@battlegrid/mcp-server 31.2.70 → 31.2.72

package/README.md

@@ -24,6 +24,94 @@ Seeing package `31.x` alongside handshake `battlegrid@33.x` — the package **be
 
 **What this changes for you:** nothing about how you call anything. Upgrading the package no longer waits on a server deploy, and a server deploy no longer strands you on a package that names the wrong contract — reconnect and the announcement follows. **Contract breaking-change notes are no longer keyed to package versions**, since a contract move is no longer a release here; the v11-and-earlier notes below are kept as history, and the live vocabulary is always discovery.
 
+## Contract history — v90 (Arena and radar deployments join the draft lifecycle)
+
+**Breaking at v90: input is refused and reshaped, output is reshaped, five error codes are removed.** v90 is the
+contract on top of v89. The Arena and radar deployment drafts now run the same five-tool lifecycle as agents and
+strategies, and the preview token is retired: a deployment commits on the draft version and the revision you read.
+
+### Rejected input — something you send is no longer accepted
+
+- **`previewToken` and `confirm`** leave `commit_deployment_policy_draft`, `commit_radar_deployment_draft`,
+  `resume_deployment_policy` and `resume_radar_deployment`.
+- **`confirm`** leaves `delete_deployment_policy`, `delete_radar_deployment`, `discard_deployment_policy_draft` and
+  `discard_radar_deployment_draft`.
+- Every input is strict, so a call naming either key is refused as an unrecognised key.
+
+### Reshaped input
+
+- **The commits** take `{ request: { presetId | coinId, draftVersion, expectedRevision } }`: exactly the
+  `draftVersion` and `committedRevision` the kind's `get_*_draft` returned (`expectedRevision: null` for a first
+  deployment).
+- **The resumes** take `{ presetId | coinId, expectedPolicyId, expectedRevision }`: the `policyId` and `revision` a
+  `COMMITTED` preview returned. Any other deployment or revision is a `CONFLICT`, and nothing is armed.
+- **`delete_radar_deployment`** gains `expectedPolicyId` beside `expectedRevision`, as `delete_deployment_policy`
+  already took. A delete naming a policy since removed and redeployed matches nothing.
+- **The discards** take `{ request: { presetId | coinId, draftVersion } }` with no dry run. A draft that moved, or
+  none, is `DRAFT_VERSION_MOVED`.
+
+### Reshaped output — something you read has a new shape
+
+- **`stage_deployment_policy_draft` and `stage_radar_deployment_draft`** gain `diagnostics`.
+- **`get_deployment_policy_draft` and `get_radar_deployment_draft`** answer the lifecycle read
+  `{ draft, draftVersion, committedRevision, diff, diagnostics, impact }`, where they answered `{ draft }`. `impact`
+  is the resolution the commit would arm and whether it plays (`enabledAfterCommit`), plus a radar first
+  deployment's coin-cap reading (`admission`); it is null when a diagnostic refuses.
+- **The commits** answer `{ presetId | coinId, revision, draftVersion }`. The radar commit answered `{ revision }`.
+- **The discards** answer `discarded: true`, never `false`.
+- **`preview_deployment_resolution` and `preview_radar_resolution`** lose `previewToken` and gain `policyId` and
+  `revision`: the deployment the preview resolved over, null for `SLOTS` and a first deployment.
+
+### Removed error codes
+
+`TOKEN_EXPIRED`, `TOKEN_BINDING_MISMATCH`, `INVALID_TOKEN_SIGNATURE`, `INVALID_TOKEN_FORMAT` and `INVALID_TOKEN_CLAIMS`
+leave the error vocabulary and every draft diagnostic's code enum — so the stage and get outputs of the agent and
+strategy drafts move too.
+
+### Behaviour behind the new schemas
+
+- **A retried commit replays its receipt.** Both commits are destructive and idempotent on
+  `<presetId | coinId>:<draftVersion>`, as the agent and strategy commits are.
+- **Refusals name the next act.** A moved draft or revision carries `details.nextAct: "get_draft"`; a refusal the
+  draft can repair (`INVALID_DEPLOYMENT_POLICY`, or the radar's `VALIDATION_ERROR`) carries `"stage"`; a retired arena
+  carries none and names the remedy.
+- **A revision conflict names the revision that won** in `details.actualRevision`, null when no deployment remains.
+- **A `DRAFT` preview at a version the draft is not at** is `DRAFT_VERSION_MOVED`.
+- **A draft whose arena or coin can no longer be deployed is still served**, with the refusal in its diagnostics and
+  a null impact, so you can show it and discard it.
+- **A radar resume of a policy already trading** answers its revision and changes nothing.
+- **The radar per-user coin cap is `FORBIDDEN`**, with no `nextAct`, where it was `VALIDATION_ERROR`.
+
+Something accepted at v89 is refused at v90 — hence the MAJOR.
+
+## Contract history — v89 (a new strategy is held to today's operator bounds)
+
+**Breaking at v89: acceptance narrows behind unchanged schemas.** v89 is the contract on top of v88.1.
+
+### Narrowed acceptance — `commit_strategy_draft`, `preview_strategy_report` (`DRAFT` source)
+
+- **A create judges every dial of the new strategy at the operator bounds configured now.** That includes a dial
+  the author typed, one a fork copied from its source, and one left at the creation default. The operator bounds
+  are the platform's ATR %, stop-loss ATR-multiple and risk:reward limits.
+- At v88.1 a create judged only the dials that differed from the fork's source or the creation default. So a copied
+  dial outside a bound tightened since the source stored it was committed.
+- At v89 `commit_strategy_draft` (`expectedRevision: null`) refuses that create with `VALIDATION_ERROR`, naming the
+  dial and the bound, for example `minAtrPct (0.1) must be >= 0.15`. Nothing is created and the draft is unchanged:
+  stage the dial inside the bound and commit again.
+- `preview_strategy_report` with `source: { kind: "DRAFT", … }` composes the draft exactly as the commit does, so it
+  refuses the same draft with the same error where v88.1 rendered it.
+- `stage_strategy_draft` and `get_strategy_draft` report the error in their diagnostics before the commit.
+- `fork_strategy`'s description now says this, so its description hash moves.
+
+### Behaviour behind unchanged schemas
+
+- **An edit still judges only what it moves.** An update or a restore carries a dial it leaves unchanged, so a stored
+  value outside a since-tightened bound stays readable and saveable on its own strategy.
+- **The platform keeps its defaults creatable.** An operator cannot set a bound that would put a creation default
+  outside it, so a create that leaves a dial untouched is never refused for a value the platform seeded.
+
+Something accepted at v88.1 is refused at v89 — hence the MAJOR.
+
 ## Contract history — v88.1 (an open position keeps the exit rules it opened under)
 
 **Additive at v88.1: acceptance widens and one served value narrows; no input or output schema

package/SKILL.md

@@ -58,15 +58,19 @@ than about authoring:
 
 - **The envelope is `{ request }`, or `{ account, request }` on a multi-account proxy** (see above).
   It applies to every draft lifecycle tool and to `get_strategy_section_template`.
-- **Every change goes through the entity's draft.** `stage_<kind>_draft({ request: { <id>?,
-  draftVersion, axes } })` writes proposed axes into the player's unsaved draft and commits nothing;
-  omit the id to open a new create draft, whose minted id the response carries.
+- **Every change goes through the entity's draft** — an agent's, a strategy's, and an Arena or radar
+  deployment's. `stage_<kind>_draft({ request: { <id>?, draftVersion, axes } })` writes proposed axes
+  into the player's unsaved draft and commits nothing. For an agent or a strategy, omit the id to open a
+  new create draft, whose minted id the response carries; a deployment draft is keyed by its `presetId`
+  or `coinId`, which every call names.
   `get_<kind>_draft({ request: { <id> } })` returns the draft, its `draftVersion`, the live
   `committedRevision`, a per-axis `diff`, `diagnostics` and `impact`.
 - **A commit names exactly the two numbers that read returned.**
   `commit_<kind>_draft({ request: { <id>, draftVersion, expectedRevision } })` — `expectedRevision`
   is `null` for an entity not created yet. Commit only after the player has seen the diff and impact
-  and said yes. `discard_<kind>_draft({ request: { <id>, draftVersion } })` is the same fence.
+  and said yes. `discard_<kind>_draft({ request: { <id>, draftVersion } })` is the same fence. The two
+  deployment commits arm wagers and require `mcp:wager`; a deployment's resume and delete name the
+  `expectedPolicyId` and `expectedRevision` a `COMMITTED` preview returned.
 - **The proxy forwards numbers and `null` unchanged.** It never fills in a version, never retries a
   refused call and never rebuilds a request. A `DRAFT_VERSION_MOVED` or `DRAFT_AXIS_CONTESTED` refusal
   carries `details.nextAct` from every tool, and a revision `CONFLICT` or validation refusal carries it
@@ -89,7 +93,7 @@ The `play-market-grid` prompt (discover via `prompts/list`) provides a guided en
 
 ## Retired operations
 
-`create_strategy`, the plan tools (`compile_strategy_plan`, `stage_strategy_plan`, `apply_strategy_plan`), `update_strategy_signal_rule`, and the direct agent writers (`create_intelligence_agent`, `update_intelligence_agent`, `rebind_intelligence_agent`) are **retired** — they are absent from discovery and cannot be invoked. Stage into the entity's draft, read it back, and commit the version you read; a signal rule is a row of the strategy draft's `SIGNAL_RULES` axis, and a strategy binding is the agent draft's `STRATEGY_BINDING` axis. Do not attempt flat legacy payloads; the server enforces a closed-world request root and the proxy never reconstructs them.
+`create_strategy`, the plan tools (`compile_strategy_plan`, `stage_strategy_plan`, `apply_strategy_plan`), `update_strategy_signal_rule`, and the direct agent writers (`create_intelligence_agent`, `update_intelligence_agent`, `rebind_intelligence_agent`) are **retired** — they are absent from discovery and cannot be invoked. Stage into the entity's draft, read it back, and commit the version you read; a signal rule is a row of the strategy draft's `SIGNAL_RULES` axis, and a strategy binding is the agent draft's `STRATEGY_BINDING` axis. A deployment preview's `previewToken`, and the `confirm` on a deployment commit, resume, delete or draft discard, are retired the same way: a strict input refuses either key. Do not attempt flat legacy payloads; the server enforces a closed-world request root and the proxy never reconstructs them.
 
 ## Common errors
 

package/dist/index.d.ts

@@ -49,7 +49,7 @@ import { type Implementation, type Prompt, type Resource } from '@modelcontextpr
  * being asked. Move it for a change to THIS package — a proxy fix, a dependency bump, a docs
  * correction. Never move it to track the server.
  */
-export declare const PACKAGE_VERSION = "31.2.70";
+export declare const PACKAGE_VERSION = "31.2.72";
 export declare const DEFAULT_URL = "https://mcp.battlegrid.trade/mcp";
 export interface EnvConfig {
     apiKeys: string[];

package/dist/index.js

@@ -52,7 +52,7 @@ import { ListToolsRequestSchema, CallToolRequestSchema, ListPromptsRequestSchema
  * being asked. Move it for a change to THIS package — a proxy fix, a dependency bump, a docs
  * correction. Never move it to track the server.
  */
-export const PACKAGE_VERSION = '31.2.70';
+export const PACKAGE_VERSION = '31.2.72';
 export const DEFAULT_URL = 'https://mcp.battlegrid.trade/mcp';
 const MAX_RETRIES = 3;
 const RETRY_DELAYS_MS = [2000, 4000, 8000];

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@battlegrid/mcp-server",
-  "version": "31.2.70",
-  "description": "BattleGrid MCP server \u2014 play crypto prediction games from AI agents",
+  "version": "31.2.72",
+  "description": "BattleGrid MCP server — play crypto prediction games from AI agents",
   "type": "module",
   "main": "dist/index.js",
   "bin": {