context-compiler 0.7.3__tar.gz → 0.7.4__tar.gz

{context_compiler-0.7.3 → context_compiler-0.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: context-compiler
-Version: 0.7.3
+Version: 0.7.4
 Summary: Deterministic conversational state engine for LLM applications.
 Project-URL: Homepage, https://github.com/rlippmann/context-compiler
 Project-URL: Repository, https://github.com/rlippmann/context-compiler
@@ -139,22 +139,55 @@ Bare REPL input behavior remains unchanged.
 
 Or in code:
 ```python
-from context_compiler import DECISION_CLARIFY, DECISION_UPDATE, create_engine
+from context_compiler import (
+    create_engine,
+    get_clarify_prompt,
+    is_clarify,
+    is_update,
+)
 
 engine = create_engine()
 
 user_input = "prohibit peanuts"
 decision = engine.step(user_input)
 
-if decision["kind"] == DECISION_CLARIFY:
-    show_to_user(decision["prompt_to_user"])
-elif decision["kind"] == DECISION_UPDATE:
+if is_clarify(decision):
+    show_to_user(get_clarify_prompt(decision))
+elif is_update(decision):
     messages = build_messages(engine.state, user_input)
     render(call_llm(messages))
 else:
     render(call_llm(user_input))
 ```
 
+Controller quick example:
+
+```python
+from context_compiler import (
+    get_decision_state,
+    is_update,
+    create_engine,
+    preview,
+    state_diff,
+    step,
+)
+
+engine = create_engine()
+
+before = engine.state
+dry_run = preview(engine, "prohibit peanuts")
+print(dry_run["would_mutate"])  # True
+planned_change = state_diff(before, dry_run["state_after"])
+print(planned_change["changed"])  # True
+
+after_preview = engine.state
+print(state_diff(before, after_preview)["changed"])  # False (preview does not mutate state)
+
+applied = step(engine, "prohibit peanuts")
+print(is_update(applied["decision"]))  # True
+print(get_decision_state(applied["decision"]) is not None)  # True
+```
+
 ## Installation
 
 Requirements:
@@ -297,6 +330,10 @@ Meaning:
 | update      | authoritative state mutated; host may call LLM with updated state |
 | clarify     | show `prompt_to_user` and do not call the LLM |
 
+For normal app code, prefer exported decision helpers (`is_clarify`,
+`is_update`, `is_passthrough`, `get_clarify_prompt`, `get_decision_state`)
+instead of direct key traversal.
+
 ---
 
 ### API Reference
@@ -334,6 +371,17 @@ Decision-kind constants are also exported for host branching readability:
 - `DECISION_UPDATE`
 - `DECISION_CLARIFY`
 
+Decision helpers are also exported for common host-side checks:
+- `is_update(decision)`
+- `is_clarify(decision)`
+- `is_passthrough(decision)`
+- `get_clarify_prompt(decision)`
+- `get_decision_state(decision)`
+
+Policy value constants are exported for explicit policy comparisons:
+- `POLICY_USE`
+- `POLICY_PROHIBIT`
+
 ---
 
 ## State Model
@@ -348,6 +396,8 @@ The compiler keeps a current state snapshot that your app can trust.
 Identical input sequences always produce identical state.
 
 The internal structure of the state is intentionally opaque to host applications.
+For normal reads, prefer `get_premise_value(state)` and
+`get_policy_items(state, ...)` over direct key traversal.
 
 ---
 
@@ -384,6 +434,9 @@ Checkpoint object shape:
 }
 ```
 
+The checkpoint shape above is an explicit serialization contract. At this
+boundary, direct key access is expected.
+
 Notes:
 
 - `pending` is `null` when no continuation is waiting for confirmation.

{context_compiler-0.7.3 → context_compiler-0.7.4}/README.md

@@ -103,22 +103,55 @@ Bare REPL input behavior remains unchanged.
 
 Or in code:
 ```python
-from context_compiler import DECISION_CLARIFY, DECISION_UPDATE, create_engine
+from context_compiler import (
+    create_engine,
+    get_clarify_prompt,
+    is_clarify,
+    is_update,
+)
 
 engine = create_engine()
 
 user_input = "prohibit peanuts"
 decision = engine.step(user_input)
 
-if decision["kind"] == DECISION_CLARIFY:
-    show_to_user(decision["prompt_to_user"])
-elif decision["kind"] == DECISION_UPDATE:
+if is_clarify(decision):
+    show_to_user(get_clarify_prompt(decision))
+elif is_update(decision):
     messages = build_messages(engine.state, user_input)
     render(call_llm(messages))
 else:
     render(call_llm(user_input))
 ```
 
+Controller quick example:
+
+```python
+from context_compiler import (
+    get_decision_state,
+    is_update,
+    create_engine,
+    preview,
+    state_diff,
+    step,
+)
+
+engine = create_engine()
+
+before = engine.state
+dry_run = preview(engine, "prohibit peanuts")
+print(dry_run["would_mutate"])  # True
+planned_change = state_diff(before, dry_run["state_after"])
+print(planned_change["changed"])  # True
+
+after_preview = engine.state
+print(state_diff(before, after_preview)["changed"])  # False (preview does not mutate state)
+
+applied = step(engine, "prohibit peanuts")
+print(is_update(applied["decision"]))  # True
+print(get_decision_state(applied["decision"]) is not None)  # True
+```
+
 ## Installation
 
 Requirements:
@@ -261,6 +294,10 @@ Meaning:
 | update      | authoritative state mutated; host may call LLM with updated state |
 | clarify     | show `prompt_to_user` and do not call the LLM |
 
+For normal app code, prefer exported decision helpers (`is_clarify`,
+`is_update`, `is_passthrough`, `get_clarify_prompt`, `get_decision_state`)
+instead of direct key traversal.
+
 ---
 
 ### API Reference
@@ -298,6 +335,17 @@ Decision-kind constants are also exported for host branching readability:
 - `DECISION_UPDATE`
 - `DECISION_CLARIFY`
 
+Decision helpers are also exported for common host-side checks:
+- `is_update(decision)`
+- `is_clarify(decision)`
+- `is_passthrough(decision)`
+- `get_clarify_prompt(decision)`
+- `get_decision_state(decision)`
+
+Policy value constants are exported for explicit policy comparisons:
+- `POLICY_USE`
+- `POLICY_PROHIBIT`
+
 ---
 
 ## State Model
@@ -312,6 +360,8 @@ The compiler keeps a current state snapshot that your app can trust.
 Identical input sequences always produce identical state.
 
 The internal structure of the state is intentionally opaque to host applications.
+For normal reads, prefer `get_premise_value(state)` and
+`get_policy_items(state, ...)` over direct key traversal.
 
 ---
 
@@ -348,6 +398,9 @@ Checkpoint object shape:
 }
 ```
 
+The checkpoint shape above is an explicit serialization contract. At this
+boundary, direct key access is expected.
+
 Notes:
 
 - `pending` is `null` when no continuation is waiting for confirmation.

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/01_persistent_guardrails.py

@@ -2,11 +2,11 @@
 
 from _util import print_decision_summary, print_state_summary
 
-from context_compiler import State, create_engine, get_policy_items
+from context_compiler import POLICY_PROHIBIT, State, create_engine, get_policy_items
 
 
 def build_prompt(state: State, user_input: str) -> str:
-    prohibit = get_policy_items(state, "prohibit")
+    prohibit = get_policy_items(state, POLICY_PROHIBIT)
     prohibit_text = ", ".join(prohibit) if prohibit else "(none)"
     return (
         "System: Follow authoritative conversation state.\n"

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/03_ambiguity_with_clarification.py

@@ -2,7 +2,7 @@
 
 from _util import print_decision_summary, print_state_summary
 
-from context_compiler import create_engine
+from context_compiler import create_engine, get_clarify_prompt, is_clarify
 
 
 def fake_llm(user_input: str) -> str:
@@ -23,9 +23,9 @@ def main() -> None:
     print_decision_summary(decision2)
     print()
 
-    if decision2["kind"] == "clarify":
+    if is_clarify(decision2):
         print("Host behavior: clarification pending, do NOT call LLM.")
-        print(f"Clarify prompt: {decision2['prompt_to_user']}")
+        print(f"Clarify prompt: {get_clarify_prompt(decision2)}")
     else:
         fake_llm("use peanuts")
     print()

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/04_tool_governance_denylist.py

@@ -4,7 +4,7 @@ from dataclasses import dataclass
 
 from _util import print_decision_summary, print_state_summary
 
-from context_compiler import create_engine, get_policy_items
+from context_compiler import POLICY_PROHIBIT, create_engine, get_policy_items
 
 
 @dataclass
@@ -32,7 +32,7 @@ def main() -> None:
     print()
 
     print("Host-side tool denylist behavior:")
-    prohibit = get_policy_items(state, "prohibit")
+    prohibit = get_policy_items(state, POLICY_PROHIBIT)
     tools = [Tool("docker"), Tool("kubectl")]
     for tool in tools:
         if tool.name in prohibit:

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/05_llm_integration_pattern.py

@@ -3,12 +3,14 @@
 from _util import print_decision_summary, print_state_summary
 
 from context_compiler import (
-    DECISION_CLARIFY,
-    DECISION_PASSTHROUGH,
-    DECISION_UPDATE,
     Engine,
     State,
     create_engine,
+    get_clarify_prompt,
+    get_decision_state,
+    is_clarify,
+    is_passthrough,
+    is_update,
 )
 
 
@@ -27,15 +29,15 @@ def handle_turn(engine_input: str, engine: Engine) -> None:
     print(f"User: {engine_input}")
     print_decision_summary(decision)
 
-    if decision["kind"] == DECISION_PASSTHROUGH:
+    if is_passthrough(decision):
         print("Host action: passthrough -> call fake_llm() without state")
         fake_llm(None, engine_input)
-    elif decision["kind"] == DECISION_UPDATE:
+    elif is_update(decision):
         print("Host action: update -> call fake_llm() with compiled state")
-        fake_llm(decision["state"], engine_input)
-    elif decision["kind"] == DECISION_CLARIFY:
+        fake_llm(get_decision_state(decision), engine_input)
+    elif is_clarify(decision):
         print("Host action: clarify -> show prompt, DO NOT call LLM")
-        print("clarify prompt:", decision["prompt_to_user"])
+        print("clarify prompt:", get_clarify_prompt(decision))
     print()
 
 

context_compiler-0.7.4/examples/08_controller_preview_diff.py

@@ -0,0 +1,30 @@
+"""Example 8: controller preview + state diff + apply flow."""
+
+from _util import print_decision_summary, print_state_summary
+
+from context_compiler import create_engine, preview, state_diff, step
+
+
+def main() -> None:
+    engine = create_engine()
+
+    state_before = engine.state
+    print_state_summary(state_before, "state before preview")
+
+    print("\nPreview: prohibit peanuts")
+    preview_result = preview(engine, "prohibit peanuts")
+    print("would_mutate:", preview_result["would_mutate"])
+    print_decision_summary(preview_result["decision"])
+
+    state_after_preview = engine.state
+    diff_after_preview = state_diff(state_before, state_after_preview)
+    print("state changed after preview:", diff_after_preview["changed"])
+
+    print("\nApply: prohibit peanuts")
+    step_result = step(engine, "prohibit peanuts")
+    print_decision_summary(step_result["decision"])
+    print_state_summary(step_result["state"], "state after step")
+
+
+if __name__ == "__main__":
+    main()

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/README.md

@@ -40,3 +40,9 @@ Shows `compile_transcript(messages)` from a fresh engine and `engine.apply_trans
 
 Demonstrates explicit single-policy correction without `reset policies`.  
 Shows `prohibit peanuts` -> `remove policy peanuts` -> `use peanuts`.
+
+## 08_controller_preview_diff.py
+
+Shows controller-layer dry-run behavior with `preview(engine, user_input)`.  
+Shows structural state inspection with `state_diff(state_before, state_after)`.  
+Shows `step(engine, user_input)` after preview to apply the same input.

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/_util.py

@@ -2,10 +2,14 @@ import json
 from typing import Any, Literal
 
 from context_compiler import (
-    DECISION_CLARIFY,
-    DECISION_UPDATE,
+    POLICY_PROHIBIT,
+    POLICY_USE,
+    get_clarify_prompt,
+    get_decision_state,
     get_policy_items,
     get_premise_value,
+    is_clarify,
+    is_update,
 )
 
 
@@ -28,22 +32,21 @@ def print_state_summary(state: Any, label: str = "state") -> None:
 
     print(f"{label}:")
     print(f"- premise: {premise_text}")
-    print(f"- use policies: {_format_policy_values(state, 'use')}")
-    print(f"- prohibit policies: {_format_policy_values(state, 'prohibit')}")
+    print(f"- use policies: {_format_policy_values(state, POLICY_USE)}")
+    print(f"- prohibit policies: {_format_policy_values(state, POLICY_PROHIBIT)}")
 
 
 def print_decision_summary(decision: Any) -> None:
-    kind = decision.get("kind")
-    if kind == DECISION_UPDATE:
+    if is_update(decision):
         print("result: updated")
-        state = decision.get("state")
+        state = get_decision_state(decision)
         assert isinstance(state, dict)
         print_state_summary(state, "compiled state")
         return
 
-    if kind == DECISION_CLARIFY:
+    if is_clarify(decision):
         print("result: clarify")
-        prompt = decision.get("prompt_to_user")
+        prompt = get_clarify_prompt(decision)
         if isinstance(prompt, str) and prompt:
             print("clarify prompt:")
             for line in prompt.splitlines():

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/integrations/README.md

@@ -17,7 +17,7 @@ export OPENAI_API_KEY=...
 export PROVIDER=openai
 ```
 
-Checkpoint continuation in these integration examples requires `context-compiler>=0.6.14`.
+Checkpoint continuation in these integration examples requires `context-compiler>=0.7.0`.
 
 ### Run
 

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/integrations/litellm/basic.py

@@ -22,9 +22,16 @@ from context_compiler import (
     DECISION_CLARIFY,
     DECISION_PASSTHROUGH,
     DECISION_UPDATE,
+    POLICY_PROHIBIT,
+    POLICY_USE,
     State,
+    get_clarify_prompt,
+    get_decision_state,
     get_policy_items,
     get_premise_value,
+    is_clarify,
+    is_passthrough,
+    is_update,
 )
 from context_compiler.engine import Engine
 from context_compiler.observability import build_trace
@@ -98,8 +105,8 @@ def _extract_response_content(response: object) -> str | None:
 
 def _render_compiled_state_contract(compiled_state: State) -> str:
     premise = get_premise_value(compiled_state)
-    use_items = sorted(get_policy_items(compiled_state, "use"))
-    prohibit_items = sorted(get_policy_items(compiled_state, "prohibit"))
+    use_items = sorted(get_policy_items(compiled_state, POLICY_USE))
+    prohibit_items = sorted(get_policy_items(compiled_state, POLICY_PROHIBIT))
 
     lines: list[str] = ["The following constraints are authoritative."]
     if premise:
@@ -272,13 +279,18 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
     checkpoint_before = engine.export_checkpoint() if has_pending_before else None
     logger.debug("litellm_basic: engine_input=%s", f"user_input len={len(user_input)}")
     decision = engine.step(user_input)
-    kind = cast(str, decision["kind"])
+    if is_clarify(decision):
+        kind = DECISION_CLARIFY
+    elif is_update(decision):
+        kind = DECISION_UPDATE
+    else:
+        kind = DECISION_PASSTHROUGH
     logger.debug("litellm_basic: decision=%s", kind)
     near_miss_prompt = _near_miss_directive_clarify(user_input)
 
-    if kind == DECISION_CLARIFY:
+    if is_clarify(decision):
         _persist_session_checkpoint_if_needed(engine, kind, session_key)
-        response_text = near_miss_prompt or decision["prompt_to_user"] or ""
+        response_text = near_miss_prompt or get_clarify_prompt(decision) or ""
         return _append_trace(
             response_text,
             original_input=user_input,
@@ -288,7 +300,7 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
             state_after=engine.state,
             llm_called=False,
         )
-    if near_miss_prompt is not None and kind == DECISION_PASSTHROUGH:
+    if near_miss_prompt is not None and is_passthrough(decision):
         return _append_trace(
             near_miss_prompt,
             original_input=user_input,
@@ -299,11 +311,7 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
             llm_called=False,
         )
     _persist_session_checkpoint_if_needed(engine, kind, session_key)
-    if (
-        kind == DECISION_UPDATE
-        and is_confirmation_text(user_input)
-        and checkpoint_before is not None
-    ):
+    if is_update(decision) and is_confirmation_text(user_input) and checkpoint_before is not None:
         response_text = _summarize_confirmation_update(user_input, checkpoint_before)
         return _append_trace(
             response_text,
@@ -314,7 +322,7 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
             state_after=engine.state,
             llm_called=False,
         )
-    if kind == DECISION_UPDATE:
+    if is_update(decision):
         response_text = _summarize_update_from_input(user_input)
         return _append_trace(
             response_text,
@@ -326,7 +334,8 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
             llm_called=False,
         )
 
-    compiled_state = decision["state"] if decision["state"] is not None else engine.state
+    decision_state = get_decision_state(decision)
+    compiled_state = decision_state if decision_state is not None else engine.state
     messages = _build_messages(user_input, compiled_state)
     response_text = _call_litellm(messages)
     return _append_trace(

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/integrations/litellm/with_preprocessor.py

@@ -28,9 +28,16 @@ from context_compiler import (
     DECISION_CLARIFY,
     DECISION_PASSTHROUGH,
     DECISION_UPDATE,
+    POLICY_PROHIBIT,
+    POLICY_USE,
     State,
+    get_clarify_prompt,
+    get_decision_state,
     get_policy_items,
     get_premise_value,
+    is_clarify,
+    is_passthrough,
+    is_update,
 )
 from context_compiler.engine import Engine
 from context_compiler.observability import build_trace
@@ -130,8 +137,8 @@ def _get_litellm_completion() -> Callable[..., object]:
 
 def _render_compiled_state_contract(compiled_state: State) -> str:
     premise = get_premise_value(compiled_state)
-    use_items = sorted(get_policy_items(compiled_state, "use"))
-    prohibit_items = sorted(get_policy_items(compiled_state, "prohibit"))
+    use_items = sorted(get_policy_items(compiled_state, POLICY_USE))
+    prohibit_items = sorted(get_policy_items(compiled_state, POLICY_PROHIBIT))
 
     lines: list[str] = ["The following constraints are authoritative."]
     if premise:
@@ -395,13 +402,18 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
     )
 
     decision = engine.step(compile_input)
-    kind = cast(str, decision["kind"])
+    if is_clarify(decision):
+        kind = DECISION_CLARIFY
+    elif is_update(decision):
+        kind = DECISION_UPDATE
+    else:
+        kind = DECISION_PASSTHROUGH
     logger.debug("preprocessor: decision=%s", kind)
     near_miss_prompt = _near_miss_directive_clarify(user_input)
 
-    if kind == DECISION_CLARIFY:
+    if is_clarify(decision):
         _persist_session_checkpoint_if_needed(engine, kind, session_key)
-        response_text = near_miss_prompt or decision["prompt_to_user"] or ""
+        response_text = near_miss_prompt or get_clarify_prompt(decision) or ""
         return _append_trace(
             response_text,
             original_input=user_input,
@@ -412,7 +424,7 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
             state_after=engine.state,
             llm_called=False,
         )
-    if near_miss_prompt is not None and kind == DECISION_PASSTHROUGH:
+    if near_miss_prompt is not None and is_passthrough(decision):
         return _append_trace(
             near_miss_prompt,
             original_input=user_input,
@@ -424,11 +436,7 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
             llm_called=False,
         )
     _persist_session_checkpoint_if_needed(engine, kind, session_key)
-    if (
-        kind == DECISION_UPDATE
-        and is_confirmation_text(user_input)
-        and checkpoint_before is not None
-    ):
+    if is_update(decision) and is_confirmation_text(user_input) and checkpoint_before is not None:
         response_text = _summarize_confirmation_update(user_input, checkpoint_before)
         return _append_trace(
             response_text,
@@ -440,7 +448,7 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
             state_after=engine.state,
             llm_called=False,
         )
-    if kind == DECISION_UPDATE:
+    if is_update(decision):
         response_text = _summarize_update_from_input(compile_input)
         return _append_trace(
             response_text,
@@ -453,7 +461,8 @@ def handle_turn(user_input: str, engine: Engine, *, session_key: str | None = No
             llm_called=False,
         )
 
-    compiled_state = decision["state"] if decision["state"] is not None else engine.state
+    decision_state = get_decision_state(decision)
+    compiled_state = decision_state if decision_state is not None else engine.state
     messages = _build_messages(user_input, compiled_state)
     response_text = _call_litellm(messages)
     return _append_trace(

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/integrations/litellm_proxy/context_compiler_precall_hook.py

@@ -20,6 +20,7 @@ except ModuleNotFoundError:
 
 
 from context_compiler import (
+    POLICY_PROHIBIT,
     State,
     Transcript,
     compile_transcript,
@@ -38,7 +39,7 @@ _SUPPORTED_CALL_TYPES = {
 
 
 def _render_compiled_state_contract(compiled_state: State) -> str:
-    prohibited = get_policy_items(compiled_state, "prohibit")
+    prohibited = get_policy_items(compiled_state, POLICY_PROHIBIT)
     premise = get_premise_value(compiled_state)
 
     lines: list[str] = ["The following constraints are authoritative."]

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/integrations/litellm_proxy/context_compiler_precall_hook_with_preprocessor.py

@@ -26,6 +26,7 @@ except ModuleNotFoundError:
 
 
 from context_compiler import (
+    POLICY_PROHIBIT,
     State,
     Transcript,
     compile_transcript,
@@ -52,7 +53,7 @@ _PROMPTS_DIR = files("experimental.preprocessor").joinpath("prompts")
 
 
 def _render_compiled_state_contract(compiled_state: State) -> str:
-    prohibited = get_policy_items(compiled_state, "prohibit")
+    prohibited = get_policy_items(compiled_state, POLICY_PROHIBIT)
     premise = get_premise_value(compiled_state)
 
     lines: list[str] = ["The following constraints are authoritative."]

{context_compiler-0.7.3 → context_compiler-0.7.4}/examples/integrations/openwebui/README.md

@@ -18,7 +18,7 @@ These examples support both sync (`0.8.x`) and async (`0.9.x`) user lookup.
 The minimal pipe path below is the easiest first-run flow and was runtime-validated in Docker via API flow with a real backend model.
 
 1. Import `open_webui_pipe.py` (recommended/default) as a Function by URL.
-2. Open WebUI installs `context-compiler>=0.7.2` from the function frontmatter requirements.
+2. Open WebUI installs `context-compiler>=0.7.4` from the function frontmatter requirements.
 3. Enable the function.
 4. Set `BASE_MODEL_ID` to a valid Open WebUI model id (required).
 5. Select the pipe model in chat.
@@ -27,7 +27,7 @@ Open WebUI is a separate runtime and must already be installed/configured separa
 Open WebUI also needs at least one real backend model/provider configured (for example Ollama or OpenAI) so `BASE_MODEL_ID` resolves to an actual model.
 Note: The `PROVIDER` environment contract used in LiteLLM examples/demos does not apply to OpenWebUI. OpenWebUI manages providers via its own connection settings and model IDs.
 
-Checkpoint continuation in these examples requires `context-compiler>=0.7.2`.
+Checkpoint continuation in these examples requires `context-compiler>=0.7.4`.
 
 ### Model configuration
 
@@ -64,8 +64,8 @@ If frontmatter dependency installs are disabled, offline, or unavailable:
 1. Open a shell in the Open WebUI container:
    - `docker exec -it <openwebui-container> sh`
 2. Install the package manually:
-  - Minimal pipe: `pip install "context-compiler>=0.7.2"`
-  - Preprocessor pipe: `pip install "context-compiler[experimental]>=0.7.2"`
+  - Minimal pipe: `pip install "context-compiler>=0.7.4"`
+  - Preprocessor pipe: `pip install "context-compiler[experimental]>=0.7.4"`
 3. Import and enable the function in Open WebUI, then configure valves.
 
 ### Finding valid model ids