@martinloop/mcp 0.5.5 → 0.5.6

package/dist/resources.js

@@ -760,173 +760,173 @@ function inferAgentNextStep(loop, verification) {
 }
 function buildMcpUsageGuide(runsRoot) {
     const metadata = buildMartinDiscoveryMetadata(MARTIN_MCP_PACKAGE_VERSION);
-    return `# Martin Loop MCP Usage
-
-Discovery revision: \`${metadata.discoveryRevision}\`
-Server version: \`${metadata.serverVersion}\`
-Runs root: \`${runsRoot}\`
-
-Martin Loop exposes governed coding workflows over MCP. Use the server health and run-store views to decide when to preflight, execute, inspect, or escalate.
-
-## Recommended Flow
-
-1. Read \`${MARTIN_STATIC_RESOURCE_URIS.serverHealth}\` or call \`martin_doctor\` to confirm the environment and run-store visibility.
-2. Use the \`martin_governed_coding_kickoff\` prompt to frame a governed coding request.
-3. Call \`martin_preflight\` before \`martin_run\` when the task or safety envelope is non-trivial.
-4. After execution, inspect \`${MARTIN_STATIC_RESOURCE_URIS.recentRuns}\`, \`martin://runs/{loopId}\`, and \`martin://runs/{loopId}/verification\`.
-5. For low-context agents, read \`${MARTIN_STATIC_RESOURCE_URIS.agentNextStep}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestSummary}\`, or \`${MARTIN_STATIC_RESOURCE_URIS.latestProofCard}\` before asking for full JSON.
-6. Read \`${MARTIN_STATIC_RESOURCE_URIS.triage}\` or call \`martin_triage_runs\` to prioritize which run needs attention first.
-7. Use \`martin_debug_failed_run\` when a loop exits failed, budget-bound, or escalated.
-
-## Current Martin MCP Surface
-
-- Tools: \`martin_run\`, \`martin_inspect\`, \`martin_status\`, \`martin_doctor\`, \`martin_preflight\`, \`martin_list_runs\`, \`martin_triage_runs\`, \`martin_get_run\`, \`martin_get_attempt\`, \`martin_get_verification_results\`, \`martin_run_dossier\`
-- Static resources: \`${MARTIN_STATIC_RESOURCE_URIS.serverHealth}\`, \`${MARTIN_STATIC_RESOURCE_URIS.recentRuns}\`, \`${MARTIN_STATIC_RESOURCE_URIS.triage}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestSummary}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestProofCard}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestBudgetStatus}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestVerifierEvidence}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestRollbackEvidence}\`, \`${MARTIN_STATIC_RESOURCE_URIS.agentNextStep}\`, \`${MARTIN_STATIC_RESOURCE_URIS.governanceStatus}\`, \`${MARTIN_STATIC_RESOURCE_URIS.modeStatus}\`, \`${MARTIN_STATIC_RESOURCE_URIS.memorySummary}\`, \`${MARTIN_STATIC_RESOURCE_URIS.mcpUsageGuide}\`, \`${MARTIN_STATIC_RESOURCE_URIS.agentStartGuide}\`, \`${MARTIN_STATIC_RESOURCE_URIS.publishReadinessGuide}\`
-- Resource templates: \`martin://runs/{loopId}\`, \`martin://runs/{loopId}/attempts/{attemptIndex}\`, \`martin://runs/{loopId}/verification\`
-- Prompts: \`martin_start\`, \`martin_preflight\`, \`martin_triage\`, \`martin_resume\`, \`martin_prove\`, \`martin_release_check\`, \`martin_governed_coding_kickoff\`, \`martin_debug_failed_run\`, \`martin_publish_readiness_review\`, \`martin_triage_run_store\`
-
-## Notes
-
-- Discovery helpers read the existing Martin run-store; they do not create new schema.
-- Verification history is derived from persisted \`verification.completed\` evidence in loop records and ledgers.
-- Attempt inspection stays aligned with the same loop selectors used by \`martin_status\` and \`martin_inspect\`.
+    return `# Martin Loop MCP Usage
+
+Discovery revision: \`${metadata.discoveryRevision}\`
+Server version: \`${metadata.serverVersion}\`
+Runs root: \`${runsRoot}\`
+
+Martin Loop exposes governed coding workflows over MCP. Use the server health and run-store views to decide when to preflight, execute, inspect, or escalate.
+
+## Recommended Flow
+
+1. Read \`${MARTIN_STATIC_RESOURCE_URIS.serverHealth}\` or call \`martin_doctor\` to confirm the environment and run-store visibility.
+2. Use the \`martin_governed_coding_kickoff\` prompt to frame a governed coding request.
+3. Call \`martin_preflight\` before \`martin_run\` when the task or safety envelope is non-trivial.
+4. After execution, inspect \`${MARTIN_STATIC_RESOURCE_URIS.recentRuns}\`, \`martin://runs/{loopId}\`, and \`martin://runs/{loopId}/verification\`.
+5. For low-context agents, read \`${MARTIN_STATIC_RESOURCE_URIS.agentNextStep}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestSummary}\`, or \`${MARTIN_STATIC_RESOURCE_URIS.latestProofCard}\` before asking for full JSON.
+6. Read \`${MARTIN_STATIC_RESOURCE_URIS.triage}\` or call \`martin_triage_runs\` to prioritize which run needs attention first.
+7. Use \`martin_debug_failed_run\` when a loop exits failed, budget-bound, or escalated.
+
+## Current Martin MCP Surface
+
+- Tools: \`martin_run\`, \`martin_inspect\`, \`martin_status\`, \`martin_doctor\`, \`martin_preflight\`, \`martin_list_runs\`, \`martin_triage_runs\`, \`martin_get_run\`, \`martin_get_attempt\`, \`martin_get_verification_results\`, \`martin_run_dossier\`
+- Static resources: \`${MARTIN_STATIC_RESOURCE_URIS.serverHealth}\`, \`${MARTIN_STATIC_RESOURCE_URIS.recentRuns}\`, \`${MARTIN_STATIC_RESOURCE_URIS.triage}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestSummary}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestProofCard}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestBudgetStatus}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestVerifierEvidence}\`, \`${MARTIN_STATIC_RESOURCE_URIS.latestRollbackEvidence}\`, \`${MARTIN_STATIC_RESOURCE_URIS.agentNextStep}\`, \`${MARTIN_STATIC_RESOURCE_URIS.governanceStatus}\`, \`${MARTIN_STATIC_RESOURCE_URIS.modeStatus}\`, \`${MARTIN_STATIC_RESOURCE_URIS.memorySummary}\`, \`${MARTIN_STATIC_RESOURCE_URIS.mcpUsageGuide}\`, \`${MARTIN_STATIC_RESOURCE_URIS.agentStartGuide}\`, \`${MARTIN_STATIC_RESOURCE_URIS.publishReadinessGuide}\`
+- Resource templates: \`martin://runs/{loopId}\`, \`martin://runs/{loopId}/attempts/{attemptIndex}\`, \`martin://runs/{loopId}/verification\`
+- Prompts: \`martin_start\`, \`martin_preflight\`, \`martin_triage\`, \`martin_resume\`, \`martin_prove\`, \`martin_release_check\`, \`martin_governed_coding_kickoff\`, \`martin_debug_failed_run\`, \`martin_publish_readiness_review\`, \`martin_triage_run_store\`
+
+## Notes
+
+- Discovery helpers read the existing Martin run-store; they do not create new schema.
+- Verification history is derived from persisted \`verification.completed\` evidence in loop records and ledgers.
+- Attempt inspection stays aligned with the same loop selectors used by \`martin_status\` and \`martin_inspect\`.
 `;
 }
 function buildAgentStartGuide(runsRoot) {
     const metadata = buildMartinDiscoveryMetadata(MARTIN_MCP_PACKAGE_VERSION);
-    return `# Agent Start Here
-
-Discovery revision: \`${metadata.discoveryRevision}\`
-Server version: \`${metadata.serverVersion}\`
-Runs root: \`${runsRoot}\`
-
-Use Martin Loop as the local governor before you spend agent tokens or retry a failed coding loop.
-
-## Cheap Default Flow
-
-1. Read \`${MARTIN_STATIC_RESOURCE_URIS.agentNextStep}\` first. It is the smallest "what should I do now?" payload.
-2. If no runs exist, call \`martin_doctor\`, then \`martin_preflight\`.
-3. If a run exists, read \`${MARTIN_STATIC_RESOURCE_URIS.latestSummary}\` before reading full run JSON.
-4. If the verifier failed, use prompt \`martin_debug_failed_run\` or \`martin_triage\`.
-5. If you need a shareable receipt, read \`${MARTIN_STATIC_RESOURCE_URIS.latestProofCard}\`.
-
-## Install Profiles
-
-- \`minimal\` (default): doctor, preflight, list, triage, dossier. Good for low tool bloat.
-- \`diagnostic\`: read-only inspection tools for debugging without execution.
-- \`full-local\`: all local tools, including \`martin_run\`.
-- \`github-review\`: review-oriented local profile for PR drafting and reviewer evidence.
-- \`starter\` and \`full\`: compatibility aliases.
-
-## Copy-Paste Agent Rule
-
-Before running or retrying an autonomous coding task, call Martin. Prefer compact resources first, then full dossiers only when the compact receipt says more evidence is needed. Never claim success unless Martin shows verifier-backed completion or a clear blocked reason.
+    return `# Agent Start Here
+
+Discovery revision: \`${metadata.discoveryRevision}\`
+Server version: \`${metadata.serverVersion}\`
+Runs root: \`${runsRoot}\`
+
+Use Martin Loop as the local governor before you spend agent tokens or retry a failed coding loop.
+
+## Cheap Default Flow
+
+1. Read \`${MARTIN_STATIC_RESOURCE_URIS.agentNextStep}\` first. It is the smallest "what should I do now?" payload.
+2. If no runs exist, call \`martin_doctor\`, then \`martin_preflight\`.
+3. If a run exists, read \`${MARTIN_STATIC_RESOURCE_URIS.latestSummary}\` before reading full run JSON.
+4. If the verifier failed, use prompt \`martin_debug_failed_run\` or \`martin_triage\`.
+5. If you need a shareable receipt, read \`${MARTIN_STATIC_RESOURCE_URIS.latestProofCard}\`.
+
+## Install Profiles
+
+- \`minimal\` (default): doctor, preflight, list, triage, dossier. Good for low tool bloat.
+- \`diagnostic\`: read-only inspection tools for debugging without execution.
+- \`full-local\`: all local tools, including \`martin_run\`.
+- \`github-review\`: review-oriented local profile for PR drafting and reviewer evidence.
+- \`starter\` and \`full\`: compatibility aliases.
+
+## Copy-Paste Agent Rule
+
+Before running or retrying an autonomous coding task, call Martin. Prefer compact resources first, then full dossiers only when the compact receipt says more evidence is needed. Never claim success unless Martin shows verifier-backed completion or a clear blocked reason.
 `;
 }
 function buildCommandMapGuide(runsRoot) {
     const metadata = buildMartinDiscoveryMetadata(MARTIN_MCP_PACKAGE_VERSION);
-    return `# Martin Command Map
-
-Discovery revision: \`${metadata.discoveryRevision}\`
-Server version: \`${metadata.serverVersion}\`
-Runs root: \`${runsRoot}\`
-
-Use this guide when an IDE or agent needs to know which Martin surface to call next.
-
-## Default Governed Sequence
-
-1. \`martin_doctor\` — confirm environment and visibility.
-2. \`martin_plan\` — propose the bounded approach without spending a run.
-3. \`martin_preflight\` — turn the plan into an explicit contract.
-4. \`martin_run\` — execute only after the contract is safe.
-5. \`martin_dossier\` — inspect what happened and what Martin prevented.
-6. \`martin_eval\` — convert the result into review posture when needed.
-
-## When To Use Which Surface
-
-- Need the smallest next action: \`${MARTIN_STATIC_RESOURCE_URIS.agentNextStep}\`
-- Need a quick receipt: \`${MARTIN_STATIC_RESOURCE_URIS.latestSummary}\`
-- Need a shareable proof object: \`${MARTIN_STATIC_RESOURCE_URIS.latestProofCard}\`
-- Need a full run review: \`martin_dossier\`
-- Need to decide whether to retry: \`martin_triage_runs\`
-- Need IDE setup guidance: \`${MARTIN_STATIC_RESOURCE_URIS.ideOnboardingGuide}\`
+    return `# Martin Command Map
+
+Discovery revision: \`${metadata.discoveryRevision}\`
+Server version: \`${metadata.serverVersion}\`
+Runs root: \`${runsRoot}\`
+
+Use this guide when an IDE or agent needs to know which Martin surface to call next.
+
+## Default Governed Sequence
+
+1. \`martin_doctor\` — confirm environment and visibility.
+2. \`martin_plan\` — propose the bounded approach without spending a run.
+3. \`martin_preflight\` — turn the plan into an explicit contract.
+4. \`martin_run\` — execute only after the contract is safe.
+5. \`martin_dossier\` — inspect what happened and what Martin prevented.
+6. \`martin_eval\` — convert the result into review posture when needed.
+
+## When To Use Which Surface
+
+- Need the smallest next action: \`${MARTIN_STATIC_RESOURCE_URIS.agentNextStep}\`
+- Need a quick receipt: \`${MARTIN_STATIC_RESOURCE_URIS.latestSummary}\`
+- Need a shareable proof object: \`${MARTIN_STATIC_RESOURCE_URIS.latestProofCard}\`
+- Need a full run review: \`martin_dossier\`
+- Need to decide whether to retry: \`martin_triage_runs\`
+- Need IDE setup guidance: \`${MARTIN_STATIC_RESOURCE_URIS.ideOnboardingGuide}\`
 `;
 }
 function buildIdeOnboardingGuide(runsRoot) {
     const metadata = buildMartinDiscoveryMetadata(MARTIN_MCP_PACKAGE_VERSION);
-    return `# Martin IDE Onboarding
-
-Discovery revision: \`${metadata.discoveryRevision}\`
-Server version: \`${metadata.serverVersion}\`
-Runs root: \`${runsRoot}\`
-
-Use this guide after the MCP server is installed so the host naturally uses MartinLoop during real work.
-
-## IDE Default Flow
-
-1. Read \`${MARTIN_STATIC_RESOURCE_URIS.agentStartGuide}\`
-2. Read \`${MARTIN_STATIC_RESOURCE_URIS.operatingRulesGuide}\`
-3. Use prompt \`martin_start\` or \`martin_governed_coding_kickoff\`
-4. Call \`martin_doctor\`
-5. Call \`martin_plan\`
-6. Call \`martin_preflight\`
-7. Only then call \`martin_run\`
-
-## Goal
-
-MartinLoop should become the normal path for coding work in the host, not a manual extra step the human has to remember.
+    return `# Martin IDE Onboarding
+
+Discovery revision: \`${metadata.discoveryRevision}\`
+Server version: \`${metadata.serverVersion}\`
+Runs root: \`${runsRoot}\`
+
+Use this guide after the MCP server is installed so the host naturally uses MartinLoop during real work.
+
+## IDE Default Flow
+
+1. Read \`${MARTIN_STATIC_RESOURCE_URIS.agentStartGuide}\`
+2. Read \`${MARTIN_STATIC_RESOURCE_URIS.operatingRulesGuide}\`
+3. Use prompt \`martin_start\` or \`martin_governed_coding_kickoff\`
+4. Call \`martin_doctor\`
+5. Call \`martin_plan\`
+6. Call \`martin_preflight\`
+7. Only then call \`martin_run\`
+
+## Goal
+
+MartinLoop should become the normal path for coding work in the host, not a manual extra step the human has to remember.
 `;
 }
 function buildOperatingRulesGuide(runsRoot) {
     const metadata = buildMartinDiscoveryMetadata(MARTIN_MCP_PACKAGE_VERSION);
-    return `# Martin Operating Rules
-
-Discovery revision: \`${metadata.discoveryRevision}\`
-Server version: \`${metadata.serverVersion}\`
-Runs root: \`${runsRoot}\`
-
-Use these rules inside the IDE or MCP host as the default MartinLoop operating posture.
-
-## Required Sequence Before Real Work
-
-1. \`martin_doctor\`
-2. \`martin_plan\`
-3. \`martin_preflight\`
-4. \`martin_run\`
-5. \`martin_dossier\`
-
-## Enforcement Rule
-
-Do not execute real coding work through MartinLoop until doctor and preflight have both been used for the current task.
-
-## Completion Rule
-
-Do not claim success until MartinLoop shows verifier-backed completion or an explicit blocked reason backed by evidence.
+    return `# Martin Operating Rules
+
+Discovery revision: \`${metadata.discoveryRevision}\`
+Server version: \`${metadata.serverVersion}\`
+Runs root: \`${runsRoot}\`
+
+Use these rules inside the IDE or MCP host as the default MartinLoop operating posture.
+
+## Required Sequence Before Real Work
+
+1. \`martin_doctor\`
+2. \`martin_plan\`
+3. \`martin_preflight\`
+4. \`martin_run\`
+5. \`martin_dossier\`
+
+## Enforcement Rule
+
+Do not execute real coding work through MartinLoop until doctor and preflight have both been used for the current task.
+
+## Completion Rule
+
+Do not claim success until MartinLoop shows verifier-backed completion or an explicit blocked reason backed by evidence.
 `;
 }
 function buildPublishReadinessGuide(runsRoot) {
     const metadata = buildMartinDiscoveryMetadata(MARTIN_MCP_PACKAGE_VERSION);
-    return `# Martin MCP Publish Readiness
-
-Discovery revision: \`${metadata.discoveryRevision}\`
-Server version: \`${metadata.serverVersion}\`
-Runs root: \`${runsRoot}\`
-
-Use this guide when reviewing whether the public MCP package is ready to publish, promote, or hand off for registry submission.
-
-## Review Areas
-
-1. Environment health: confirm \`${MARTIN_STATIC_RESOURCE_URIS.serverHealth}\` shows a sane working directory, runs root, and engine availability for the target mode.
-2. Discovery surface: verify tools, prompts, static resources, and resource templates are all discoverable and named consistently.
-3. Run evidence: inspect \`${MARTIN_STATIC_RESOURCE_URIS.recentRuns}\` and, when relevant, \`martin://runs/{loopId}/verification\` to confirm verification outcomes are explainable from persisted data.
-4. Packaging lane: run the MCP package test, build, and smoke-pack commands before calling the package publish-ready.
-5. Findings-first reporting: call out missing schema, integration gaps, triage-critical runs, and verification blockers before summarizing strengths.
-
-## Evidence Expectations
-
-- Prefer concrete run IDs, attempt indices, and verification summaries over vague statements.
-- Distinguish local package validation from live registry readiness.
-- If a discovery helper exists but is not yet wired into the server, report that as an integration gap instead of treating the capability as fully shipped.
+    return `# Martin MCP Publish Readiness
+
+Discovery revision: \`${metadata.discoveryRevision}\`
+Server version: \`${metadata.serverVersion}\`
+Runs root: \`${runsRoot}\`
+
+Use this guide when reviewing whether the public MCP package is ready to publish, promote, or hand off for registry submission.
+
+## Review Areas
+
+1. Environment health: confirm \`${MARTIN_STATIC_RESOURCE_URIS.serverHealth}\` shows a sane working directory, runs root, and engine availability for the target mode.
+2. Discovery surface: verify tools, prompts, static resources, and resource templates are all discoverable and named consistently.
+3. Run evidence: inspect \`${MARTIN_STATIC_RESOURCE_URIS.recentRuns}\` and, when relevant, \`martin://runs/{loopId}/verification\` to confirm verification outcomes are explainable from persisted data.
+4. Packaging lane: run the MCP package test, build, and smoke-pack commands before calling the package publish-ready.
+5. Findings-first reporting: call out missing schema, integration gaps, triage-critical runs, and verification blockers before summarizing strengths.
+
+## Evidence Expectations
+
+- Prefer concrete run IDs, attempt indices, and verification summaries over vague statements.
+- Distinguish local package validation from live registry readiness.
+- If a discovery helper exists but is not yet wired into the server, report that as an integration gap instead of treating the capability as fully shipped.
 `;
 }
 function withDiscoveryMetadata(value, runsRoot) {

package/dist/server.js

@@ -26,6 +26,9 @@ import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"
 import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js";
 import { CallToolRequestSchema, GetPromptRequestSchema, ListPromptsRequestSchema, ListResourcesRequestSchema, ListResourceTemplatesRequestSchema, ListToolsRequestSchema, ReadResourceRequestSchema } from "@modelcontextprotocol/sdk/types.js";
 import { MARTIN_MCP_PACKAGE_VERSION } from "./package-version.js";
+import { MARTIN_ARCADE_FALLBACK_TEXT, MARTIN_ARCADE_MIME_TYPE, MARTIN_ARCADE_RESOURCE_URI, MARTIN_ARCADE_UI_EXTENSION_ID, buildArcadeToolDefinitions, supportsMartinArcadeApp } from "./arcade/capabilities.js";
+import { listArcadeResources, readArcadeResource } from "./arcade/resource.js";
+import { readArcadeStatus } from "./arcade/status.js";
 import { getMartinPrompt, listMartinPrompts } from "./prompts.js";
 import { listMartinResources, listMartinResourceTemplates, readMartinResource } from "./resources.js";
 import { martinDoctorTool } from "./tools/doctor.js";
@@ -56,15 +59,6 @@ const stringArraySchema = {
     type: "array",
     items: { type: "string" }
 };
-function describeCostProvenance(provenance) {
-    if (provenance === "actual")
-        return "provider-settled actual";
-    if (provenance === "calculated")
-        return "calculated from observed usage";
-    if (provenance === "estimated")
-        return "estimated";
-    return "unavailable";
-}
 const loopPreviewSchema = {
     type: "object",
     additionalProperties: true,
@@ -78,10 +72,6 @@ const loopPreviewSchema = {
         updatedAt: { type: "string" },
         attempts: { type: "integer" },
         costUsd: { type: "number" },
-        costProvenance: {
-            type: "string",
-            enum: ["actual", "calculated", "estimated", "unavailable"]
-        },
         avoidedUsd: { type: "number" },
         pressure: { type: "string" },
         shouldStop: { type: "boolean" },
@@ -101,7 +91,6 @@ const loopPreviewSchema = {
         "lifecycleState",
         "attempts",
         "costUsd",
-        "costProvenance",
         "avoidedUsd",
         "pressure",
         "shouldStop",
@@ -267,10 +256,6 @@ const runOutputSchema = {
         reason: { type: "string" },
         attempts: { type: "integer" },
         costUsd: { type: "number" },
-        costProvenance: {
-            type: "string",
-            enum: ["actual", "calculated", "estimated", "unavailable"]
-        },
         verificationPassed: { type: "boolean" },
         loopId: { type: "string" },
         pressure: { type: "string" },
@@ -302,7 +287,6 @@ const runOutputSchema = {
         "reason",
         "attempts",
         "costUsd",
-        "costProvenance",
         "verificationPassed",
         "loopId",
         "pressure",
@@ -370,10 +354,6 @@ const statusOutputSchema = {
         lifecycleState: { type: "string" },
         attempts: { type: "integer" },
         costUsd: { type: "number" },
-        costProvenance: {
-            type: "string",
-            enum: ["actual", "calculated", "estimated", "unavailable"]
-        },
         avoidedUsd: { type: "number" },
         pressure: { type: "string" },
         shouldStop: { type: "boolean" },
@@ -397,7 +377,6 @@ const statusOutputSchema = {
         "lifecycleState",
         "attempts",
         "costUsd",
-        "costProvenance",
         "avoidedUsd",
         "pressure",
         "shouldStop",
@@ -747,7 +726,16 @@ export function createMartinMcpServer(serverInfo) {
     const server = new Server({
         name: serverInfo?.name ?? "martin-loop",
         version: serverInfo?.version ?? MARTIN_MCP_PACKAGE_VERSION
-    }, { capabilities: { tools: {}, resources: {}, prompts: {} } });
+    }, {
+        capabilities: {
+            tools: {},
+            resources: {},
+            prompts: {},
+            extensions: {
+                [MARTIN_ARCADE_UI_EXTENSION_ID]: { mimeTypes: [MARTIN_ARCADE_MIME_TYPE] }
+            }
+        }
+    });
     server.setRequestHandler(ListToolsRequestSchema, () => ({
         tools: [
             {
@@ -1469,17 +1457,23 @@ export function createMartinMcpServer(serverInfo) {
                     },
                     required: ["objective", "engine", "budgetUsd", "selectedMode", "confidence", "expectedCostUsd", "expectedPreworkBurnPct", "reason"]
                 }
-            }
+            },
+            ...buildArcadeToolDefinitions(server.getClientCapabilities())
         ]
     }));
-    server.setRequestHandler(ListResourcesRequestSchema, () => ({
-        ...listMartinResources()
-    }));
+    server.setRequestHandler(ListResourcesRequestSchema, () => {
+        const listed = listMartinResources();
+        const arcade = listArcadeResources(server.getClientCapabilities());
+        return { resources: [...listed.resources, ...arcade.resources] };
+    });
     server.setRequestHandler(ListResourceTemplatesRequestSchema, () => ({
         ...listMartinResourceTemplates()
     }));
     server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
         try {
+            if (request.params.uri === MARTIN_ARCADE_RESOURCE_URI) {
+                return await readArcadeResource(request.params.uri);
+            }
             return await readMartinResource({ uri: request.params.uri });
         }
         catch (error) {
@@ -1509,6 +1503,29 @@ export function createMartinMcpServer(serverInfo) {
     server.setRequestHandler(CallToolRequestSchema, async (request) => {
         const { name, arguments: args } = request.params;
         try {
+            if (name === "martin_arcade") {
+                const available = supportsMartinArcadeApp(server.getClientCapabilities());
+                return createToolSuccessResult({
+                    available,
+                    resourceUri: available ? MARTIN_ARCADE_RESOURCE_URI : null
+                }, MARTIN_ARCADE_FALLBACK_TEXT, { human: MARTIN_ARCADE_FALLBACK_TEXT });
+            }
+            if (name === "martin_arcade_status") {
+                const input = args ?? {};
+                if (!input || typeof input !== "object" || Array.isArray(input)) {
+                    throw new MartinToolError("invalid_arguments", "Arcade status input must be an object.", {
+                        category: "invalid_input"
+                    });
+                }
+                const keys = Object.keys(input);
+                if (keys.some((key) => key !== "loopId") || ("loopId" in input && typeof input.loopId !== "string")) {
+                    throw new MartinToolError("invalid_arguments", "Arcade status accepts only an optional loopId.", {
+                        category: "invalid_input"
+                    });
+                }
+                const output = await readArcadeStatus(input);
+                return createToolSuccessResult(output, `MartinLoop Arcade status for ${output.loopId}: ${output.displayOutcome ?? output.lifecycleState}.`);
+            }
             if (name === "martin_run") {
                 const input = validateToolInput("martin_run", args);
                 const runsRoot = resolveRunsRoot(process.env);
@@ -1544,7 +1561,7 @@ export function createMartinMcpServer(serverInfo) {
                 const output = await runLoopTool(input);
                 return createToolSuccessResult(output, [
                     `Run ${output.loopId} is ${output.status}/${output.lifecycleState}`,
-                    `after ${output.attempts} attempt(s); recorded cost ${output.costUsd.toFixed(2)} USD (${describeCostProvenance(output.costProvenance)}).`,
+                    `after ${output.attempts} attempt(s); spend ${output.costUsd.toFixed(2)} USD.`,
                     `Execution mode: ${output.executionMode}; governance claim eligible:`,
                     `${output.governanceClaimEligible ? "yes" : "no"}.`
                 ].join(" "));
@@ -1552,12 +1569,12 @@ export function createMartinMcpServer(serverInfo) {
             if (name === "martin_inspect") {
                 const input = validateToolInput("martin_inspect", args);
                 const output = await inspectLoopTool(input);
-                return createToolSuccessResult(output, `Inspected ${output.loopCount} run(s) from ${output.source}; total recorded cost ${output.portfolio.totalActualUsd.toFixed(2)} USD.`);
+                return createToolSuccessResult(output, `Inspected ${output.loopCount} run(s) from ${output.source}; total actual spend ${output.portfolio.totalActualUsd.toFixed(2)} USD.`);
             }
             if (name === "martin_status") {
                 const input = validateToolInput("martin_status", args);
                 const output = await getStatusTool(input);
-                return createToolSuccessResult(output, `Loop ${output.loopId} is ${output.status}/${output.lifecycleState}; recorded cost is ${output.costUsd.toFixed(2)} USD (${describeCostProvenance(output.costProvenance)}), and pressure is ${output.pressure} with ${output.remainingBudgetUsd.toFixed(2)} USD remaining.`);
+                return createToolSuccessResult(output, `Loop ${output.loopId} is ${output.status}/${output.lifecycleState}; pressure is ${output.pressure} with ${output.remainingBudgetUsd.toFixed(2)} USD remaining.`);
             }
             if (name === "martin_doctor") {
                 const input = validateToolInput("martin_doctor", args);

package/dist/tools/run-loop.d.ts

@@ -1,6 +1,6 @@
 import { type SpawnLike } from "../vendor/adapters/index.js";
 import { type RunStore } from "../vendor/core/index.js";
-import type { CostProvenance, ExecutionMode, LoopBudget, ReceiptScope } from "../vendor/contracts/index.js";
+import type { ExecutionMode, LoopBudget, ReceiptScope } from "../vendor/contracts/index.js";
 import { buildArtifactSummary, buildVerificationSummary, buildLoopPreview, type MartinEngine } from "./tool-support.js";
 export interface RunLoopInput {
     objective: string;
@@ -24,7 +24,6 @@ export interface RunLoopOutput {
     reason: string;
     attempts: number;
     costUsd: number;
-    costProvenance: CostProvenance;
     verificationPassed: boolean;
     executionMode: ExecutionMode;
     governanceClaimEligible: boolean;

package/dist/tools/run-loop.js

@@ -1,4 +1,4 @@
-import { createClaudeCliAdapter, createCodexCliAdapter, createGeminiCliAdapter, createVerifierOnlyAdapter, probeCodexLaunch, resolveCliCommandAvailability } from "../vendor/adapters/index.js";
+import { createClaudeCliAdapter, createCodexCliAdapter, createGeminiCliAdapter, probeCodexLaunch, resolveCliCommandAvailability, createVerifierOnlyAdapter } from "../vendor/adapters/index.js";
 import { createFileRunStore, evaluateCostGovernor, resolveRunsRoot, runMartin } from "../vendor/core/index.js";
 import { normalizeSafePathPatterns, resolveSafeRepoRoot } from "../server-validation.js";
 import { MartinToolError } from "./tool-errors.js";
@@ -166,7 +166,6 @@ export async function runLoopTool(input) {
         reason: result.decision.reason,
         attempts: result.loop.attempts.length,
         costUsd: result.loop.cost.actualUsd,
-        costProvenance: result.loop.cost.provenance ?? "unavailable",
         verificationPassed,
         executionMode: evidenceExecutionMode,
         governanceClaimEligible: evidenceExecutionMode === "governed",

package/dist/vendor/adapters/claude-cli.js

@@ -749,6 +749,7 @@ export function createAgentCliAdapter(options) {
                 workspaceId: request.workspaceId,
                 cwd: workingDirectory,
             });
+            const verificationConfigured = verification.binding.commands.length > 0;
             // Check for zero-diff (agent ran but made no file changes)
             const postRunChangedFiles = gitRepoRoot
                 ? await readGitChangedFiles(gitRepoRoot, 5_000, options.spawnImpl)
@@ -791,7 +792,7 @@ export function createAgentCliAdapter(options) {
             }
             // Derive structural classHint from evidence, not keyword scanning
             const structuralHint = inferStructuralClassHint(agentText, verification.summary, agentResult.exitCode, request.context.objective);
-            if (verification.passed) {
+            if (verification.passed || !verificationConfigured) {
                 return {
                     status: "completed",
                     summary,

package/dist/vendor/adapters/cli-bridge.js

@@ -154,7 +154,13 @@ export async function runVerification(commands, cwd, timeoutMs, verificationStac
         commands: steps.map((step) => step.command),
     };
     if (steps.length === 0) {
-        return { passed: true, summary: "No verification commands specified.", steps: [], binding: executionBinding };
+        return {
+            passed: false,
+            summary: "No verification commands specified; execution is not VERIFIED.",
+            steps: [],
+            warnings: ["Execution completed without verifier evidence."],
+            binding: executionBinding,
+        };
     }
     const failedSteps = [];
     const stepOutcomes = [];

package/dist/vendor/adapters/index.d.ts

@@ -4,5 +4,6 @@ export { createCodexCliAdapter, type CodexCliAdapterOptions } from "./codex-cli.
 export { createOpenAiCompatibleAdapter, resolveOpenAiCompatibleRuntimeConfig, type OpenAiCompatibleAdapterOptions } from "./openai-compatible.js";
 export { createVerifierOnlyAdapter, type VerifierOnlyAdapterOptions } from "./verifier-only.js";
 /** @internal Test-only compatibility export. Public package builders strip this surface. */
+export { createStubAgentCliAdapter, type StubAgentCliAdapterOptions, createStubDirectProviderAdapter, type StubDirectProviderAdapterOptions } from "./stub-agent-cli.js";
 export { buildCodexExecArgs, buildCodexStdin, clearCodexCapabilityCacheForTests, detectCodexHostPlatform, diagnoseCodexHost, probeCodexCapabilities, probeCodexLaunch, resolveCliCommandAvailability, type CliCommandAvailability, type CodexApprovalCapability, type CodexAutonomyResolution, type CodexCapabilityFlag, type CodexCapabilityProfile, type CodexFlagScope, type CodexHostDiagnosis, type CodexHostPlatform, type CodexLaunchProbeResult, type CodexPromptTransport, type CodexSandboxCapability, checkCodexSandboxPreflight, probeFilesystemWriteCapability, type CodexSandboxPreflightOk, type CodexSandboxPreflightOutcome, type CodexSandboxPreflightReadOnly } from "./codex-launcher.js";
 export { createSpawnPlan, type SpawnLike, type SpawnPlan, type SubprocessResult, type VerificationOutcome } from "./cli-bridge.js";

package/dist/vendor/adapters/index.js

@@ -4,5 +4,6 @@ export { createCodexCliAdapter } from "./codex-cli.js";
 export { createOpenAiCompatibleAdapter, resolveOpenAiCompatibleRuntimeConfig } from "./openai-compatible.js";
 export { createVerifierOnlyAdapter } from "./verifier-only.js";
 /** @internal Test-only compatibility export. Public package builders strip this surface. */
+export { createStubAgentCliAdapter, createStubDirectProviderAdapter } from "./stub-agent-cli.js";
 export { buildCodexExecArgs, buildCodexStdin, clearCodexCapabilityCacheForTests, detectCodexHostPlatform, diagnoseCodexHost, probeCodexCapabilities, probeCodexLaunch, resolveCliCommandAvailability, checkCodexSandboxPreflight, probeFilesystemWriteCapability } from "./codex-launcher.js";
 export { createSpawnPlan } from "./cli-bridge.js";

package/dist/vendor/adapters/openai-compatible.js

@@ -103,12 +103,12 @@ function normalizeOpenAiCompatibleUsage(input) {
 // ---------------------------------------------------------------------------
 // Prompt builder
 // ---------------------------------------------------------------------------
-const DEFAULT_SYSTEM_PROMPT = `You are an expert software engineer executing a governed coding task.
-Follow these rules exactly:
-- Read the task description carefully and implement only what is asked.
-- Do not add features, refactors, or improvements beyond the stated task.
-- If the task asks you to write or modify code, output the complete file content with changes applied.
-- Be precise, minimal, and test-backed in all changes.
+const DEFAULT_SYSTEM_PROMPT = `You are an expert software engineer executing a governed coding task.
+Follow these rules exactly:
+- Read the task description carefully and implement only what is asked.
+- Do not add features, refactors, or improvements beyond the stated task.
+- If the task asks you to write or modify code, output the complete file content with changes applied.
+- Be precise, minimal, and test-backed in all changes.
 - State what you changed and why at the end of your response.`;
 export const DEFAULT_OPENAI_BASE_URL = "https://api.openai.com";
 export function resolveOpenAiCompatibleRuntimeConfig(env = process.env) {
@@ -347,11 +347,14 @@ export function createOpenAiCompatibleAdapter(options) {
                     ? (await readGitChangedFiles(workingDirectory, 5_000)).filter((file) => !baselineChangedFiles.has(file))
                     : []
             };
+            const verificationConfigured = verification.binding.commands.length > 0;
             return {
-                status: verification.passed ? "completed" : "failed",
+                status: verification.passed || !verificationConfigured ? "completed" : "failed",
                 summary: verification.passed
                     ? `${model} completed the task. Verifier passed.`
-                    : `${model} completed but verifier failed: ${verification.summary}`,
+                    : !verificationConfigured
+                        ? `${model} completed the task without verifier evidence; outcome is not VERIFIED.`
+                        : `${model} completed but verifier failed: ${verification.summary}`,
                 usage: normalizeOpenAiCompatibleUsage({
                     model,
                     tokensIn,
@@ -362,7 +365,7 @@ export function createOpenAiCompatibleAdapter(options) {
                 }),
                 verification,
                 execution,
-                ...(verification.passed ? {} : {
+                ...(verification.passed || !verificationConfigured ? {} : {
                     failure: { message: verification.summary }
                 })
             };

package/dist/vendor/adapters/stub-agent-cli.d.ts

@@ -0,0 +1,9 @@
+import type { MartinAdapter, MartinAdapterRequest, MartinAdapterResult } from "../core/index.js";
+export interface StubAgentCliAdapterOptions {
+    command: string[];
+    profile?: string;
+    label?: string;
+    responder?: (request: MartinAdapterRequest) => Promise<MartinAdapterResult> | MartinAdapterResult;
+}
+export declare function createStubAgentCliAdapter(options: StubAgentCliAdapterOptions): MartinAdapter;
+export { createStubDirectProviderAdapter, type StubDirectProviderAdapterOptions } from "./stub-direct-provider.js";