24, cost: 0.000424 },
 			}), { status: 200, headers: { "content-type": "application/json" } })

scripts/rsi-benchmark/self-hosted-harness-smoke.ts

@@ -4,7 +4,7 @@ import { createHash } from "node:crypto"
 import * as fs from "node:fs/promises"
 import * as os from "node:os"
 import * as path from "node:path"
-import { FileOpenRouterInferenceLedger, RSI_OPENROUTER_MODEL, startOpenRouterBroker, type OpenRouterBrokerLimits } from "../../src/rsi/inference-broker.js"
+import { FileOpenRouterInferenceLedger, RSI_OPENROUTER_ENDPOINT_PROVIDER, RSI_OPENROUTER_ENDPOINT_TAG, RSI_OPENROUTER_MODEL, startOpenRouterBroker, type OpenRouterBrokerLimits } from "../../src/rsi/inference-broker.js"
 import { createMutationSnapshotBundle, runOpenShellMutation } from "../../src/rsi/openshell.js"
 import { workerHarnessSentinelDiff } from "../../src/rsi/worker-harness-sentinel.js"
 import type { CandidateRecord, RsiConfig, WorkerHarnessMode, WorkerHarnessRuntimeIdentity } from "../../src/rsi/types.js"
@@ -54,7 +54,7 @@ function mockUpstream(stage: "seed" | "bridge" | "sentinel", observed: { sentine
 	return async (input: RequestInfo | URL, init?: RequestInit): Promise<Response> => {
 		const url = String(input)
 		if (url.endsWith(`/models/${RSI_OPENROUTER_MODEL}/endpoints`)) {
-			return new Response(JSON.stringify({ data: { endpoints: [{ provider_slug: "deepseek", pricing: { prompt: "0.000001", completion: "0.000001" } }] } }), { status: 200, headers: { "content-type": "application/json" } })
+			return new Response(JSON.stringify({ data: { endpoints: [{ provider_name: "DeepInfra", tag: RSI_OPENROUTER_ENDPOINT_TAG, quantization: "fp8", status: 0, supported_parameters: ["tools", "tool_choice", "temperature", "seed", "max_tokens"], supports_tool_choice: { auto: true, required: true, function: true }, pricing: { prompt: "0.000001", completion: "0.000001" } }] } }), { status: 200, headers: { "content-type": "application/json" } })
 		}
 		assert.equal(url, "https://openrouter.ai/api/v1/chat/completions")
 		assert.equal(new Headers(init?.headers).get("authorization"), "Bearer mock-only-not-a-provider-key")
@@ -81,6 +81,7 @@ function mockUpstream(stage: "seed" | "bridge" | "sentinel", observed: { sentine
 		return new Response(JSON.stringify({
 			id: `mock-self-hosted-${stage}-${calls}`,
 			model: RSI_OPENROUTER_MODEL,
+			openrouter_metadata: { endpoints: { available: [{ provider: RSI_OPENROUTER_ENDPOINT_PROVIDER, selected: true }] } },
 			choices: [{ message, finish_reason: "tool_calls" }],
 			usage: { prompt_tokens: 10_000, completion_tokens: 200, cost: 0.0102 },
 		}), { status: 200, headers: { "content-type": "application/json" } })