evarness 0.2.1__tar.gz → 0.2.2__tar.gz

{evarness-0.2.1 → evarness-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: evarness
-Version: 0.2.1
+Version: 0.2.2
 Summary: The governed agent harness for small local models. It proves what it did.
 License: Apache-2.0
 License-File: LICENSE
@@ -122,14 +122,16 @@ evarness email demo                 # a synthetic mailbox, a scripted model, no
 The demo needs no account, no credentials and no model server. It fetches a 200-message
 synthetic mailbox, sorts it, previews and writes labels, prints a first digest, and ends with
 what it did, audit rows included. The demo keeps its own home, `~/.evarness-demo`, and never
-touches yours. Export that home's proof bundle and verify it offline:
+touches yours. Export that home's proof bundle, ledger and session logs both, and verify it
+offline:
 
 ```bash
-evarness governance proof-bundle export --db ~/.evarness-demo/governance/audit.db --out bundle.json
+evarness governance proof-bundle export --db ~/.evarness-demo/governance/audit.db \
+    --session-logs ~/.evarness-demo/logs --out bundle.json
 evarness governance proof-bundle verify bundle.json   # exit 0 verified, 1 a violation
 ```
 
-<img alt="A terminal recording: evarness email demo runs to its summary, then the proof bundle is exported and verified." src="https://github.com/evarness-ai/evarness/releases/latest/download/launch.gif" width="800">
+<img alt="A terminal recording: evarness email demo runs to its summary, then the proof bundle is exported and verified." src="https://github.com/evarness-ai/evarness/raw/main/docs/assets/recording/launch.gif" width="800">
 
 For your own mail you need [Ollama](https://ollama.com/download) and 8 GB of RAM for the
 `lite` model set, 16 GB for `standard`. Connect an account, let `evarness doctor --fix` pull
@@ -140,29 +142,14 @@ the known snags.
 
 ## How it works
 
-```mermaid
-flowchart TD
-    U["CLI, web console, Telegram, MCP clients"] --> S
-    subgraph T["Turn pipeline"]
-        direction TB
-        S["Input screen"] --> D{"A deterministic handler claims the turn?"}
-        D -- yes --> X["Exact answer, no model call"]
-        D -- no --> A["Agent loop: route, plan, act with tools, curate"]
-    end
-    subgraph G["Governance kernel: every model call, tool call and answer"]
-        direction LR
-        C["Classify data"] --> E["Egress gate"] --> P["Tool policy, approvals"] --> L["Audit ledger"]
-    end
-    X --> G
-    A --> G
-    G --> M["Model tiers: router, local tiers on Ollama or LM Studio, opt-in cloud"]
-    G --> PL["Plugins: tools, handlers, channels, mail providers"]
-```
+<img alt="How a turn is governed: the input screen, then either a deterministic handler answers with no model call or the agent loop runs; both paths pass the governance kernel (classify, egress gate, tool policy and approvals, audit ledger) before model tiers or plugins are reached." src="https://github.com/evarness-ai/evarness/raw/main/docs/assets/how-a-turn-is-governed.png" width="800">
 
 The kernel is a passage, not a filter: it runs at
 [nine fixed hook points](https://evarness-ai.github.io/evarness/concepts/governance/#hook-points)
 in every turn, and plugins cannot add, remove or reorder them. The stage-by-stage view is in
-[Architecture](https://evarness-ai.github.io/evarness/concepts/architecture/).
+[Architecture](https://evarness-ai.github.io/evarness/concepts/architecture/); the editable
+source of the drawing is
+[`docs/architecture/how-a-turn-is-governed.excalidraw`](docs/architecture/how-a-turn-is-governed.excalidraw).
 
 ## Three things a bigger model would not give you
 

{evarness-0.2.1 → evarness-0.2.2}/README.md

@@ -52,14 +52,16 @@ evarness email demo                 # a synthetic mailbox, a scripted model, no
 The demo needs no account, no credentials and no model server. It fetches a 200-message
 synthetic mailbox, sorts it, previews and writes labels, prints a first digest, and ends with
 what it did, audit rows included. The demo keeps its own home, `~/.evarness-demo`, and never
-touches yours. Export that home's proof bundle and verify it offline:
+touches yours. Export that home's proof bundle, ledger and session logs both, and verify it
+offline:
 
 ```bash
-evarness governance proof-bundle export --db ~/.evarness-demo/governance/audit.db --out bundle.json
+evarness governance proof-bundle export --db ~/.evarness-demo/governance/audit.db \
+    --session-logs ~/.evarness-demo/logs --out bundle.json
 evarness governance proof-bundle verify bundle.json   # exit 0 verified, 1 a violation
 ```
 
-<img alt="A terminal recording: evarness email demo runs to its summary, then the proof bundle is exported and verified." src="https://github.com/evarness-ai/evarness/releases/latest/download/launch.gif" width="800">
+<img alt="A terminal recording: evarness email demo runs to its summary, then the proof bundle is exported and verified." src="https://github.com/evarness-ai/evarness/raw/main/docs/assets/recording/launch.gif" width="800">
 
 For your own mail you need [Ollama](https://ollama.com/download) and 8 GB of RAM for the
 `lite` model set, 16 GB for `standard`. Connect an account, let `evarness doctor --fix` pull
@@ -70,29 +72,14 @@ the known snags.
 
 ## How it works
 
-```mermaid
-flowchart TD
-    U["CLI, web console, Telegram, MCP clients"] --> S
-    subgraph T["Turn pipeline"]
-        direction TB
-        S["Input screen"] --> D{"A deterministic handler claims the turn?"}
-        D -- yes --> X["Exact answer, no model call"]
-        D -- no --> A["Agent loop: route, plan, act with tools, curate"]
-    end
-    subgraph G["Governance kernel: every model call, tool call and answer"]
-        direction LR
-        C["Classify data"] --> E["Egress gate"] --> P["Tool policy, approvals"] --> L["Audit ledger"]
-    end
-    X --> G
-    A --> G
-    G --> M["Model tiers: router, local tiers on Ollama or LM Studio, opt-in cloud"]
-    G --> PL["Plugins: tools, handlers, channels, mail providers"]
-```
+<img alt="How a turn is governed: the input screen, then either a deterministic handler answers with no model call or the agent loop runs; both paths pass the governance kernel (classify, egress gate, tool policy and approvals, audit ledger) before model tiers or plugins are reached." src="https://github.com/evarness-ai/evarness/raw/main/docs/assets/how-a-turn-is-governed.png" width="800">
 
 The kernel is a passage, not a filter: it runs at
 [nine fixed hook points](https://evarness-ai.github.io/evarness/concepts/governance/#hook-points)
 in every turn, and plugins cannot add, remove or reorder them. The stage-by-stage view is in
-[Architecture](https://evarness-ai.github.io/evarness/concepts/architecture/).
+[Architecture](https://evarness-ai.github.io/evarness/concepts/architecture/); the editable
+source of the drawing is
+[`docs/architecture/how-a-turn-is-governed.excalidraw`](docs/architecture/how-a-turn-is-governed.excalidraw).
 
 ## Three things a bigger model would not give you
 

{evarness-0.2.1 → evarness-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "evarness"
-version = "0.2.1"
+version = "0.2.2"
 description = "The governed agent harness for small local models. It proves what it did."
 authors = ["Evarness contributors"]
 readme = "README.md"

{evarness-0.2.1 → evarness-0.2.2}/src/evarness/__init__.py

@@ -10,6 +10,6 @@ from evarness.foundation.legacy import alias_legacy_environment
 
 __all__ = ["__version__"]
 
-__version__ = "0.2.1"
+__version__ = "0.2.2"
 
 alias_legacy_environment()