@battlegrid/mcp-server 31.2.103 → 31.2.106

package/README.md

@@ -24,6 +24,22 @@ 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 — v110.9 (the price zone reads the channel of the bars before)
+
+**Served values move at v110.9; no schema moves.** v110.9 is the contract on top of v110.8. Nothing you send
+is refused.
+
+### Behaviour behind unchanged schemas
+
+- **`zone` (`PRICE_ZONE`) classifies the price against the channel of the 20 bars before the classified one**
+  (`DONCHIAN_UPPER_PRIOR` / `DONCHIAN_LOWER_PRIOR`). `breakout high` and `breakdown low` now hold on a close
+  beyond that channel: they are the label form of `dist_donchianHiPrior gt 0` and `dist_donchianLoPrior lt 0`.
+  Against the same-bar channel, which includes the bar's own high and low, they could never be read. A `zone`
+  clause's condition levels are the two prior rails.
+- **`near high` and `near low` are the outer fifth of that channel by position**: at least 0.8 of the way from
+  the low to the high, or at most 0.2. Before, they meant within 1% of price of an edge. The nearer edge wins,
+  and the band widens with the channel. A channel with an absent rail or no width reads `null`.
+
 ## Contract history — v110.6 (the Donchian channel as of the bar before)
 
 **Additive at v110.6: two Donchian metric keys, and level-interaction labels judged against the level in

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 = "31.2.103";
+export declare const PACKAGE_VERSION = "31.2.106";
 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 = '31.2.103';
+export const PACKAGE_VERSION = '31.2.106';
 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": "31.2.103",
+  "version": "31.2.106",
   "description": "BattleGrid MCP server — play crypto prediction games from AI agents",
   "type": "module",
   "main": "dist/index.js",

package/skills/EXPORT.json

@@ -1,8 +1,8 @@
 {
   "generator": "battlegrid-app/server/scripts/export-mcp-skills.mjs",
-  "contractVersion": "110.4.0",
+  "contractVersion": "110.10.0",
   "files": {
-    "battlegrid-agent-management/SKILL.md": "34a868f8068df189ce13af47c23011aabcf6a1f07128da4d4706066628cfaa5f",
+    "battlegrid-agent-management/SKILL.md": "9dc151c32c3578d06e8895c6752d7a64959bff6a6681a01d62ab65e1ea1590d1",
     "battlegrid-agent-management/references/agent-stage-examples.md": "d47555906ce8dedf4c17422f8f5d60187f2d6b3c0af5d9545617a10a5bdb59a1",
     "battlegrid-arena-play/SKILL.md": "88534714cdbaa31344e1798b2b3f18836bf543f5610d118d76095d1a0dbea502",
     "battlegrid-arena-play/references/entry-stage-examples.md": "3bc62f9faca7b5529d51a9794e162333216acb23f0d7f644d5180b9cbc696fca",
@@ -10,13 +10,13 @@
     "battlegrid-radar-deployment/SKILL.md": "652325c4923d79b9c9b78026a5493bfaaedf01f600641511438a9c4bf497c0b1",
     "battlegrid-radar-deployment/references/arena-stage-examples.md": "f605aaa266a291ef1b6d02a0e8885ad5df2fea88c800be2b6625cd629cd741f2",
     "battlegrid-radar-deployment/references/radar-stage-examples.md": "1ddad4a11f021dd65234ee65cc12d7d1561fe9acfd61cb021f4352080d4cecd5",
-    "battlegrid-strategy-authoring/SKILL.md": "098308e69093796db3bb0a6dab64031128aaffbc108117b72393595564581da1",
+    "battlegrid-strategy-authoring/SKILL.md": "5ce41e11d50658226230cfccb70a5c5f08e52755ef737c528d98872f239b3d4e",
     "battlegrid-strategy-authoring/references/strategy-stage-examples.md": "9822cc2bcc8975a3e436c2a960b10e03c95e6e6b4b04bc2206e0ac90688cab66",
     "battlegrid-strategy-doctor/SKILL.md": "e34e055b0cc9b355bc1adeb5d49d464eaa0756ca3f48dc89ca2ccdda94e1311f",
-    "battlegrid-strategy-examples/SKILL.md": "375a85a38b21a356291d05af3668a57949f11ba49968a4a53f08dcc590228375",
+    "battlegrid-strategy-examples/SKILL.md": "597ddacdfc00955fcfd5a1afcc40b5ea72a0f658acbbebc8264afeecc46d2306",
     "battlegrid-strategy-examples/references/playbooks.md": "2309eb7e8324f563c5b1b51e05da931b37c542484135a2be749eff6ef78aa40f",
     "battlegrid-strategy-examples/references/recipes.md": "635e03d163100f6de37cda1f6cc12928d5d36aa0ea883bf44fc72f17cbf3e98e",
-    "battlegrid-strategy-examples/references/tradingview-ports.md": "1b9440bd7180330fb77c8e245e852cbe0b5a9f7df3448233199ecd341565b2b6",
+    "battlegrid-strategy-examples/references/tradingview-ports.md": "9eaa926cbe8606c6a09f91007a0606042afbfdc50173a5b13ae9336d2e9e9b08",
     "battlegrid-trade-analysis/SKILL.md": "3f927b4f9796178526fa1673a2043c5f14358c39aa955de33192ea58641f18fb",
     "battlegrid-trade-proposal/SKILL.md": "e761fc6bddc0d1db79fcb90046d03a18439562c8658de726ec286830edd6369b"
   }

package/skills/battlegrid-agent-management/SKILL.md

@@ -36,8 +36,8 @@ step named beside it before doing anything else.
 `list_strategies` and `get_strategy` are yours — the binding lookup is part of commissioning, and
 which strategy an agent is bound to is the agent's own STRATEGY_BINDING axis (step 4).
 `stage_strategy_draft`, `commit_strategy_draft`, `discard_strategy_draft`, `fork_strategy`,
-`archive_strategy` and `restore_strategy` are **not**, even though activating this skill makes them
-visible in the conversation.
+`archive_strategy`, `restore_strategy`, `save_report_section` and `remove_saved_report_section` are
+**not**, even though activating this skill makes them visible in the conversation.
 
 When the work is a strategy change, activate `strategy-authoring` and let its arc run — its
 evidence, spec-lock, stage-review and confirm rules bind from that point. Do not drive a strategy

package/skills/battlegrid-strategy-authoring/SKILL.md

@@ -103,6 +103,18 @@ anywhere; if the two ever disagree, you have created the exact ambiguity this st
 `list_strategy_categories` → `list_strategy_vocabulary` → `get_strategy_column_contract` and
 `get_strategy_section_template`.
 
+The player's own saved sections are listed among the vocabulary's templates as `kind: "saved"`.
+When the player names one, fetch it with `get_strategy_section_template` and place its title, note,
+`benchmarkTicker` and columns in a new custom section — a copy, with no `sectionKey`.
+
+**Keeping a section.** `save_report_section` keeps a custom section in the player's library: send its
+title, note, `benchmarkTicker` and columns as `section`, dropping `kind` and `sectionKey`. Save only
+when the player asks to keep one — offer it, never decide it. Before the save, say whether the
+vocabulary already lists that title as `saved`; if it does, the save replaces that saved section's
+note, subject and columns whole. `remove_saved_report_section` drops one by its `savedSectionId`:
+before it, say the library entry goes with no other copy, and that strategies already carrying a
+copy keep theirs. Each waits for the player's explicit confirming pick.
+
 Compose sections, columns and conditions **only** from vocabulary returned in this conversation. A
 field you remember from another strategy is not discovery.
 
@@ -351,9 +363,9 @@ the other verbs writes content.
   the restored revision. To change the content as it comes back, stage the change into the
   strategy's draft and commit it — that commit restores it, and its read says `operation: RESTORE`.
 
-**Your `ask_user` is the approval, and the server does not repeat it.** No strategy verb takes a
-confirmation flag. So never call `commit_strategy_draft`, `archive_strategy`, `restore_strategy` or
-`discard_strategy_draft` on a turn where the player has not made an explicit confirming pick —
+**Your `ask_user` is the approval, and the server does not repeat it.** No verb here takes a
+confirmation flag. So never call `commit_strategy_draft`, `archive_strategy`, `restore_strategy`,
+`discard_strategy_draft`, `save_report_section` or `remove_saved_report_section` on a turn where the player has not made an explicit confirming pick —
 never because you judged the change safe. Free text typed while a confirmation is open is not
 consent: answer it, then present the same confirmation again. That covers words typed into the
 form's own answer box as well as words sent in chat — a confirming pick is one of the options you

package/skills/battlegrid-strategy-examples/SKILL.md

@@ -153,6 +153,16 @@ Recipes — each one clause:
 - **Squeeze released** — `kcSqueeze exits "on"`, over a `KC_SQUEEZE` value column.
 - **New 20-bar high** — `donchianHi increased`, over a `DONCHIAN_UPPER` value column: the 20-bar
   upper channel rises exactly when the decided bar's high exceeds every high of the 20 bars before it.
+- **Close above the prior 20-bar high (Donchian / Turtle breakout)** — `dist_donchianHiPrior crossesAbove 0`,
+  over a `DONCHIAN_UPPER_PRIOR × distance` column: Pine's `ta.crossover(close, ta.highest(high, 20)[1])`,
+  TRUE on the first close of a breakout run. `dist_donchianHiPrior gt 0` is Pine's
+  `close > ta.highest(high, 20)[1]` and holds on every close of the run. Mirror with
+  `dist_donchianLoPrior crossesBelow 0` / `lt 0` over `DONCHIAN_LOWER_PRIOR`.
+- **Failed breakout of the prior 20-bar high** — `donchianHiPrior_lvl is "reject_from_below"`, over a
+  `DONCHIAN_UPPER_PRIOR × levelInteraction` column: the high pierced the prior 20-bar high and the close
+  came back under it. `dist_donchianHiPrior crossesBelow 0` is NOT "fell back into the channel": the rail
+  rises to each breakout bar's high, so it fires once on the first bar of a breakout run that does not
+  close above the raised rail — the run of new closing highs ended.
 - **RSI crossed above 50 within the last 3 closes** — `RSI14_now crossesAbove 50` holding
   `{ "atLeast": 1, "of": 3 }`.
 
@@ -371,9 +381,12 @@ column: it takes a timeframe reference and the Confirmed / Developing selector l
 
 **`levelInteraction` — what the bar did at a level.** It classifies the newest bar of the column as
 one of five labels: `touch_from_below`, `touch_from_above`, `reject_from_below`, `reject_from_above`,
-`none`. The side is where the PRIOR close stood against the PRIOR bar's level — from below when it
-closed at or under it — so a level that moved between the two bars is judged on the bar it stood at.
-From below: a bar that closes through the level is a break and reads `none`; a bar whose high
+`none`. The side is where the PRIOR close stood against the level IN FORCE WHEN THE BAR OPENED — from
+below when it closed at or under it. For a level computed from its own bar (a band, `VWAP`, a moving
+average, `ST_LINE`, `PSAR`, the Ichimoku conversion and base lines) that is the prior bar's level, so a
+level that moved between the two bars is judged on the bar it stood at; for a level whose price was fixed
+before the bar (a prior-bar Donchian rail, the break memory, a swing level, the displaced Ichimoku lines, a
+prior-session level or pivot) it is the bar's own level. From below: a bar that closes through the level is a break and reads `none`; a bar whose high
 reached the level and whose close came back under it is `reject_from_below`; a bar whose high came
 within the buffer of the level is `touch_from_below`. From above is the mirror on the low.
 
@@ -385,18 +398,22 @@ within the buffer of the level is `touch_from_below`. From above is the mirror o
 - **A break is a crossing, never a label.** The break of a level is `distance` over the same level
   crossing 0: `dist_bbUpper crossesAbove 0` from below, `crossesBelow 0` from above. On the strategy's
   own rung a `…_from_below` label never holds on a bar where `crossesAbove 0` holds.
-- **Which levels take it.** A candle-homed level — a band (`BB_UPPER`, `BB_LOWER`, `KC_UPPER`,
-  `KC_LOWER`), `VWAP`, a moving average (`SMA20`, `EMA20`, …), `ST_LINE`, `PSAR`, the Donchian break
-  memory (`DONCHIAN_BROKEN_HI`, `DONCHIAN_BROKEN_LO`), the
-  Ichimoku lines, the swing levels (`SWING_FRACTAL_HIGH`, `SWING_FRACTAL_LOW`) — reads its own value at
-  each of the two bars. A prior-session level or pivot (`PDH`,
-  `PDL`, `PDO`, `PIVOT_P`, `PRIOR_TPO_POC`, …) has one reading for the session, used as both bars' level;
-  a clause over it is a single read with no hold, because the session profile keeps no earlier
-  reading. A developing-session level (`TPO_POC`, `TPO_VAH`, …) and the naked points of control move
-  between bars with no earlier reading kept, so they are not offered it; neither are the Donchian
-  rails (`DONCHIAN_UPPER`, `DONCHIAN_LOWER`), each the extreme of the window ending at the very bar it
-  would classify, which a close can never pass. A price fact (`CLOSE`, `HLC3`, `MARK`) is refused: it
-  is the price, not a level.
+- **Which levels take it.**
+  - **Offered:** a candle-homed level — a band (`BB_UPPER`, `BB_LOWER`, `KC_UPPER`, `KC_LOWER`),
+    `VWAP`, a moving average (`SMA20`, `EMA20`, …), `ST_LINE`, `PSAR`, the prior-bar Donchian rails
+    (`DONCHIAN_UPPER_PRIOR`, `DONCHIAN_LOWER_PRIOR`), the Donchian break memory (`DONCHIAN_BROKEN_HI`,
+    `DONCHIAN_BROKEN_LO`), the Ichimoku lines, the swing levels (`SWING_FRACTAL_HIGH`,
+    `SWING_FRACTAL_LOW`) — reads its own value at each bar. A prior-session level or pivot (`PDH`, `PDL`,
+    `PDO`, `PIVOT_P`, `PRIOR_TPO_POC`, …) has one reading for the session; a clause over it is a single
+    read with no hold, because the session profile keeps no earlier reading. On `PSAR` a wick that
+    trades through the SAR flips it on that bar, so a rejection needs the low (high) to meet the SAR
+    exactly and a touch needs a buffer; its flip is `dist_PSAR crossesAbove 0` / `crossesBelow 0`.
+  - **Not offered:** a developing-session level (`TPO_POC`, `TPO_VAH`, …), the naked points of
+    control and the single prints (`TPO_SINGLE_PRINT_ABOVE`/`_BELOW`, `NAKED_SINGLE_PRINT_ABOVE`/`_BELOW`),
+    which move between bars with no earlier reading kept; and the same-bar Donchian rails
+    (`DONCHIAN_UPPER`, `DONCHIAN_LOWER`), each the extreme of the window ending at the very bar it would
+    classify, which a close can never pass — read `DONCHIAN_UPPER_PRIOR` / `DONCHIAN_LOWER_PRIOR`. A
+    price fact (`CLOSE`, `HLC3`, `MARK`) is refused: it is the price, not a level.
 - **A higher-rung level reads that rung's completed bar.** `bbUpper_htf_lvl` classifies the last
   completed regime-rung bar from its own high, low and close, never the strategy bar's price — so
   compose its break on the same rung, `dist_bbUpper_htf crossesAbove 0`.
@@ -479,8 +496,8 @@ its side replaces it.
   clause over it reads FALSE.
 - **A swing level does not remember a broken level.** Two to four bars after a break the level steps
   to the next swing, so a retest of the BROKEN level is not a swing-level read.
-- **The two levels take what every candle level takes** — `distance`, `spread`, `aggregate`,
-  `trajectory`, `efficiency` and `levelInteraction` — and both rank across the board
+- **The two levels take** `distance`, `spread`, `aggregate`, `trajectory`, `efficiency` and
+  `levelInteraction`, and both rank across the board
   (`dist_fractalHi_rank_near`: the coins closest to their own last swing high).
 - **The break is the crossing toward the level.** `dist_fractalHi crossesAbove 0` is a close through the
   last swing high and never fires when the level steps onto a new swing, because the bar that confirms

package/skills/battlegrid-strategy-examples/references/tradingview-ports.md

@@ -60,10 +60,15 @@ rules about the columns themselves, not about porting — they live in the skill
 - **VWAP reversion** → `dist_VWAP` band + `dist_VWAP_rank_far lte 5` for board-relative
   stretch; required `NOT [ADX_state in ["trending","extreme"]]` veto; scalp geometry +
   aggressive timeDecay (VWAP anchors daily at 00:00 UTC).
-- **Donchian / Turtle breakout** → `zone is "breakout high"` + `dist_donchianHi gte 0` +
-  `RVOL gte 1.5`; turtle exits = trend preset (trail from
-  1R, giveback 50). Mirror with `"breakdown low"`. **Daily-breakout variant on any anchor:**
-  pin the structure at 1d — `zone_1d is "breakout high"`, `dist_donchianHi_1d gte 0` (validated).
+- **Donchian / Turtle breakout** (`close > ta.highest(high, 20)[1]`) → `dist_donchianHiPrior crossesAbove 0`
+  over `DONCHIAN_UPPER_PRIOR × distance` (the breakout bar; `dist_donchianHiPrior gt 0` holds on every
+  close of the run) + `RVOL gte 1.5`; turtle exits = trend preset (trail from 1R, giveback 50). Mirror with
+  `dist_donchianLoPrior crossesBelow 0`. The same-bar rail (`dist_donchianHi`) includes the breakout bar's
+  own high, so it can never confirm a close-based break — do not AND it in. `zone is "breakout high"` reads
+  the prior-bar rail: it is the label form of the `dist_donchianHiPrior gt 0` state, holds on every close of
+  the run, and adds nothing to the crossing; `"breakdown low"` mirrors it.
+  **Daily-breakout variant on any anchor:** pin the rail at 1d — `dist_donchianHiPrior_1d crossesAbove 0`
+  (`gt 0` for the held state).
   **Literal previous-day levels are native**: `dist_PDH gte 0` composes directly. They are TIMELESS
   and take `{rel: 'anchor'}` — see `## Header grammar` in the skill body.
 - **ICT / SMC (FVG + order blocks)** → `STRUCT_ZONES` is the native zone engine: