perplexity/Timmy-time-dashboard
Archived
1
0
Fork 0
forked from Rockachopa/Timmy-time-dashboard
Code Issues Pull Requests 1 Activity

Merge pull request '[loop-cycle-29] perf: eliminate redundant LLM calls in agentic loop (#24)' (#115) from fix/perf-redundant-llm-calls-24 into main

Browse Source
This commit is contained in:
hermes
2026-03-14 20:56:33 -04:00
parent bbbbdcdfa9 b9b78adaa2
commit 24b20a05ca
4 changed files with 29 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
src/timmy/agentic_loop.py
View File

@@ -58,6 +58,8 @@ class AgenticResult:
# Agent factory
# ---------------------------------------------------------------------------
_loop_agent = None
def _get_loop_agent():
"""Create a fresh agent for the agentic loop.
@@ -65,9 +67,12 @@ def _get_loop_agent():
Returns the same type of agent as `create_timmy()` but with a
dedicated session so it doesn't pollute the main chat history.
"""
from timmy.agent import create_timmy
global _loop_agent
if _loop_agent is None:
from timmy.agent import create_timmy
return create_timmy()
_loop_agent = create_timmy()
return _loop_agent
# ---------------------------------------------------------------------------
@@ -168,11 +173,11 @@ async def run_agentic_loop(
for i, step_desc in enumerate(steps, 1):
step_start = time.monotonic()
recent = completed_results[-2:] if completed_results else []
context = (
f"Task: {task}\n"
f"Plan: {plan_text}\n"
f"Completed so far: {completed_results}\n\n"
f"Now do step {i}: {step_desc}\n"
f"Step {i}/{total_steps}: {step_desc}\n"
f"Recent progress: {recent}\n\n"
f"Execute this step and report what you did."
)
@@ -273,27 +278,15 @@ async def run_agentic_loop(
completed_results.append(f"Step {i}: FAILED")
# ── Phase 3: Summary ───────────────────────────────────────────────────
summary_prompt = (
f"Task: {task}\n"
f"Results:\n" + "\n".join(completed_results) + "\n\n"
"Summarise what was accomplished in 2-3 sentences."
)
try:
summary_run = await asyncio.to_thread(
agent.run,
summary_prompt,
stream=False,
session_id=f"{session_id}_summary",
)
result.summary = (
summary_run.content if hasattr(summary_run, "content") else str(summary_run)
)
from timmy.session import _clean_response
result.summary = _clean_response(result.summary)
except Exception as exc:
logger.error("Agentic loop summary failed: %s", exc)
result.summary = f"Completed {len(result.steps)} steps."
completed_count = sum(1 for s in result.steps if s.status == "completed")
adapted_count = sum(1 for s in result.steps if s.status == "adapted")
failed_count = sum(1 for s in result.steps if s.status == "failed")
parts = [f"Completed {completed_count}/{total_steps} steps"]
if adapted_count:
parts.append(f"{adapted_count} adapted")
if failed_count:
parts.append(f"{failed_count} failed")
result.summary = f"{task}: {', '.join(parts)}."
# Determine final status
if was_truncated:

6
tests/e2e/test_agentic_chain.py
View File

@@ -28,7 +28,6 @@ async def test_multistep_chain_completes_all_steps():
_mock_run("Found 5 articles about AI in March 2026."),
_mock_run("Wrote summary to /tmp/ai_news.md"),
_mock_run("File exists, 15 lines."),
_mock_run("Searched, wrote, verified."),
]
)
@@ -40,7 +39,7 @@ async def test_multistep_chain_completes_all_steps():
assert result.status == "completed"
assert len(result.steps) == 3
assert mock_agent.run.call_count == 5 # plan + 3 steps + summary
assert mock_agent.run.call_count == 4 # plan + 3 steps
@pytest.mark.asyncio
@@ -54,7 +53,6 @@ async def test_multistep_chain_adapts_on_failure():
Exception("Permission denied"),
_mock_run("Adapted: wrote to ~/config.yaml instead"),
_mock_run("Verified: timeout=60"),
_mock_run("Updated config. Used ~/config.yaml due to permissions."),
]
)
@@ -77,7 +75,6 @@ async def test_max_steps_enforced():
_mock_run("1. A\n2. B\n3. C\n4. D\n5. E"),
_mock_run("A done"),
_mock_run("B done"),
_mock_run("Completed 2 of 5 steps."),
]
)
@@ -105,7 +102,6 @@ async def test_progress_events_fire():
_mock_run("1. Do A\n2. Do B"),
_mock_run("A done"),
_mock_run("B done"),
_mock_run("All done"),
]
)

13
tests/test_agentic_loop.py
View File

@@ -59,7 +59,6 @@ async def test_planning_phase_produces_steps():
_mock_run("Found 5 articles about AI."),
_mock_run("Wrote summary to /tmp/ai_news.md"),
_mock_run("File verified, 15 lines."),
_mock_run("Searched, wrote, verified."),
]
)
@@ -82,7 +81,6 @@ async def test_loop_executes_all_steps():
_mock_run("1. Do A\n2. Do B"),
_mock_run("A done"),
_mock_run("B done"),
_mock_run("All done"),
]
)
@@ -92,8 +90,8 @@ async def test_loop_executes_all_steps():
):
result = await run_agentic_loop("Do A and B")
# plan + 2 steps + summary = 4 calls
assert mock_agent.run.call_count == 4
# plan + 2 steps = 3 calls
assert mock_agent.run.call_count == 3
assert len(result.steps) == 2
@@ -106,7 +104,6 @@ async def test_loop_respects_max_steps():
_mock_run("1. A\n2. B\n3. C\n4. D\n5. E"),
_mock_run("A done"),
_mock_run("B done"),
_mock_run("Completed 2 of 5 steps."),
]
)
@@ -131,7 +128,6 @@ async def test_failure_triggers_adaptation():
Exception("Permission denied"),
_mock_run("Adapted: wrote to ~/config.yaml instead"),
_mock_run("Verified: timeout=60"),
_mock_run("Updated config via alternative path."),
]
)
@@ -159,7 +155,6 @@ async def test_progress_callback_fires():
_mock_run("1. Do A\n2. Do B"),
_mock_run("A done"),
_mock_run("B done"),
_mock_run("All done"),
]
)
@@ -183,7 +178,6 @@ async def test_result_contains_step_metadata():
_mock_run("1. Search\n2. Write"),
_mock_run("Found results"),
_mock_run("Written to file"),
_mock_run("Done"),
]
)
@@ -207,10 +201,9 @@ async def test_config_default_used():
# Return more steps than default config allows (10)
steps_text = "\n".join(f"{i}. Step {i}" for i in range(1, 15))
side_effects = [_mock_run(steps_text)]
# 10 step results + summary
# 10 step results
for i in range(1, 11):
side_effects.append(_mock_run(f"Step {i} done"))
side_effects.append(_mock_run("Summary"))
mock_agent.run = MagicMock(side_effect=side_effects)

12
tests/timmy/test_cli.py
View File

@@ -229,7 +229,7 @@ def test_chat_stdin_empty_exits_with_error():
def test_repl_exits_on_ctrl_c():
"""repl should exit gracefully on Ctrl+C (KeyboardInterrupt)."""
with patch("builtins.input", side_effect=KeyboardInterrupt):
runner.invoke(app, ["repl"])
result = runner.invoke(app, ["repl"])
assert result.exit_code == 0
assert "Goodbye" in result.output
@@ -238,7 +238,7 @@ def test_repl_exits_on_ctrl_c():
def test_repl_exits_on_ctrl_d():
"""repl should exit gracefully on Ctrl+D (EOFError)."""
with patch("builtins.input", side_effect=EOFError):
runner.invoke(app, ["repl"])
result = runner.invoke(app, ["repl"])
assert result.exit_code == 0
assert "Goodbye" in result.output
@@ -247,7 +247,7 @@ def test_repl_exits_on_ctrl_d():
def test_repl_exits_on_quit_command():
"""repl should exit when user types 'quit'."""
with patch("builtins.input", return_value="quit"):
runner.invoke(app, ["repl"])
result = runner.invoke(app, ["repl"])
assert result.exit_code == 0
assert "Goodbye" in result.output
@@ -256,7 +256,7 @@ def test_repl_exits_on_quit_command():
def test_repl_exits_on_exit_command():
"""repl should exit when user types 'exit'."""
with patch("builtins.input", return_value="exit"):
runner.invoke(app, ["repl"])
result = runner.invoke(app, ["repl"])
assert result.exit_code == 0
assert "Goodbye" in result.output
@@ -269,7 +269,7 @@ def test_repl_sends_message_to_chat():
patch("timmy.session.chat") as mock_chat,
):
mock_chat.return_value = "Hi there!"
runner.invoke(app, ["repl"])
result = runner.invoke(app, ["repl"])
mock_chat.assert_called()
assert result.exit_code == 0
@@ -309,7 +309,7 @@ def test_repl_handles_chat_errors():
patch("timmy.session.chat") as mock_chat,
):
mock_chat.side_effect = Exception("Chat error")
runner.invoke(app, ["repl"])
result = runner.invoke(app, ["repl"])
assert result.exit_code == 0
assert "Error" in result.output