@battlegrid/mcp-server 31.2.71 → 31.2.74

package/README.md

@@ -24,6 +24,158 @@ 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 — v92 (every section you read is the JSON the agent reads)
+
+**Breaking at v92: the section fields are reshaped, the report preview's default narrows, and its size is measured
+in characters.** v92 is the contract on top of v91. Every tool that published a section as markdown text publishes
+it as the JSON object the agent reads, and `preview_strategy_report` takes a detail level.
+
+### Reshaped output — a section is its JSON
+
+A **section read** is `{ shape: "table", section }` — `{ id, title, notes, provenance?, anchorTf, groups, columns,
+rows, addendum? }`, rows positional and every cell its raw value, each column stating its `unit`, `precision`, bar
+set (`bars`) and, on a rank column, the ranked set's `universe`, with a key absent where the column has nothing to
+say — or `{ shape: "facts", section }`, `{ id, title, facts, glossary }`. It replaces:
+
+- **`preview_strategy_report.renderedSections[]`**: `{ sectionKey, section: { title, text }, structure,
+  authoredNote }` → `{ sectionKey }` and a section read, or `{ sectionKey, shape: "skipped" }` for a row that
+  rendered nothing. A custom section's authored note is its section's `notes`.
+- **`get_market_context.sections[]`**: `{ kind, title, content, structure }` → `{ kind }` and a section read.
+- **`get_context_source_full_preview.content`** → **`read`**, a section read or `null`.
+- **`get_context_sources_preview`**: each source's `value` → **`section`**, a section read or `null`, a coin-row
+  table sampled to its first five coins.
+- **`get_signal_log.reportSections[]`**: a section read, `skipped`, or `{ sectionKey, shape: "text", title, text }`
+  — a row stored before custom sections carried a structure, kept as its agent read it.
+- **`preview_strategy_report.conditionsTableText`** and **`.tradeConditionsBlockText`** → **`gridConditions`** and
+  **`tradeConditions`**, each `{ glossary, register }`: the glossary prose and the register object the text carried
+  as one JSON line. Each is `null` where its text was.
+
+### Widened output — the register names what decided the verdict
+
+- **`decidedBy`** joins the conditions register: on each `GRID` coin and on the `TRADE` register, the key of the
+  condition the `verdict` came from, `null` when no single condition made the call. It reaches you in
+  `gridConditions.register`, `tradeConditions.register`, and the register `get_agent_prompt_context_preview` shows,
+  and the conditions glossary gains the sentence defining it.
+
+### Narrowed default, new input — `preview_strategy_report` `detail`
+
+- **`detail`** is `"concise"` (the default) or `"detailed"`. A concise preview is exactly what the agent reads.
+- **`conditionColumns`** and **`conditionOutcomes`** leave the top level. With each row's `headerBindings`
+  (`{ sectionKey, columnIndexByHeader }`) they make up **`authoring`**, served only at `"detailed"` and `null`
+  otherwise. If you read either field, ask for `"detailed"` and read it under `authoring`.
+- **`marketReadMarkers[]`** lose `resolvedName` and `resolvedValue`.
+
+### Result size in characters
+
+- **`tokenCountModel`** and **`budgetUsage.estimatedTokens`** leave the preview. **`budgetUsage.resultChars`** is
+  the exact `JSON.stringify` length of the response that carries it, its own digits included, against the cap.
+- **`list_strategy_vocabulary`** drops `budgets.estimatedTokens`, and `previewExecutionLimits.maxResultBytes` is
+  renamed **`maxResultChars`**.
+- A preview over the cap is refused with **`PREVIEW_LIMIT_EXCEEDED`** and `limit: "result_chars"`;
+  `estimated_tokens` and `mcp_result_bytes` are retired. Every preview refusal now carries its `previewErrorCode`
+  and its bound (`deadlineMs`, or `limit`, `actual` and `maximum`) in the error's details.
+- **`preview_strategy_report`**, **`get_market_context`** and **`get_context_sources_preview`** declare the cap as
+  `_meta["anthropic/maxResultSizeChars"]`, so Claude Code keeps a large result inline.
+
+Something read at v91 is reshaped or gone at v92, and a default narrows — hence the MAJOR.
+
+## Contract history — v91 (every data block an agent reads is one JSON object)
+
+**Breaking at v91: one output field is removed, and the published text that is the agent's prompt carries JSON.**
+v91 is the contract on top of v90. Every data block BattleGrid's trading agents read — the strategy's resolved
+conditions, fact sections, and the trade-decision blocks — is one JSON object naming itself with `id` and `title`.
+Instructions stay prose under their `## Title`. The tools that show you the prompt therefore show that JSON.
+
+### Removed output — something you read is gone
+
+- **`promptDataSerialization`** leaves `get_signal_log`'s owner detail. There is one serialization, so a trade
+  record stores none. `reportSections` and `missingData` are unchanged, and a trade recorded before capture still
+  serves both as `null`.
+
+### Reshaped output — the same fields, carrying JSON
+
+- **`preview_strategy_report.conditionsTableText`** is the conditions glossary as a `## Strategy Conditions
+  Glossary` instruction, then the conditions register as one JSON line: `surface: "GRID"`, and `coins[]` each with
+  `outcomes` keyed by condition and `verdict` by display name (`null` when the strategy declares no verdict). It was a
+  markdown table followed by the glossary.
+- **`preview_strategy_report.tradeConditionsBlockText`** is the trade glossary, a blank line, then the target coin's
+  register as one JSON line: `surface: "TRADE"`, `verdict` as `{ name, description }`, and `conditions[]` each with
+  `outcome`, `required`, `provisional`, `counts`, `exitRule` and the evaluator's `evidence`. It was a
+  `## STRATEGY CONDITIONS` heading, a table and evidence bullets.
+- **A fact section's text is its JSON**, `{ id, title, facts, glossary }` with `facts` keyed by label, in
+  `get_market_context.sections[].content`, `get_context_source_full_preview.content`,
+  `preview_strategy_report.renderedSections[].section.text`, and the `get_signal_log` report of trades recorded
+  from v91 on. The session field is a fact section. A table section's text is still its markdown.
+- **`get_agent_prompt_context_preview.promptSections[].content`** is each section as the agent reads it: a data
+  section's JSON, a table's included, and an instruction's prose.
+
+### Widened enum
+
+- **`get_agent_prompt_context_preview.promptSections[].kind`** gains `strategy-conditions-glossary`, the instruction
+  read before the conditions register. The market-context reads exclude it, as they exclude the register.
+
+Something read at v90 is gone or reshaped at v91 — hence the MAJOR.
+
+## 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.

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 = "31.2.71";
+export declare const PACKAGE_VERSION = "31.2.74";
 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 = '31.2.71';
+export const PACKAGE_VERSION = '31.2.74';
 export const DEFAULT_URL = 'https://mcp.battlegrid.trade/mcp';
 const MAX_RETRIES = 3;
 const RETRY_DELAYS_MS = [2000, 4000, 8000];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@battlegrid/mcp-server",
-  "version": "31.2.71",
+  "version": "31.2.74",
   "description": "BattleGrid MCP server — play crypto prediction games from AI agents",
   "type": "module",
   "main": "dist/index.js",