streamline tool schema and improve LLM workflow instructions

- Remove the `goal` field from the TODO state and `plan` operation, as discrete tasks often do not share a single high-level objective.
- Unify the JSON tool parameter schema to use `snake_case` (e.g., `active_summary`) to match existing fields like `blocked_by`.
- Restrict the `active_summary` parameter exclusively to the `start` operation, where it semantically belongs.
- Update agent prompts (`todo.md`, `code_agent.md`) to explicitly forbid batch-starting tasks unless performing genuinely parallel work (e.g., dispatching subagents).
- Update all corresponding tool tests to reflect the new state shape and validation logic.

Author: zikajk

resources/prompts/code_agent.md

@@ -34,15 +34,14 @@ You have tools at your disposal to solve the coding task. Follow these rules reg
 You have access to a `eca__todo` tool for tracking multi-step work within this chat.
 
 ### Workflow:
-1. Use `plan` to create TODO with goal and tasks
-2. Use `start` before working on a task (marks it as in_progress)
-3. Use `complete` only for tasks that are actually finished; for each targeted task that has `done_when`, verify it first.
+1. Use `plan` to create TODO with initial tasks
+2. Use `start` before working on a task (marks it as in_progress and requires an `active_summary`)
+3. Use `complete` only for tasks that are actually finished; for each targeted task, verify its acceptance criteria first.
 4. Use `add` if you discover additional work
-5. When a plan is fully completed and no further work is needed for the current goal, always use the `clear` operation to clean up the workspace.
-6. Delegate focused work to subagents when helpful. Work sequentially by default; batch operations ONLY for tasks executing simultaneously.
+5. When a plan is fully completed and no further work is needed, always use the `clear` operation to clean up the workspace.
+6. When helpful, delegate focused work to subagents. You MAY start multiple independent tasks in parallel (keep the number of in_progress tasks small), then update/complete the TODO based on subagent outputs. Prefer that only the main agent updates the TODO; subagents should focus on producing outputs.
 
-### done_when guidance:
-- `done_when` is optional.
-- Prefer setting it for non-trivial tasks where completion should be objectively verifiable.
-- For trivial tasks, you may omit it to keep tracking lightweight.
+### Task tracking guidance:
+- Make sure to add acceptance criteria inside your task `description`.
+- Objective verification of acceptance criteria is required for completion.
 {% endif %}

resources/prompts/tools/todo.md

@@ -13,29 +13,28 @@ When NOT to Use:
 
 Operations:
 - read: View current TODO state
-- plan: Create/replace TODO with goal and tasks (required: goal, tasks)
+- plan: Create/replace TODO with initial tasks (required: tasks)
 - add: Append task(s) to existing TODO
-- update: Modify a single task metadata by `id` (content, priority, done_when, blocked_by) — cannot change status
-- start: Begin work on tasks by `ids` (sets to in_progress; rejects blocked or done tasks)
-- complete: Mark tasks by `ids` as done (verify done_when criteria first)
+- update: Modify a single task metadata by `id` (subject, description, priority, blocked_by) — cannot change status
+- start: Begin work on tasks by `ids` (sets to in_progress; rejects blocked or done tasks). Requires `active_summary` to summarize what you are about to do.
+- complete: Mark tasks by `ids` as done (verify acceptance criteria in description first)
 - delete: Remove tasks by `ids`
-- clear: Reset entire TODO (removes goal and all tasks)
+- clear: Reset entire TODO (removes all tasks)
 
 Workflow:
-1. Use 'plan' to create TODO with goal and initial tasks
-2. Use 'start' before working on a task — marks it as in_progress
+1. Use 'plan' to create TODO with initial tasks
+2. Use 'start' before working on a task — marks it as in_progress and requires an `active_summary`
 3. Work sequentially by default. Batch 'start' or 'complete' operations (using multiple 'ids') ONLY for independent tasks being executed simultaneously (e.g., via subagents).
-4. Use 'complete' only for tasks that are actually finished; for each targeted task that has `done_when`, verify it first — the response tells you which tasks got unblocked
+4. Use 'complete' only for tasks that are actually finished; verify acceptance criteria first — the response tells you which tasks got unblocked
 5. Use 'add' if you discover additional work during execution
-6. When a plan is fully completed and no further work is needed for the current goal, always use the 'clear' operation to clean up the workspace.
+6. When a plan is fully completed and no further work is needed, always use the 'clear' operation to clean up the workspace.
 
-How to use done_when:
-- `done_when` is optional.
-- Use it for non-trivial tasks where completion must be verifiable (tests passing, behavior implemented, specific file changes, etc.).
-- For trivial/obvious tasks, you may omit `done_when` to avoid overhead.
+Task Schema:
+- `subject`: A brief, actionable title in imperative form (e.g. "Fix login bug")
+- `description`: Detailed description of what needs to be done, including context and acceptance criteria
 
 Task Completion Integrity:
 - Mark tasks complete as soon as they are finished.
-- If a task has `done_when`, ONLY mark it as completed when ALL `done_when` criteria are actually met (for each task in a batch).
+- ONLY mark it as completed when ALL acceptance criteria from the `description` are actually met (for each task in a batch).
 - Do NOT complete if: tests failing, implementation partial, or errors unresolved.
 - When completing reveals follow-up work, use 'add' to append new tasks.

src/eca/db.clj

@@ -60,13 +60,13 @@
                         :messages [{:role (or "user" "assistant" "tool_call" "tool_call_output" "reason")
                                     :content (or :string [::any-map]) ;; string for simple text, map/vector for structured content
                                     :content-id :string}]
-                        :todo {:goal :string
-                               :next-id :number
+                        :todo {:next-id :number
+                               :active-summary (or :string nil)
                                :tasks [{:id :number
-                                        :content :string
+                                        :subject :string
+                                        :description :string
                                         :status (or :pending :in-progress :done)
                                         :priority (or :high :medium :low)
-                                        :done-when (or :string nil)
                                         :blocked-by #{:number}}]}
                         :tool-calls {"<tool-call-id>"
                                      {:status (or :initial :preparing :check-approval :waiting-approval