@battlegrid/mcp-server 32.0.104 → 32.0.106
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md
CHANGED
|
@@ -38,6 +38,42 @@ Seeing package `31.x` alongside handshake `battlegrid@33.x` — the package **be
|
|
|
38
38
|
|
|
39
39
|
**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.
|
|
40
40
|
|
|
41
|
+
## Contract history — v182 (a Developing read states when it was read)
|
|
42
|
+
|
|
43
|
+
**v182 is MAJOR: a published output field is removed.** No input schema moves, and everything v181 accepted is still
|
|
44
|
+
accepted.
|
|
45
|
+
|
|
46
|
+
Since v175 a Developing read decides on the higher-timeframe bar as it stood at one minute: the decided bar's final
|
|
47
|
+
minute on a decided bar, the newest folded minute at the latest values. v182 serves that minute as the read's
|
|
48
|
+
**cut-off**: an ISO instant, the close of the newest source minute folded into the bar in progress. On a decided bar
|
|
49
|
+
that is the decided bar's close.
|
|
50
|
+
|
|
51
|
+
### Removed output — the reason v182 is MAJOR
|
|
52
|
+
|
|
53
|
+
- **A condition outcome loses `developingRead` and serves `developingAsOf` in its place.** `developingAsOf` is the
|
|
54
|
+
cut-off of the outcome's Developing reads, the earliest across its operands, or `null` where it read no bar in
|
|
55
|
+
progress. This applies wherever an outcome is served: `preview_strategy_report`'s detailed
|
|
56
|
+
`authoring.conditionOutcomes`, `get_radar_close_decisions`, `list_gate_blocks`, `preview_radar_resolution` and
|
|
57
|
+
`get_agent_coin_qualification`. Read `developingAsOf !== null` where you read `developingRead`. It is narrower:
|
|
58
|
+
a Developing column that read a bar its own close completed, and a fixed-horizon change (`chg4h` on a `1h`
|
|
59
|
+
strategy), read no bar in progress and serve `null`. A record written before v182 serves `null`.
|
|
60
|
+
- **The authoring inventory keeps `developingRead`.** On a report condition column, a scalar vocabulary entry and an
|
|
61
|
+
anchor relation it still states which bar a header reads, before anything is read.
|
|
62
|
+
|
|
63
|
+
### Added output
|
|
64
|
+
|
|
65
|
+
- **`get_signal_log` and `get_public_agent_signal_log_detail`:** each condition outcome serves `developingAsOf`,
|
|
66
|
+
`null` on a row written before v182.
|
|
67
|
+
- **Every trade condition register** serves `developingAsOf` on each condition, beside `provisional`.
|
|
68
|
+
- **A rendered section column** serves an optional `asOf`, present only where a row it renders read a bar in progress:
|
|
69
|
+
the earliest cut-off across its rows. This is served by `preview_strategy_report`, `get_market_context`,
|
|
70
|
+
`get_context_sources_preview`, `get_context_source_full_preview` and the signal logs' stored report.
|
|
71
|
+
|
|
72
|
+
### Changed text
|
|
73
|
+
|
|
74
|
+
- **The trade condition glossary** defines `developingAsOf`, and **the report columns glossary** defines `asOf`. Both
|
|
75
|
+
warn that volume and range on a bar in progress cover only the part of it elapsed by the cut-off.
|
|
76
|
+
|
|
41
77
|
## Contract history — v181 (price is the base of every spread over another reading)
|
|
42
78
|
|
|
43
79
|
**v181 is MAJOR: a spread that takes a reference price as its second side over another reading is refused.** No
|
package/dist/index.d.ts
CHANGED
|
@@ -47,7 +47,7 @@ import { Client, StreamableHTTPClientTransport } from '@modelcontextprotocol/cli
|
|
|
47
47
|
* being asked. Move it for a change to THIS package — a proxy fix, a dependency bump, a docs
|
|
48
48
|
* correction. Never move it to track the server.
|
|
49
49
|
*/
|
|
50
|
-
export declare const PACKAGE_VERSION = "32.0.
|
|
50
|
+
export declare const PACKAGE_VERSION = "32.0.106";
|
|
51
51
|
export declare const DEFAULT_URL = "https://mcp.battlegrid.trade/mcp";
|
|
52
52
|
export interface EnvConfig {
|
|
53
53
|
apiKeys: string[];
|
package/dist/index.js
CHANGED
|
@@ -49,7 +49,7 @@ import { Client, SdkHttpError, StreamableHTTPClientTransport } from '@modelconte
|
|
|
49
49
|
* being asked. Move it for a change to THIS package — a proxy fix, a dependency bump, a docs
|
|
50
50
|
* correction. Never move it to track the server.
|
|
51
51
|
*/
|
|
52
|
-
export const PACKAGE_VERSION = '32.0.
|
|
52
|
+
export const PACKAGE_VERSION = '32.0.106';
|
|
53
53
|
export const DEFAULT_URL = 'https://mcp.battlegrid.trade/mcp';
|
|
54
54
|
const MAX_RETRIES = 3;
|
|
55
55
|
const RETRY_DELAYS_MS = [2000, 4000, 8000];
|
package/package.json
CHANGED
package/skills/EXPORT.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"generator": "battlegrid-app/server/scripts/export-mcp-skills.mjs",
|
|
3
|
-
"contractVersion": "
|
|
3
|
+
"contractVersion": "182.3.1",
|
|
4
4
|
"files": {
|
|
5
5
|
"battlegrid-agent-management/SKILL.md": "f0dde6b2f3dfbb340cd9bf785dc514f8f6c36cb1118be75df17016de0980ef56",
|
|
6
6
|
"battlegrid-agent-management/references/agent-stage-examples.md": "dffcc353d61dfc7b5bb6a2b3077fc6bf8c760a34c287cafb3b59b99306f24195",
|
|
@@ -13,10 +13,10 @@
|
|
|
13
13
|
"battlegrid-radar-deployment/SKILL.md": "fc170e09efe674519d8b5d2dbe3b926de6b24c5f1d8d1f90b706b2ea28a26cf0",
|
|
14
14
|
"battlegrid-radar-deployment/references/arena-stage-examples.md": "0987397c848738881e1d5a871b349f29389e98b2746f92491198ff1297408387",
|
|
15
15
|
"battlegrid-radar-deployment/references/radar-stage-examples.md": "08658ccf548bd680633e75813196e52dd19c2c30ffff37883337b017e461efcd",
|
|
16
|
-
"battlegrid-strategy-authoring/SKILL.md": "
|
|
16
|
+
"battlegrid-strategy-authoring/SKILL.md": "f3df63011e185032973985d002b70fbc06db4290f7e9ea1ac79be6640ef96157",
|
|
17
17
|
"battlegrid-strategy-authoring/references/strategy-stage-examples.md": "0eb41edd013f95092f5822a922c7cdd731584892ed90da575dbb65c93a1a00b6",
|
|
18
18
|
"battlegrid-strategy-doctor/SKILL.md": "aa8c7b9b8dde043c1e3d027c2b370979ea18b45e0f7757e77164bd0fffbe8236",
|
|
19
|
-
"battlegrid-strategy-examples/SKILL.md": "
|
|
19
|
+
"battlegrid-strategy-examples/SKILL.md": "90d61be4485e4b6f135f287c99a7ae3089cf1c0ccafb96b95e397bf09452219f",
|
|
20
20
|
"battlegrid-strategy-examples/references/playbooks.md": "a08e5dd43a2fd3ff7b9eac7833331464edf6a533845824b80953e1e24422c48c",
|
|
21
21
|
"battlegrid-strategy-examples/references/recipes.md": "e24483ec52cbcedba08ed6fa7f2a28b0fde170b2d4b1876162d180538cd789f2",
|
|
22
22
|
"battlegrid-strategy-examples/references/tradingview-ports.md": "8eddbe31d445080cf772c357f0608c912b620583c7bc62de71ddaf98c10c8820",
|
|
@@ -358,13 +358,16 @@ is the **trail objective**, which sets how far the runner's trail measures and e
|
|
|
358
358
|
raise restates the menu without it. The `strategy-examples` skill's *Trade levels* section carries the menu's
|
|
359
359
|
options, how pairs are built and what the save refuses. Before committing a TRADE_LEVEL_POLICY change, show the
|
|
360
360
|
player `preview_strategy_trade_levels({ coinTicker, source: { kind: "DRAFT", strategyId, draftVersion } })`: every
|
|
361
|
-
stop with its verdict and
|
|
361
|
+
stop with its verdict and the ATR distance it was judged at (an ATR option's own multiple, so a stop on a bound is
|
|
362
|
+
kept), the pairs that survive with each target's price and close %, each
|
|
362
363
|
runner's trail distance in ATR and R, the pairs refused and why, and the reachable stop band, per direction. Show it
|
|
363
364
|
for an ENTRY change too: under a level trigger each direction's `entry` says where the order rests on that coin now
|
|
364
|
-
(the level, the placed price, its side of price
|
|
365
|
-
|
|
366
|
-
|
|
367
|
-
|
|
365
|
+
(the level, the placed price, its side of price, whether a stop or a limit rests, how far it sits from price in percent
|
|
366
|
+
and in ATR, and how many minutes it stays valid), and the trade is built from that placed price; a verdict that does
|
|
367
|
+
not rest (`WRONG_SIDE` with the side it needed, `LEVEL_UNREAD`, `ATR_UNAVAILABLE`) means the agent would not place that
|
|
368
|
+
trade on that coin now. An R
|
|
369
|
+
target there is measured from its own pair's stop; `minRiskRewardRatio` judges each pair's plan risk-reward, stated to
|
|
370
|
+
three decimals. The same holds for a condition: CONDITIONS carries every condition, each with its
|
|
368
371
|
`required` flag and verdict as they stand. Never set `required` or a verdict from memory, and never
|
|
369
372
|
change either unless the player asked: a wrong value there is how a building block silently becomes
|
|
370
373
|
a mandatory trade gate, or a gate silently disappears.
|
|
@@ -945,11 +945,16 @@ that target is the **trail objective** — it places no order and only sets how
|
|
|
945
945
|
`[2R closing 50%, 6R closing 0%]` banks half at 2R and trails the rest with a trail sized to 6R. One target closing
|
|
946
946
|
100% is today's single take-profit.
|
|
947
947
|
|
|
948
|
-
A level reference is the same shape the entry axis names, and must be a level the report yields.
|
|
948
|
+
A level reference is the same shape the entry axis names, and must be a level the report yields. A nearest level — a
|
|
949
|
+
structure-zone edge or midpoint, a liquidity pool, a naked POC or a single print — used as a stop or target is the
|
|
950
|
+
level's own pick among those on that option's side of the entry: the report's level whenever that one is usable there,
|
|
951
|
+
otherwise the next of its kind beyond the entry, and the preview's stop row shows the reading a level stop was built
|
|
952
|
+
from (`levelReading`). At each decision the
|
|
949
953
|
platform pairs every stop with every exit plan and prices each target on the decided bar beside that stop. It drops a
|
|
950
954
|
pair whose stop is not on the loss side of entry, a stop tighter than `minStopLossAtrMultiple` or wider than
|
|
951
|
-
`maxStopLossAtrMultiple` (or the 5×ATR cap)
|
|
952
|
-
|
|
955
|
+
`maxStopLossAtrMultiple` (or the 5×ATR cap) — judged in ATR multiples, an ATR option at its own multiple, so a stop
|
|
956
|
+
authored on a bound (`ATR 1.5` beside a 1.5 floor) is always kept — a plan whose targets do not run away from entry in
|
|
957
|
+
plan order beside that stop, a pair whose plan risk-reward, stated to three decimals, is under `minRiskRewardRatio`, and — for an agent — a plan one of whose target
|
|
953
958
|
legs would fall under the exchange's minimum order value at the smallest order the agent can place. A level with no
|
|
954
959
|
reading on the bar drops the plans that name it; nothing is stretched, merged or substituted. Pairs that land on the
|
|
955
960
|
same stop, target prices and shares are one setup naming every option and plan that made it. The agent chooses one
|
|
@@ -959,7 +964,9 @@ setup; a one-entry list is a fixed choice.
|
|
|
959
964
|
stop|` from entry for the stop it is paired with, so 2R beside a 2×ATR stop is twice as far as 2R beside a 1×ATR stop.
|
|
960
965
|
A plan's risk-reward is each share at its target's distance plus the runner at the distance of the last target that
|
|
961
966
|
closes a share, over the stop's risk; a trail objective adds nothing. `[1R closing 50%, 3R closing 50%]` pays 2.0 and
|
|
962
|
-
`[1R closing 50%]` pays 1.0.
|
|
967
|
+
`[1R closing 50%]` pays 1.0. A risk-reward is stated to three decimals, the precision each setup records, and the
|
|
968
|
+
editor, the save and every pair judge that one figure: `[1.4R closing 75%, 1.8R closing 25%]` is 1.5 and meets a 1.5
|
|
969
|
+
minimum. An all-R plan has the same risk-reward beside every stop, so the save refuses one below
|
|
963
970
|
`minRiskRewardRatio` (it could never trade) rather than dropping it per trade; a plan's early target may sit below
|
|
964
971
|
the minimum when the plan as a whole clears it.
|
|
965
972
|
|