@khalilgharbaoui/opencode-claude-code-plugin 0.53.2 → 0.53.4

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@khalilgharbaoui/opencode-claude-code-plugin",
-  "version": "0.53.2",
+  "version": "0.53.4",
   "description": "Claude Code CLI provider plugin for opencode",
   "homepage": "https://opencode-claude-code-plugin.dev/",
   "funding": {

package/skills/claude-code-plugin/SKILL.md

@@ -140,7 +140,7 @@ Defaults below describe normal headless opencode use when the key is absent.
 | `strictMcpConfig` | boolean | `false` | Headless `--strict-mcp-config`: use only explicitly supplied MCP configs, ignoring other MCP sources, not all settings/credentials/hooks. The interactive wrapper adds it whenever it passes MCP paths, independently of this option. |
 | `hotReloadMcp` | boolean | `true` | With bridging on, compare merged MCP config/status at turn start and respawn on drift, so a server enabled, disabled or finished connecting since the spawn reaches the model. Keeps the session via `--resume` on both transports. Acts only at a safe boundary: never during compaction, and never while a proxied call is pending, a turn is in flight or a plan-mode approval is outstanding. Logs the joined and left server names at INFO. One respawn per conversation per `CLAUDE_CODE_MCP_HOT_RELOAD_COOLDOWN_MS` (default 60000) so a flapping server cannot respawn every turn. Does not reload arbitrary provider options or watch explicit `mcpConfig` contents. |
 | `mcpConnectWaitMs` | number | `3000` | How long the first turn waits for MCP servers the host reports as still connecting before planning the spawn without them. Only opencode 2 reports that state (`pending`); opencode 1's status call blocks until every server decides, so this is a no-op there and costs one status call as before. `0` disables the wait; negative or non-numeric values fall back to the default. Aborting the turn ends the wait at once, and the turn then spawns nothing. A server slower than the budget is still bridged (pending is not read as disabled) and `hotReloadMcp` brings a later one in on the next turn. |
-| `proxyOpencodeMcpTools` | boolean | `false` | Route opencode's MCP-backed tools through opencode's executor instead of Claude's own `--mcp-config` child, so each call is permission-prompted and rendered as an opencode tool row. Default changed `true` to `false` here, with no behaviour change: at `true` it routed nothing, because discovery read opencode's tool registry, which never contains MCP tools. Discovery now reads the model tool set opencode passes the provider, verified live on opencode 1.18.31 / Claude Code 2.1.263. **Tell the user to set `strictMcpConfig: true` alongside it**: a server also present in Claude Code's own config is reached directly and the proxy is bypassed, which looks exactly like the option doing nothing. A routed call runs with the calling agent's permissions. Servers whose tools are not found stay on the direct bridge and log a warning. Inert with `bridgeOpencodeMcp: false`, which leaves no bridged server list to match names against. Do not promise exactly-once side effects across failures, retries or opencode versions; verify routing before using write-capable tools. |
+| `proxyOpencodeMcpTools` | boolean | `false` | Route opencode's MCP-backed tools through opencode's executor instead of Claude's own `--mcp-config` child, so each call is permission-prompted and rendered as an opencode tool row. Default changed `true` to `false` here, with no behaviour change: at `true` it routed nothing, because discovery read opencode's tool registry, which never contains MCP tools. Discovery now reads the model tool set opencode passes the provider, verified live on opencode 1.18.31 / Claude Code 2.1.263. **Tell the user to set `strictMcpConfig: true` alongside it**: a server also present in Claude Code's own config is reached directly and the proxy is bypassed, which looks exactly like the option doing nothing. A routed call runs with the calling agent's permissions. Per server: a tool in the agent's tool set means proxied; `connected` in opencode with none of its tools in the agent's set means left out of that spawn entirely (this is what keeps an `explore` subagent from starting its own copy of every MCP server and being handed servers opencode withheld from it); anything else keeps the direct bridge. One INFO line, `proxyOpencodeMcpTools: MCP servers outside this agent's tool set`, names the `withheld` and `bridged` lists. With the option off every enabled server is bridged into every spawn, subagents included: suggest turning it on when subagents start slowly or get MCP servers they should not have. Inert with `bridgeOpencodeMcp: false`, which leaves no bridged server list to match names against. Do not promise exactly-once side effects across failures, retries or opencode versions; verify routing before using write-capable tools. |
 | `proxyOpencodeTools` | string[] | `[]` | Forward explicitly named opencode tools (case-insensitive): V1 resolves registry ids; V2 resolves the current model tool snapshot and its actual JSON Schema, including synthesized Code Mode `execute`, without re-exposing tools absent from that snapshot. Covers plugin-declared tools such as DCP's `compress` and V2 Code Mode. Same broker as other proxies; collisions and unknown names warn. Explicit allowlist only, because calls run in opencode with the agent's permissions. `execute` grants access to the session's whole Code Mode catalog, not just MCP, and is refused by the read-only preset. |
 | `stripContextReminders` | boolean | `false` | Strip opencode-dcp `<dcp-system-reminder>` blocks from user/assistant message text, including the fresh-session rebuild. Only when no `compress` is proxied via `proxyTools` or `proxyOpencodeTools`; reachable compress makes it inert. Resolved from config, so a configured-but-unregistered name still counts as reachable. Leaves opencode's own `<system-reminder>` blocks alone. |
 | `multiStepContinuation` | boolean | `true` | Append a system-prompt hint to chain tool calls in one turn instead of stopping between subtasks. |
@@ -854,6 +854,16 @@ the opencode major, what decided it (the live `task` schema, a registry that did
 answer, or opencode 2 offering it unconditionally), and the background tasks this
 process has collected or cancelled. The gate is read while a turn plans its proxy tools,
 so a fresh process reports `Not read yet this process` until one message has been sent.
+It opens with `running now: N (of M started by this process)`: the answer to "how many
+subagents are working at once" when a user worries about overloading the machine or the
+usage window. It counts only background dispatches Claude made through this opencode
+process, uses `task_status`'s own running test, and never collects a result.
+Claude is told the same number: an accepted background dispatch's result gets one
+trailing line, `Background subagents running now: N (including this one).` (one line per
+`task_batch`, `(including the 2 just started)`). Foreground results and every other tool
+are unchanged. The lookup is bounded (four at a time, 500 ms in all) and the line is
+simply left out when it runs over or a child cannot be read, so a missing line is not a
+fault. There is no option for it.
 
 ### Let Claude load the user's opencode skills
 
@@ -1112,7 +1122,8 @@ at 200 characters, because its stdout is spliced into the model's context. The p
 never passes `--include-hook-events`, so only `SessionStart` (and `Setup`) hooks are
 reported at all; `cancelled` is not a failure, since an abort produces it.
 
-A **Background subagents** section is always printed: whether `background` was offered
+A **Background subagents** section is always printed: first `running now: N (of M
+started by this process)`, then whether `background` was offered
 to Claude and `task_status` / `task_cancel` registered, the opencode major, what decided
 it, and the background tasks this process collected or cancelled. It reads
 `Not read yet this process` until a turn has planned its proxy tools, which is not the