Implemented the next parity slice: prompt-budget preflight and context collapse.

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

tests/test_token_budget.py

@@ -0,0 +1,100 @@
+from __future__ import annotations
+
+import unittest
+from unittest.mock import patch
+
+from src.agent_session import AgentSessionState
+from src.agent_context_usage import ContextUsageReport, MessageBreakdown
+from src.agent_types import BudgetConfig
+from src.token_budget import calculate_token_budget, format_token_budget
+
+
+class TokenBudgetTests(unittest.TestCase):
+    def test_calculate_token_budget_reports_soft_and_hard_limits(self) -> None:
+        session = AgentSessionState.create(
+            ['# System\nYou are helpful.'],
+            'Inspect the repository and summarize the current implementation status.',
+            user_context={'currentDate': "Today's date is 2026-04-11."},
+            system_context={'gitStatus': 'Current branch: main'},
+        )
+        session.append_assistant('Reading files and checking runtime state.')
+
+        fake_usage = ContextUsageReport(
+            model='test-model',
+            total_tokens=200,
+            raw_max_tokens=128_000,
+            percentage=0.15,
+            strategy='token_budget',
+            message_count=len(session.messages),
+            categories=(),
+            system_prompt_sections=(),
+            user_context_entries=(),
+            system_context_entries=(),
+            memory_files=(),
+            message_breakdown=MessageBreakdown(
+                user_message_tokens=50,
+                assistant_message_tokens=50,
+                tool_call_tokens=0,
+                tool_result_tokens=0,
+                user_context_tokens=10,
+                tool_calls_by_type=(),
+            ),
+            token_counter_backend='heuristic',
+            token_counter_source='test',
+            token_counter_accurate=False,
+        )
+        with patch('src.token_budget.collect_context_usage', return_value=fake_usage):
+            snapshot = calculate_token_budget(
+                session=session,
+                model='test-model',
+                budget_config=BudgetConfig(),
+            )
+        rendered = format_token_budget(snapshot)
+
+        self.assertGreater(snapshot.projected_input_tokens, 0)
+        self.assertGreater(snapshot.hard_input_limit_tokens, snapshot.soft_input_limit_tokens)
+        self.assertGreater(snapshot.chat_overhead_tokens, 0)
+        self.assertIn('# Token Budget', rendered)
+        self.assertIn('Hard input limit', rendered)
+        self.assertIn('Auto-compact buffer', rendered)
+
+    def test_calculate_token_budget_honors_explicit_max_input_tokens(self) -> None:
+        session = AgentSessionState.create(
+            ['# System\nYou are helpful.'],
+            'This prompt is deliberately longer than the tiny configured input budget. ' * 4,
+        )
+
+        fake_usage = ContextUsageReport(
+            model='test-model',
+            total_tokens=120,
+            raw_max_tokens=128_000,
+            percentage=0.09,
+            strategy='token_budget',
+            message_count=len(session.messages),
+            categories=(),
+            system_prompt_sections=(),
+            user_context_entries=(),
+            system_context_entries=(),
+            memory_files=(),
+            message_breakdown=MessageBreakdown(
+                user_message_tokens=80,
+                assistant_message_tokens=0,
+                tool_call_tokens=0,
+                tool_result_tokens=0,
+                user_context_tokens=0,
+                tool_calls_by_type=(),
+            ),
+            token_counter_backend='heuristic',
+            token_counter_source='test',
+            token_counter_accurate=False,
+        )
+        with patch('src.token_budget.collect_context_usage', return_value=fake_usage):
+            snapshot = calculate_token_budget(
+                session=session,
+                model='test-model',
+                budget_config=BudgetConfig(max_input_tokens=20),
+            )
+
+        self.assertTrue(snapshot.exceeds_hard_limit)
+        self.assertGreater(snapshot.overflow_tokens, 0)
+        self.assertLessEqual(snapshot.hard_input_limit_tokens, 20)