Merge remote-tracking branch 'origin/master' into fix/all-except-first-drops-an-agent

# Conflicts:
#	swarms/structs/conversation.py

Author: ayaangazali

.github/workflows/RELEASE.yml

@@ -20,10 +20,10 @@ jobs:
       - uses: actions/checkout@v6
       - name: Install poetry
         run: pipx install poetry==$POETRY_VERSION
-      - name: Set up Python 3.9
+      - name: Set up Python 3.10
         uses: actions/setup-python@v6
         with:
-          python-version: "3.9"
+          python-version: "3.10"
           cache: "poetry"
       - name: Build project for distribution
         run: poetry build

.github/workflows/python-package.yml

@@ -15,6 +15,7 @@ jobs:
   build:
 
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     strategy:
       fail-fast: false
       matrix:
@@ -31,6 +32,8 @@ jobs:
         python -m pip install --upgrade pip
         python -m pip install flake8 pytest
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        # The tests import swarms, so the package under test has to be installed.
+        python -m pip install -e . --no-deps
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names

.github/workflows/test-main-features.yml

@@ -51,7 +51,7 @@ jobs:
 
     - name: Install dependencies
       run: |
-        poetry install --with test --no-dev
+        poetry install --only main,test
 
     - name: Set up environment variables
       run: |
@@ -65,7 +65,6 @@ jobs:
 
     - name: Run Main Features Tests
       run: |
-        cd /Users/swarms_wd/Desktop/research/swarms
         poetry run python tests/test_main_features.py
 
     - name: Upload test results

.github/workflows/tests.yml

@@ -9,6 +9,7 @@ on:
 jobs:
   test:
     runs-on: ubuntu-latest
+    timeout-minutes: 20
 
     steps:
     - uses: actions/checkout@v6

CLAUDE.md

@@ -110,9 +110,9 @@ print(result)
 | `interactive` | bool | `False` | REPL mode — prompt user for input each loop |
 | `context_length` | int | `None` | Token budget; triggers compression at 90 % |
 | `context_compression` | bool | `True` | Auto-summarise when near context limit (v12) |
-| `persistent_memory` | bool | `True` | Read/write MEMORY.md across restarts (v12) |
+| `persistent_memory` | bool | `False` | Read/write MEMORY.md across restarts (v12); opt in explicitly |
 | `temperature` | float | `0.5` | Sampling temperature |
-| `max_tokens` | int | `4096` | Max tokens per LLM call |
+| `max_tokens` | int | model's max output | Max tokens per LLM call. Unset resolves to the model's own output limit |
 | `reasoning_effort` | str | `None` | `"low"`, `"medium"`, `"high"` for reasoning models |
 | `thinking_tokens` | int | `None` | Extended thinking budget (Claude) |
 | `output_type` | str | `"str-all-except-first"` | How to format returned output |
@@ -173,25 +173,30 @@ result = agent.run(
 
 ## Memory & Persistence (v12)
 
-### `persistent_memory=True` (default)
+### `persistent_memory=True` (opt in)
 
 On startup the agent reads `{workspace}/agents/{agent_name}/MEMORY.md` and injects it as a system preamble. On each response it appends to that file. State survives process restarts automatically.
 
 ```python
 agent = Agent(
     agent_name="ProjectAssistant",
     model_name="gpt-5.4",
-    persistent_memory=True,   # default
+    persistent_memory=True,   # off by default; opt in
 )
 # First run: agent has no prior context
 agent.run("My project is called Helios. Remember that.")
 
-# New process, same agent_name → agent remembers "Helios"
-agent2 = Agent(agent_name="ProjectAssistant", model_name="gpt-5.4")
+# New process, same agent_name → agent remembers "Helios".
+# persistent_memory must be set here too; it is False by default.
+agent2 = Agent(
+    agent_name="ProjectAssistant",
+    model_name="gpt-5.4",
+    persistent_memory=True,
+)
 agent2.run("What is my project called?")
 ```
 
-### `persistent_memory=False`
+### `persistent_memory=False` (default)
 
 Fully stateless — no disk reads or writes. Use for short, isolated tasks where carry-over would be harmful.
 
@@ -502,10 +507,8 @@ result = router.run("Write a blog post about transformer architectures.")
 | `"HeavySwarm"` | Intensive multi-loop deep analysis |
 | `"RoundRobin"` | Round-robin task distribution |
 | `"PlannerWorkerSwarm"` | Planner + worker delegation |
-| `"BatchedGridWorkflow"` | Grid-based batch execution |
 | `"LLMCouncil"` | LLM-based council decisions |
 | `"AutoSwarmBuilder"` | Auto-configures everything |
-| `"auto"` | Router selects swarm_type automatically |
 
 ---
 
@@ -933,7 +936,7 @@ agent = Agent(
 | High-stakes ruling with deliberation | `CouncilAsAJudge` |
 | Structured adversarial debate | `DebateWithJudge` |
 | Deep research, many loops | `HeavySwarm` |
-| Don't know yet / rapid prototyping | `AutoSwarmBuilder` or `SwarmRouter(swarm_type="auto")` |
+| Don't know yet / rapid prototyping | `AutoSwarmBuilder` |
 | Need to switch architectures easily | `SwarmRouter` |
 
 ---
@@ -1081,8 +1084,6 @@ from swarms import Agent
 
 **Don't instantiate heavyweight structures inside tight loops** — create agents and workflows once, reuse them across calls.
 
-**Don't pass `tools=[]` (empty list)** — pass `tools=None` instead. An empty list can confuse schema generation.
-
 **Don't use `streaming_on=True` and `streaming_callback` together on the same agent** — `streaming_on` streams to stdout; `streaming_callback` streams to your function. Pick one.
 
 **Don't set `context_compression=False` on very long autonomous sessions** — without compression the agent will eventually hit the context limit and raise an error.