feat(mcp-client): auto-reconnect with bounded backoff after transport close

A per-instance connection supervisor restarts the original server config
with exponential backoff when the transport closes, re-runs tool discovery
on success, and atomically replaces the previous generation. Default policy
retries for ~2.5 minutes (10 attempts, 500ms→30s doubling) before giving up
and unregistering the server's tools.

New config block reconnect { enabled, initialDelayMs, maxDelayMs, maxAttempts }
on both transports; misconfiguration fails plugin load. A connection that
survives past the stability window (maxDelayMs) resets the attempt budget,
so occasional crashes recover indefinitely while a crash loop still exhausts
the cap.

Integrates with the upstream failOnStartupError: the initial sync uses
registrationFailure:'throw' when that flag is set so a squatted namespace
still rejects activation.

Fixes #1746

docs/config-catalog.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/config-catalog.md
-config-catalog.md: 51c6ae46eeca1279390c9d9315a6161edd2de618
-config-catalog.zh.md: dc93f5b4b55b07c52c58405ba4793c2c6eca28df
+config-catalog.md: 76f1d0344d3e172416af36eff27bd4cb8544ed4a
+config-catalog.zh.md: d5752a1922d8b8b2e70f055ec05117ed20c445bf

docs/config-catalog.md

@@ -1069,6 +1069,8 @@ export interface StdioConfig {
   toolCallTimeoutMs: number
   /** Fail plugin activation when the initial connection or tool synchronization fails. */
   failOnStartupError: boolean
+  /** Automatic reconnect policy after a lost connection; omission uses the defaults. */
+  reconnect?: ReconnectConfig
 }
 
 /** Config for connecting to an MCP server over Streamable HTTP (SSE). */
@@ -1089,10 +1091,24 @@ export interface StreamableHttpConfig {
   toolCallTimeoutMs: number
   /** Fail plugin activation when the initial connection or tool synchronization fails. */
   failOnStartupError: boolean
+  /** Automatic reconnect policy after a lost connection; omission uses the defaults. */
+  reconnect?: ReconnectConfig
+}
+
+/** Automatic reconnect policy for one MCP server connection. */
+export interface ReconnectConfig {
+  /** Reconnect automatically after a lost connection (default true). */
+  enabled?: boolean
+  /** First reconnect delay in milliseconds; doubles per consecutive failed attempt (default 500). */
+  initialDelayMs?: number
+  /** Backoff ceiling in milliseconds; also the uptime after which the attempt budget resets (default 30000). */
+  maxDelayMs?: number
+  /** Consecutive failed attempts per outage before giving up for good (default 10). */
+  maxAttempts?: number
 }
 ```
 
-Source: [`packages/mcp/mcp-client/src/index.ts:100`](../packages/mcp/mcp-client/src/index.ts)
+Source: [`packages/mcp/mcp-client/src/index.ts:104`](../packages/mcp/mcp-client/src/index.ts)
 
 ## `@deepseek-ai/dsh-permission`
 

docs/config-catalog.zh.md

@@ -1071,6 +1071,8 @@ export interface StdioConfig {
   toolCallTimeoutMs: number
   /** Fail plugin activation when the initial connection or tool synchronization fails. */
   failOnStartupError: boolean
+  /** Automatic reconnect policy after a lost connection; omission uses the defaults. */
+  reconnect?: ReconnectConfig
 }
 
 /** Config for connecting to an MCP server over Streamable HTTP (SSE). */
@@ -1091,6 +1093,20 @@ export interface StreamableHttpConfig {
   toolCallTimeoutMs: number
   /** Fail plugin activation when the initial connection or tool synchronization fails. */
   failOnStartupError: boolean
+  /** Automatic reconnect policy after a lost connection; omission uses the defaults. */
+  reconnect?: ReconnectConfig
+}
+
+/** Automatic reconnect policy for one MCP server connection. */
+export interface ReconnectConfig {
+  /** Reconnect automatically after a lost connection (default true). */
+  enabled?: boolean
+  /** First reconnect delay in milliseconds; doubles per consecutive failed attempt (default 500). */
+  initialDelayMs?: number
+  /** Backoff ceiling in milliseconds; also the uptime after which the attempt budget resets (default 30000). */
+  maxDelayMs?: number
+  /** Consecutive failed attempts per outage before giving up for good (default 10). */
+  maxAttempts?: number
 }
 ```
 

docs/module-graph.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/module-graph.md
-module-graph.md: 6763ca6e84a5cc2e5e776a56e5cfc20b710017aa
-module-graph.zh.md: 339345b39a8225c34ecf0ba73efff34d4b940046
+module-graph.md: 78beee5f9311ae4c75a9ac291d1c7882914bfb8f
+module-graph.zh.md: 6b71b0997ce542d53285cd815277556dba46b353

docs/module-graph.md

@@ -920,6 +920,7 @@ flowchart TD
   pkg_mcp_client --> pkg_invariants
   pkg_mcp_client --> pkg_llm
   pkg_mcp_client --> pkg_subprocess
+  pkg_mcp_client --> pkg_timeout
   pkg_mcp_client --> pkg_tools
   pkg_tool_bash_persistent --> pkg_agent
   pkg_tool_bash_persistent --> pkg_invariants
@@ -1403,7 +1404,7 @@ flowchart TD
 | [`timeout-policy`](../packages/guard/timeout-policy) | `guard` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`tool-ask-user`](../packages/interaction/tool-ask-user) | `interaction` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tools`](../packages/core/tools), [`user-interaction`](../packages/interaction/user-interaction) |
 | [`tool-lsp`](../packages/lsp/tool-lsp) | `lsp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`system-prompt`](../packages/core/system-prompt), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
-| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`tools`](../packages/core/tools) |
+| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`tool-bash-persistent`](../packages/pty/tool-bash-persistent) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`tool-pty`](../packages/pty/tool-pty) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`pty`](../packages/pty/pty), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
 | [`tool-cordis`](../packages/self-modification/tool-cordis) | `self-modification` | [`invariants`](../packages/support/invariants), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) |

docs/module-graph.zh.md

@@ -922,6 +922,7 @@ flowchart TD
   pkg_mcp_client --> pkg_invariants
   pkg_mcp_client --> pkg_llm
   pkg_mcp_client --> pkg_subprocess
+  pkg_mcp_client --> pkg_timeout
   pkg_mcp_client --> pkg_tools
   pkg_tool_bash_persistent --> pkg_agent
   pkg_tool_bash_persistent --> pkg_invariants
@@ -1405,7 +1406,7 @@ flowchart TD
 | [`timeout-policy`](../packages/guard/timeout-policy) | `guard` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`tool-ask-user`](../packages/interaction/tool-ask-user) | `interaction` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tools`](../packages/core/tools), [`user-interaction`](../packages/interaction/user-interaction) |
 | [`tool-lsp`](../packages/lsp/tool-lsp) | `lsp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`system-prompt`](../packages/core/system-prompt), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
-| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`tools`](../packages/core/tools) |
+| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`tool-bash-persistent`](../packages/pty/tool-bash-persistent) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`tool-pty`](../packages/pty/tool-pty) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`pty`](../packages/pty/pty), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
 | [`tool-cordis`](../packages/self-modification/tool-cordis) | `self-modification` | [`invariants`](../packages/support/invariants), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) |