remove reasoning_think tool and prompt

Backend now streams native thinking tokens via StreamEvent.Reasoning.
The no-op scratchpad tool is redundant.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

agents/coding.json

@@ -4,7 +4,6 @@
     "prime tools-task 2>/dev/null || true",
     "$OLLIE/x/prime agent-coding",
     "$OLLIE/x/prime tools-file",
-    "$OLLIE/x/prime tools-reasoning",
     "$OLLIE/x/prime tools-memory",
     "$OLLIE/x/prime tools-subagent",
     "$OLLIE/x/prime tools-elevate",

agents/default.json

@@ -3,7 +3,6 @@
     "$OLLIE/x/prime SYSTEM_PROMPT",
     "prime tools-task 2>/dev/null || true",
     "$OLLIE/x/prime tools-file",
-    "$OLLIE/x/prime tools-reasoning",
     "$OLLIE/x/prime tools-memory",
     "$OLLIE/x/prime tools-subagent",
     "bash -c 'd=$PWD; while [ \"$d\" != / ]; do [ -d \"$d/.beads\" ] && exec bd prime; [ ! -e \"$d/.git\" ] && break; d=$(dirname \"$d\"); done' 2>/dev/null || true"

agents/devops.json

@@ -4,7 +4,6 @@
     "prime tools-task 2>/dev/null || true",
     "$OLLIE/x/prime agent-devops",
     "$OLLIE/x/prime tools-file",
-    "$OLLIE/x/prime tools-reasoning",
     "$OLLIE/x/prime tools-memory",
     "$OLLIE/x/prime tools-subagent",
     "$OLLIE/x/prime tools-elevate",

agents/qa.json

@@ -4,7 +4,6 @@
     "prime tools-task 2>/dev/null || true",
     "$OLLIE/x/prime agent-qa",
     "$OLLIE/x/prime tools-file",
-    "$OLLIE/x/prime tools-reasoning",
     "$OLLIE/x/prime tools-memory",
     "$OLLIE/x/prime tools-subagent",
     "bash -c 'd=$PWD; while [ \"$d\" != / ]; do [ -d \"$d/.beads\" ] && exec bd prime; [ ! -e \"$d/.git\" ] && break; d=$(dirname \"$d\"); done' 2>/dev/null || true"

agents/reviewer.json

@@ -4,7 +4,6 @@
     "prime tools-task 2>/dev/null || true",
     "$OLLIE/x/prime agent-reviewer",
     "$OLLIE/x/prime tools-file",
-    "$OLLIE/x/prime tools-reasoning",
     "$OLLIE/x/prime tools-memory",
     "$OLLIE/x/prime tools-subagent",
     "bash -c 'd=$PWD; while [ \"$d\" != / ]; do [ -d \"$d/.beads\" ] && exec bd prime; [ ! -e \"$d/.git\" ] && break; d=$(dirname \"$d\"); done' 2>/dev/null || true"

agents/sysarchitect.json

@@ -4,7 +4,6 @@
     "prime tools-task 2>/dev/null || true",
     "$OLLIE/x/prime agent-sysarchitect",
     "$OLLIE/x/prime tools-file",
-    "$OLLIE/x/prime tools-reasoning",
     "$OLLIE/x/prime tools-memory",
     "$OLLIE/x/prime tools-subagent",
     "bash -c 'd=$PWD; while [ \"$d\" != / ]; do [ -d \"$d/.beads\" ] && exec bd prime; [ ! -e \"$d/.git\" ] && break; d=$(dirname \"$d\"); done' 2>/dev/null || true"

agents/writer.json

@@ -4,7 +4,6 @@
     "prime tools-task 2>/dev/null || true",
     "$OLLIE/x/prime agent-writer",
     "$OLLIE/x/prime tools-file",
-    "$OLLIE/x/prime tools-reasoning",
     "$OLLIE/x/prime tools-memory",
     "$OLLIE/x/prime tools-subagent",
     "bash -c 'd=$PWD; while [ \"$d\" != / ]; do [ -d \"$d/.beads\" ] && exec bd prime; [ ! -e \"$d/.git\" ] && break; d=$(dirname \"$d\"); done' 2>/dev/null || true"

prompts/tools-reasoning.md

@@ -1,14 +0,0 @@
-# reasoning_think
-
-A scratchpad for externalizing reasoning. The thought is recorded in conversation history — informing subsequent actions — but not shown to the user.
-
-**Trigger condition**: before acting on any non-trivial task — complex problems, multi-step logic, decisions with trade-offs, or any point where acting without thinking first risks a wrong turn. Skip it for simple, single-step tasks where the right action is immediately obvious.
-
-**Calling convention**:
-```
-execute_code: steps=[{tool: "reasoning_think", args: ["your full reasoning here"]}]
-```
-
-**Returns**: nothing. The value is entirely in writing the thought.
-
-**Constraints**: one call per decision point is enough.

tools/reasoning_think

@@ -1,7 +0,0 @@
-#!/usr/bin/env bash
-# ollie:parallel read
-# description: Internal reasoning scratchpad; think through complex problems before acting
-# Args: <thought>
-
-[ -z "$*" ] && echo "usage: reasoning_think <thought>" && exit 1
-exit 0