devopsiq 0.1.1__tar.gz → 0.1.3__tar.gz

{devopsiq-0.1.1/devopsiq.egg-info → devopsiq-0.1.3}/PKG-INFO

@@ -1,12 +1,13 @@
 Metadata-Version: 2.4
 Name: devopsiq
-Version: 0.1.1
+Version: 0.1.3
 Summary: A from-scratch, read-only AI agent that investigates real DevOps problems — Kubernetes, Docker, Helm, Argo CD, Istio, Terraform, GitHub Actions, cloud, New Relic and more.
 Author: DevOpsAbhii
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/DevOpsAbhii/devops-ai-agent
 Project-URL: Repository, https://github.com/DevOpsAbhii/devops-ai-agent
 Project-URL: Issues, https://github.com/DevOpsAbhii/devops-ai-agent/issues
+Project-URL: Changelog, https://github.com/DevOpsAbhii/devops-ai-agent/blob/main/CHANGELOG.md
 Keywords: devops,kubernetes,docker,helm,argocd,istio,terraform,github-actions,observability,newrelic,incident-response,root-cause-analysis,ai-agent,cli
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
@@ -29,6 +30,13 @@ Dynamic: license-file
 
 # DevOps AI Agent
 
+[![PyPI](https://img.shields.io/pypi/v/devopsiq)](https://pypi.org/project/devopsiq/)
+[![Python](https://img.shields.io/pypi/pyversions/devopsiq)](https://pypi.org/project/devopsiq/)
+[![Release](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml/badge.svg)](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml)
+[![Docker](https://img.shields.io/badge/ghcr-devops--ai--agent-2496ED?logo=docker&logoColor=white)](https://github.com/DevOpsAbhii/devops-ai-agent/pkgs/container/devops-ai-agent)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Tests](https://img.shields.io/badge/tests-181%20offline-brightgreen)](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml)
+
 An AI agent that investigates real DevOps problems. The end goal: ask it
 something like *"Why is my Kubernetes pod in CrashLoopBackOff?"* and have it
 gather evidence, reason about the evidence, identify the likely root cause,
@@ -55,10 +63,21 @@ from environment config), and Ansible listing (inventory, playbook tasks).
 open alerts over NerdGraph — credentials from env), Trivy image
 vulnerability scanning, Helm releases (list/status/history), Argo CD
 (GitOps app sync/health), Istio mesh proxy status, and Docker Compose
-(project and service listing). The repository is git-tracked.
+(project and service listing). **Phase 10 ships it as a product:** the
+[`devopsiq` package on PyPI](https://pypi.org/project/devopsiq/) and a
+prebuilt multi-arch Docker image (`ghcr.io/devopsabhii/devops-ai-agent`) —
+both cut automatically by pushing a `v*` tag (test gate → PyPI via Trusted
+Publishing + GHCR in parallel). **No API key? The agent still runs:** it
+starts in model-less mode — record commands (`/report`, `/investigations`)
+and the whole 58-tool layer work without a key; only questions to the model
+need one. The repository is git-tracked.
 Every phase still built from scratch — no LangChain, LangGraph,
 AutoGen, CrewAI, or MCP.
 
+> **New here?** The [Install & run guide (PDF)](DevOps_User_Guide.pdf) walks
+> you from zero to investigating — three install routes, credentials
+> (or none at all), model choice, and every command.
+
 > **Want to use this in your own project?** See [INTEGRATION.md](INTEGRATION.md)
 > for the three integration levels: drive it as a CLI from cron/CI (exit
 > codes + `--json`), embed it as a Python library, or extend it with your
@@ -73,7 +92,7 @@ model is called, how conversation history flows, how tool selection +
 execution + evidence feedback work — instead of depending on a framework
 for it.
 
-In Phase 5 the agent:
+Today the agent:
 - holds a conversation with **GLM 5.3** through **OpenRouter**;
 - has **58 real, read-only tools** across fifteen domains: host facts,
   Kubernetes (12 tools), Linux system (4), Docker + Compose (10),
@@ -133,8 +152,8 @@ Module map:
 
 | Path                        | Responsibility                                              |
 | --------------------------- | ------------------------------------------------------------ |
-| `main.py`                   | REPL loop, one-shot CLI, environment loading, `/investigate` commands, error messages |
-| `agent/agent.py`            | `DevOpsAgent` — client, history, `ask()`, `_complete()` loop |
+| `main.py`                   | REPL loop, one-shot CLI, environment loading, `/investigate` commands, error messages, model-less start |
+| `agent/agent.py`            | `DevOpsAgent` — client (`None` = model-less mode), history, `ask()`, `_complete()` loop |
 | `agent/prompts.py`          | The system prompt (versioned/tested separately)              |
 | `agent/investigation.py`    | First-class investigation record: hypotheses, verdicts, evidence, report renderer (pure data) |
 | `agent/store.py`            | `InvestigationStore` — one JSON file per record, atomic writes, resume/list (Phase 7) |
@@ -163,6 +182,11 @@ Module map:
 | `tests/test_phase7.py`      | Offline suite: round-trip serialization, store files, auto-save, resume, CLI flags (Phase 7) |
 | `tests/test_phase8.py`      | Offline suite: argv templates + validation for the 21 Phase 8 tools (fake CLIs, env-based monitoring) |
 | `tests/test_phase9.py`      | Offline suite: New Relic env-credential + payload tests, trivy/helm/argocd/istio/compose argv templates (Phase 9) |
+| `pyproject.toml`            | Package `devopsiq`: metadata, MIT, console script `devopsiq = main:main` (Phase 10) |
+| `Dockerfile`                | Prebuilt image: slim base + kubectl/helm/trivy/gh + app, non-root, `/data` record store (Phase 10) |
+| `.github/workflows/release.yml` | Tag-driven release: test gate → PyPI (Trusted Publishing) + GHCR multi-arch (Phase 10) |
+| `docs/generate_pdf.py`      | Builds the project documentation PDF from live source |
+| `docs/generate_release_guide.py` | Builds the release & update playbook PDF |
 
 ### The tool-use loop
 
@@ -209,6 +233,7 @@ the CLI exposes it directly:
 | `/investigations`        | List saved records on disk (newest first; `← active` marks the live one) |
 | `/report`                | Show the canonical report (once concluded)          |
 | `/endinvestigation`      | Clear the record (memory only — the saved copy stays as history) |
+| `/model [<name>]`        | Show the active model, or save a default (config.json) and switch to it |
 
 The report the agent ends with and `/report` render are kept consistent by
 construction: `tool` results confirm each record call and the tracker, and
@@ -396,16 +421,22 @@ official `openai` Python SDK works as our client with two config lines:
 OpenAI(api_key=..., base_url="https://openrouter.ai/api/v1")
 ```
 
-Swapping to another OpenRouter model later is a one-line change (an env var
-today); moving to any other OpenAI-compatible provider changes only
-`agent/agent.py` configuration.
+Swapping to another OpenRouter model later is a one-liner (env var, `/model`
+command, or `--model` flag); moving to any other OpenAI-compatible provider
+changes only `agent/agent.py` configuration.
 
 **Your model, your choice.** The default is baked in as a fallback, never a
-restriction — set `OPENROUTER_MODEL` (shell or `.env`) to any model on
-OpenRouter:
+restriction. Four ways to set the model — the first one set wins:
+
+1. `--model NAME` flag (one run: `devopsiq --model openai/gpt-5.2 "why?"`)
+2. `/model <name>` in the REPL — saves it to `~/.devops-ai-agent/config.json`
+   so every future run uses it
+3. `OPENROUTER_MODEL` (shell or `.env`)
+4. built-in default (`z-ai/glm-5.3`)
 
 ```bash
 export OPENROUTER_MODEL=anthropic/claude-sonnet-5   # or openai/gpt-5.2, google/gemini-2.5-pro, ...
+devopsiq /model openai/gpt-5.2                      # or save a default from the REPL
 ```
 
 Two things to weigh when picking: the agent is a tool-use loop, so choose a
@@ -558,6 +589,7 @@ setup/API errors — so it drops straight into a pipeline:
 .venv/bin/python main.py --json "why is api-5d6f crash-looping?"   # structured report
 .venv/bin/python main.py --resume --json "any update?"             # continue a prior run
 .venv/bin/python main.py --store-dir /tmp/runs --out report.json "..."  # pipeline paths
+.venv/bin/python main.py --model openai/gpt-5.2 "why is it down?"   # one-run model override
 ```
 
 With `--json` the stdout is one JSON document (see `render_report_json` in
@@ -599,8 +631,8 @@ Tools:   ansible_inventory, ansible_playbook_tasks, aws_identity,
          k8s_top_nodes, k8s_top_pods, loki_query, prom_query,
          sys_open_ports, sys_service_logs, sys_service_status,
          sys_top_processes, system_info, tf_plan, tf_show, tf_state_list
-Commands: /investigate <problem>, /investigation, /investigations, /report, /endinvestigation
-One-shot: python main.py [--json] [--resume] [--out report.json] [--store-dir DIR] "<problem>"
+Commands: /investigate <problem>, /investigation, /investigations, /report, /endinvestigation, /model [<name>]
+One-shot: python main.py [--json] [--resume] [--out report.json] [--store-dir DIR] [--model NAME] "<problem>"
 Type 'exit' to quit.
 
 You: The checkout service container keeps exiting in Docker. Investigate.
@@ -617,7 +649,7 @@ You: exit
 Type `exit` / `quit`, or press Ctrl-D / Ctrl-C to leave. Slash commands are
 handled locally and never reach the model.
 
-## 8. Current limitations (Phase 9)
+## 8. Current limitations
 
 - **Each domain needs its CLI installed and reachable.** Missing CLIs,
   unauthenticated `gh`, a dead docker daemon, an uninitialized terraform
@@ -702,8 +734,22 @@ handled locally and never reach the model.
   `helm_history` — reads only), Argo CD (`argocd_apps`,
   `argocd_app_status`), Istio (`istioctl_proxy_status`), Docker Compose
   (`docker_compose_ls`, `docker_compose_ps` — live-verified on this host).
+- **Phase 10 — distribution. ✅ Done.** The `devopsiq` package on PyPI
+  (console command `devopsiq`, MIT) and the prebuilt multi-arch GHCR image,
+  cut by a tag-driven release workflow: an offline test gate, then PyPI
+  (Trusted Publishing — no token in the repo) and GHCR (amd64 + arm64) in
+  parallel. **`v0.1.1` added model-less mode:** with no API key the agent
+  still constructs — record commands (`/report`, `/investigations`) and the
+  58-tool layer work; only model questions exit 1 with the setup message.
+  Verified end-to-end against the published package.
+- **Model choice + resilient calls (v0.1.2). ✅ Done.** The model is
+  set by a 4-rung ladder — `--model` flag > `/model`-saved config file
+  (`~/.devops-ai-agent/config.json`) > `OPENROUTER_MODEL` > baked-in
+  default — and transient model-call failures (timeouts, connection
+  errors, 429s, 5xx) retry with exponential backoff (2s→4s→8s + jitter,
+  honoring a 429's Retry-After); a rejected key fails immediately.
 - **Later — region-scoped cloud resources** (ec2 describe-*, compute
   instances list, ...) behind the same template pattern; more observability
   depth (New Relic dashboards/entities, Prometheus range queries); streaming;
-  conversation-history persistence; and a human-approval gate before any
-  mutating action is ever allowed.
+  conversation-history persistence; and a human-approval gate
+  before any mutating action is ever allowed.

{devopsiq-0.1.1 → devopsiq-0.1.3}/README.md

@@ -1,5 +1,12 @@
 # DevOps AI Agent
 
+[![PyPI](https://img.shields.io/pypi/v/devopsiq)](https://pypi.org/project/devopsiq/)
+[![Python](https://img.shields.io/pypi/pyversions/devopsiq)](https://pypi.org/project/devopsiq/)
+[![Release](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml/badge.svg)](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml)
+[![Docker](https://img.shields.io/badge/ghcr-devops--ai--agent-2496ED?logo=docker&logoColor=white)](https://github.com/DevOpsAbhii/devops-ai-agent/pkgs/container/devops-ai-agent)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Tests](https://img.shields.io/badge/tests-181%20offline-brightgreen)](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml)
+
 An AI agent that investigates real DevOps problems. The end goal: ask it
 something like *"Why is my Kubernetes pod in CrashLoopBackOff?"* and have it
 gather evidence, reason about the evidence, identify the likely root cause,
@@ -26,10 +33,21 @@ from environment config), and Ansible listing (inventory, playbook tasks).
 open alerts over NerdGraph — credentials from env), Trivy image
 vulnerability scanning, Helm releases (list/status/history), Argo CD
 (GitOps app sync/health), Istio mesh proxy status, and Docker Compose
-(project and service listing). The repository is git-tracked.
+(project and service listing). **Phase 10 ships it as a product:** the
+[`devopsiq` package on PyPI](https://pypi.org/project/devopsiq/) and a
+prebuilt multi-arch Docker image (`ghcr.io/devopsabhii/devops-ai-agent`) —
+both cut automatically by pushing a `v*` tag (test gate → PyPI via Trusted
+Publishing + GHCR in parallel). **No API key? The agent still runs:** it
+starts in model-less mode — record commands (`/report`, `/investigations`)
+and the whole 58-tool layer work without a key; only questions to the model
+need one. The repository is git-tracked.
 Every phase still built from scratch — no LangChain, LangGraph,
 AutoGen, CrewAI, or MCP.
 
+> **New here?** The [Install & run guide (PDF)](DevOps_User_Guide.pdf) walks
+> you from zero to investigating — three install routes, credentials
+> (or none at all), model choice, and every command.
+
 > **Want to use this in your own project?** See [INTEGRATION.md](INTEGRATION.md)
 > for the three integration levels: drive it as a CLI from cron/CI (exit
 > codes + `--json`), embed it as a Python library, or extend it with your
@@ -44,7 +62,7 @@ model is called, how conversation history flows, how tool selection +
 execution + evidence feedback work — instead of depending on a framework
 for it.
 
-In Phase 5 the agent:
+Today the agent:
 - holds a conversation with **GLM 5.3** through **OpenRouter**;
 - has **58 real, read-only tools** across fifteen domains: host facts,
   Kubernetes (12 tools), Linux system (4), Docker + Compose (10),
@@ -104,8 +122,8 @@ Module map:
 
 | Path                        | Responsibility                                              |
 | --------------------------- | ------------------------------------------------------------ |
-| `main.py`                   | REPL loop, one-shot CLI, environment loading, `/investigate` commands, error messages |
-| `agent/agent.py`            | `DevOpsAgent` — client, history, `ask()`, `_complete()` loop |
+| `main.py`                   | REPL loop, one-shot CLI, environment loading, `/investigate` commands, error messages, model-less start |
+| `agent/agent.py`            | `DevOpsAgent` — client (`None` = model-less mode), history, `ask()`, `_complete()` loop |
 | `agent/prompts.py`          | The system prompt (versioned/tested separately)              |
 | `agent/investigation.py`    | First-class investigation record: hypotheses, verdicts, evidence, report renderer (pure data) |
 | `agent/store.py`            | `InvestigationStore` — one JSON file per record, atomic writes, resume/list (Phase 7) |
@@ -134,6 +152,11 @@ Module map:
 | `tests/test_phase7.py`      | Offline suite: round-trip serialization, store files, auto-save, resume, CLI flags (Phase 7) |
 | `tests/test_phase8.py`      | Offline suite: argv templates + validation for the 21 Phase 8 tools (fake CLIs, env-based monitoring) |
 | `tests/test_phase9.py`      | Offline suite: New Relic env-credential + payload tests, trivy/helm/argocd/istio/compose argv templates (Phase 9) |
+| `pyproject.toml`            | Package `devopsiq`: metadata, MIT, console script `devopsiq = main:main` (Phase 10) |
+| `Dockerfile`                | Prebuilt image: slim base + kubectl/helm/trivy/gh + app, non-root, `/data` record store (Phase 10) |
+| `.github/workflows/release.yml` | Tag-driven release: test gate → PyPI (Trusted Publishing) + GHCR multi-arch (Phase 10) |
+| `docs/generate_pdf.py`      | Builds the project documentation PDF from live source |
+| `docs/generate_release_guide.py` | Builds the release & update playbook PDF |
 
 ### The tool-use loop
 
@@ -180,6 +203,7 @@ the CLI exposes it directly:
 | `/investigations`        | List saved records on disk (newest first; `← active` marks the live one) |
 | `/report`                | Show the canonical report (once concluded)          |
 | `/endinvestigation`      | Clear the record (memory only — the saved copy stays as history) |
+| `/model [<name>]`        | Show the active model, or save a default (config.json) and switch to it |
 
 The report the agent ends with and `/report` render are kept consistent by
 construction: `tool` results confirm each record call and the tracker, and
@@ -367,16 +391,22 @@ official `openai` Python SDK works as our client with two config lines:
 OpenAI(api_key=..., base_url="https://openrouter.ai/api/v1")
 ```
 
-Swapping to another OpenRouter model later is a one-line change (an env var
-today); moving to any other OpenAI-compatible provider changes only
-`agent/agent.py` configuration.
+Swapping to another OpenRouter model later is a one-liner (env var, `/model`
+command, or `--model` flag); moving to any other OpenAI-compatible provider
+changes only `agent/agent.py` configuration.
 
 **Your model, your choice.** The default is baked in as a fallback, never a
-restriction — set `OPENROUTER_MODEL` (shell or `.env`) to any model on
-OpenRouter:
+restriction. Four ways to set the model — the first one set wins:
+
+1. `--model NAME` flag (one run: `devopsiq --model openai/gpt-5.2 "why?"`)
+2. `/model <name>` in the REPL — saves it to `~/.devops-ai-agent/config.json`
+   so every future run uses it
+3. `OPENROUTER_MODEL` (shell or `.env`)
+4. built-in default (`z-ai/glm-5.3`)
 
 ```bash
 export OPENROUTER_MODEL=anthropic/claude-sonnet-5   # or openai/gpt-5.2, google/gemini-2.5-pro, ...
+devopsiq /model openai/gpt-5.2                      # or save a default from the REPL
 ```
 
 Two things to weigh when picking: the agent is a tool-use loop, so choose a
@@ -529,6 +559,7 @@ setup/API errors — so it drops straight into a pipeline:
 .venv/bin/python main.py --json "why is api-5d6f crash-looping?"   # structured report
 .venv/bin/python main.py --resume --json "any update?"             # continue a prior run
 .venv/bin/python main.py --store-dir /tmp/runs --out report.json "..."  # pipeline paths
+.venv/bin/python main.py --model openai/gpt-5.2 "why is it down?"   # one-run model override
 ```
 
 With `--json` the stdout is one JSON document (see `render_report_json` in
@@ -570,8 +601,8 @@ Tools:   ansible_inventory, ansible_playbook_tasks, aws_identity,
          k8s_top_nodes, k8s_top_pods, loki_query, prom_query,
          sys_open_ports, sys_service_logs, sys_service_status,
          sys_top_processes, system_info, tf_plan, tf_show, tf_state_list
-Commands: /investigate <problem>, /investigation, /investigations, /report, /endinvestigation
-One-shot: python main.py [--json] [--resume] [--out report.json] [--store-dir DIR] "<problem>"
+Commands: /investigate <problem>, /investigation, /investigations, /report, /endinvestigation, /model [<name>]
+One-shot: python main.py [--json] [--resume] [--out report.json] [--store-dir DIR] [--model NAME] "<problem>"
 Type 'exit' to quit.
 
 You: The checkout service container keeps exiting in Docker. Investigate.
@@ -588,7 +619,7 @@ You: exit
 Type `exit` / `quit`, or press Ctrl-D / Ctrl-C to leave. Slash commands are
 handled locally and never reach the model.
 
-## 8. Current limitations (Phase 9)
+## 8. Current limitations
 
 - **Each domain needs its CLI installed and reachable.** Missing CLIs,
   unauthenticated `gh`, a dead docker daemon, an uninitialized terraform
@@ -673,8 +704,22 @@ handled locally and never reach the model.
   `helm_history` — reads only), Argo CD (`argocd_apps`,
   `argocd_app_status`), Istio (`istioctl_proxy_status`), Docker Compose
   (`docker_compose_ls`, `docker_compose_ps` — live-verified on this host).
+- **Phase 10 — distribution. ✅ Done.** The `devopsiq` package on PyPI
+  (console command `devopsiq`, MIT) and the prebuilt multi-arch GHCR image,
+  cut by a tag-driven release workflow: an offline test gate, then PyPI
+  (Trusted Publishing — no token in the repo) and GHCR (amd64 + arm64) in
+  parallel. **`v0.1.1` added model-less mode:** with no API key the agent
+  still constructs — record commands (`/report`, `/investigations`) and the
+  58-tool layer work; only model questions exit 1 with the setup message.
+  Verified end-to-end against the published package.
+- **Model choice + resilient calls (v0.1.2). ✅ Done.** The model is
+  set by a 4-rung ladder — `--model` flag > `/model`-saved config file
+  (`~/.devops-ai-agent/config.json`) > `OPENROUTER_MODEL` > baked-in
+  default — and transient model-call failures (timeouts, connection
+  errors, 429s, 5xx) retry with exponential backoff (2s→4s→8s + jitter,
+  honoring a 429's Retry-After); a rejected key fails immediately.
 - **Later — region-scoped cloud resources** (ec2 describe-*, compute
   instances list, ...) behind the same template pattern; more observability
   depth (New Relic dashboards/entities, Prometheus range queries); streaming;
-  conversation-history persistence; and a human-approval gate before any
-  mutating action is ever allowed.
+  conversation-history persistence; and a human-approval gate
+  before any mutating action is ever allowed.

{devopsiq-0.1.1 → devopsiq-0.1.3}/agent/agent.py

@@ -26,9 +26,18 @@ exits; the delegates below expose resume/list/store-location to the CLI.
 """
 
 import os
+import random
+import time
+
+from openai import (
+    APIConnectionError,
+    APIStatusError,
+    APITimeoutError,
+    OpenAI,
+    RateLimitError,
+)
 
-from openai import OpenAI
-
+from agent.config import load_user_config
 from agent.prompts import SYSTEM_PROMPT
 from agent.store import InvestigationStore
 from tools import (  # noqa: F401 — side effect: each module registers its tools
@@ -68,6 +77,50 @@ PLACEHOLDER_KEY = "your_key_here"
 # Safety valve: the model gets at most this many tool-use turns before we stop.
 MAX_TOOL_ITERATIONS = 10
 
+# Transient-failure retries for the model call itself (network blips, 429,
+# 5xx). MAX_MODEL_RETRIES attempts beyond the first, exponential backoff
+# starting at RETRY_BASE_DELAY (2s -> 4s -> 8s) plus jitter, capped at
+# RETRY_MAX_DELAY. A 429's Retry-After header wins when present.
+MAX_MODEL_RETRIES = 3
+RETRY_BASE_DELAY = 2.0
+RETRY_MAX_DELAY = 60.0
+
+_sleep = time.sleep  # test seam: offline tests patch agent.agent._sleep
+
+
+def _is_transient(exc: Exception) -> bool:
+    """True when retrying `exc` can plausibly succeed.
+
+    Timeouts, connection failures, rate limits, and server-side 5xx are
+    transient. A rejected key (401) or any other client 4xx is not — the
+    same request would fail identically forever, so it fails immediately.
+    """
+    if isinstance(exc, (APITimeoutError, APIConnectionError, RateLimitError)):
+        return True
+    if isinstance(exc, APIStatusError):
+        return exc.status_code >= 500
+    return False
+
+
+def _retry_delay(exc: Exception, attempt: int) -> float:
+    """Seconds to wait before retry number `attempt` (0-based).
+
+    Exponential backoff with jitter, except on a rate limit carrying a
+    Retry-After header — the server knows its own budget, so it wins
+    (clamped to [1, RETRY_MAX_DELAY] so a bad header cannot hurt us).
+    """
+    response = getattr(exc, "response", None)
+    retry_after = getattr(response, "headers", {}).get("retry-after")
+    if retry_after:
+        try:
+            return min(max(float(retry_after), 1.0), RETRY_MAX_DELAY)
+        except (TypeError, ValueError):
+            pass  # non-numeric header: fall through to backoff
+    return min(
+        RETRY_BASE_DELAY * (2 ** attempt) + random.uniform(0, 1),
+        RETRY_MAX_DELAY,
+    )
+
 
 class DevOpsAgent:
     """Minimal DevOps investigation assistant (read-only by design)."""
@@ -81,7 +134,12 @@ class DevOpsAgent:
         # Configuration resolution order: explicit argument > environment > default.
         self.api_key = api_key or os.getenv("OPENROUTER_API_KEY")
 
-        self.model = model or os.getenv("OPENROUTER_MODEL", DEFAULT_MODEL)
+        self.model = (
+            model                                   # 1. explicit --model flag
+            or load_user_config().get("model")      # 2. ~/.devops-ai-agent/config.json
+            or os.getenv("OPENROUTER_MODEL")        # 3. environment / .env
+            or DEFAULT_MODEL                        # 4. built-in default
+        )
         self.base_url = base_url or os.getenv("OPENROUTER_BASE_URL", DEFAULT_BASE_URL)
 
         # Model-less mode: a missing (or placeholder) key no longer blocks
@@ -197,7 +255,7 @@ class DevOpsAgent:
             if self.tools:
                 request["tools"] = [tool.schema() for tool in self.tools]
 
-            response = self.client.chat.completions.create(**request)
+            response = self._call_model(request)
             message = response.choices[0].message
 
             if not message.tool_calls:
@@ -219,6 +277,23 @@ class DevOpsAgent:
             f"The model did not finish after {MAX_TOOL_ITERATIONS} tool-use turns."
         )
 
+    def _call_model(self, request: dict):
+        """One model call with bounded retries on transient failures.
+
+        Timeouts, connection errors, rate limits (429) and server-side 5xx
+        are retried up to MAX_MODEL_RETRIES times with exponential backoff
+        (2s, 4s, 8s + jitter); a 429's Retry-After header wins when present.
+        Client errors — a rejected key (401) most notably — fail immediately,
+        because retrying the identical request cannot fix them.
+        """
+        for attempt in range(MAX_MODEL_RETRIES + 1):
+            try:
+                return self.client.chat.completions.create(**request)
+            except Exception as exc:  # noqa: BLE001 — classified right below
+                if attempt >= MAX_MODEL_RETRIES or not _is_transient(exc):
+                    raise
+                _sleep(_retry_delay(exc, attempt))
+
 
 def _echo_tool_request(message) -> dict:
     """Rebuild the assistant turn that requested tools, verbatim.

devopsiq-0.1.3/agent/config.py

@@ -0,0 +1,45 @@
+"""Per-user preferences: ~/.devops-ai-agent/config.json.
+
+The `devopsiq` equivalent of "my settings" — currently the preferred model,
+written by the /model command and read by the agent at startup. Precedence
+for the model, highest first:
+
+    --model flag  >  config.json  >  OPENROUTER_MODEL env  >  built-in default
+
+The file is tiny JSON, one flat object. Every read is tolerant: a missing
+file, an unreadable home directory, or corrupt content yields {} — a broken
+config never blocks the agent (the same degrade-don't-crash rule the
+investigation store follows). Tests point AGENT_CONFIG_FILE at a tmp path.
+"""
+
+import json
+import os
+from pathlib import Path
+
+DEFAULT_CONFIG_PATH = Path.home() / ".devops-ai-agent" / "config.json"
+
+
+def config_path() -> Path:
+    """The active config file (AGENT_CONFIG_FILE overrides; tests use tmp)."""
+    return Path(os.getenv("AGENT_CONFIG_FILE") or DEFAULT_CONFIG_PATH)
+
+
+def load_user_config() -> dict:
+    """Read the config file; {} when missing or unreadable — never raise."""
+    try:
+        raw = config_path().read_text(encoding="utf-8")
+        data = json.loads(raw)
+        return data if isinstance(data, dict) else {}
+    except (OSError, ValueError):
+        return {}
+
+
+def save_user_config(update: dict) -> Path:
+    """Merge `update` into the config file (create the directory if needed)."""
+    path = config_path()
+    data = load_user_config()
+    data.update(update)
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(json.dumps(data, indent=2, sort_keys=True) + "\n",
+                    encoding="utf-8")
+    return path

{devopsiq-0.1.1 → devopsiq-0.1.3/devopsiq.egg-info}/PKG-INFO

@@ -1,12 +1,13 @@
 Metadata-Version: 2.4
 Name: devopsiq
-Version: 0.1.1
+Version: 0.1.3
 Summary: A from-scratch, read-only AI agent that investigates real DevOps problems — Kubernetes, Docker, Helm, Argo CD, Istio, Terraform, GitHub Actions, cloud, New Relic and more.
 Author: DevOpsAbhii
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/DevOpsAbhii/devops-ai-agent
 Project-URL: Repository, https://github.com/DevOpsAbhii/devops-ai-agent
 Project-URL: Issues, https://github.com/DevOpsAbhii/devops-ai-agent/issues
+Project-URL: Changelog, https://github.com/DevOpsAbhii/devops-ai-agent/blob/main/CHANGELOG.md
 Keywords: devops,kubernetes,docker,helm,argocd,istio,terraform,github-actions,observability,newrelic,incident-response,root-cause-analysis,ai-agent,cli
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
@@ -29,6 +30,13 @@ Dynamic: license-file
 
 # DevOps AI Agent
 
+[![PyPI](https://img.shields.io/pypi/v/devopsiq)](https://pypi.org/project/devopsiq/)
+[![Python](https://img.shields.io/pypi/pyversions/devopsiq)](https://pypi.org/project/devopsiq/)
+[![Release](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml/badge.svg)](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml)
+[![Docker](https://img.shields.io/badge/ghcr-devops--ai--agent-2496ED?logo=docker&logoColor=white)](https://github.com/DevOpsAbhii/devops-ai-agent/pkgs/container/devops-ai-agent)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Tests](https://img.shields.io/badge/tests-181%20offline-brightgreen)](https://github.com/DevOpsAbhii/devops-ai-agent/actions/workflows/release.yml)
+
 An AI agent that investigates real DevOps problems. The end goal: ask it
 something like *"Why is my Kubernetes pod in CrashLoopBackOff?"* and have it
 gather evidence, reason about the evidence, identify the likely root cause,
@@ -55,10 +63,21 @@ from environment config), and Ansible listing (inventory, playbook tasks).
 open alerts over NerdGraph — credentials from env), Trivy image
 vulnerability scanning, Helm releases (list/status/history), Argo CD
 (GitOps app sync/health), Istio mesh proxy status, and Docker Compose
-(project and service listing). The repository is git-tracked.
+(project and service listing). **Phase 10 ships it as a product:** the
+[`devopsiq` package on PyPI](https://pypi.org/project/devopsiq/) and a
+prebuilt multi-arch Docker image (`ghcr.io/devopsabhii/devops-ai-agent`) —
+both cut automatically by pushing a `v*` tag (test gate → PyPI via Trusted
+Publishing + GHCR in parallel). **No API key? The agent still runs:** it
+starts in model-less mode — record commands (`/report`, `/investigations`)
+and the whole 58-tool layer work without a key; only questions to the model
+need one. The repository is git-tracked.
 Every phase still built from scratch — no LangChain, LangGraph,
 AutoGen, CrewAI, or MCP.
 
+> **New here?** The [Install & run guide (PDF)](DevOps_User_Guide.pdf) walks
+> you from zero to investigating — three install routes, credentials
+> (or none at all), model choice, and every command.
+
 > **Want to use this in your own project?** See [INTEGRATION.md](INTEGRATION.md)
 > for the three integration levels: drive it as a CLI from cron/CI (exit
 > codes + `--json`), embed it as a Python library, or extend it with your
@@ -73,7 +92,7 @@ model is called, how conversation history flows, how tool selection +
 execution + evidence feedback work — instead of depending on a framework
 for it.
 
-In Phase 5 the agent:
+Today the agent:
 - holds a conversation with **GLM 5.3** through **OpenRouter**;
 - has **58 real, read-only tools** across fifteen domains: host facts,
   Kubernetes (12 tools), Linux system (4), Docker + Compose (10),
@@ -133,8 +152,8 @@ Module map:
 
 | Path                        | Responsibility                                              |
 | --------------------------- | ------------------------------------------------------------ |
-| `main.py`                   | REPL loop, one-shot CLI, environment loading, `/investigate` commands, error messages |
-| `agent/agent.py`            | `DevOpsAgent` — client, history, `ask()`, `_complete()` loop |
+| `main.py`                   | REPL loop, one-shot CLI, environment loading, `/investigate` commands, error messages, model-less start |
+| `agent/agent.py`            | `DevOpsAgent` — client (`None` = model-less mode), history, `ask()`, `_complete()` loop |
 | `agent/prompts.py`          | The system prompt (versioned/tested separately)              |
 | `agent/investigation.py`    | First-class investigation record: hypotheses, verdicts, evidence, report renderer (pure data) |
 | `agent/store.py`            | `InvestigationStore` — one JSON file per record, atomic writes, resume/list (Phase 7) |
@@ -163,6 +182,11 @@ Module map:
 | `tests/test_phase7.py`      | Offline suite: round-trip serialization, store files, auto-save, resume, CLI flags (Phase 7) |
 | `tests/test_phase8.py`      | Offline suite: argv templates + validation for the 21 Phase 8 tools (fake CLIs, env-based monitoring) |
 | `tests/test_phase9.py`      | Offline suite: New Relic env-credential + payload tests, trivy/helm/argocd/istio/compose argv templates (Phase 9) |
+| `pyproject.toml`            | Package `devopsiq`: metadata, MIT, console script `devopsiq = main:main` (Phase 10) |
+| `Dockerfile`                | Prebuilt image: slim base + kubectl/helm/trivy/gh + app, non-root, `/data` record store (Phase 10) |
+| `.github/workflows/release.yml` | Tag-driven release: test gate → PyPI (Trusted Publishing) + GHCR multi-arch (Phase 10) |
+| `docs/generate_pdf.py`      | Builds the project documentation PDF from live source |
+| `docs/generate_release_guide.py` | Builds the release & update playbook PDF |
 
 ### The tool-use loop
 
@@ -209,6 +233,7 @@ the CLI exposes it directly:
 | `/investigations`        | List saved records on disk (newest first; `← active` marks the live one) |
 | `/report`                | Show the canonical report (once concluded)          |
 | `/endinvestigation`      | Clear the record (memory only — the saved copy stays as history) |
+| `/model [<name>]`        | Show the active model, or save a default (config.json) and switch to it |
 
 The report the agent ends with and `/report` render are kept consistent by
 construction: `tool` results confirm each record call and the tracker, and
@@ -396,16 +421,22 @@ official `openai` Python SDK works as our client with two config lines:
 OpenAI(api_key=..., base_url="https://openrouter.ai/api/v1")
 ```
 
-Swapping to another OpenRouter model later is a one-line change (an env var
-today); moving to any other OpenAI-compatible provider changes only
-`agent/agent.py` configuration.
+Swapping to another OpenRouter model later is a one-liner (env var, `/model`
+command, or `--model` flag); moving to any other OpenAI-compatible provider
+changes only `agent/agent.py` configuration.
 
 **Your model, your choice.** The default is baked in as a fallback, never a
-restriction — set `OPENROUTER_MODEL` (shell or `.env`) to any model on
-OpenRouter:
+restriction. Four ways to set the model — the first one set wins:
+
+1. `--model NAME` flag (one run: `devopsiq --model openai/gpt-5.2 "why?"`)
+2. `/model <name>` in the REPL — saves it to `~/.devops-ai-agent/config.json`
+   so every future run uses it
+3. `OPENROUTER_MODEL` (shell or `.env`)
+4. built-in default (`z-ai/glm-5.3`)
 
 ```bash
 export OPENROUTER_MODEL=anthropic/claude-sonnet-5   # or openai/gpt-5.2, google/gemini-2.5-pro, ...
+devopsiq /model openai/gpt-5.2                      # or save a default from the REPL
 ```
 
 Two things to weigh when picking: the agent is a tool-use loop, so choose a
@@ -558,6 +589,7 @@ setup/API errors — so it drops straight into a pipeline:
 .venv/bin/python main.py --json "why is api-5d6f crash-looping?"   # structured report
 .venv/bin/python main.py --resume --json "any update?"             # continue a prior run
 .venv/bin/python main.py --store-dir /tmp/runs --out report.json "..."  # pipeline paths
+.venv/bin/python main.py --model openai/gpt-5.2 "why is it down?"   # one-run model override
 ```
 
 With `--json` the stdout is one JSON document (see `render_report_json` in
@@ -599,8 +631,8 @@ Tools:   ansible_inventory, ansible_playbook_tasks, aws_identity,
          k8s_top_nodes, k8s_top_pods, loki_query, prom_query,
          sys_open_ports, sys_service_logs, sys_service_status,
          sys_top_processes, system_info, tf_plan, tf_show, tf_state_list
-Commands: /investigate <problem>, /investigation, /investigations, /report, /endinvestigation
-One-shot: python main.py [--json] [--resume] [--out report.json] [--store-dir DIR] "<problem>"
+Commands: /investigate <problem>, /investigation, /investigations, /report, /endinvestigation, /model [<name>]
+One-shot: python main.py [--json] [--resume] [--out report.json] [--store-dir DIR] [--model NAME] "<problem>"
 Type 'exit' to quit.
 
 You: The checkout service container keeps exiting in Docker. Investigate.
@@ -617,7 +649,7 @@ You: exit
 Type `exit` / `quit`, or press Ctrl-D / Ctrl-C to leave. Slash commands are
 handled locally and never reach the model.
 
-## 8. Current limitations (Phase 9)
+## 8. Current limitations
 
 - **Each domain needs its CLI installed and reachable.** Missing CLIs,
   unauthenticated `gh`, a dead docker daemon, an uninitialized terraform
@@ -702,8 +734,22 @@ handled locally and never reach the model.
   `helm_history` — reads only), Argo CD (`argocd_apps`,
   `argocd_app_status`), Istio (`istioctl_proxy_status`), Docker Compose
   (`docker_compose_ls`, `docker_compose_ps` — live-verified on this host).
+- **Phase 10 — distribution. ✅ Done.** The `devopsiq` package on PyPI
+  (console command `devopsiq`, MIT) and the prebuilt multi-arch GHCR image,
+  cut by a tag-driven release workflow: an offline test gate, then PyPI
+  (Trusted Publishing — no token in the repo) and GHCR (amd64 + arm64) in
+  parallel. **`v0.1.1` added model-less mode:** with no API key the agent
+  still constructs — record commands (`/report`, `/investigations`) and the
+  58-tool layer work; only model questions exit 1 with the setup message.
+  Verified end-to-end against the published package.
+- **Model choice + resilient calls (v0.1.2). ✅ Done.** The model is
+  set by a 4-rung ladder — `--model` flag > `/model`-saved config file
+  (`~/.devops-ai-agent/config.json`) > `OPENROUTER_MODEL` > baked-in
+  default — and transient model-call failures (timeouts, connection
+  errors, 429s, 5xx) retry with exponential backoff (2s→4s→8s + jitter,
+  honoring a 429's Retry-After); a rejected key fails immediately.
 - **Later — region-scoped cloud resources** (ec2 describe-*, compute
   instances list, ...) behind the same template pattern; more observability
   depth (New Relic dashboards/entities, Prometheus range queries); streaming;
-  conversation-history persistence; and a human-approval gate before any
-  mutating action is ever allowed.
+  conversation-history persistence; and a human-approval gate
+  before any mutating action is ever allowed.

{devopsiq-0.1.1 → devopsiq-0.1.3}/devopsiq.egg-info/SOURCES.txt

@@ -4,6 +4,7 @@ main.py
 pyproject.toml
 agent/__init__.py
 agent/agent.py
+agent/config.py
 agent/investigation.py
 agent/prompts.py
 agent/store.py

{devopsiq-0.1.1 → devopsiq-0.1.3}/main.py

@@ -10,6 +10,7 @@ One-shot (for cron / CI / scripts):
     python main.py --json "why is api-5d6f crash-looping?"   # structured report
     python main.py --resume --json "any update?"             # continue prior run
     python main.py --store-dir DIR --out report.json "..."   # pipeline paths
+    python main.py --model openai/gpt-4o-mini "..."          # one-run model override
 
 One-shot mode sends the problem once, prints the agent's report, and exits
 with a status code (0 = completed, 1 = setup/API error). With --json the
@@ -41,6 +42,7 @@ from openai import (
 )
 
 from agent.agent import DevOpsAgent
+from agent.config import config_path, save_user_config
 
 EXIT_WORDS = {"exit", "quit"}
 
@@ -55,6 +57,7 @@ COMMAND_ALIASES = {
     "/report": "/report",
     "/endinvestigation": "/endinvestigation",
     "/end": "/endinvestigation",
+    "/model": "/model",
 }
 
 
@@ -82,8 +85,32 @@ def handle_command(text: str, agent: DevOpsAgent) -> str | None:
         return agent.investigation_report_text() or "(no investigation recorded)"
     if canonical == "/endinvestigation":
         return agent.end_investigation()
+    if canonical == "/model":
+        return handle_model_command(rest, agent)
     return (f"unknown command: {cmd}. Try /investigate <problem>, "
-            "/investigation, /investigations, /report, /endinvestigation")
+            "/investigation, /investigations, /report, /endinvestigation, "
+            "/model")
+
+
+def handle_model_command(rest: str, agent: DevOpsAgent) -> str:
+    """/model (show the active model and where it came from) or /model <name>.
+
+    With a name: save it as the user's preference in the config file
+    (~/.devops-ai-agent/config.json) and switch this session to it. The
+    next run picks it up automatically — the flag and env still outrank it.
+    """
+    name = rest.strip()
+    if not name:
+        return (f"Model: {agent.model}\n"
+                f"Config file: {config_path()} "
+                "(save a default with /model <name>)")
+    if len(name.split()) != 1:
+        return "Model name must be a single token, e.g. /model openai/gpt-4o-mini"
+    path = save_user_config({"model": name})
+    agent.model = name
+    return (f"Model set to {name} (saved in {path}).\n"
+            "This session now uses it; the --model flag and OPENROUTER_MODEL "
+            "still override it per run.")
 
 
 class OneShotArgs(NamedTuple):
@@ -94,9 +121,10 @@ class OneShotArgs(NamedTuple):
     store_dir: str | None  # --store-dir PATH (persistence override)
     resume: bool           # --resume (continue the newest in-progress record)
     out: str | None        # --out PATH (also write the JSON report there)
+    model: str | None      # --model NAME (one-run model override)
 
 
-_VALUE_FLAGS = ("--store-dir", "--out")
+_VALUE_FLAGS = ("--store-dir", "--out", "--model")
 
 
 def _flag_value(argv: list[str], flag: str) -> str | None:
@@ -114,14 +142,16 @@ def parse_args(argv: list[str]) -> OneShotArgs:
     --json switches the one-shot output from markdown to the structured JSON
     report; --resume continues the newest in-progress record from the store;
     --store-dir PATH overrides the persistence directory for this run; --out
-    PATH additionally writes the JSON report to an exact path. Example:
+    PATH additionally writes the JSON report to an exact path; --model NAME
+    overrides the model for this run (highest model precedence). Example:
     `python main.py --json --out r.json "why is it down?"` ->
-    ("why is it down?", True, None, False, "r.json").
+    ("why is it down?", True, None, False, "r.json", None).
     """
     as_json = "--json" in argv
     do_resume = "--resume" in argv
     store_dir = _flag_value(argv, "--store-dir")
     out = _flag_value(argv, "--out")
+    model = _flag_value(argv, "--model")
     positionals: list[str] = []
     skip_next = False
     for arg in argv:
@@ -136,8 +166,8 @@ def parse_args(argv: list[str]) -> OneShotArgs:
         positionals.append(arg)
     text = " ".join(positionals).strip()
     if not positionals or not text:
-        return OneShotArgs(None, as_json, store_dir, do_resume, out)
-    return OneShotArgs(text, as_json, store_dir, do_resume, out)
+        return OneShotArgs(None, as_json, store_dir, do_resume, out, model)
+    return OneShotArgs(text, as_json, store_dir, do_resume, out, model)
 
 
 def run_one_shot(
@@ -147,6 +177,7 @@ def run_one_shot(
     store_dir: str | None = None,
     resume: bool = False,
     out: str | None = None,
+    model: str | None = None,
 ) -> int:
     """Non-interactive single run: send `task`, print the result, exit cleanly.
 
@@ -155,14 +186,14 @@ def run_one_shot(
     opened an investigation this is a hard failure (exit 1) — a caller asked
     for a report and there is none to give. The record is auto-saved on every
     mutation regardless; store_dir points persistence somewhere else for this
-    run, resume continues the newest in-progress record before asking, and
-    out additionally writes the JSON report to an exact path. `agent` lets
-    embedders reuse a configured agent (also the test seam); default builds a
-    fresh one from the environment.
+    run, resume continues the newest in-progress record before asking, out
+    additionally writes the JSON report to an exact path, and model overrides
+    the model for this run. `agent` lets embedders reuse a configured agent
+    (also the test seam); default builds a fresh one from the environment.
     """
     if agent is None:
         try:
-            agent = DevOpsAgent()
+            agent = DevOpsAgent(model=model)
         except ValueError as exc:
             print(f"[setup] {exc}", file=sys.stderr)
             return 1
@@ -245,10 +276,11 @@ def main() -> int:
             store_dir=args.store_dir,
             resume=args.resume,
             out=args.out,
+            model=args.model,
         )
 
     try:
-        agent = DevOpsAgent()
+        agent = DevOpsAgent(model=args.model)
     except ValueError as exc:
         print(f"[setup] {exc}", file=sys.stderr)
         return 1
@@ -268,9 +300,9 @@ def main() -> int:
     print(f"Store:   {agent.store_dir or '(persistence off)'}")
     print(f"Tools:   {tool_names}")
     print("Commands: /investigate <problem>, /investigation, /investigations, "
-          "/report, /endinvestigation")
+          "/report, /endinvestigation, /model [<name>]")
     print("One-shot: python main.py [--json] [--resume] [--out report.json] "
-          "[--store-dir DIR] \"<problem>\"")
+          "[--store-dir DIR] [--model NAME] \"<problem>\"")
     print("Type 'exit' to quit.")
     print()
 

{devopsiq-0.1.1 → devopsiq-0.1.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "devopsiq"
-version = "0.1.1"
+version = "0.1.3"
 description = "A from-scratch, read-only AI agent that investigates real DevOps problems — Kubernetes, Docker, Helm, Argo CD, Istio, Terraform, GitHub Actions, cloud, New Relic and more."
 readme = "README.md"
 license = "MIT"
@@ -38,6 +38,7 @@ dependencies = [
 Homepage = "https://github.com/DevOpsAbhii/devops-ai-agent"
 Repository = "https://github.com/DevOpsAbhii/devops-ai-agent"
 Issues = "https://github.com/DevOpsAbhii/devops-ai-agent/issues"
+Changelog = "https://github.com/DevOpsAbhii/devops-ai-agent/blob/main/CHANGELOG.md"
 
 [project.scripts]
 devopsiq = "main:main"

{devopsiq-0.1.1 → devopsiq-0.1.3}/tests/test_automation.py

@@ -11,12 +11,25 @@ import contextlib
 import io
 import json
 import os
+import tempfile
+import time
 import types
 import unittest
+from pathlib import Path
 
+import httpx2 as httpx  # openai 3.19 depends on the httpx2 fork
 import main as main_module
-from agent.agent import DevOpsAgent
+import agent.agent as agent_module
+from agent import config as user_config
+from agent.agent import DEFAULT_MODEL, DevOpsAgent
 from agent.investigation import Investigation
+from openai import (
+    APIConnectionError,
+    APIStatusError,
+    APITimeoutError,
+    AuthenticationError,
+    RateLimitError,
+)
 from tools import investigation as inv_tools
 
 
@@ -187,19 +200,27 @@ class OneShotCliTests(unittest.TestCase):
 
     def test_parse_args(self):
         self.assertEqual(
-            main_module.parse_args([]), (None, False, None, False, None)
+            main_module.parse_args([]), (None, False, None, False, None, None)
         )
         self.assertEqual(
             main_module.parse_args(["why is it down?"]),
-            ("why is it down?", False, None, False, None),
+            ("why is it down?", False, None, False, None, None),
         )
         self.assertEqual(
             main_module.parse_args(["--json", "why", "is it down?"]),
-            ("why is it down?", True, None, False, None),
+            ("why is it down?", True, None, False, None, None),
         )
         self.assertEqual(
             main_module.parse_args(["--json"]),
-            (None, True, None, False, None),
+            (None, True, None, False, None, None),
+        )
+        self.assertEqual(
+            main_module.parse_args(["--model", "openai/gpt-4o-mini", "why?"]),
+            ("why?", False, None, False, None, "openai/gpt-4o-mini"),
+        )
+        self.assertEqual(
+            main_module.parse_args(["--model", "anthropic/claude-sonnet-5"]),
+            (None, False, None, False, None, "anthropic/claude-sonnet-5"),
         )
 
     def test_slash_command_routes_without_model(self):
@@ -300,5 +321,207 @@ class KeylessTests(unittest.TestCase):
         self.assertIn("OPENROUTER_API_KEY", err.getvalue())
 
 
+class ModelChoiceTests(unittest.TestCase):
+    """Model preference ladder + the /model command + agent/config.py.
+
+    Precedence, highest first: explicit model argument > config.json >
+    OPENROUTER_MODEL env > built-in default. Tests point AGENT_CONFIG_FILE
+    at a tmp file so the developer's real ~/.devops-ai-agent/config.json
+    is never read or written.
+    """
+
+    def setUp(self):
+        tmp = tempfile.NamedTemporaryFile(suffix=".json", delete=False)
+        tmp.close()
+        self.config_file = tmp.name
+        os.environ["AGENT_CONFIG_FILE"] = self.config_file
+        self.addCleanup(self._restore)
+
+    def _restore(self):
+        os.environ.pop("AGENT_CONFIG_FILE", None)
+        Path(self.config_file).unlink(missing_ok=True)
+
+    def _set_env(self, name, value):
+        old = os.environ.get(name)
+        os.environ[name] = value
+        self.addCleanup(lambda: (
+            os.environ.pop(name, None) if old is None
+            else os.environ.__setitem__(name, old)
+        ))
+
+    def test_config_round_trip_and_corrupt_tolerance(self):
+        self.assertEqual(user_config.load_user_config(), {})  # missing file
+        path = user_config.save_user_config({"model": "openai/gpt-4o-mini"})
+        self.assertEqual(path, Path(self.config_file))
+        self.assertEqual(user_config.load_user_config(),
+                         {"model": "openai/gpt-4o-mini"})
+        # Merging keeps existing keys and overwrites the given one.
+        user_config.save_user_config({"model": "anthropic/claude-sonnet-5"})
+        self.assertEqual(user_config.load_user_config(),
+                         {"model": "anthropic/claude-sonnet-5"})
+        # Corrupt content degrades to {} instead of raising.
+        Path(self.config_file).write_text("{not json", encoding="utf-8")
+        self.assertEqual(user_config.load_user_config(), {})
+
+    def test_model_precedence_ladder(self):
+        # 4. built-in default
+        self.assertEqual(DevOpsAgent().model, DEFAULT_MODEL)
+        # 3. environment
+        self._set_env("OPENROUTER_MODEL", "env/model")
+        self.assertEqual(DevOpsAgent().model, "env/model")
+        # 2. config file (outranks env)
+        user_config.save_user_config({"model": "config/model"})
+        self.assertEqual(DevOpsAgent().model, "config/model")
+        # 1. explicit argument (outranks everything)
+        self.assertEqual(DevOpsAgent(model="flag/model").model, "flag/model")
+
+    def test_model_command_shows_current_model(self):
+        agent = DevOpsAgent()
+        before = agent.model
+        text = main_module.handle_command("/model", agent)
+        self.assertIn(before, text)
+        self.assertIn(str(user_config.config_path()), text)
+        self.assertEqual(agent.model, before)  # show-only changes nothing
+
+    def test_model_command_saves_and_switches(self):
+        agent = DevOpsAgent()
+        out = io.StringIO()
+        with contextlib.redirect_stdout(out):
+            text = main_module.handle_command(
+                "/model openai/gpt-4o-mini", agent)
+        self.assertIn("openai/gpt-4o-mini", text)
+        self.assertEqual(agent.model, "openai/gpt-4o-mini")
+        self.assertEqual(
+            user_config.load_user_config(), {"model": "openai/gpt-4o-mini"})
+        # A multi-token name is rejected; the config stays untouched.
+        text = main_module.handle_command("/model two words", agent)
+        self.assertIn("single token", text)
+        self.assertEqual(agent.model, "openai/gpt-4o-mini")
+
+
+class FlakyChat:
+    """Chat stub that raises the queued errors, then answers with content."""
+
+    def __init__(self, errors: list[Exception], content: str = "ok"):
+        self._errors = list(errors)
+        self._content = content
+        self.calls = 0
+
+    def create(self, **kwargs):  # noqa: D102
+        self.calls += 1
+        if self._errors:
+            raise self._errors.pop(0)
+        message = types.SimpleNamespace(content=self._content, tool_calls=None)
+        return types.SimpleNamespace(
+            choices=[types.SimpleNamespace(message=message)]
+        )
+
+
+def _api_status_error(status: int, headers: dict | None = None):
+    """Build an openai status error offline (no HTTP round-trip)."""
+    request = httpx.Request(
+        "POST", "https://openrouter.ai/api/v1/chat/completions")
+    response = httpx.Response(
+        status, request=request, headers=headers or {})
+    return APIStatusError("boom", response=response, body=None)
+
+
+def _api_connection_error():
+    request = httpx.Request(
+        "POST", "https://openrouter.ai/api/v1/chat/completions")
+    return APIConnectionError(request=request)
+
+
+class RetryTests(unittest.TestCase):
+    """_call_model: transient failures retry with backoff, others fail fast.
+
+    Sleeps are intercepted via the agent.agent._sleep seam, so the tests
+    run instantly; the recorded delays prove the backoff schedule.
+    """
+
+    def setUp(self):
+        self._old_key = os.environ.get("OPENROUTER_API_KEY")
+        os.environ["OPENROUTER_API_KEY"] = "test-key-for-offline-tests"
+        self.agent = DevOpsAgent()
+        self.sleeps: list[float] = []
+        agent_module._sleep = self.sleeps.append
+        self.addCleanup(self._restore)
+
+    def _restore(self):
+        agent_module._sleep = time.sleep
+        os.environ.pop("OPENROUTER_API_KEY", None)
+        if self._old_key is not None:
+            os.environ["OPENROUTER_API_KEY"] = self._old_key
+
+    def test_connection_errors_are_retried_then_succeed(self):
+        chat = FlakyChat([_api_connection_error(), _api_connection_error()])
+        self.agent.client.chat.completions = chat
+        self.assertEqual(self.agent.ask("why is it down?"), "ok")
+        self.assertEqual(chat.calls, 3)  # original + 2 retries
+        # Backoff: attempt 0 -> ~2s (+jitter), attempt 1 -> ~4s (+jitter).
+        self.assertGreaterEqual(self.sleeps[0], 2.0)
+        self.assertLessEqual(self.sleeps[0], 3.0)
+        self.assertGreaterEqual(self.sleeps[1], 4.0)
+        self.assertLessEqual(self.sleeps[1], 5.0)
+
+    def test_timeout_is_transient(self):
+        request = httpx.Request("POST", "https://openrouter.ai/api/v1")
+        chat = FlakyChat([APITimeoutError(request)])
+        self.agent.client.chat.completions = chat
+        self.assertEqual(self.agent.ask("hello"), "ok")
+        self.assertEqual(chat.calls, 2)
+
+    def test_rate_limit_honors_retry_after_header(self):
+        request = httpx.Request("POST", "https://openrouter.ai/api/v1")
+        response = httpx.Response(
+            429, request=request, headers={"retry-after": "7"})
+        chat = FlakyChat([RateLimitError("slow down", response=response,
+                                         body=None)])
+        self.agent.client.chat.completions = chat
+        self.assertEqual(self.agent.ask("hello"), "ok")
+        self.assertEqual(self.sleeps, [7.0])
+
+    def test_rate_limit_without_header_uses_backoff(self):
+        request = httpx.Request("POST", "https://openrouter.ai/api/v1")
+        response = httpx.Response(429, request=request)
+        chat = FlakyChat([RateLimitError("slow down", response=response,
+                                         body=None)])
+        self.agent.client.chat.completions = chat
+        self.assertEqual(self.agent.ask("hello"), "ok")
+        self.assertGreaterEqual(self.sleeps[0], 2.0)
+
+    def test_auth_error_fails_immediately(self):
+        request = httpx.Request("POST", "https://openrouter.ai/api/v1")
+        response = httpx.Response(401, request=request)
+        chat = FlakyChat([AuthenticationError("bad key", response=response,
+                                              body=None)])
+        self.agent.client.chat.completions = chat
+        with self.assertRaises(AuthenticationError):
+            self.agent.ask("hello")
+        self.assertEqual(chat.calls, 1)  # no retry on a rejected key
+        self.assertEqual(self.sleeps, [])
+
+    def test_client_400_fails_immediately(self):
+        chat = FlakyChat([_api_status_error(400)])
+        self.agent.client.chat.completions = chat
+        with self.assertRaises(APIStatusError):
+            self.agent.ask("hello")
+        self.assertEqual(chat.calls, 1)
+
+    def test_server_500_is_retried(self):
+        chat = FlakyChat([_api_status_error(500), _api_status_error(502)])
+        self.agent.client.chat.completions = chat
+        self.assertEqual(self.agent.ask("hello"), "ok")
+        self.assertEqual(chat.calls, 3)
+
+    def test_retries_are_exhausted_loudly(self):
+        chat = FlakyChat([_api_connection_error() for _ in range(4)])
+        self.agent.client.chat.completions = chat
+        with self.assertRaises(APIConnectionError):
+            self.agent.ask("hello")
+        self.assertEqual(chat.calls, 4)  # original + 3 retries, then raise
+        self.assertEqual(len(self.sleeps), 3)  # 2s, 4s, 8s schedule
+
+
 if __name__ == "__main__":
     unittest.main()

{devopsiq-0.1.1 → devopsiq-0.1.3}/tests/test_phase7.py

@@ -329,11 +329,11 @@ class CliTests(unittest.TestCase):
 
     def test_parse_args_defaults(self):
         self.assertEqual(
-            main_module.parse_args([]), (None, False, None, False, None)
+            main_module.parse_args([]), (None, False, None, False, None, None)
         )
         self.assertEqual(
             main_module.parse_args(["why is it down?"]),
-            ("why is it down?", False, None, False, None),
+            ("why is it down?", False, None, False, None, None),
         )
 
     def test_parse_args_all_flags(self):
@@ -341,18 +341,19 @@ class CliTests(unittest.TestCase):
             ["--json", "--resume", "--store-dir", "/tmp/s", "--out", "r.json",
              "why", "is it down?"]
         )
-        self.assertEqual(args, ("why is it down?", True, "/tmp/s", True, "r.json"))
+        self.assertEqual(
+            args, ("why is it down?", True, "/tmp/s", True, "r.json", None))
 
     def test_parse_args_flags_only_runs_repl(self):
         self.assertEqual(
             main_module.parse_args(["--json", "--resume"]),
-            (None, True, None, True, None),
+            (None, True, None, True, None, None),
         )
 
     def test_parse_args_flag_without_value_is_ignored(self):
         self.assertEqual(
             main_module.parse_args(["--store-dir"]),
-            (None, False, None, False, None),
+            (None, False, None, False, None, None),
         )
 
     # --- --store-dir ----------------------------------------------------------