fix(athena): address 5 audit findings — remove harmful thinking config, add error handling, improve tests

- Remove applyModelThinkingConfig and all callers (OpenCode handles thinking natively)

- Add try/catch error handling to prepare_council_prompt filesystem operations

- Add mode input validation to prepare_council_prompt tool

- Add 2 missing placeholder test cases (RETRY_FAILED_IF_OTHERS_FINISHED, CANCEL_RETRYING_ON_QUORUM)

- Remove redundant 'Do NOT use TodoWrite' prompt section from council member agent

src/agents/athena/agent.ts

@@ -1,7 +1,6 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
 import type { AgentMode, AgentPromptMetadata } from "../types"
 import { createAgentToolRestrictions } from "../../shared/permission-compat"
-import { applyModelThinkingConfig } from "./model-thinking-config"
 
 const MODE: AgentMode = "primary"
 
@@ -326,6 +325,6 @@ export function createAthenaAgent(model: string): AgentConfig {
     color: "#1F8EFA",
   }
 
-  return applyModelThinkingConfig(base, model)
+  return base
 }
 createAthenaAgent.mode = MODE

src/agents/athena/athena-config-injection.test.ts

@@ -21,6 +21,14 @@ describe("Athena prompt config injection placeholders", () => {
       it("#then contains timeout reference with 30000", () => {
         expect(athenaConfig.prompt).toContain("30000")
       })
+
+      it("#then contains RETRY_FAILED_IF_OTHERS_FINISHED placeholder", () => {
+        expect(athenaConfig.prompt).toContain("{RETRY_FAILED_IF_OTHERS_FINISHED}")
+      })
+
+      it("#then contains CANCEL_RETRYING_ON_QUORUM placeholder", () => {
+        expect(athenaConfig.prompt).toContain("{CANCEL_RETRYING_ON_QUORUM}")
+      })
     })
   })
 })

src/agents/athena/council-member-agent.ts

@@ -1,7 +1,6 @@
 import type { AgentConfig } from "@opencode-ai/sdk"
 import type { AgentMode } from "../types"
 import { createAgentToolAllowlist } from "../../shared"
-import { applyModelThinkingConfig } from "./model-thinking-config"
 
 const MODE: AgentMode = "subagent"
 
@@ -57,12 +56,7 @@ You MUST wrap your final analysis in <COUNCIL_MEMBER_RESPONSE> tags. This is how
 </COUNCIL_MEMBER_RESPONSE>
 \`\`\`
 
-If you do not wrap your response in these tags, your analysis will not be included in the synthesis.
+If you do not wrap your response in these tags, your analysis will not be included in the synthesis.`
-
-## CRITICAL: Do NOT use TodoWrite
-- Do NOT create todos or task lists
-- Do NOT use the TodoWrite tool under any circumstances
-- Simply report your findings directly in your response`
 
 export const COUNCIL_SOLO_ADDENDUM = `
 ## Solo Analysis Mode
@@ -129,6 +123,6 @@ export function createCouncilMemberAgent(model: string): AgentConfig {
     ...restrictions,
   }
 
-  return applyModelThinkingConfig(base, model)
+  return base
 }
 createCouncilMemberAgent.mode = MODE

src/agents/athena/index.ts

@@ -1,3 +1,2 @@
 export { createAthenaAgent, ATHENA_PROMPT_METADATA } from "./agent"
 export { createCouncilMemberAgent, COUNCIL_MEMBER_PROMPT, COUNCIL_SOLO_ADDENDUM, COUNCIL_DELEGATION_ADDENDUM } from "./council-member-agent"
-export { applyModelThinkingConfig } from "./model-thinking-config"

src/agents/athena/model-thinking-config.test.ts

@@ -1,81 +0,0 @@
-import { describe, expect, test } from "bun:test"
-import type { AgentConfig } from "@opencode-ai/sdk"
-import { applyModelThinkingConfig } from "./model-thinking-config"
-
-const BASE_CONFIG: AgentConfig = {
-  name: "test-agent",
-  description: "test",
-  model: "anthropic/claude-opus-4-6",
-  temperature: 0.1,
-}
-
-describe("applyModelThinkingConfig", () => {
-  describe("#given a GPT model", () => {
-    test("#then returns reasoningEffort medium", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "gpt-5.2")
-      expect(result).toEqual({ ...BASE_CONFIG, reasoningEffort: "medium" })
-    })
-
-    test("#then returns reasoningEffort medium for openai-prefixed model", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "openai/gpt-5.2")
-      expect(result).toEqual({ ...BASE_CONFIG, reasoningEffort: "medium" })
-    })
-  })
-
-  describe("#given an Anthropic model", () => {
-    test("#then returns thinking config with budgetTokens 32000", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "anthropic/claude-opus-4-6")
-      expect(result).toEqual({
-        ...BASE_CONFIG,
-        thinking: { type: "enabled", budgetTokens: 32000 },
-      })
-    })
-  })
-
-  describe("#given a Google model", () => {
-    test("#then returns base config unchanged", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "google/gemini-3-pro")
-      expect(result).toBe(BASE_CONFIG)
-    })
-  })
-
-  describe("#given a Kimi model", () => {
-    test("#then returns base config unchanged", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "kimi/kimi-k2.5")
-      expect(result).toBe(BASE_CONFIG)
-    })
-  })
-
-  describe("#given a model with no provider prefix", () => {
-    test("#then returns base config unchanged for non-GPT model", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "gemini-3-pro")
-      expect(result).toBe(BASE_CONFIG)
-    })
-  })
-
-  describe("#given a Claude model through a non-Anthropic provider", () => {
-    test("#then returns thinking config for github-copilot/claude-opus-4-6", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "github-copilot/claude-opus-4-6")
-      expect(result).toEqual({
-        ...BASE_CONFIG,
-        thinking: { type: "enabled", budgetTokens: 32000 },
-      })
-    })
-
-    test("#then returns thinking config for opencode/claude-opus-4-6", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "opencode/claude-opus-4-6")
-      expect(result).toEqual({
-        ...BASE_CONFIG,
-        thinking: { type: "enabled", budgetTokens: 32000 },
-      })
-    })
-
-    test("#then returns thinking config for opencode/claude-sonnet-4-6", () => {
-      const result = applyModelThinkingConfig(BASE_CONFIG, "opencode/claude-sonnet-4-6")
-      expect(result).toEqual({
-        ...BASE_CONFIG,
-        thinking: { type: "enabled", budgetTokens: 32000 },
-      })
-    })
-  })
-})

src/agents/athena/model-thinking-config.ts

@@ -1,20 +0,0 @@
-import type { AgentConfig } from "@opencode-ai/sdk"
-import { parseModelString } from "../../tools/delegate-task/model-string-parser"
-import { isGptModel } from "../types"
-
-export function applyModelThinkingConfig(base: AgentConfig, model: string): AgentConfig {
-  if (isGptModel(model)) {
-    return { ...base, reasoningEffort: "medium" }
-  }
-
-  const parsed = parseModelString(model)
-  if (!parsed) {
-    return base
-  }
-
-  if (parsed.providerID.toLowerCase() === "anthropic" || parsed.modelID.startsWith("claude")) {
-    return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } }
-  }
-
-  return base
-}

src/tools/prepare-council-prompt/tools.ts

@@ -61,36 +61,45 @@ Returns the file path to reference in subsequent task() calls.`
         return "Prompt cannot be empty."
       }
 
+      if (args.mode !== undefined && args.mode !== "solo" && args.mode !== "delegation") {
+        return `Invalid mode: "${args.mode}". Valid modes: "solo", "delegation".`
+      }
+
       const mode = args.mode === "delegation" ? "delegation" : "solo"
-      const tmpDir = join(directory, COUNCIL_TMP_DIR)
-      await mkdir(tmpDir, { recursive: true })
 
-      const filename = `athena-council-${randomUUID().slice(0, 8)}.md`
+      try {
-      const filePath = join(tmpDir, filename)
+        const tmpDir = join(directory, COUNCIL_TMP_DIR)
+        await mkdir(tmpDir, { recursive: true })
 
-      const modeAddendum = mode === "delegation" ? COUNCIL_DELEGATION_ADDENDUM : COUNCIL_SOLO_ADDENDUM
+        const filename = `athena-council-${randomUUID().slice(0, 8)}.md`
-      const content = `${modeAddendum}
+        const filePath = join(tmpDir, filename)
+
+        const modeAddendum = mode === "delegation" ? COUNCIL_DELEGATION_ADDENDUM : COUNCIL_SOLO_ADDENDUM
+        const content = `${modeAddendum}
 
 ## Analysis Question
 
 ${args.prompt}`
 
-      await writeFile(filePath, content, "utf-8")
+        await writeFile(filePath, content, "utf-8")
 
-      setTimeout(() => {
+        setTimeout(() => {
-        unlink(filePath).catch((err) => {
+          unlink(filePath).catch((err) => {
-          log("[prepare-council-prompt] Failed to clean up temp file", { filePath, error: String(err) })
+            log("[prepare-council-prompt] Failed to clean up temp file", { filePath, error: String(err) })
-        })
+          })
-      }, CLEANUP_DELAY_MS)
+        }, CLEANUP_DELAY_MS)
 
-      log("[prepare-council-prompt] Saved prompt", { filePath, length: args.prompt.length, mode })
+        log("[prepare-council-prompt] Saved prompt", { filePath, length: args.prompt.length, mode })
 
-      return `Council prompt saved to: ${filePath} (mode: ${mode})
+        return `Council prompt saved to: ${filePath} (mode: ${mode})
 
 Use this path in each council member's task() call:
 - prompt: "Read ${filePath} for your instructions."
 
 The file auto-deletes after 30 minutes.`
+      } catch (err) {
+        return `Error saving council prompt: ${String(err)}`
+      }
     },
   })
 }