openreflex 0.3.2__tar.gz → 0.5.0__tar.gz

{openreflex-0.3.2/src/openreflex.egg-info → openreflex-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openreflex
-Version: 0.3.2
+Version: 0.5.0
 Summary: Muscle memory for AI coding agents: learns from every task, advises the next one, and flags failure loops live
 Author: vishnu-77
 License-Expression: MIT
@@ -54,16 +54,17 @@ Dynamic: license-file
 
 ## What is OpenReflex
 
-OpenReflex gives AI coding agents muscle memory. It plugs into Claude Code, Codex, Cursor, and OpenCode through
-lifecycle hooks and MCP, quietly records how each task actually went, and hands the next similar task what worked
-before: the approach, the files that mattered, and the fix for the error you hit last time.
+OpenReflex gives AI coding agents muscle memory across coding, investigation, and reasoning work. It plugs into
+Claude Code, Codex, Cursor, and OpenCode through lifecycle hooks and MCP, quietly records how each task actually
+went, and hands the next similar task the useful parts of that experience.
 
-You install it once and keep working normally. Everything stays on your machine in a local SQLite database.
-There is no account, no service, and no telemetry.
+You install it once and keep working normally. Core memory stays on your machine in a local SQLite database.
+There is no OpenReflex account or hosted service. Optional Claude token accounting uses Claude Code's local
+OpenTelemetry export to a loopback-only OpenReflex receiver and stores counts only.
 
 <p align="center">
   <a href="docs/walkthrough.md">
-    <img alt="Recording of a real Claude Code session with OpenReflex: OpenReflex reports one similar past task and adds 162 context tokens, Claude finds and fixes the coupon bug, runs the tests, records the verified outcome through OpenReflex's MCP tool, and OpenReflex shows the completion recap with the path taken, cost and regret" src="https://raw.githubusercontent.com/vishnu-77/openreflex/main/docs/screenshots/claude-code-session.gif" width="860">
+    <img alt="Recording of a real Claude Code session with OpenReflex: OpenReflex reports one similar past task and adds 162 context tokens, Claude finds and fixes the coupon bug, runs the tests, records the verified outcome through OpenReflex's MCP tool, and OpenReflex shows the completion recap with the path taken and observed cost" src="https://raw.githubusercontent.com/vishnu-77/openreflex/main/docs/screenshots/claude-code-session.gif" width="860">
   </a>
   <br>
   <sub>A real Claude Code session, recorded from the terminal and sped up. OpenReflex had seen one similar task in this repository, so it adds 162 tokens of context before the first tool call; after the fix, Claude records the outcome through OpenReflex's MCP tool. The step-by-step walkthrough is in <a href="docs/walkthrough.md">docs/walkthrough.md</a>.</sub>
@@ -77,15 +78,16 @@ There is no account, no service, and no telemetry.
 - **It catches loops while they happen.** Repeated failing commands, identical retries, stalled progress, and
   runaway context growth raise one alert that says whether to continue, pivot to another approach, or stop and
   check in with you, never a stream of nags.
-- **It learns after every task.** OpenReflex infers the outcome from real verification (a test or build that
-  passed or failed after the last edit), estimates Execution Regret against the alternatives, and extracts lessons.
+- **It learns after every task.** Build work closes against tests/lint/build evidence; investigations can close
+  against cross-checked sources; reasoning-only work can complete without external tools. A simple **Path check**
+  only names a better option when comparable past tasks actually support one.
 - **It is private by design.** Only coarse, project-relative metadata is stored. File contents, commands, tool
   output, and transcripts never are, and capture is off until you approve a project.
 
 <p align="center">
   <picture>
     <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vishnu-77/openreflex/main/assets/how-it-works-dark.svg">
-    <img alt="Before a task: retrieve similar experience, score candidate paths, inject context and a budget. During a task: watch every tool call, flag loops and stalls, advise continue, pivot or stop. After a task: infer the outcome from checks, estimate Execution Regret, extract lessons. Lessons feed the Experience Graph for the next task." src="https://raw.githubusercontent.com/vishnu-77/openreflex/main/assets/how-it-works-light.svg" width="860">
+    <img alt="Before a task: retrieve similar experience, score candidate paths, inject context and a budget. During a task: watch every tool call, flag loops and stalls, advise continue, pivot or stop. After a task: close the outcome using evidence appropriate to the work, run a simple Path check, extract lessons. Lessons feed the Experience Graph for the next task." src="https://raw.githubusercontent.com/vishnu-77/openreflex/main/assets/how-it-works-light.svg" width="860">
   </picture>
 </p>
 
@@ -118,8 +120,14 @@ Then work as usual. After a few tasks:
 openreflex context "fix the login redirect bug"   # preview the context a task would receive
 openreflex status                                 # what has been captured and learned
 openreflex doctor                                 # installation checks and recent hook errors
+openreflex update --check                         # check the latest stable release
 ```
 
+Package updates preserve local memory and project configuration. Managed `pipx` and `uv tool` installs can use
+`openreflex update`, `openreflex update --reinstall`, or `openreflex self reinstall`. To remove only the package,
+use `openreflex self uninstall --yes`; project memory is preserved. A fresh bootstrap still starts with
+`pipx install openreflex` or `uv tool install openreflex` because the `openreflex` command does not exist before installation.
+
 ## Use it with your agent
 
 OpenReflex installs per project with `openreflex install <agent>`, or as a plugin.
@@ -147,12 +155,11 @@ Execution -failed_with-> ToolCall -resolved_by-> ToolCall
 Execution -caused-> Outcome -caused-> Experience -caused-> Lesson
 ```
 
-- **Before a task:** similar experiences are retrieved and three strategies (`inspect-first`, `test-first`,
-  `incremental`) are estimated on success probability, time, tool calls, context cost, risk, uncertainty,
-  reversibility, and expected regret. Strategies that another one beats on every measure are dropped as
-  dominated (Pareto efficiency), the rest are ranked by utility within any limits you set, and the chosen path
-  gets an execution budget for time, tool calls, and context. A context of at most 1,400 characters is
-  injected; nothing is injected without relevant experience.
+- **Before a task:** similar experiences are retrieved and OpenReflex first identifies the work mode. **BUILD**
+  uses `inspect-first`, `test-first`, and `incremental`; **INVESTIGATE** uses `source-first`,
+  `cross-check`, and `broad-then-deep`; **THINK** uses `reason-first`, `compare-options`, and
+  `evidence-first`. Paths are ranked using past evidence, estimated cost, risk, uncertainty and reversibility.
+  A compact context is injected only when relevant experience exists.
 - **During a task:** when a detector finds a failure loop, repeated calls, stalled progress, context growth,
   or work past the budget, OpenReflex estimates the marginal value of more work. The current path's success
   estimate is updated with each call that makes no progress or fails, and compared with the cost of the work
@@ -160,9 +167,9 @@ Execution -caused-> Outcome -caused-> Experience -caused-> Lesson
   to another strategy, or **stop** and ask the user. Each problem, pivot, or stop is raised once, with a cooldown
   between messages.
 - **After a task:** outcome and chosen path come from the agent's `record_outcome` / `choose_path` MCP calls when
-  available, and are otherwise inferred from tool activity. Execution Regret compares the path taken with the
-  best plausible alternative; it is withheld when the outcome is unknown, and feeds back into how strategies
-  are ranked next time, along with success, cost, and how often a strategy ran into trouble.
+  available, and are otherwise inferred from work-mode-appropriate evidence. The **Path check** says either
+  `better option: <path>` when comparable completed tasks support it or `better option: none proven`.
+  Recommendations are never presented as paths that were actually executed.
 
 Every recommendation is stored as a decision snapshot with a **Reflex Score** (0-100): how strong the
 recommendation is, which is separate from the estimated chance that the task succeeds. `openreflex why` explains
@@ -183,7 +190,7 @@ Agents can also query OpenReflex directly through its MCP server.
 | `get_execution_context` | Plan a task: similar past tasks, the suggested strategy with alternatives, a budget, likely files, lessons. Optional `max_tool_calls`, `max_minutes`, `max_context_tokens`. |
 | `check_progress` | Whether more work on the current path is worth it: continue, pivot or stop. |
 | `choose_path` | Declare the strategy being followed when it differs from the suggestion. |
-| `record_outcome` | Record a verified outcome (tests passed, user confirmed, or failure) and learn from it. |
+| `record_outcome` | Record a confirmed outcome (tests/builds, cross-checked research, user confirmation, or failure) and learn from it. |
 | `explain_decision` | Why the latest recommendation was made: Reflex Score, signals, confidence, next-best route. |
 | `get_execution_trace` | The decision timeline of the most recent task. |
 | `get_reflex_score` | The latest Reflex Score and its components as JSON. |
@@ -201,12 +208,16 @@ Agents can also query OpenReflex directly through its MCP server.
 |---|---|
 | `install <agent> [--dry-run]` | Write project hooks and MCP config, and enable the project |
 | `uninstall <agent> [--dry-run]` | Remove OpenReflex's project hooks and MCP config; captured memory is kept |
+| `update [--check] [--reinstall]` | Check or update a managed pipx/uv-tool installation; optionally force a reinstall |
+| `self reinstall` | Repair/reinstall the managed OpenReflex package while preserving memory/config |
+| `self uninstall --yes` | Remove only the managed OpenReflex package; memory/config remain on disk |
 | `approve` / `revoke` | Enable or disable capture for the current project |
 | `context "<task>"` | Preview the Execution Context a task would receive |
-| `status [--json]` | What has been captured, reused, and learned |
+| `status [--json]` | What has been captured, reused, learned, and how model-token usage compares |
 | `why` / `trace` | Explain the latest recommendation, or show the decision timeline |
 | `doctor` | Installation, project resolution, and recent hook activity checks |
 | `forget --yes` | Delete the project's data |
+| `tokens enable` / `tokens status` / `tokens disable` | Opt in to local Claude Code token accounting, inspect it, or remove OpenReflex-owned telemetry settings |
 | `benchmark` | Run the simulated benchmark |
 | `hook <agent> <event>` / `mcp` | Used by agent configs |
 
@@ -218,8 +229,9 @@ Agents can also query OpenReflex directly through its MCP server.
 | A fingerprint of the arguments | Command text |
 | Project-relative file paths | Tool output |
 | Pass or fail, duration, output size | Transcripts and model output |
+| Optional model-token counts, model/source label, estimated cost | Prompt/response/tool contents from Claude telemetry |
 | A masked one-line error signature | Paths outside the project |
-| The prompt as a task description (up to 1,000 characters, secrets redacted) | Anything sent to a server: there is none |
+| The prompt as a task description (up to 1,000 characters, secrets redacted) | Anything sent to an OpenReflex-hosted service: there is none |
 
 Data lives in `~/.openreflex/projects/<hash>/experience.sqlite3`. Set `OPENREFLEX_HOME` to move it,
 `OPENREFLEX_DISABLE=1` to turn capture off everywhere, `openreflex forget --yes` to delete a project's data, or ask
@@ -228,9 +240,10 @@ your agent to `forget_experience` a single task.
 ## Research
 
 OpenReflex is also a research project in budget-aware execution: instead of treating success as a yes or no, it
-studies how agents choose execution paths, spend tool calls and context, respond to uncertainty, and whether more
-computation still adds value. The loop is experience retrieval, Pareto path selection, budget-aware execution and
-counterfactual regret. The [Researcher view](https://openreflex.cc/?view=research) on the site explains the idea,
+studies how agents choose execution paths, spend tool calls, model tokens and context, respond to uncertainty, and
+whether past work makes similar future work cheaper without reducing outcome quality. The loop is experience
+retrieval, evidence-aware path selection, budget-aware execution, work-mode-specific completion and plain-language
+path comparison. The [Researcher view](https://openreflex.cc/?view=research) on the site explains the idea,
 lets you step through one reflex forming in the graph, and places it next to related work.
 
 ## Community & Contributing

{openreflex-0.3.2 → openreflex-0.5.0}/README.md

@@ -22,16 +22,17 @@
 
 ## What is OpenReflex
 
-OpenReflex gives AI coding agents muscle memory. It plugs into Claude Code, Codex, Cursor, and OpenCode through
-lifecycle hooks and MCP, quietly records how each task actually went, and hands the next similar task what worked
-before: the approach, the files that mattered, and the fix for the error you hit last time.
+OpenReflex gives AI coding agents muscle memory across coding, investigation, and reasoning work. It plugs into
+Claude Code, Codex, Cursor, and OpenCode through lifecycle hooks and MCP, quietly records how each task actually
+went, and hands the next similar task the useful parts of that experience.
 
-You install it once and keep working normally. Everything stays on your machine in a local SQLite database.
-There is no account, no service, and no telemetry.
+You install it once and keep working normally. Core memory stays on your machine in a local SQLite database.
+There is no OpenReflex account or hosted service. Optional Claude token accounting uses Claude Code's local
+OpenTelemetry export to a loopback-only OpenReflex receiver and stores counts only.
 
 <p align="center">
   <a href="docs/walkthrough.md">
-    <img alt="Recording of a real Claude Code session with OpenReflex: OpenReflex reports one similar past task and adds 162 context tokens, Claude finds and fixes the coupon bug, runs the tests, records the verified outcome through OpenReflex's MCP tool, and OpenReflex shows the completion recap with the path taken, cost and regret" src="https://raw.githubusercontent.com/vishnu-77/openreflex/main/docs/screenshots/claude-code-session.gif" width="860">
+    <img alt="Recording of a real Claude Code session with OpenReflex: OpenReflex reports one similar past task and adds 162 context tokens, Claude finds and fixes the coupon bug, runs the tests, records the verified outcome through OpenReflex's MCP tool, and OpenReflex shows the completion recap with the path taken and observed cost" src="https://raw.githubusercontent.com/vishnu-77/openreflex/main/docs/screenshots/claude-code-session.gif" width="860">
   </a>
   <br>
   <sub>A real Claude Code session, recorded from the terminal and sped up. OpenReflex had seen one similar task in this repository, so it adds 162 tokens of context before the first tool call; after the fix, Claude records the outcome through OpenReflex's MCP tool. The step-by-step walkthrough is in <a href="docs/walkthrough.md">docs/walkthrough.md</a>.</sub>
@@ -45,15 +46,16 @@ There is no account, no service, and no telemetry.
 - **It catches loops while they happen.** Repeated failing commands, identical retries, stalled progress, and
   runaway context growth raise one alert that says whether to continue, pivot to another approach, or stop and
   check in with you, never a stream of nags.
-- **It learns after every task.** OpenReflex infers the outcome from real verification (a test or build that
-  passed or failed after the last edit), estimates Execution Regret against the alternatives, and extracts lessons.
+- **It learns after every task.** Build work closes against tests/lint/build evidence; investigations can close
+  against cross-checked sources; reasoning-only work can complete without external tools. A simple **Path check**
+  only names a better option when comparable past tasks actually support one.
 - **It is private by design.** Only coarse, project-relative metadata is stored. File contents, commands, tool
   output, and transcripts never are, and capture is off until you approve a project.
 
 <p align="center">
   <picture>
     <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vishnu-77/openreflex/main/assets/how-it-works-dark.svg">
-    <img alt="Before a task: retrieve similar experience, score candidate paths, inject context and a budget. During a task: watch every tool call, flag loops and stalls, advise continue, pivot or stop. After a task: infer the outcome from checks, estimate Execution Regret, extract lessons. Lessons feed the Experience Graph for the next task." src="https://raw.githubusercontent.com/vishnu-77/openreflex/main/assets/how-it-works-light.svg" width="860">
+    <img alt="Before a task: retrieve similar experience, score candidate paths, inject context and a budget. During a task: watch every tool call, flag loops and stalls, advise continue, pivot or stop. After a task: close the outcome using evidence appropriate to the work, run a simple Path check, extract lessons. Lessons feed the Experience Graph for the next task." src="https://raw.githubusercontent.com/vishnu-77/openreflex/main/assets/how-it-works-light.svg" width="860">
   </picture>
 </p>
 
@@ -86,8 +88,14 @@ Then work as usual. After a few tasks:
 openreflex context "fix the login redirect bug"   # preview the context a task would receive
 openreflex status                                 # what has been captured and learned
 openreflex doctor                                 # installation checks and recent hook errors
+openreflex update --check                         # check the latest stable release
 ```
 
+Package updates preserve local memory and project configuration. Managed `pipx` and `uv tool` installs can use
+`openreflex update`, `openreflex update --reinstall`, or `openreflex self reinstall`. To remove only the package,
+use `openreflex self uninstall --yes`; project memory is preserved. A fresh bootstrap still starts with
+`pipx install openreflex` or `uv tool install openreflex` because the `openreflex` command does not exist before installation.
+
 ## Use it with your agent
 
 OpenReflex installs per project with `openreflex install <agent>`, or as a plugin.
@@ -115,12 +123,11 @@ Execution -failed_with-> ToolCall -resolved_by-> ToolCall
 Execution -caused-> Outcome -caused-> Experience -caused-> Lesson
 ```
 
-- **Before a task:** similar experiences are retrieved and three strategies (`inspect-first`, `test-first`,
-  `incremental`) are estimated on success probability, time, tool calls, context cost, risk, uncertainty,
-  reversibility, and expected regret. Strategies that another one beats on every measure are dropped as
-  dominated (Pareto efficiency), the rest are ranked by utility within any limits you set, and the chosen path
-  gets an execution budget for time, tool calls, and context. A context of at most 1,400 characters is
-  injected; nothing is injected without relevant experience.
+- **Before a task:** similar experiences are retrieved and OpenReflex first identifies the work mode. **BUILD**
+  uses `inspect-first`, `test-first`, and `incremental`; **INVESTIGATE** uses `source-first`,
+  `cross-check`, and `broad-then-deep`; **THINK** uses `reason-first`, `compare-options`, and
+  `evidence-first`. Paths are ranked using past evidence, estimated cost, risk, uncertainty and reversibility.
+  A compact context is injected only when relevant experience exists.
 - **During a task:** when a detector finds a failure loop, repeated calls, stalled progress, context growth,
   or work past the budget, OpenReflex estimates the marginal value of more work. The current path's success
   estimate is updated with each call that makes no progress or fails, and compared with the cost of the work
@@ -128,9 +135,9 @@ Execution -caused-> Outcome -caused-> Experience -caused-> Lesson
   to another strategy, or **stop** and ask the user. Each problem, pivot, or stop is raised once, with a cooldown
   between messages.
 - **After a task:** outcome and chosen path come from the agent's `record_outcome` / `choose_path` MCP calls when
-  available, and are otherwise inferred from tool activity. Execution Regret compares the path taken with the
-  best plausible alternative; it is withheld when the outcome is unknown, and feeds back into how strategies
-  are ranked next time, along with success, cost, and how often a strategy ran into trouble.
+  available, and are otherwise inferred from work-mode-appropriate evidence. The **Path check** says either
+  `better option: <path>` when comparable completed tasks support it or `better option: none proven`.
+  Recommendations are never presented as paths that were actually executed.
 
 Every recommendation is stored as a decision snapshot with a **Reflex Score** (0-100): how strong the
 recommendation is, which is separate from the estimated chance that the task succeeds. `openreflex why` explains
@@ -151,7 +158,7 @@ Agents can also query OpenReflex directly through its MCP server.
 | `get_execution_context` | Plan a task: similar past tasks, the suggested strategy with alternatives, a budget, likely files, lessons. Optional `max_tool_calls`, `max_minutes`, `max_context_tokens`. |
 | `check_progress` | Whether more work on the current path is worth it: continue, pivot or stop. |
 | `choose_path` | Declare the strategy being followed when it differs from the suggestion. |
-| `record_outcome` | Record a verified outcome (tests passed, user confirmed, or failure) and learn from it. |
+| `record_outcome` | Record a confirmed outcome (tests/builds, cross-checked research, user confirmation, or failure) and learn from it. |
 | `explain_decision` | Why the latest recommendation was made: Reflex Score, signals, confidence, next-best route. |
 | `get_execution_trace` | The decision timeline of the most recent task. |
 | `get_reflex_score` | The latest Reflex Score and its components as JSON. |
@@ -169,12 +176,16 @@ Agents can also query OpenReflex directly through its MCP server.
 |---|---|
 | `install <agent> [--dry-run]` | Write project hooks and MCP config, and enable the project |
 | `uninstall <agent> [--dry-run]` | Remove OpenReflex's project hooks and MCP config; captured memory is kept |
+| `update [--check] [--reinstall]` | Check or update a managed pipx/uv-tool installation; optionally force a reinstall |
+| `self reinstall` | Repair/reinstall the managed OpenReflex package while preserving memory/config |
+| `self uninstall --yes` | Remove only the managed OpenReflex package; memory/config remain on disk |
 | `approve` / `revoke` | Enable or disable capture for the current project |
 | `context "<task>"` | Preview the Execution Context a task would receive |
-| `status [--json]` | What has been captured, reused, and learned |
+| `status [--json]` | What has been captured, reused, learned, and how model-token usage compares |
 | `why` / `trace` | Explain the latest recommendation, or show the decision timeline |
 | `doctor` | Installation, project resolution, and recent hook activity checks |
 | `forget --yes` | Delete the project's data |
+| `tokens enable` / `tokens status` / `tokens disable` | Opt in to local Claude Code token accounting, inspect it, or remove OpenReflex-owned telemetry settings |
 | `benchmark` | Run the simulated benchmark |
 | `hook <agent> <event>` / `mcp` | Used by agent configs |
 
@@ -186,8 +197,9 @@ Agents can also query OpenReflex directly through its MCP server.
 | A fingerprint of the arguments | Command text |
 | Project-relative file paths | Tool output |
 | Pass or fail, duration, output size | Transcripts and model output |
+| Optional model-token counts, model/source label, estimated cost | Prompt/response/tool contents from Claude telemetry |
 | A masked one-line error signature | Paths outside the project |
-| The prompt as a task description (up to 1,000 characters, secrets redacted) | Anything sent to a server: there is none |
+| The prompt as a task description (up to 1,000 characters, secrets redacted) | Anything sent to an OpenReflex-hosted service: there is none |
 
 Data lives in `~/.openreflex/projects/<hash>/experience.sqlite3`. Set `OPENREFLEX_HOME` to move it,
 `OPENREFLEX_DISABLE=1` to turn capture off everywhere, `openreflex forget --yes` to delete a project's data, or ask
@@ -196,9 +208,10 @@ your agent to `forget_experience` a single task.
 ## Research
 
 OpenReflex is also a research project in budget-aware execution: instead of treating success as a yes or no, it
-studies how agents choose execution paths, spend tool calls and context, respond to uncertainty, and whether more
-computation still adds value. The loop is experience retrieval, Pareto path selection, budget-aware execution and
-counterfactual regret. The [Researcher view](https://openreflex.cc/?view=research) on the site explains the idea,
+studies how agents choose execution paths, spend tool calls, model tokens and context, respond to uncertainty, and
+whether past work makes similar future work cheaper without reducing outcome quality. The loop is experience
+retrieval, evidence-aware path selection, budget-aware execution, work-mode-specific completion and plain-language
+path comparison. The [Researcher view](https://openreflex.cc/?view=research) on the site explains the idea,
 lets you step through one reflex forming in the graph, and places it next to related work.
 
 ## Community & Contributing
@@ -225,4 +238,4 @@ OpenReflex is listed in the [MCP Registry](https://registry.modelcontextprotocol
 
 ## License
 
-OpenReflex is released under the [MIT License](https://github.com/vishnu-77/openreflex/blob/main/LICENSE).
+OpenReflex is released under the [MIT License](https://github.com/vishnu-77/openreflex/blob/main/LICENSE).

{openreflex-0.3.2 → openreflex-0.5.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "openreflex"
-version = "0.3.2"
+version = "0.5.0"
 description = "Muscle memory for AI coding agents: learns from every task, advises the next one, and flags failure loops live"
 readme = "README.md"
 license = "MIT"
@@ -35,7 +35,7 @@ Issues = "https://github.com/vishnu-77/openreflex/issues"
 dev = ["pytest>=8,<9", "ruff>=0.12", "build>=1.2", "twine>=6"]
 
 [project.scripts]
-openreflex = "openreflex.cli:main"
+openreflex = "openreflex.entrypoint:main"
 
 [tool.setuptools.packages.find]
 where = ["src"]

{openreflex-0.3.2 → openreflex-0.5.0}/src/openreflex/__init__.py

@@ -1,3 +1,3 @@
 """Ambient, local execution intelligence."""
 
-__version__ = "0.3.2"
+__version__ = "0.5.0"

{openreflex-0.3.2 → openreflex-0.5.0}/src/openreflex/__main__.py

@@ -1,5 +1,5 @@
 import sys
 
-from .cli import main
+from .entrypoint import main
 
 sys.exit(main())

{openreflex-0.3.2 → openreflex-0.5.0}/src/openreflex/benchmark.py

@@ -206,11 +206,9 @@ def format_report(report: dict) -> str:
     b, g, c = report["baseline"], report["guided"], report["relative_change"]
     rows = [
         ("tool calls / task", b["tool_calls"], g["tool_calls"], f"{c['tool_calls']:+.0%}"),
-        ("output tokens / task", b["tokens"], g["tokens"], f"{c['tokens']:+.0%}"),
+        ("sim. tool-output tokens / task", b["tokens"], g["tokens"], f"{c['tokens']:+.0%}"),
         ("time / task (s)", b["seconds"], g["seconds"], f"{c['time']:+.0%}"),
         ("success rate", b["success_rate"], g["success_rate"], f"{c['success_rate_points']:+.3f} pts"),
-        ("regret, first quarter", b["regret_first_quarter"], g["regret_first_quarter"], ""),
-        ("regret, last quarter", b["regret_last_quarter"], g["regret_last_quarter"], ""),
         ("routing agreement (2nd half)", "-", g["routing_agreement_second_half"], ""),
     ]
     lines = [f"SIMULATED benchmark - {report['episodes_per_arm']} tasks/arm x {report['seeds']} seeds "

openreflex-0.5.0/src/openreflex/claude_ui.py

@@ -0,0 +1,52 @@
+"""Claude Code presentation integration.
+
+OpenReflex only installs its status line when the project has no existing custom
+statusLine. A user-owned status line is never replaced.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from pathlib import Path
+
+STATUSLINE_COMMAND = "openreflex statusline"
+
+
+def _load(path: Path) -> dict:
+    try:
+        value = json.loads(path.read_text(encoding="utf-8"))
+        return value if isinstance(value, dict) else {}
+    except (OSError, ValueError):
+        return {}
+
+
+def _write(path: Path, data: dict) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    temp = path.with_suffix(path.suffix + ".tmp")
+    temp.write_text(json.dumps(data, indent=2) + "\n", encoding="utf-8")
+    os.replace(temp, path)
+
+
+def configure_statusline(project: Path) -> str:
+    path = project / ".claude" / "settings.json"
+    data = _load(path)
+    existing = data.get("statusLine")
+    if isinstance(existing, dict):
+        if existing.get("command") == STATUSLINE_COMMAND:
+            return "already-configured"
+        return "preserved-existing"
+    data["statusLine"] = {"type": "command", "command": STATUSLINE_COMMAND, "padding": 0, "refreshInterval": 2}
+    _write(path, data)
+    return "configured"
+
+
+def remove_statusline(project: Path) -> bool:
+    path = project / ".claude" / "settings.json"
+    data = _load(path)
+    current = data.get("statusLine")
+    if not isinstance(current, dict) or current.get("command") != STATUSLINE_COMMAND:
+        return False
+    data.pop("statusLine", None)
+    _write(path, data)
+    return True

{openreflex-0.3.2 → openreflex-0.5.0}/src/openreflex/cli.py

@@ -117,7 +117,7 @@ def cmd_status(args) -> int:
     if args.json:
         print(json.dumps(data, indent=2))
         return 0
-    reuse, regret, routing = data["experience_reuse"], data["execution_regret"], data["routing"]
+    reuse, path_check, routing = data["experience_reuse"], data["path_check"], data["routing"]
     eff = data["efficiency_observational"]
     print(f"OpenReflex {__version__} - {project}")
     print(f"  enabled: {data['enabled']}   agents: {', '.join(data['engagement']['agents']) or '-'}")
@@ -128,7 +128,10 @@ def cmd_status(args) -> int:
     print(f"  success rate (known outcomes): {data['outcomes']['success_rate']}   verified: {data['outcomes']['verified']}")
     print(f"  tool calls with vs without prior experience: {eff['with_prior_experience']['tool_calls']} vs "
           f"{eff['without_prior_experience']['tool_calls']} (observational)")
-    print(f"  mean execution regret: {regret['mean']}   routing agreement: {routing['agreement']}")
+    print(f"  model tokens with vs without prior experience: {eff['with_prior_experience']['model_tokens']} vs "
+          f"{eff['without_prior_experience']['model_tokens']} (observational)")
+    print(f"  path checks: {path_check['comparisons']}   better option found: {path_check['better_option_found']}   "
+          f"routing agreement: {routing['agreement']}")
     print(f"  live alerts: {data['live_alerts'] or '-'}")
     control = data["execution_control"]
     print(f"  verdicts: {control['verdicts'] or '-'}   tasks within tool-call budget: {control['tasks_within_tool_call_budget']}")
@@ -168,6 +171,128 @@ def cmd_trace(args) -> int:
     return 0
 
 
+def cmd_update(args) -> int:
+    from .updater import (
+        check_for_update,
+        detect_install_plan,
+        installed_version_after_update,
+        run_reinstall,
+        run_update,
+    )
+
+    print("OPENREFLEX / UPDATE")
+    try:
+        status = check_for_update(__version__)
+    except RuntimeError as exc:
+        print(f"  current     {__version__}")
+        print(f"  check       failed ({exc})")
+        print("\nNo changes were made.")
+        return 1
+
+    plan = detect_install_plan()
+    print(f"  current     {status.current}")
+    print(f"  latest      {status.latest}")
+    print(f"  install     {plan.method}")
+
+    if args.check:
+        if status.update_available:
+            print("\n  update      available")
+            print("Run `openreflex update` to install it.")
+        elif status.current == status.latest:
+            print("\n  [ok] already up to date")
+        else:
+            print("\n  [ok] current build is newer than the latest PyPI release")
+        return 0
+
+    if args.reinstall:
+        if plan.reinstall_command is None:
+            print(f"\n  [--] automatic reinstall unavailable: {plan.detail}")
+            print("No changes were made.")
+            return 2
+        print(f"  method      {' '.join(plan.reinstall_command)}")
+        print("\nReinstalling OpenReflex...")
+        returncode = run_reinstall(plan)
+    else:
+        if not status.update_available:
+            if status.current == status.latest:
+                print("\n  [ok] already up to date")
+            else:
+                print("\n  [ok] current build is newer than the latest PyPI release")
+            return 0
+        if plan.command is None:
+            print(f"\n  [--] automatic update unavailable: {plan.detail}")
+            print("No changes were made.")
+            return 2
+        print(f"  method      {' '.join(plan.command)}")
+        print("\nUpdating OpenReflex...")
+        returncode = run_update(plan)
+
+    if returncode != 0:
+        action = "reinstall" if args.reinstall else "update"
+        print(f"\n  [--] {action} failed with exit code {returncode}")
+        print("Your project memory and agent configuration were not modified by OpenReflex.")
+        return returncode or 1
+
+    installed = installed_version_after_update()
+    action = "reinstalled" if args.reinstall else "updated"
+    print(f"\n  [ok] {action} {installed or status.latest}")
+    if not args.reinstall and installed and installed != status.latest:
+        print(f"  note        expected {status.latest}; executable reports {installed}")
+    print("  memory      preserved")
+    print("  config      preserved")
+    print("\nRestart active Claude Code, Codex, Cursor, or OpenCode sessions to reload hooks and MCP.")
+    return 0
+
+
+def cmd_self(args) -> int:
+    from .updater import detect_install_plan, run_reinstall, run_uninstall
+
+    plan = detect_install_plan()
+    print("OPENREFLEX / SELF")
+    print(f"  action      {args.self_action}")
+    print(f"  install     {plan.method}")
+
+    if args.self_action == "reinstall":
+        if plan.reinstall_command is None:
+            print(f"\n  [--] automatic reinstall unavailable: {plan.detail}")
+            print("No changes were made.")
+            return 2
+        print(f"  method      {' '.join(plan.reinstall_command)}")
+        print("\nReinstalling OpenReflex...")
+        returncode = run_reinstall(plan)
+        if returncode != 0:
+            print(f"\n  [--] reinstall failed with exit code {returncode}")
+            return returncode or 1
+        print("\n  [ok] package reinstalled")
+        print("  memory      preserved")
+        print("  config      preserved")
+        print("\nRestart active agent sessions to reload hooks and MCP.")
+        return 0
+
+    if args.self_action == "uninstall":
+        if not args.yes:
+            print("\nThis removes the OpenReflex executable/package but preserves ~/.openreflex memory and project configuration.")
+            print("Re-run with `openreflex self uninstall --yes` to confirm.")
+            return 1
+        if plan.uninstall_command is None:
+            print(f"\n  [--] automatic uninstall unavailable: {plan.detail}")
+            print("No changes were made.")
+            return 2
+        print(f"  method      {' '.join(plan.uninstall_command)}")
+        print("\nUninstalling OpenReflex package...")
+        returncode = run_uninstall(plan)
+        if returncode != 0:
+            print(f"\n  [--] uninstall failed with exit code {returncode}")
+            return returncode or 1
+        print("\n  [ok] package uninstalled")
+        print("  memory      preserved")
+        print("  config      preserved")
+        print("\nProject hooks/config remain on disk but cannot run until OpenReflex is installed again.")
+        return 0
+
+    return 2
+
+
 def _json(path: Path) -> dict:
     try:
         value = json.loads(path.read_text(encoding="utf-8"))
@@ -300,7 +425,21 @@ def build_parser() -> argparse.ArgumentParser:
         command.add_argument("--dry-run", action="store_true")
         command.set_defaults(func=func)
 
-    status = sub.add_parser("status", help="Show capture, reuse, regret, and routing metrics")
+    update = sub.add_parser("update", help="Check PyPI and safely update the managed OpenReflex installation")
+    update_group = update.add_mutually_exclusive_group()
+    update_group.add_argument("--check", action="store_true", help="Only report whether an update is available")
+    update_group.add_argument("--reinstall", action="store_true", help="Reinstall the stable package even if already current")
+    update.set_defaults(func=cmd_update)
+
+    self_cmd = sub.add_parser("self", help="Manage the installed OpenReflex package without deleting memory")
+    self_sub = self_cmd.add_subparsers(dest="self_action", required=True)
+    self_reinstall = self_sub.add_parser("reinstall", help="Reinstall the managed OpenReflex package")
+    self_reinstall.set_defaults(func=cmd_self)
+    self_uninstall = self_sub.add_parser("uninstall", help="Remove the OpenReflex package but preserve memory/config")
+    self_uninstall.add_argument("--yes", action="store_true", help="Confirm package removal")
+    self_uninstall.set_defaults(func=cmd_self)
+
+    status = sub.add_parser("status", help="Show capture, reuse, token efficiency, path checks, and routing metrics")
     status.add_argument("--project")
     status.add_argument("--json", action="store_true")
     status.set_defaults(func=cmd_status)