feat: selective tool proxying, session isolation, MCP bridging, and streaming fixes

.github/workflows/publish.yml

@@ -12,10 +12,11 @@ jobs:
       id-token: write
     steps:
       - uses: actions/checkout@v6
-      - uses: actions/setup-node@v4
+      - uses: actions/setup-node@v6
         with:
           node-version: 24
           registry-url: https://registry.npmjs.org
+      - run: npm install -g npm@latest
       - run: npm install
       - run: npm run build
       - name: Publish package

TODO.md

@@ -0,0 +1,82 @@
+# Deferred Checks
+
+## Ideas
+
+- 2026-09-06, maintainer: "maybe someday we still want to align it with plan mode of opencode maybe".
+  Deferred, not scheduled. Make `permissionMode: "plan"` follow opencode's own plan/build agent
+  instead of being a static provider option.
+
+  Cheaper than it looks, and the objection that killed it the first time does not apply:
+  the opencode agent is already part of the session key
+  (`...::ses_...::context=["claude-code-appical","build"]`), so plan and build turns already
+  run as separate `claude` processes. A Tab back to build would spawn one without the flag,
+  so a coupled design is not a one-way door the way the static option is.
+
+  What still argues against it, and what to re-check before building:
+  1. `"plan"` is only a name. Users define their own agents called plan, some of which write
+     plan documents into the repo, and forcing CLI plan mode would break those silently.
+     Any implementation needs an explicit opt-in rather than a name match.
+  2. The two disagree about how you leave. Claude Code expects an `ExitPlanMode` tool call
+     that headless `--print` never offers (measured on 2.1.258, probes recorded in AGENTS.md),
+     so the model searches for a tool it cannot find and narrates confusion. Re-run those
+     probes first: if a newer CLI offers `ExitPlanMode` headless, this objection dies and the
+     `planModeQuestion` bridge becomes reachable at the same time.
+  3. It buys little for the common config. opencode's plan mode already denies its own tools,
+     and `Bash`/`Edit`/`Write` are proxied by default, so the only gap it closes is Claude's
+     unproxied built-ins.
+
+  Shape if built: an explicit option (something like `planModePermission: "follow-agent"`),
+  never silent coupling. Do not start this without a user asking for it.
+
+- 2026-09-09, maintainer: "pin to appical but if limits hit switch to default is that possible?"
+  Asked while designing the `dev-support` agent, which must run on the appical account for
+  its per-profile MCP servers (Linear, Aikido, Sentry) but should survive that account's
+  spend limit. Today it is not possible: the account is the provider, it is fixed for the
+  life of the `claude` process, and a `forceModel` agent inherits whoever invoked it. When
+  the limit error arrives ("You've hit your individual spend limit", resets at a stated
+  time) the turn simply fails and the human restarts on the other account.
+
+  Shape if built: an optional `fallbackAccounts: ["default"]` per agent or per provider.
+  On a recognised limit error the plugin respawns the session on the next account with
+  the same model, effort and cwd, and says so in the turn. Things to check first:
+  1. The failover account may lack the MCP servers the run depends on; the resumed turn
+     would need to re-announce its tool list, or the option should refuse to fail over when
+     the tool sets differ.
+  2. Session key includes the account, so a failover is a new process and loses in-process
+     state; opencode's own transcript is what carries over, which is probably enough.
+  3. Detection must match the CLI's limit message exactly, not any 4xx, or a transient
+     error would silently move billing to another account.
+
+## Dropped
+
+- Dropped 2026-09-06 at the user's request: live observation of `idleProcessTimeoutMs: 900000`. The 15-minute eviction and subsequent resume remain unverified in the user's window; no test is planned.
+
+## Backlog
+
+## Deferred decisions
+
+- 2026-09-20: The maintainer chose "later" for adding the Appical MCP project block
+  to `Appical.IaC`, `Cl-nica-Aurora---Player-team`, `Manager-toolkit`,
+  `NOW-player-web` and `workshop-sep-2026`.
+- 2026-09-20: The maintainer chose "later" for choosing a Slack authentication
+  strategy. The current global server can still pay a 30-second 1Password unlock
+  timeout on startup.
+- 2026-09-20: The maintainer chose "later" for completing opencode's separate,
+  global Linear OAuth authentication.
+
+## Open from you
+
+Questions the maintainer still owes an answer on. Written here the turn they are
+raised, so they survive context compaction; removed when answered, done or dropped.
+
+No pending questions.
+
+## In progress
+
+- 2026-09-20: two lanes dispatched after the maintainer said `go` to every recommendation.
+  Lane 1, account failover: on whenever more than one account is configured; a synthetic
+  `question` tool-call on a recognised limit rejection; the pick applies inside the same
+  opencode turn; sticky for the limited account until its reset time; subagents follow
+  the parent's pick and never ask; a dismissed form ends the turn as the rate-limit error
+  does today. Lane 2, small cleanup: stale plan-mode comment, visible result-fallback
+  timeout, bounded serve-mode maps, silent-turn nudge.

e2e-claude-session-bun.ts

@@ -0,0 +1,97 @@
+/**
+ * E2E for src/claude-session-bun.ts against REAL claude over Bun's native
+ * ConPTY. Plain runnable script (not part of the offline suite; spawns claude,
+ * needs a logged-in subscription). Run:
+ *
+ *   bun e2e-claude-session-bun.ts
+ *
+ * Milestone proof: multiple messages in one live chat session, context retained
+ * across turns (subscription interactive path), with prompt-cache reuse.
+ */
+import { ClaudeSession, askOnce } from "./src/claude-session-bun.js"
+
+const TERMINAL = new Set(["end_turn", "stop_sequence", "max_tokens"])
+let failures = 0
+function check(cond: boolean, msg: string) {
+  if (cond) console.log("  PASS:", msg)
+  else {
+    failures++
+    console.log("  FAIL:", msg)
+  }
+}
+
+async function main() {
+  console.log("=== e2e claude-session-bun (Bun native ConPTY) ===")
+  console.log(
+    "bun:",
+    Bun.version,
+    "| Bun.Terminal:",
+    typeof (Bun as any).Terminal,
+  )
+
+  console.log("\n[A] one-shot 2+2")
+  const r = await askOnce("What is 2+2? Reply with only the number.", {
+    settingSources: "",
+  })
+  console.log("  reply:", JSON.stringify(r.text), "stop:", r.stopReason)
+  check(TERMINAL.has(r.stopReason ?? ""), "one-shot terminal stop")
+  check(/4/.test(r.text), "one-shot says 4")
+
+  console.log("\n[B] multi-turn: 3 messages, one live process")
+  const s = new ClaudeSession({ settingSources: "" })
+  await s.start()
+  try {
+    const t1 = await s.ask(
+      "Remember two facts for this conversation: my favorite number is 42 and my favorite color is teal. Reply with exactly: OK",
+    )
+    console.log("  turn1:", JSON.stringify(t1.text), "stop:", t1.stopReason)
+    check(TERMINAL.has(t1.stopReason ?? ""), "turn1 terminal stop")
+
+    const t2 = await s.ask(
+      "What is my favorite number? Reply with only the number.",
+    )
+    console.log(
+      "  turn2:",
+      JSON.stringify(t2.text),
+      "stop:",
+      t2.stopReason,
+      "cacheRead:",
+      t2.cacheReadTokens,
+      "eph1h:",
+      t2.ephemeral1hTokens,
+    )
+    check(TERMINAL.has(t2.stopReason ?? ""), "turn2 terminal stop")
+    check(/42/.test(t2.text), "turn2 recalls 42 (context retained across turns)")
+
+    const t3 = await s.ask(
+      "What is my favorite color? Reply with only the word.",
+    )
+    console.log(
+      "  turn3:",
+      JSON.stringify(t3.text),
+      "stop:",
+      t3.stopReason,
+      "cacheRead:",
+      t3.cacheReadTokens,
+    )
+    check(TERMINAL.has(t3.stopReason ?? ""), "turn3 terminal stop")
+    check(/teal/i.test(t3.text), "turn3 recalls teal (context retained across turns)")
+
+    check(
+      t2.cacheReadTokens > 0 || t3.cacheReadTokens > 0,
+      "prompt-cache reuse on later turns (1h tier)",
+    )
+  } finally {
+    s.dispose()
+  }
+
+  console.log(
+    `\n=== ${failures === 0 ? "ALL PASS" : failures + " FAILURE(S)"} ===`,
+  )
+  process.exit(failures === 0 ? 0 : 1)
+}
+
+main().catch((e) => {
+  console.error("FATAL:", e?.stack ?? e)
+  process.exit(2)
+})

jsr.json

@@ -1,5 +1,5 @@
 {
-  "name": "@unixfox/opencode-claude-code-plugin",
+  "name": "@khalilgharbaoui/opencode-claude-code-plugin",
   "version": "0.1.0",
   "license": "MIT",
   "exports": "./mod.ts"

package.json

@@ -1,7 +1,8 @@
 {
-  "name": "opencode-claude-code-plugin",
-  "version": "0.1.2",
+  "name": "@khalilgharbaoui/opencode-claude-code-plugin",
+  "version": "0.24.0",
   "description": "Claude Code CLI provider plugin for opencode",
+  "author": "Khalil Gharbaoui",
   "type": "module",
   "main": "dist/index.js",
   "module": "dist/index.js",
@@ -13,20 +14,24 @@
     }
   },
   "files": [
-    "dist"
+    "dist",
+    "skills"
   ],
   "scripts": {
     "build": "tsup",
     "dev": "tsup --watch",
-    "typecheck": "tsc --noEmit"
+    "typecheck": "tsc --noEmit",
+    "test": "tsx --test test-bridge.ts test-broker.ts test-proxy-mcp.ts test-proxy-task.ts test-auto-continue.ts test-has-new-user-content.ts test-get-claude-user-message.ts test-logger.ts test-cli-args.ts test-session-manager.ts test-compaction-model.ts test-tool-mapping.ts test-cwd-resolution.ts test-todo-ledger.ts test-session-affinity.ts test-config-models.ts test-ask-user-question.ts test-claude-session-wrapper.ts test-spawn-env.ts test-respawn.ts test-startup-diagnostics.ts test-subagent-hint.ts test-exit-plan-mode-question.ts test-compress-tool.ts test-agent-models.ts test-side-question.ts test-btw-command.ts test-effort-sessions.ts test-tool-block-index.ts test-skill-bridge.ts test-turn-stats.ts test-cli-events.ts test-cli-events-stream.ts test-result-fallback.ts test-doctor.ts test-configure-skill.ts test-unattended-replay.ts test-process-lifecycle.ts test-account-failover.ts"
   },
   "dependencies": {
-    "@ai-sdk/provider": "^2.0.0",
-    "@ai-sdk/provider-utils": "^2.0.0"
+    "@ai-sdk/provider": "^3.0.8",
+    "@ai-sdk/provider-utils": "^3.0.8",
+    "jsonc-parser": "3.3.1"
   },
   "devDependencies": {
     "@types/node": "^25.5.0",
     "tsup": "^8.0.0",
+    "tsx": "^4.22.4",
     "typescript": "^5.7.0"
   },
   "keywords": [
@@ -39,6 +44,9 @@
   "license": "MIT",
   "repository": {
     "type": "git",
-    "url": "https://github.com/unixfox/opencode-claude-code-plugin"
+    "url": "git+https://github.com/khalilgharbaoui/opencode-claude-code-plugin.git"
+  },
+  "publishConfig": {
+    "access": "public"
   }
 }