feat(opencode): add plan mode, reasoning effort, and status telemetry (#688)

* feat(opencode): support plan mode

* feat(opencode): support reasoning effort

* feat(opencode): surface context usage in web

Bridge OpenCode ACP usage updates into the existing token-count pipeline so the web status bar can show live context and cache information without a separate UI path.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(opencode): restrict plan mode to remote, rollback reasoning effort on failure

- Block local OpenCode plan startup (tools not enforced in local path)
- Allow remote OpenCode plan only (ACP permission handler denies tools)
- Guard web /permission-mode endpoint for local OpenCode plan sessions
- Rollback session reasoning effort when OpenCode rejects set_config_option
- Wire rollback callback through opencodeLoop to runOpencode closure
- Add tests: local plan rejected, remote plan allowed, web guard, effort rollback

* fix(web): auto-retry OpenCode models query to populate model selector without refresh

- Retry early failures (RPC may still be registering on new sessions)
- Poll briefly until availableModels is non-empty
- Stop polling once model options are discovered
- Add tests for retry/poll/stop policy

* fix(opencode): cap model discovery polling

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

web/src/chat/normalize.test.ts

@@ -641,6 +641,42 @@ describe('normalizeDecryptedMessage', () => {
         })
     })
 
+    it('normalizes token_count payloads with explicit contextTokens', () => {
+        const message = makeMessage({
+            role: 'agent',
+            content: {
+                type: 'codex',
+                data: {
+                    type: 'token_count',
+                    info: {
+                        total: {
+                            inputTokens: 8_119,
+                            outputTokens: 2,
+                            cachedInputTokens: 5_760,
+                            thoughtTokens: 11,
+                            totalTokens: 13_892
+                        },
+                        contextTokens: 13_879,
+                        modelContextWindow: 65_536
+                    }
+                }
+            }
+        })
+
+        const normalized = normalizeDecryptedMessage(message)
+
+        expect(normalized).toMatchObject({
+            role: 'event',
+            usage: {
+                input_tokens: 8119,
+                output_tokens: 2,
+                cache_read_input_tokens: 5760,
+                context_tokens: 13879,
+                context_window: 65536
+            }
+        })
+    })
+
     it('normalizes Codex context_compacted as a compact event', () => {
         const message = makeMessage({
             role: 'agent',

web/src/chat/normalizeAgent.ts

@@ -88,7 +88,12 @@ function normalizeCodexTokenUsage(value: unknown, data?: Record<string, unknown>
             ?? usageSource.cacheReadInputTokens
             ?? usageSource.cache_read_input_tokens
         ) ?? undefined,
-        context_tokens: inputTokens,
+        context_tokens: asNumber(
+            info.contextTokens
+            ?? info.context_tokens
+            ?? usageSource.contextTokens
+            ?? usageSource.context_tokens
+        ) ?? inputTokens,
         context_window: asNumber(info.modelContextWindow ?? info.model_context_window) ?? undefined,
         thread_id: asString(
             data?.thread_id