Abdelrahman Abdallah
b5e5824a56
Core changes:
- Added claw-code/src/token_budget.py for projected prompt size, chat-framing overhead, output reserve, and soft/hard input limits.
- Wired preflight prompt-length validation and auto-compact/context collapse into claw-code/src/agent_runtime.py.
- Extended claw-code/src/compact.py so compaction reports usage back to the runtime.
- Added inspection surfaces in claw-code/src/agent_slash_commands.py and claw-code/src/main.py:
- /token-budget and /budget
- token-budget
- Hardened claw-code/src/tokenizer_runtime.py so arbitrary simple model names fall back cleanly instead of trying a slow Transformers
lookup.
- Exported the new helpers in claw-code/src/__init__.py.
Docs and tracking:
- Updated claw-code/PARITY_CHECKLIST.md to mark prompt-length validation, token-budget calculation, and auto-compact/context collapse as
done.
- Updated claw-code/README.md and claw-code/TESTING_GUIDE.md with the new commands and behavior.
Tests:
- Added claw-code/tests/test_token_budget.py.
- Updated claw-code/tests/test_agent_runtime.py, claw-code/tests/test_agent_slash_commands.py, claw-code/tests/test_main.py, and claw-code/
tests/test_agent_context_usage.py.
- Verified with:
- /data/fs201059/aa17626/miniconda3/bin/python3 -m compileall src tests
- /data/fs201059/aa17626/miniconda3/bin/python3 -m unittest -v tests.test_token_budget
tests.test_agent_runtime.AgentRuntimeTests.test_agent_rejects_prompt_before_backend_when_preflight_input_budget_is_exceeded
tests.test_agent_runtime.AgentRuntimeTests.test_agent_auto_compacts_context_before_next_model_call tests.test_agent_slash_commands
tests.test_main tests.test_compact tests.test_tokenizer_runtime tests.test_agent_context_usage
- Result: 71 tests, OK
42 lines
1.5 KiB
Python
42 lines
1.5 KiB
Python
from __future__ import annotations
|
|
|
|
import unittest
|
|
|
|
from src.agent_context_usage import collect_context_usage, format_context_usage
|
|
from src.agent_session import AgentSessionState
|
|
|
|
|
|
class AgentContextUsageTests(unittest.TestCase):
|
|
def test_collect_context_usage_formats_breakdown(self) -> None:
|
|
session = AgentSessionState.create(
|
|
['# Intro\nhello', '# System\nworld'],
|
|
'inspect repo',
|
|
user_context={'currentDate': "Today's date is 2026-04-01."},
|
|
system_context={'gitStatus': 'Current branch: main'},
|
|
)
|
|
session.append_assistant(
|
|
'Reading files',
|
|
(
|
|
{
|
|
'id': 'call_1',
|
|
'type': 'function',
|
|
'function': {'name': 'read_file', 'arguments': '{"path":"a.py"}'},
|
|
},
|
|
),
|
|
)
|
|
session.append_tool('read_file', 'call_1', '{"ok": true, "content": "print(1)"}')
|
|
|
|
report = collect_context_usage(
|
|
session=session,
|
|
model='test-model',
|
|
strategy='test session',
|
|
)
|
|
rendered = format_context_usage(report)
|
|
|
|
self.assertGreater(report.total_tokens, 0)
|
|
self.assertIn('## Context Usage', rendered)
|
|
self.assertIn('**Token counter:**', rendered)
|
|
self.assertIn('### System Prompt Sections', rendered)
|
|
self.assertIn('### Message Breakdown', rendered)
|
|
self.assertIn('#### Top Tools', rendered)
|