Implement analysis phase.

tools/gemini-cli-bot/critique/policy_evaluation.md

@@ -0,0 +1,32 @@
+# Phase: Policy Critique & Evaluation
+
+## Goal
+
+Evaluate the effectiveness of current repository policies and automation, and
+suggest improvements based on empirical data.
+
+## Context
+
+- Current "Pulse" scripts are in `tools/gemini-cli-bot/processes/scripts/`.
+  (Note: These may be empty if not yet implemented).
+- Metrics and investigation results are available.
+- Previous lessons learned are in `tools/gemini-cli-bot/lessons-learned.md`.
+
+## Instructions
+
+1.  **Review Policies**: Examine the existing automation in `.github/workflows/`
+    and any scripts in `tools/gemini-cli-bot/processes/scripts/`.
+2.  **Analyze Effectiveness**: Based on the metrics analysis from the
+    Investigation phase, determine if the current policies are achieving their
+    goals.
+    - Is the "Pulse" triage effectively reducing issue/PR latency?
+    - Are stale issues being closed as expected?
+    - Is the "Brain" identifying the right problems?
+3.  **Identify Gaps**: Where is the automation failing? Are there manual tasks
+    that should be automated?
+4.  **Propose Changes**: Recommend specific changes to:
+    - GitHub Workflows.
+    - Triage scripts.
+    - Repository `CONTRIBUTING.md` or `GEMINI.md` guidelines.
+5.  **Record Critique**: Append your evaluation and proposed changes to
+    `tools/gemini-cli-bot/lessons-learned.md`.

tools/gemini-cli-bot/investigations/metrics_analysis.md

@@ -0,0 +1,83 @@
+# Phase: Metrics Investigation & Root-Cause Analysis
+
+## Goal
+
+Analyze time-series repository metrics to identify trends and anomalies,
+formulate hypotheses, and rigorously investigate root causes to safely improve
+repository health.
+
+## Context
+
+- Time-series repository metrics are stored in
+  `tools/gemini-cli-bot/history/metrics-timeseries.csv`.
+- Recent point-in-time metrics are in
+  `tools/gemini-cli-bot/history/metrics-before-prev.csv` and the current run's
+  metrics.
+- Findings and state are recorded in `tools/gemini-cli-bot/lessons-learned.md`.
+
+## Repo Policy Priorities
+
+When analyzing data and proposing solutions, prioritize the following in order:
+
+1.  **Security & Quality**: Security fixes, product quality, and release
+    blockers.
+2.  **Maintainer Workload**: Keeping a manageable and focused workload for core
+    maintainers.
+3.  **Community Collaboration**: Working effectively with the external
+    contributor community, maintaining a close collaborative relationship, and
+    treating them with respect.
+
+## Instructions
+
+### 1. Read & Identify Trends (Time-Series Analysis)
+
+- Load and analyze `tools/gemini-cli-bot/history/metrics-timeseries.csv`.
+- Identify significant anomalies or deteriorating trends over time (e.g.,
+  `latency_pr_overall_hours` steadily increasing, `open_issues` growing faster
+  than closure rates, spikes in `review_distribution_variance`).
+
+### 2. Hypothesis Testing & Deep Dive
+
+For each metric not meeting goals or showing a negative trend:
+
+- **Develop Competing Hypotheses**: Brainstorm multiple potential root causes
+  (e.g., "PR Latency is high because CI is flaky" vs. "PR Latency is high
+  because reviewers are unresponsive").
+- **Gather Evidence**: Use your tools (e.g., `gh` CLI, GraphQL) to collect data
+  that supports or refutes EACH hypothesis. You may write temporary local
+  scripts to slice the data (e.g., checking issue labels, ages, or assignees).
+- **Select Root Cause**: Identify the hypothesis most strongly supported by the
+  data.
+- **Prioritize Impact**: Always prioritize solving for verified hypotheses that
+  have the largest impact (e.g., if 30 out of 500 PRs have merge conflicts,
+  fixing merge conflicts is lower priority than addressing a bottleneck
+  affecting 300 PRs).
+
+### 3. Maintainer Workload Assessment
+
+Before blaming or proposing processes that rely on maintainer action (e.g., more
+triage, more reviews):
+
+- **Quantify Capacity**: Assess the volume of open, unactioned work (untriaged
+  issues, review requests) against the number of active maintainers.
+- If the ratio indicates overload, **do not propose solutions that simply
+  generate more pings**. Instead, prioritize systemic triage, automated routing,
+  or auto-closure processes.
+
+### 4. Actor-Aware Bottleneck Identification
+
+Before proposing an intervention, accurately identify the blocker:
+
+- **Waiting on Author**: Needs a polite nudge or closure grace period.
+- **Waiting on Maintainer**: Needs routing, aggregated reports, or escalation
+  (do not nudge the author).
+- **Waiting on System (CI/Infra)**: Needs tooling fixes or reporting.
+
+### 5. Record Findings & Propose Actions
+
+- Document your formulated hypotheses, the evidence gathered, and your final
+  conclusions in `tools/gemini-cli-bot/lessons-learned.md`.
+- Propose specific, data-backed actions or script updates to address the root
+  cause. Ensure proposed actions align with the Repo Policy Priorities and
+  include concepts like graceful closures and terminal escalations to prevent
+  spam.