loopgain 0.1.2__tar.gz → 0.1.3__tar.gz

{loopgain-0.1.2 → loopgain-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: loopgain
-Version: 0.1.2
+Version: 0.1.3
 Summary: Barkhausen stability monitor for AI agent loops. Real-time loop-gain (Aβ) monitoring with five named threshold bands, best-so-far rollback, and ETA prediction.
 Author-email: Dave Fitzsimmons <dave_fitz@icloud.com>
 License: Apache-2.0
@@ -101,7 +101,7 @@ Plus a short-circuit: if observed error drops at or below `target_error`, the lo
 
 The `±0.05` noise band around `Aβ=1` absorbs stochastic jitter from agent outputs without triggering false-positive aborts. The `0.85` `STALLING` boundary is an early warning — by the time `Aβ` crosses `1.0`, you've already wasted iterations.
 
-These threshold defaults work well for typical agent loops out of the box. Tune them per domain (via the `ThresholdBands` argument) once you have production traces.
+These threshold defaults are derived from the Barkhausen-stability analysis and serve as reasonable starting points. Tune them per domain (via the `ThresholdBands` argument) once you have production traces.
 
 ---
 
@@ -234,5 +234,3 @@ Loop types this applies to in practice:
 - **Code generation with linter/test feedback** — generate, run tests/linter, fix, repeat. Error = failing test count or linter violation count.
 - **Multi-step reasoning loops** — ReAct-style think/act/observe iterations. Error = whatever the agent's quality assessor returns.
 - **Custom feedback loops** — anything where you can produce a number that should drop toward zero as the loop succeeds.
-
-See [loopgain.ai](https://loopgain.ai) for the longer write-up.

{loopgain-0.1.2 → loopgain-0.1.3}/README.md

@@ -73,7 +73,7 @@ Plus a short-circuit: if observed error drops at or below `target_error`, the lo
 
 The `±0.05` noise band around `Aβ=1` absorbs stochastic jitter from agent outputs without triggering false-positive aborts. The `0.85` `STALLING` boundary is an early warning — by the time `Aβ` crosses `1.0`, you've already wasted iterations.
 
-These threshold defaults work well for typical agent loops out of the box. Tune them per domain (via the `ThresholdBands` argument) once you have production traces.
+These threshold defaults are derived from the Barkhausen-stability analysis and serve as reasonable starting points. Tune them per domain (via the `ThresholdBands` argument) once you have production traces.
 
 ---
 
@@ -206,5 +206,3 @@ Loop types this applies to in practice:
 - **Code generation with linter/test feedback** — generate, run tests/linter, fix, repeat. Error = failing test count or linter violation count.
 - **Multi-step reasoning loops** — ReAct-style think/act/observe iterations. Error = whatever the agent's quality assessor returns.
 - **Custom feedback loops** — anything where you can produce a number that should drop toward zero as the loop succeeds.
-
-See [loopgain.ai](https://loopgain.ai) for the longer write-up.

{loopgain-0.1.2 → loopgain-0.1.3}/loopgain/__init__.py

@@ -24,7 +24,7 @@ from loopgain.core import (
 )
 from loopgain.telemetry import build_payload as build_telemetry_payload
 
-__version__ = "0.1.2"
+__version__ = "0.1.3"
 
 __all__ = [
     "LoopGain",

{loopgain-0.1.2 → loopgain-0.1.3}/loopgain/core.py

@@ -10,7 +10,7 @@ named states and decides whether to continue, stop, or roll back.
 
 The math is foundational EE control theory. The product layer is the
 threshold bands, the best-so-far buffer, the ETA prediction, and the
-clean Python API. See https://loopgain.ai for the long-form write-up.
+clean Python API.
 
 License: Apache-2.0
 """

{loopgain-0.1.2 → loopgain-0.1.3}/loopgain/telemetry.py

@@ -28,7 +28,7 @@ if TYPE_CHECKING:
 SCHEMA_VERSION = 1
 
 # Library version (kept in sync with __init__.py).
-LIBRARY_VERSION = "0.1.2"
+LIBRARY_VERSION = "0.1.3"
 
 
 def build_payload(

{loopgain-0.1.2 → loopgain-0.1.3}/loopgain.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: loopgain
-Version: 0.1.2
+Version: 0.1.3
 Summary: Barkhausen stability monitor for AI agent loops. Real-time loop-gain (Aβ) monitoring with five named threshold bands, best-so-far rollback, and ETA prediction.
 Author-email: Dave Fitzsimmons <dave_fitz@icloud.com>
 License: Apache-2.0
@@ -101,7 +101,7 @@ Plus a short-circuit: if observed error drops at or below `target_error`, the lo
 
 The `±0.05` noise band around `Aβ=1` absorbs stochastic jitter from agent outputs without triggering false-positive aborts. The `0.85` `STALLING` boundary is an early warning — by the time `Aβ` crosses `1.0`, you've already wasted iterations.
 
-These threshold defaults work well for typical agent loops out of the box. Tune them per domain (via the `ThresholdBands` argument) once you have production traces.
+These threshold defaults are derived from the Barkhausen-stability analysis and serve as reasonable starting points. Tune them per domain (via the `ThresholdBands` argument) once you have production traces.
 
 ---
 
@@ -234,5 +234,3 @@ Loop types this applies to in practice:
 - **Code generation with linter/test feedback** — generate, run tests/linter, fix, repeat. Error = failing test count or linter violation count.
 - **Multi-step reasoning loops** — ReAct-style think/act/observe iterations. Error = whatever the agent's quality assessor returns.
 - **Custom feedback loops** — anything where you can produce a number that should drop toward zero as the loop succeeds.
-
-See [loopgain.ai](https://loopgain.ai) for the longer write-up.

{loopgain-0.1.2 → loopgain-0.1.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "loopgain"
-version = "0.1.2"
+version = "0.1.3"
 description = "Barkhausen stability monitor for AI agent loops. Real-time loop-gain (Aβ) monitoring with five named threshold bands, best-so-far rollback, and ETA prediction."
 authors = [{name = "Dave Fitzsimmons", email = "dave_fitz@icloud.com"}]
 readme = "README.md"