@battlegrid/mcp-server 31.2.34 → 31.2.36

package/README.md

@@ -24,6 +24,90 @@ 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 — v63.2
+
+Purely additive again, and smaller: **one optional input field.** Drafts now cover a strategy that
+does not exist yet, so a playbook you author in chat survives between compiles instead of starting
+over each time.
+
+### Wider input — one optional field on one tool
+
+- **`compile_strategy_plan`'s CREATE arm gains an optional `strategyId`**, naming the create draft
+  this compile continues. Omit it and the server mints an id exactly as it always has, so nothing
+  you send today breaks.
+
+- **Send it to accumulate; omit it to start fresh.** A first CREATE names nothing and mints; stage
+  that plan and the draft opens at the minted id, which `list_strategy_drafts` and the plan itself
+  both report. Name that id on the next CREATE and the second plan carries the same identity, so the
+  one draft accumulates rather than a second opening beside it.
+
+- **WHY YOU HAVE TO SAY IT.** The server will not choose for you. A compile knows only who you are —
+  it has no conversation id — and you may hold several create drafts, so picking one could write this
+  playbook's values over another's. A compile that names none mints a third id rather than guessing.
+
+- **It names a draft; it does not choose an id.** It is accepted only as the identity of a create
+  draft you own. An id naming no such draft is refused, as is one naming a draft for a strategy that
+  already exists.
+
+### Behaviour changes behind unchanged schemas
+
+- **`stage_strategy_plan` admits a CREATE plan**, opening the create draft at the plan's own id when
+  none exists yet. Its input is still `{ planToken }` alone, and the contested-axis refusal applies
+  identically.
+
+- **`list_strategy_drafts` rows gain `baseRevision`.** It is `null` for a create draft — a strategy
+  that does not exist has no committed revision to be based on — and that null is the only thing that
+  distinguishes one. There is no `kind`, `isNew` or `status` field beside it.
+
+- **A create draft reserves nothing.** It consumes no quota and holds no name, so both are decided
+  when the strategy is actually created. Holding drafts past your limit is legal; creating past it is
+  not.
+
+### Vocabulary
+
+`axes.create` gains `strategyId`. No domain gains a value, and `toolCount` stays 122.
+
+## Contract history — v63.1
+
+Purely additive: **four new tools, nothing you send today changes.** A strategy now has an
+owner-scoped *draft* — the unsaved authored values a player is part-way through — and these are how
+an agent reads it, writes a compiled plan into it, and destroys one. The canonical record for every
+contract move is `docs/architecture/MCP_CONTRACT_HISTORY.md` in `battlegrid-app`; the served version
+is what the handshake announces.
+
+### Wider surface — four tools added
+
+- **`stage_strategy_plan({ request: { planToken } })`** writes a compiled plan's own changed axes
+  into the owner's draft. It commits nothing and does **not** spend the plan, so the same token is
+  still directly applicable afterwards. `planToken` is the only member the request accepts.
+
+- **`get_strategy_draft({ request: { strategyId } })`** reads one draft, or answers `{ draft: null }`
+  — "you are not part-way through this one" is a value, not an error. It reports `baseMoved` when the
+  strategy has been committed past the revision the draft was written against.
+
+- **`list_strategy_drafts({ request: { cursor? } })`** answers "what am I part-way through?" for a
+  conversation holding no id. It includes a draft whose strategy you can no longer see, marked
+  `strategyExists: false`, because that is exactly the work a player has lost track of.
+
+- **`discard_strategy_draft({ request: { strategyId, confirm: true } })`** destroys one draft. The
+  confirmation is required and unsaved values have no other copy; the strategy, its revisions and
+  your other drafts are untouched.
+
+### Refusals worth knowing before you stage
+
+- **A staged plan refuses the axes you typed after it compiled.** `stage_strategy_plan` answers
+  `CONFLICT` naming `contestedAxes`, the version the plan compiled over and the draft's own version
+  per axis. Compile again so the plan absorbs those edits, then stage. A *previous staging* on the
+  same axis is not a contest — only the owner's own hand is.
+
+- **An apply refuses a plan whose draft has moved since.** Moved, discarded and
+  already-committed-by-a-sibling are one answer with one recovery: compile again.
+
+### Vocabulary
+
+`toolCount` 118 → 122. No input or output schema of an existing tool moves — the draft version a
+plan was compiled over rides inside the opaque plan token, which no schema declares.
+
 ## Contract history — v61
 
 One part to read first: **the per-condition evidence clock is gone**, and what replaced it is not a

package/SKILL.md

@@ -57,14 +57,16 @@ than about authoring:
 
 - **The envelope is `{ request }`, or `{ account, request }` on a multi-account proxy** (see above).
   It applies to `get_strategy_section_template`, `update_strategy_signal_rule`,
-  `compile_strategy_plan` and `apply_strategy_plan`.
+  `compile_strategy_plan`, `apply_strategy_plan` and `stage_strategy_plan`.
 - **`planToken` is opaque and is forwarded byte-for-byte.** Never retype, paraphrase, abbreviate or
   rebuild it from memory — the proxy passes the bytes through unchanged, and a mangled token
   addresses no approved plan and is refused. It lives five minutes.
 - **`apply_strategy_plan` carries no `plan` member.** One is rejected as an unknown key: the server
   reads back the plan its own compile approved, so nothing is copied out of the compile response and
   nothing can be truncated or half-reconstructed in transit. Send
-  `{ request: { planToken, confirm: true } }` and nothing else.
+  `{ request: { planToken, confirm: true } }` and nothing else. **`stage_strategy_plan` is the same
+  shape with the token alone** — it puts the plan into the player's unsaved draft for them to review
+  in the builder, commits nothing, and leaves the token still applicable.
 
 Agents bind to a strategy at creation (`create_intelligence_agent({ …, modelId, strategyId })`);
 there is no direct strategy-creation tool. **`battlegrid-agent-management`** carries commissioning,

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 = "31.2.34";
+export declare const PACKAGE_VERSION = "31.2.36";
 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 = '31.2.34';
+export const PACKAGE_VERSION = '31.2.36';
 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": "31.2.34",
-  "description": "BattleGrid MCP server — play crypto prediction games from AI agents",
+  "version": "31.2.36",
+  "description": "BattleGrid MCP server \u2014 play crypto prediction games from AI agents",
   "type": "module",
   "main": "dist/index.js",
   "bin": {