From 03a8405b7706d03b680644a0bb285ec04f0df9c5 Mon Sep 17 00:00:00 2001 From: Landon Cox Date: Fri, 3 Apr 2026 15:38:23 -0700 Subject: [PATCH 1/5] fix: align token workflows with gh-aw logs --json schema gh aw logs --json returns an object with a .runs array (not a bare array), and run objects use snake_case field names. All 4 token workflows (copilot/claude analyzers and optimizers) assumed a bare array with camelCase fields, causing jq errors like: Cannot index array with string "workflowName" Changes: - Extract .runs array from JSON object before processing - Replace camelCase fields with snake_case (workflow_name, token_usage, database_id, created_at) - Replace non-existent estimatedCost with 0 placeholder - Update documentation sections with correct field names Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- .../workflows/claude-token-optimizer.lock.yml | 32 +++++++++---------- .github/workflows/claude-token-optimizer.md | 23 +++++++------ .../claude-token-usage-analyzer.lock.yml | 32 +++++++++---------- .../workflows/claude-token-usage-analyzer.md | 13 +++++--- .../copilot-token-optimizer.lock.yml | 32 +++++++++---------- .github/workflows/copilot-token-optimizer.md | 23 +++++++------ .../copilot-token-usage-analyzer.lock.yml | 32 +++++++++---------- .../workflows/copilot-token-usage-analyzer.md | 13 +++++--- 8 files changed, 106 insertions(+), 94 deletions(-) diff --git a/.github/workflows/claude-token-optimizer.lock.yml b/.github/workflows/claude-token-optimizer.lock.yml index 96f5140a91..f04877ee44 100644 --- a/.github/workflows/claude-token-optimizer.lock.yml +++ b/.github/workflows/claude-token-optimizer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"e548ad0bac042ffe9ee9929d5ca90115d0d981f73c87902a8178b17947616869","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"d28ca01966ea04e0f3dbad739cdce71c88eef80ccc8091c3cbff3401dac2e05c","strict":true,"agent_id":"copilot"} name: "Claude Token Optimizer" "on": @@ -144,14 +144,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_e5e6cd140cb03f4e_EOF' + cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' - GH_AW_PROMPT_e5e6cd140cb03f4e_EOF + GH_AW_PROMPT_b4eb75949c6211e2_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_e5e6cd140cb03f4e_EOF' + cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -183,13 +183,13 @@ jobs: {{/if}} - GH_AW_PROMPT_e5e6cd140cb03f4e_EOF + GH_AW_PROMPT_b4eb75949c6211e2_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_e5e6cd140cb03f4e_EOF' + cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/claude-token-optimizer.md}} - GH_AW_PROMPT_e5e6cd140cb03f4e_EOF + GH_AW_PROMPT_b4eb75949c6211e2_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -327,7 +327,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Find and download artifacts from the most expensive Claude workflow - run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer-claude\n\necho \"đŸ“Ĩ Loading Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer-claude/claude-runs.json\n\nRUN_COUNT=$(jq '. | length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Claude runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Claude runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n group_by(.workflowName) |\n map({\n workflow: .[0].workflowName,\n total_tokens: (map(.tokenUsage) | add),\n total_cost: (map(.estimatedCost) | add),\n run_count: length,\n avg_tokens: ((map(.tokenUsage) | add) / length),\n run_ids: map(.databaseId),\n latest_run_id: (sort_by(.createdAt) | last | .databaseId),\n latest_run_url: (sort_by(.createdAt) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer-claude/claude-runs.json > /tmp/token-optimizer-claude/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer-claude/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer-claude/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run\nARTIFACT_DIR=\"/tmp/token-optimizer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer-claude/token-usage.jsonl\n echo \"Records: $(wc -l < /tmp/token-optimizer-claude/token-usage.jsonl)\"\n\n # Pre-compute Anthropic-specific metrics\n echo \"📊 Computing Anthropic cache efficiency metrics...\"\n awk '\n BEGIN { ti=0; to=0; cr=0; cw=0; tr=0 }\n {\n if (match($0, /\"input_tokens\" *: *([0-9]+)/, m)) ti += m[1]+0\n if (match($0, /\"output_tokens\" *: *([0-9]+)/, m)) to += m[1]+0\n if (match($0, /\"cache_read_tokens\" *: *([0-9]+)/, m)) cr += m[1]+0\n if (match($0, /\"cache_write_tokens\" *: *([0-9]+)/, m)) cw += m[1]+0\n tr += 1\n }\n END {\n total = ti + to + cr + cw\n if (tr == 0) exit\n printf \"Requests: %d\\n\", tr\n printf \"Input tokens: %d\\n\", ti\n printf \"Output tokens: %d\\n\", to\n printf \"Cache read tokens: %d\\n\", cr\n printf \"Cache write tokens: %d\\n\", cw\n printf \"Total tokens: %d\\n\", total\n if (ti + cr > 0) printf \"Cache hit rate: %.1f%%\\n\", (cr / (ti + cr)) * 100\n if (ti + cw > 0) printf \"Cache write rate: %.1f%%\\n\", (cw / (ti + cw)) * 100\n if (cw > 0) printf \"Cache read/write ratio: %.2f\\n\", (cr / cw)\n }' /tmp/token-optimizer-claude/token-usage.jsonl > /tmp/token-optimizer-claude/cache-metrics.txt\n cat /tmp/token-optimizer-claude/cache-metrics.txt\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer-claude/token-usage.jsonl\n touch /tmp/token-optimizer-claude/cache-metrics.txt\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer-claude/workflow-source.md\nelse\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer-claude/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source\nif [ -f /tmp/token-optimizer-claude/workflow-source.md ]; then\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer-claude/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer-claude/declared-tools.txt || true\nfi\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer-claude\n\necho \"đŸ“Ĩ Loading Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer-claude/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer-claude/claude-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-optimizer-claude/claude-runs-raw.json > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer-claude/claude-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Claude runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Claude runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer-claude/claude-runs.json > /tmp/token-optimizer-claude/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer-claude/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer-claude/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run\nARTIFACT_DIR=\"/tmp/token-optimizer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer-claude/token-usage.jsonl\n echo \"Records: $(wc -l < /tmp/token-optimizer-claude/token-usage.jsonl)\"\n\n # Pre-compute Anthropic-specific metrics\n echo \"📊 Computing Anthropic cache efficiency metrics...\"\n awk '\n BEGIN { ti=0; to=0; cr=0; cw=0; tr=0 }\n {\n if (match($0, /\"input_tokens\" *: *([0-9]+)/, m)) ti += m[1]+0\n if (match($0, /\"output_tokens\" *: *([0-9]+)/, m)) to += m[1]+0\n if (match($0, /\"cache_read_tokens\" *: *([0-9]+)/, m)) cr += m[1]+0\n if (match($0, /\"cache_write_tokens\" *: *([0-9]+)/, m)) cw += m[1]+0\n tr += 1\n }\n END {\n total = ti + to + cr + cw\n if (tr == 0) exit\n printf \"Requests: %d\\n\", tr\n printf \"Input tokens: %d\\n\", ti\n printf \"Output tokens: %d\\n\", to\n printf \"Cache read tokens: %d\\n\", cr\n printf \"Cache write tokens: %d\\n\", cw\n printf \"Total tokens: %d\\n\", total\n if (ti + cr > 0) printf \"Cache hit rate: %.1f%%\\n\", (cr / (ti + cr)) * 100\n if (ti + cw > 0) printf \"Cache write rate: %.1f%%\\n\", (cw / (ti + cw)) * 100\n if (cw > 0) printf \"Cache read/write ratio: %.2f\\n\", (cr / cw)\n }' /tmp/token-optimizer-claude/token-usage.jsonl > /tmp/token-optimizer-claude/cache-metrics.txt\n cat /tmp/token-optimizer-claude/cache-metrics.txt\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer-claude/token-usage.jsonl\n touch /tmp/token-optimizer-claude/cache-metrics.txt\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer-claude/workflow-source.md\nelse\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer-claude/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source\nif [ -f /tmp/token-optimizer-claude/workflow-source.md ]; then\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer-claude/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer-claude/declared-tools.txt || true\nfi\n" - name: Configure Git credentials env: @@ -378,12 +378,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_99f3c82673c40c75_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_0fb88f09872c1369_EOF' {"create_issue":{"close_older_issues":true,"expires":168,"labels":["automated-analysis","token-optimization","claude","cost-reduction"],"max":1,"title_prefix":"⚡ Claude Token Optimization: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_99f3c82673c40c75_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_0fb88f09872c1369_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_016c509bb887d8a7_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_971214b094014a4d_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"⚡ Claude Token Optimization: \". Labels [\"automated-analysis\" \"token-optimization\" \"claude\" \"cost-reduction\"] will be automatically added." @@ -391,8 +391,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_016c509bb887d8a7_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_8bdfec3203e0fed8_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_971214b094014a4d_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_ad5d398c6bc28877_EOF' { "create_issue": { "defaultMax": 1, @@ -485,7 +485,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_8bdfec3203e0fed8_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_ad5d398c6bc28877_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -555,7 +555,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_7859ed28542ae487_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_c6bfa07f5408b430_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -596,7 +596,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_7859ed28542ae487_EOF + GH_AW_MCP_CONFIG_c6bfa07f5408b430_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/claude-token-optimizer.md b/.github/workflows/claude-token-optimizer.md index 22d7bb0405..9553c52ba8 100644 --- a/.github/workflows/claude-token-optimizer.md +++ b/.github/workflows/claude-token-optimizer.md @@ -67,9 +67,12 @@ steps: --start-date -1d \ --json \ -c 300 \ - > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-optimizer-claude/claude-runs.json + > /tmp/token-optimizer-claude/claude-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-optimizer-claude/claude-runs-raw.json - RUN_COUNT=$(jq '. | length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0) + # Extract runs array from the JSON output + jq '.runs // []' /tmp/token-optimizer-claude/claude-runs-raw.json > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-optimizer-claude/claude-runs.json + + RUN_COUNT=$(jq 'length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0) echo "Found ${RUN_COUNT} Claude runs" if [ "$RUN_COUNT" -eq 0 ]; then @@ -80,16 +83,16 @@ steps: # Find the most expensive workflow (by total tokens across all its runs) echo "🔍 Identifying most expensive workflow..." jq -r ' - group_by(.workflowName) | + group_by(.workflow_name) | map({ - workflow: .[0].workflowName, - total_tokens: (map(.tokenUsage) | add), - total_cost: (map(.estimatedCost) | add), + workflow: .[0].workflow_name, + total_tokens: (map(.token_usage) | add), + total_cost: 0, run_count: length, - avg_tokens: ((map(.tokenUsage) | add) / length), - run_ids: map(.databaseId), - latest_run_id: (sort_by(.createdAt) | last | .databaseId), - latest_run_url: (sort_by(.createdAt) | last | .url) + avg_tokens: ((map(.token_usage) | add) / length), + run_ids: map(.database_id), + latest_run_id: (sort_by(.created_at) | last | .database_id), + latest_run_url: (sort_by(.created_at) | last | .url) }) | sort_by(.total_tokens) | reverse | .[0] ' /tmp/token-optimizer-claude/claude-runs.json > /tmp/token-optimizer-claude/top-workflow.json diff --git a/.github/workflows/claude-token-usage-analyzer.lock.yml b/.github/workflows/claude-token-usage-analyzer.lock.yml index e568b2f3b6..f4363eb968 100644 --- a/.github/workflows/claude-token-usage-analyzer.lock.yml +++ b/.github/workflows/claude-token-usage-analyzer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"e69b0617753455baec21652278430e9c3520a4d1be3eb97cd0032ddd5d6857c1","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"6d66eade0456e72f7633fe59372e82e86d56afc2d374492975124f67ea898cf1","strict":true,"agent_id":"copilot"} name: "Claude Token Usage Analyzer" "on": @@ -132,14 +132,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_8006b394fe911ee1_EOF' + cat << 'GH_AW_PROMPT_e1a5813608bb58e3_EOF' - GH_AW_PROMPT_8006b394fe911ee1_EOF + GH_AW_PROMPT_e1a5813608bb58e3_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_8006b394fe911ee1_EOF' + cat << 'GH_AW_PROMPT_e1a5813608bb58e3_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -171,13 +171,13 @@ jobs: {{/if}} - GH_AW_PROMPT_8006b394fe911ee1_EOF + GH_AW_PROMPT_e1a5813608bb58e3_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_8006b394fe911ee1_EOF' + cat << 'GH_AW_PROMPT_e1a5813608bb58e3_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/claude-token-usage-analyzer.md}} - GH_AW_PROMPT_8006b394fe911ee1_EOF + GH_AW_PROMPT_e1a5813608bb58e3_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -310,7 +310,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Download Claude workflow runs (last 24h) - run: "set -euo pipefail\nmkdir -p /tmp/token-analyzer-claude\n\necho \"đŸ“Ĩ Downloading Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-analyzer-claude/claude-runs.json\n\nRUN_COUNT=$(jq '. | length' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"✅ Found ${RUN_COUNT} Claude workflow runs\"\n\n# Download token-usage.jsonl artifacts for per-model breakdown\nARTIFACT_DIR=\"/tmp/token-analyzer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading token-usage.jsonl artifacts...\"\njq -r '.[0:50][]?.databaseId' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null > /tmp/token-analyzer-claude/run-ids.txt || true\nwhile read -r run_id; do\n run_dir=\"$ARTIFACT_DIR/$run_id\"\n mkdir -p \"$run_dir\"\n gh run download \"$run_id\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$run_dir\" \\\n 2>/dev/null || true\ndone < /tmp/token-analyzer-claude/run-ids.txt\n\n# Count how many token-usage.jsonl files we got\nJSONL_COUNT=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | wc -l)\necho \"✅ Downloaded ${JSONL_COUNT} token-usage.jsonl artifacts\"\n\n# Merge all token-usage.jsonl files annotated with run_id\nMERGED_FILE=\"/tmp/token-analyzer-claude/token-usage-merged.jsonl\"\n> \"$MERGED_FILE\"\nfind \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" > /tmp/token-analyzer-claude/jsonl-files.txt 2>/dev/null || true\nwhile read -r f; do\n run_id=$(echo \"$f\" | grep -oP '(?<=/artifacts/)\\d+(?=/)' || true)\n while IFS= read -r line; do\n if [ -n \"$line\" ]; then\n echo \"${line}\" | jq --arg run_id \"$run_id\" '. + {run_id: $run_id}' >> \"$MERGED_FILE\" 2>/dev/null || true\n fi\n done < \"$f\"\ndone < /tmp/token-analyzer-claude/jsonl-files.txt\n\nRECORD_COUNT=$(wc -l < \"$MERGED_FILE\" 2>/dev/null || echo 0)\necho \"✅ Merged ${RECORD_COUNT} token usage records\"\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-analyzer-claude\n\necho \"đŸ“Ĩ Downloading Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-analyzer-claude/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-analyzer-claude/claude-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-analyzer-claude/claude-runs-raw.json > /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-analyzer-claude/claude-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"✅ Found ${RUN_COUNT} Claude workflow runs\"\n\n# Download token-usage.jsonl artifacts for per-model breakdown\nARTIFACT_DIR=\"/tmp/token-analyzer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading token-usage.jsonl artifacts...\"\njq -r '.[0:50][]?.database_id' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null > /tmp/token-analyzer-claude/run-ids.txt || true\nwhile read -r run_id; do\n run_dir=\"$ARTIFACT_DIR/$run_id\"\n mkdir -p \"$run_dir\"\n gh run download \"$run_id\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$run_dir\" \\\n 2>/dev/null || true\ndone < /tmp/token-analyzer-claude/run-ids.txt\n\n# Count how many token-usage.jsonl files we got\nJSONL_COUNT=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | wc -l)\necho \"✅ Downloaded ${JSONL_COUNT} token-usage.jsonl artifacts\"\n\n# Merge all token-usage.jsonl files annotated with run_id\nMERGED_FILE=\"/tmp/token-analyzer-claude/token-usage-merged.jsonl\"\n> \"$MERGED_FILE\"\nfind \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" > /tmp/token-analyzer-claude/jsonl-files.txt 2>/dev/null || true\nwhile read -r f; do\n run_id=$(echo \"$f\" | grep -oP '(?<=/artifacts/)\\d+(?=/)' || true)\n while IFS= read -r line; do\n if [ -n \"$line\" ]; then\n echo \"${line}\" | jq --arg run_id \"$run_id\" '. + {run_id: $run_id}' >> \"$MERGED_FILE\" 2>/dev/null || true\n fi\n done < \"$f\"\ndone < /tmp/token-analyzer-claude/jsonl-files.txt\n\nRECORD_COUNT=$(wc -l < \"$MERGED_FILE\" 2>/dev/null || echo 0)\necho \"✅ Merged ${RECORD_COUNT} token usage records\"\n" - name: Configure Git credentials env: @@ -361,12 +361,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_6145119542beae75_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_a4ba8bab8dcca375_EOF' {"create_issue":{"close_older_issues":true,"expires":48,"labels":["automated-analysis","token-usage","claude"],"max":1,"title_prefix":"📊 Claude Token Usage Report: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_6145119542beae75_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_a4ba8bab8dcca375_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_eaa180fbfdb4f218_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_e2f42f9d919138fa_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"📊 Claude Token Usage Report: \". Labels [\"automated-analysis\" \"token-usage\" \"claude\"] will be automatically added." @@ -374,8 +374,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_eaa180fbfdb4f218_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_8bb554f7bb6db76c_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_e2f42f9d919138fa_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_89ae148174e0a909_EOF' { "create_issue": { "defaultMax": 1, @@ -468,7 +468,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_8bb554f7bb6db76c_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_89ae148174e0a909_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -538,7 +538,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_b511e335517d7f14_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_d12389cf810a9482_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -579,7 +579,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_b511e335517d7f14_EOF + GH_AW_MCP_CONFIG_d12389cf810a9482_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/claude-token-usage-analyzer.md b/.github/workflows/claude-token-usage-analyzer.md index caabb9f1ff..491a9e2cd6 100644 --- a/.github/workflows/claude-token-usage-analyzer.md +++ b/.github/workflows/claude-token-usage-analyzer.md @@ -59,9 +59,12 @@ steps: --start-date -1d \ --json \ -c 300 \ - > /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-analyzer-claude/claude-runs.json + > /tmp/token-analyzer-claude/claude-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-analyzer-claude/claude-runs-raw.json - RUN_COUNT=$(jq '. | length' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo 0) + # Extract runs array from the JSON output + jq '.runs // []' /tmp/token-analyzer-claude/claude-runs-raw.json > /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-analyzer-claude/claude-runs.json + + RUN_COUNT=$(jq 'length' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo 0) echo "✅ Found ${RUN_COUNT} Claude workflow runs" # Download token-usage.jsonl artifacts for per-model breakdown @@ -69,7 +72,7 @@ steps: mkdir -p "$ARTIFACT_DIR" echo "đŸ“Ĩ Downloading token-usage.jsonl artifacts..." - jq -r '.[0:50][]?.databaseId' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null > /tmp/token-analyzer-claude/run-ids.txt || true + jq -r '.[0:50][]?.database_id' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null > /tmp/token-analyzer-claude/run-ids.txt || true while read -r run_id; do run_dir="$ARTIFACT_DIR/$run_id" mkdir -p "$run_dir" @@ -119,7 +122,7 @@ You are the Claude Token Usage Analyzer. Your job is to analyze Claude/Anthropic Pre-downloaded data is available in `/tmp/token-analyzer-claude/`: -- **`/tmp/token-analyzer-claude/claude-runs.json`** — All Claude workflow runs from the last 24 hours (array of run objects with `workflowName`, `databaseId`, `tokenUsage`, `estimatedCost`, `turns`, `url`, `conclusion`, etc.) +- **`/tmp/token-analyzer-claude/claude-runs.json`** — All Claude workflow runs from the last 24 hours (array of run objects with `workflow_name`, `database_id`, `token_usage`, `turns`, `url`, `conclusion`, etc.) - **`/tmp/token-analyzer-claude/token-usage-merged.jsonl`** — Merged per-request token records from `firewall-audit-logs` artifacts, with fields: `model`, `provider`, `input_tokens`, `output_tokens`, `cache_read_tokens`, `cache_write_tokens`, `duration_ms`, `run_id` ## Analysis Process @@ -129,7 +132,7 @@ Pre-downloaded data is available in `/tmp/token-analyzer-claude/`: Process `/tmp/token-analyzer-claude/claude-runs.json` to compute per-workflow statistics: ```bash -jq -r '.[] | [.workflowName, .tokenUsage, .estimatedCost, .turns, .conclusion, .url, .databaseId] | @tsv' \ +jq -r '.[] | [.workflow_name, .token_usage, .turns, .conclusion, .url, .database_id] | @tsv' \ /tmp/token-analyzer-claude/claude-runs.json ``` diff --git a/.github/workflows/copilot-token-optimizer.lock.yml b/.github/workflows/copilot-token-optimizer.lock.yml index b9547ce301..9e585f38b2 100644 --- a/.github/workflows/copilot-token-optimizer.lock.yml +++ b/.github/workflows/copilot-token-optimizer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"a8f59f14c06aff09cf7fdc31208a784b762c3c12b7d12fa5d1bb3a2dbfe6567c","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"fd23e1427b2313e8891e828fe49ebfd23bdc4abc966f587a004d381370a68f13","strict":true,"agent_id":"copilot"} name: "Copilot Token Optimizer" "on": @@ -144,14 +144,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_9c06ceb9fc3e8446_EOF' + cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' - GH_AW_PROMPT_9c06ceb9fc3e8446_EOF + GH_AW_PROMPT_68c5831fe1087681_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_9c06ceb9fc3e8446_EOF' + cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -183,13 +183,13 @@ jobs: {{/if}} - GH_AW_PROMPT_9c06ceb9fc3e8446_EOF + GH_AW_PROMPT_68c5831fe1087681_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_9c06ceb9fc3e8446_EOF' + cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/copilot-token-optimizer.md}} - GH_AW_PROMPT_9c06ceb9fc3e8446_EOF + GH_AW_PROMPT_68c5831fe1087681_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -327,7 +327,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Find and download artifacts from the most expensive Copilot workflow - run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer\n\necho \"đŸ“Ĩ Loading Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer/copilot-runs.json\n\nRUN_COUNT=$(jq '. | length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Copilot runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Copilot runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n group_by(.workflowName) |\n map({\n workflow: .[0].workflowName,\n total_tokens: (map(.tokenUsage) | add),\n total_cost: (map(.estimatedCost) | add),\n run_count: length,\n avg_tokens: ((map(.tokenUsage) | add) / length),\n run_ids: map(.databaseId),\n latest_run_id: (sort_by(.createdAt) | last | .databaseId),\n latest_run_url: (sort_by(.createdAt) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer/copilot-runs.json > /tmp/token-optimizer/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run of that workflow\nARTIFACT_DIR=\"/tmp/token-optimizer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts (contains prompt and tool usage logs)\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer/token-usage.jsonl\n wc -l < /tmp/token-optimizer/token-usage.jsonl\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer/token-usage.jsonl\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer/workflow-source.md\nelse\n echo \"Workflow source not found at $WORKFLOW_MD, searching...\"\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source (if available)\nif [ -f /tmp/token-optimizer/workflow-source.md ]; then\n echo \"📋 Extracting declared tools from workflow source...\"\n # Extract tools section from frontmatter\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer/declared-tools.txt || true\n cat /tmp/token-optimizer/declared-tools.txt\nfi\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer\n\necho \"đŸ“Ĩ Loading Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer/copilot-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-optimizer/copilot-runs-raw.json > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer/copilot-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Copilot runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Copilot runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer/copilot-runs.json > /tmp/token-optimizer/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run of that workflow\nARTIFACT_DIR=\"/tmp/token-optimizer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts (contains prompt and tool usage logs)\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer/token-usage.jsonl\n wc -l < /tmp/token-optimizer/token-usage.jsonl\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer/token-usage.jsonl\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer/workflow-source.md\nelse\n echo \"Workflow source not found at $WORKFLOW_MD, searching...\"\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source (if available)\nif [ -f /tmp/token-optimizer/workflow-source.md ]; then\n echo \"📋 Extracting declared tools from workflow source...\"\n # Extract tools section from frontmatter\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer/declared-tools.txt || true\n cat /tmp/token-optimizer/declared-tools.txt\nfi\n" - name: Configure Git credentials env: @@ -378,12 +378,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_bdb51c7b3aee79ae_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_178afd5b56c5bba7_EOF' {"create_issue":{"close_older_issues":true,"expires":168,"labels":["automated-analysis","token-optimization","copilot","cost-reduction"],"max":1,"title_prefix":"⚡ Copilot Token Optimization: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_bdb51c7b3aee79ae_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_178afd5b56c5bba7_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_5f6440cb818356b0_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_cec4f6a3637a6d3b_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"⚡ Copilot Token Optimization: \". Labels [\"automated-analysis\" \"token-optimization\" \"copilot\" \"cost-reduction\"] will be automatically added." @@ -391,8 +391,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_5f6440cb818356b0_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_685e42b2b99de53a_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_cec4f6a3637a6d3b_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_2089a1213782993a_EOF' { "create_issue": { "defaultMax": 1, @@ -485,7 +485,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_685e42b2b99de53a_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_2089a1213782993a_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -555,7 +555,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_ce5a4d1c93479cfc_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_27cc3fbbc713df4f_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -596,7 +596,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_ce5a4d1c93479cfc_EOF + GH_AW_MCP_CONFIG_27cc3fbbc713df4f_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/copilot-token-optimizer.md b/.github/workflows/copilot-token-optimizer.md index e722e076f5..b3f203ff6f 100644 --- a/.github/workflows/copilot-token-optimizer.md +++ b/.github/workflows/copilot-token-optimizer.md @@ -67,9 +67,12 @@ steps: --start-date -1d \ --json \ -c 300 \ - > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-optimizer/copilot-runs.json + > /tmp/token-optimizer/copilot-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-optimizer/copilot-runs-raw.json - RUN_COUNT=$(jq '. | length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0) + # Extract runs array from the JSON output + jq '.runs // []' /tmp/token-optimizer/copilot-runs-raw.json > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-optimizer/copilot-runs.json + + RUN_COUNT=$(jq 'length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0) echo "Found ${RUN_COUNT} Copilot runs" if [ "$RUN_COUNT" -eq 0 ]; then @@ -80,16 +83,16 @@ steps: # Find the most expensive workflow (by total tokens across all its runs) echo "🔍 Identifying most expensive workflow..." jq -r ' - group_by(.workflowName) | + group_by(.workflow_name) | map({ - workflow: .[0].workflowName, - total_tokens: (map(.tokenUsage) | add), - total_cost: (map(.estimatedCost) | add), + workflow: .[0].workflow_name, + total_tokens: (map(.token_usage) | add), + total_cost: 0, run_count: length, - avg_tokens: ((map(.tokenUsage) | add) / length), - run_ids: map(.databaseId), - latest_run_id: (sort_by(.createdAt) | last | .databaseId), - latest_run_url: (sort_by(.createdAt) | last | .url) + avg_tokens: ((map(.token_usage) | add) / length), + run_ids: map(.database_id), + latest_run_id: (sort_by(.created_at) | last | .database_id), + latest_run_url: (sort_by(.created_at) | last | .url) }) | sort_by(.total_tokens) | reverse | .[0] ' /tmp/token-optimizer/copilot-runs.json > /tmp/token-optimizer/top-workflow.json diff --git a/.github/workflows/copilot-token-usage-analyzer.lock.yml b/.github/workflows/copilot-token-usage-analyzer.lock.yml index 2f00dbb165..af26d0d589 100644 --- a/.github/workflows/copilot-token-usage-analyzer.lock.yml +++ b/.github/workflows/copilot-token-usage-analyzer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"b1ce75410b09f89b58a1f4df88bc49635b77fb7d802528b5869f504e3085b94b","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"b289a6f4ddae47c218302a21a6199546f19abebf8650b1963e2c8699302c4666","strict":true,"agent_id":"copilot"} name: "Copilot Token Usage Analyzer" "on": @@ -132,14 +132,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_77b51c2908cd9c50_EOF' + cat << 'GH_AW_PROMPT_ac218341b6979b04_EOF' - GH_AW_PROMPT_77b51c2908cd9c50_EOF + GH_AW_PROMPT_ac218341b6979b04_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_77b51c2908cd9c50_EOF' + cat << 'GH_AW_PROMPT_ac218341b6979b04_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -171,13 +171,13 @@ jobs: {{/if}} - GH_AW_PROMPT_77b51c2908cd9c50_EOF + GH_AW_PROMPT_ac218341b6979b04_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_77b51c2908cd9c50_EOF' + cat << 'GH_AW_PROMPT_ac218341b6979b04_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/copilot-token-usage-analyzer.md}} - GH_AW_PROMPT_77b51c2908cd9c50_EOF + GH_AW_PROMPT_ac218341b6979b04_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -310,7 +310,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Download Copilot workflow runs (last 24h) - run: "set -euo pipefail\nmkdir -p /tmp/token-analyzer\n\necho \"đŸ“Ĩ Downloading Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-analyzer/copilot-runs.json\n\nRUN_COUNT=$(jq '. | length' /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo 0)\necho \"✅ Found ${RUN_COUNT} Copilot workflow runs\"\n\n# Download token-usage.jsonl artifacts for per-model breakdown\n# We look for the firewall-audit-logs artifact which contains token-usage.jsonl\nARTIFACT_DIR=\"/tmp/token-analyzer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading token-usage.jsonl artifacts...\"\njq -r '.[0:50][]?.databaseId' /tmp/token-analyzer/copilot-runs.json 2>/dev/null > /tmp/token-analyzer/run-ids.txt || true\nwhile read -r run_id; do\n run_dir=\"$ARTIFACT_DIR/$run_id\"\n mkdir -p \"$run_dir\"\n gh run download \"$run_id\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$run_dir\" \\\n 2>/dev/null || true\ndone < /tmp/token-analyzer/run-ids.txt\n\n# Count how many token-usage.jsonl files we got\nJSONL_COUNT=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | wc -l)\necho \"✅ Downloaded ${JSONL_COUNT} token-usage.jsonl artifacts\"\n\n# Merge all token-usage.jsonl files into a single aggregate file annotated with run_id\nMERGED_FILE=\"/tmp/token-analyzer/token-usage-merged.jsonl\"\n> \"$MERGED_FILE\"\nfind \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" > /tmp/token-analyzer/jsonl-files.txt 2>/dev/null || true\nwhile read -r f; do\n run_id=$(echo \"$f\" | grep -oP '(?<=/artifacts/)\\d+(?=/)' || true)\n while IFS= read -r line; do\n if [ -n \"$line\" ]; then\n echo \"${line}\" | jq --arg run_id \"$run_id\" '. + {run_id: $run_id}' >> \"$MERGED_FILE\" 2>/dev/null || true\n fi\n done < \"$f\"\ndone < /tmp/token-analyzer/jsonl-files.txt\n\nRECORD_COUNT=$(wc -l < \"$MERGED_FILE\" 2>/dev/null || echo 0)\necho \"✅ Merged ${RECORD_COUNT} token usage records\"\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-analyzer\n\necho \"đŸ“Ĩ Downloading Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-analyzer/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-analyzer/copilot-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-analyzer/copilot-runs-raw.json > /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-analyzer/copilot-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo 0)\necho \"✅ Found ${RUN_COUNT} Copilot workflow runs\"\n\n# Download token-usage.jsonl artifacts for per-model breakdown\n# We look for the firewall-audit-logs artifact which contains token-usage.jsonl\nARTIFACT_DIR=\"/tmp/token-analyzer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading token-usage.jsonl artifacts...\"\njq -r '.[0:50][]?.database_id' /tmp/token-analyzer/copilot-runs.json 2>/dev/null > /tmp/token-analyzer/run-ids.txt || true\nwhile read -r run_id; do\n run_dir=\"$ARTIFACT_DIR/$run_id\"\n mkdir -p \"$run_dir\"\n gh run download \"$run_id\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$run_dir\" \\\n 2>/dev/null || true\ndone < /tmp/token-analyzer/run-ids.txt\n\n# Count how many token-usage.jsonl files we got\nJSONL_COUNT=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | wc -l)\necho \"✅ Downloaded ${JSONL_COUNT} token-usage.jsonl artifacts\"\n\n# Merge all token-usage.jsonl files into a single aggregate file annotated with run_id\nMERGED_FILE=\"/tmp/token-analyzer/token-usage-merged.jsonl\"\n> \"$MERGED_FILE\"\nfind \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" > /tmp/token-analyzer/jsonl-files.txt 2>/dev/null || true\nwhile read -r f; do\n run_id=$(echo \"$f\" | grep -oP '(?<=/artifacts/)\\d+(?=/)' || true)\n while IFS= read -r line; do\n if [ -n \"$line\" ]; then\n echo \"${line}\" | jq --arg run_id \"$run_id\" '. + {run_id: $run_id}' >> \"$MERGED_FILE\" 2>/dev/null || true\n fi\n done < \"$f\"\ndone < /tmp/token-analyzer/jsonl-files.txt\n\nRECORD_COUNT=$(wc -l < \"$MERGED_FILE\" 2>/dev/null || echo 0)\necho \"✅ Merged ${RECORD_COUNT} token usage records\"\n" - name: Configure Git credentials env: @@ -361,12 +361,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_0237bbe3896dae81_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_34f7182c6d0b277b_EOF' {"create_issue":{"close_older_issues":true,"expires":48,"labels":["automated-analysis","token-usage","copilot"],"max":1,"title_prefix":"📊 Copilot Token Usage Report: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_0237bbe3896dae81_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_34f7182c6d0b277b_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_21502b3c7d44f092_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_840971bf025c07cc_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"📊 Copilot Token Usage Report: \". Labels [\"automated-analysis\" \"token-usage\" \"copilot\"] will be automatically added." @@ -374,8 +374,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_21502b3c7d44f092_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_5df732c7ff691456_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_840971bf025c07cc_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_b0e902b7f47a2fc6_EOF' { "create_issue": { "defaultMax": 1, @@ -468,7 +468,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_5df732c7ff691456_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_b0e902b7f47a2fc6_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -538,7 +538,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_85f5bf5a0a3b4a96_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_b6b35d61ba8b5d52_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -579,7 +579,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_85f5bf5a0a3b4a96_EOF + GH_AW_MCP_CONFIG_b6b35d61ba8b5d52_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/copilot-token-usage-analyzer.md b/.github/workflows/copilot-token-usage-analyzer.md index 33793fd52c..2b85b75157 100644 --- a/.github/workflows/copilot-token-usage-analyzer.md +++ b/.github/workflows/copilot-token-usage-analyzer.md @@ -59,9 +59,12 @@ steps: --start-date -1d \ --json \ -c 300 \ - > /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-analyzer/copilot-runs.json + > /tmp/token-analyzer/copilot-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-analyzer/copilot-runs-raw.json - RUN_COUNT=$(jq '. | length' /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo 0) + # Extract runs array from the JSON output + jq '.runs // []' /tmp/token-analyzer/copilot-runs-raw.json > /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-analyzer/copilot-runs.json + + RUN_COUNT=$(jq 'length' /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo 0) echo "✅ Found ${RUN_COUNT} Copilot workflow runs" # Download token-usage.jsonl artifacts for per-model breakdown @@ -70,7 +73,7 @@ steps: mkdir -p "$ARTIFACT_DIR" echo "đŸ“Ĩ Downloading token-usage.jsonl artifacts..." - jq -r '.[0:50][]?.databaseId' /tmp/token-analyzer/copilot-runs.json 2>/dev/null > /tmp/token-analyzer/run-ids.txt || true + jq -r '.[0:50][]?.database_id' /tmp/token-analyzer/copilot-runs.json 2>/dev/null > /tmp/token-analyzer/run-ids.txt || true while read -r run_id; do run_dir="$ARTIFACT_DIR/$run_id" mkdir -p "$run_dir" @@ -120,7 +123,7 @@ You are the Copilot Token Usage Analyzer. Your job is to analyze Copilot token c Pre-downloaded data is available in `/tmp/token-analyzer/`: -- **`/tmp/token-analyzer/copilot-runs.json`** — All Copilot workflow runs from the last 24 hours (array of run objects with `workflowName`, `databaseId`, `tokenUsage`, `estimatedCost`, `turns`, `url`, `conclusion`, etc.) +- **`/tmp/token-analyzer/copilot-runs.json`** — All Copilot workflow runs from the last 24 hours (array of run objects with `workflow_name`, `database_id`, `token_usage`, `turns`, `url`, `conclusion`, etc.) - **`/tmp/token-analyzer/token-usage-merged.jsonl`** — Merged per-request token records from `firewall-audit-logs` artifacts, with fields: `model`, `provider`, `input_tokens`, `output_tokens`, `cache_read_tokens`, `cache_write_tokens`, `duration_ms`, `run_id` ## Analysis Process @@ -130,7 +133,7 @@ Pre-downloaded data is available in `/tmp/token-analyzer/`: Process `/tmp/token-analyzer/copilot-runs.json` to compute per-workflow statistics: ```bash -jq -r '.[] | [.workflowName, .tokenUsage, .estimatedCost, .turns, .conclusion, .url, .databaseId] | @tsv' \ +jq -r '.[] | [.workflow_name, .token_usage, .turns, .conclusion, .url, .database_id] | @tsv' \ /tmp/token-analyzer/copilot-runs.json ``` From 5949c35a05970dfa879222792f7987e03cca3bd9 Mon Sep 17 00:00:00 2001 From: Landon Cox Date: Fri, 3 Apr 2026 15:56:09 -0700 Subject: [PATCH 2/5] Update .github/workflows/copilot-token-optimizer.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --- .github/workflows/copilot-token-optimizer.md | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/copilot-token-optimizer.md b/.github/workflows/copilot-token-optimizer.md index b3f203ff6f..457c7258f1 100644 --- a/.github/workflows/copilot-token-optimizer.md +++ b/.github/workflows/copilot-token-optimizer.md @@ -83,6 +83,7 @@ steps: # Find the most expensive workflow (by total tokens across all its runs) echo "🔍 Identifying most expensive workflow..." jq -r ' + sort_by(.workflow_name) | group_by(.workflow_name) | map({ workflow: .[0].workflow_name, From 35666e43edb6eaeab9abd4d557e74a122b7e2e86 Mon Sep 17 00:00:00 2001 From: Landon Cox Date: Fri, 3 Apr 2026 15:57:07 -0700 Subject: [PATCH 3/5] Update .github/workflows/claude-token-optimizer.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --- .github/workflows/claude-token-optimizer.md | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/claude-token-optimizer.md b/.github/workflows/claude-token-optimizer.md index 9553c52ba8..97c9f3fba5 100644 --- a/.github/workflows/claude-token-optimizer.md +++ b/.github/workflows/claude-token-optimizer.md @@ -83,6 +83,7 @@ steps: # Find the most expensive workflow (by total tokens across all its runs) echo "🔍 Identifying most expensive workflow..." jq -r ' + sort_by(.workflow_name) | group_by(.workflow_name) | map({ workflow: .[0].workflow_name, From 39f9224b5e67103b4517b2170cf3310c5a111c08 Mon Sep 17 00:00:00 2001 From: Landon Cox Date: Fri, 3 Apr 2026 16:03:25 -0700 Subject: [PATCH 4/5] fix: recompile lock files after sort_by addition Recompile copilot-token-optimizer and claude-token-optimizer lock files to match the sort_by(.workflow_name) additions made via UI. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- .../workflows/claude-token-optimizer.lock.yml | 32 +++++++++---------- .../copilot-token-optimizer.lock.yml | 32 +++++++++---------- 2 files changed, 32 insertions(+), 32 deletions(-) diff --git a/.github/workflows/claude-token-optimizer.lock.yml b/.github/workflows/claude-token-optimizer.lock.yml index f04877ee44..9ebdd50148 100644 --- a/.github/workflows/claude-token-optimizer.lock.yml +++ b/.github/workflows/claude-token-optimizer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"d28ca01966ea04e0f3dbad739cdce71c88eef80ccc8091c3cbff3401dac2e05c","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"13c7cfc5295aa61b7c28a922b22cd0b487ba6300261433bc1162560a4ccf53dc","strict":true,"agent_id":"copilot"} name: "Claude Token Optimizer" "on": @@ -144,14 +144,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' + cat << 'GH_AW_PROMPT_589ef83e3bd3cda7_EOF' - GH_AW_PROMPT_b4eb75949c6211e2_EOF + GH_AW_PROMPT_589ef83e3bd3cda7_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' + cat << 'GH_AW_PROMPT_589ef83e3bd3cda7_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -183,13 +183,13 @@ jobs: {{/if}} - GH_AW_PROMPT_b4eb75949c6211e2_EOF + GH_AW_PROMPT_589ef83e3bd3cda7_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' + cat << 'GH_AW_PROMPT_589ef83e3bd3cda7_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/claude-token-optimizer.md}} - GH_AW_PROMPT_b4eb75949c6211e2_EOF + GH_AW_PROMPT_589ef83e3bd3cda7_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -327,7 +327,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Find and download artifacts from the most expensive Claude workflow - run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer-claude\n\necho \"đŸ“Ĩ Loading Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer-claude/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer-claude/claude-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-optimizer-claude/claude-runs-raw.json > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer-claude/claude-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Claude runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Claude runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer-claude/claude-runs.json > /tmp/token-optimizer-claude/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer-claude/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer-claude/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run\nARTIFACT_DIR=\"/tmp/token-optimizer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer-claude/token-usage.jsonl\n echo \"Records: $(wc -l < /tmp/token-optimizer-claude/token-usage.jsonl)\"\n\n # Pre-compute Anthropic-specific metrics\n echo \"📊 Computing Anthropic cache efficiency metrics...\"\n awk '\n BEGIN { ti=0; to=0; cr=0; cw=0; tr=0 }\n {\n if (match($0, /\"input_tokens\" *: *([0-9]+)/, m)) ti += m[1]+0\n if (match($0, /\"output_tokens\" *: *([0-9]+)/, m)) to += m[1]+0\n if (match($0, /\"cache_read_tokens\" *: *([0-9]+)/, m)) cr += m[1]+0\n if (match($0, /\"cache_write_tokens\" *: *([0-9]+)/, m)) cw += m[1]+0\n tr += 1\n }\n END {\n total = ti + to + cr + cw\n if (tr == 0) exit\n printf \"Requests: %d\\n\", tr\n printf \"Input tokens: %d\\n\", ti\n printf \"Output tokens: %d\\n\", to\n printf \"Cache read tokens: %d\\n\", cr\n printf \"Cache write tokens: %d\\n\", cw\n printf \"Total tokens: %d\\n\", total\n if (ti + cr > 0) printf \"Cache hit rate: %.1f%%\\n\", (cr / (ti + cr)) * 100\n if (ti + cw > 0) printf \"Cache write rate: %.1f%%\\n\", (cw / (ti + cw)) * 100\n if (cw > 0) printf \"Cache read/write ratio: %.2f\\n\", (cr / cw)\n }' /tmp/token-optimizer-claude/token-usage.jsonl > /tmp/token-optimizer-claude/cache-metrics.txt\n cat /tmp/token-optimizer-claude/cache-metrics.txt\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer-claude/token-usage.jsonl\n touch /tmp/token-optimizer-claude/cache-metrics.txt\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer-claude/workflow-source.md\nelse\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer-claude/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source\nif [ -f /tmp/token-optimizer-claude/workflow-source.md ]; then\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer-claude/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer-claude/declared-tools.txt || true\nfi\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer-claude\n\necho \"đŸ“Ĩ Loading Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer-claude/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer-claude/claude-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-optimizer-claude/claude-runs-raw.json > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer-claude/claude-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Claude runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Claude runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n sort_by(.workflow_name) |\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer-claude/claude-runs.json > /tmp/token-optimizer-claude/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer-claude/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer-claude/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run\nARTIFACT_DIR=\"/tmp/token-optimizer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer-claude/token-usage.jsonl\n echo \"Records: $(wc -l < /tmp/token-optimizer-claude/token-usage.jsonl)\"\n\n # Pre-compute Anthropic-specific metrics\n echo \"📊 Computing Anthropic cache efficiency metrics...\"\n awk '\n BEGIN { ti=0; to=0; cr=0; cw=0; tr=0 }\n {\n if (match($0, /\"input_tokens\" *: *([0-9]+)/, m)) ti += m[1]+0\n if (match($0, /\"output_tokens\" *: *([0-9]+)/, m)) to += m[1]+0\n if (match($0, /\"cache_read_tokens\" *: *([0-9]+)/, m)) cr += m[1]+0\n if (match($0, /\"cache_write_tokens\" *: *([0-9]+)/, m)) cw += m[1]+0\n tr += 1\n }\n END {\n total = ti + to + cr + cw\n if (tr == 0) exit\n printf \"Requests: %d\\n\", tr\n printf \"Input tokens: %d\\n\", ti\n printf \"Output tokens: %d\\n\", to\n printf \"Cache read tokens: %d\\n\", cr\n printf \"Cache write tokens: %d\\n\", cw\n printf \"Total tokens: %d\\n\", total\n if (ti + cr > 0) printf \"Cache hit rate: %.1f%%\\n\", (cr / (ti + cr)) * 100\n if (ti + cw > 0) printf \"Cache write rate: %.1f%%\\n\", (cw / (ti + cw)) * 100\n if (cw > 0) printf \"Cache read/write ratio: %.2f\\n\", (cr / cw)\n }' /tmp/token-optimizer-claude/token-usage.jsonl > /tmp/token-optimizer-claude/cache-metrics.txt\n cat /tmp/token-optimizer-claude/cache-metrics.txt\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer-claude/token-usage.jsonl\n touch /tmp/token-optimizer-claude/cache-metrics.txt\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer-claude/workflow-source.md\nelse\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer-claude/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source\nif [ -f /tmp/token-optimizer-claude/workflow-source.md ]; then\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer-claude/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer-claude/declared-tools.txt || true\nfi\n" - name: Configure Git credentials env: @@ -378,12 +378,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_0fb88f09872c1369_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_3e75008c6ba33aa9_EOF' {"create_issue":{"close_older_issues":true,"expires":168,"labels":["automated-analysis","token-optimization","claude","cost-reduction"],"max":1,"title_prefix":"⚡ Claude Token Optimization: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_0fb88f09872c1369_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_3e75008c6ba33aa9_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_971214b094014a4d_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_38b3fd6c6344de36_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"⚡ Claude Token Optimization: \". Labels [\"automated-analysis\" \"token-optimization\" \"claude\" \"cost-reduction\"] will be automatically added." @@ -391,8 +391,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_971214b094014a4d_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_ad5d398c6bc28877_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_38b3fd6c6344de36_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_9ad1a16787d3f182_EOF' { "create_issue": { "defaultMax": 1, @@ -485,7 +485,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_ad5d398c6bc28877_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_9ad1a16787d3f182_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -555,7 +555,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_c6bfa07f5408b430_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_725b2de35e77c40e_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -596,7 +596,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_c6bfa07f5408b430_EOF + GH_AW_MCP_CONFIG_725b2de35e77c40e_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/copilot-token-optimizer.lock.yml b/.github/workflows/copilot-token-optimizer.lock.yml index 9e585f38b2..61bb581ce1 100644 --- a/.github/workflows/copilot-token-optimizer.lock.yml +++ b/.github/workflows/copilot-token-optimizer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"fd23e1427b2313e8891e828fe49ebfd23bdc4abc966f587a004d381370a68f13","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"4a77b0829a21910b7fa4fb4e195a1c5381fd9f6529ee7c616e10c45271ca5a6d","strict":true,"agent_id":"copilot"} name: "Copilot Token Optimizer" "on": @@ -144,14 +144,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' + cat << 'GH_AW_PROMPT_ab867cbc4c45e654_EOF' - GH_AW_PROMPT_68c5831fe1087681_EOF + GH_AW_PROMPT_ab867cbc4c45e654_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' + cat << 'GH_AW_PROMPT_ab867cbc4c45e654_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -183,13 +183,13 @@ jobs: {{/if}} - GH_AW_PROMPT_68c5831fe1087681_EOF + GH_AW_PROMPT_ab867cbc4c45e654_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' + cat << 'GH_AW_PROMPT_ab867cbc4c45e654_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/copilot-token-optimizer.md}} - GH_AW_PROMPT_68c5831fe1087681_EOF + GH_AW_PROMPT_ab867cbc4c45e654_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -327,7 +327,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Find and download artifacts from the most expensive Copilot workflow - run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer\n\necho \"đŸ“Ĩ Loading Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer/copilot-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-optimizer/copilot-runs-raw.json > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer/copilot-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Copilot runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Copilot runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer/copilot-runs.json > /tmp/token-optimizer/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run of that workflow\nARTIFACT_DIR=\"/tmp/token-optimizer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts (contains prompt and tool usage logs)\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer/token-usage.jsonl\n wc -l < /tmp/token-optimizer/token-usage.jsonl\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer/token-usage.jsonl\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer/workflow-source.md\nelse\n echo \"Workflow source not found at $WORKFLOW_MD, searching...\"\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source (if available)\nif [ -f /tmp/token-optimizer/workflow-source.md ]; then\n echo \"📋 Extracting declared tools from workflow source...\"\n # Extract tools section from frontmatter\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer/declared-tools.txt || true\n cat /tmp/token-optimizer/declared-tools.txt\nfi\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer\n\necho \"đŸ“Ĩ Loading Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer/copilot-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-optimizer/copilot-runs-raw.json > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer/copilot-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Copilot runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Copilot runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n sort_by(.workflow_name) |\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer/copilot-runs.json > /tmp/token-optimizer/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run of that workflow\nARTIFACT_DIR=\"/tmp/token-optimizer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts (contains prompt and tool usage logs)\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer/token-usage.jsonl\n wc -l < /tmp/token-optimizer/token-usage.jsonl\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer/token-usage.jsonl\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer/workflow-source.md\nelse\n echo \"Workflow source not found at $WORKFLOW_MD, searching...\"\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source (if available)\nif [ -f /tmp/token-optimizer/workflow-source.md ]; then\n echo \"📋 Extracting declared tools from workflow source...\"\n # Extract tools section from frontmatter\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer/declared-tools.txt || true\n cat /tmp/token-optimizer/declared-tools.txt\nfi\n" - name: Configure Git credentials env: @@ -378,12 +378,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_178afd5b56c5bba7_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_8004a01d2ab0d07a_EOF' {"create_issue":{"close_older_issues":true,"expires":168,"labels":["automated-analysis","token-optimization","copilot","cost-reduction"],"max":1,"title_prefix":"⚡ Copilot Token Optimization: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_178afd5b56c5bba7_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_8004a01d2ab0d07a_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_cec4f6a3637a6d3b_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_c400a077d5e74753_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"⚡ Copilot Token Optimization: \". Labels [\"automated-analysis\" \"token-optimization\" \"copilot\" \"cost-reduction\"] will be automatically added." @@ -391,8 +391,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_cec4f6a3637a6d3b_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_2089a1213782993a_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_c400a077d5e74753_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_94580559ea46ee78_EOF' { "create_issue": { "defaultMax": 1, @@ -485,7 +485,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_2089a1213782993a_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_94580559ea46ee78_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -555,7 +555,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_27cc3fbbc713df4f_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_d40d7a82d24074ef_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -596,7 +596,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_27cc3fbbc713df4f_EOF + GH_AW_MCP_CONFIG_d40d7a82d24074ef_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: From 55b258130cd4de2a1b92ed13a8f4162d8decd49c Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Fri, 3 Apr 2026 23:12:06 +0000 Subject: [PATCH 5/5] feat: extract shared token-logs-fetch workflow and cache logs to avoid rate-limiting Agent-Logs-Url: https://github.com/github/gh-aw/sessions/37b38e9c-5938-4c6f-a082-9bc64b2a8b7b Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --- .../workflows/claude-token-optimizer.lock.yml | 32 +- .github/workflows/claude-token-optimizer.md | 49 +- .../claude-token-usage-analyzer.lock.yml | 32 +- .../workflows/claude-token-usage-analyzer.md | 49 +- .../copilot-token-optimizer.lock.yml | 32 +- .github/workflows/copilot-token-optimizer.md | 49 +- .../copilot-token-usage-analyzer.lock.yml | 32 +- .../workflows/copilot-token-usage-analyzer.md | 49 +- .github/workflows/token-logs-fetch.lock.yml | 1183 +++++++++++++++++ .github/workflows/token-logs-fetch.md | 91 ++ 10 files changed, 1494 insertions(+), 104 deletions(-) create mode 100644 .github/workflows/token-logs-fetch.lock.yml create mode 100644 .github/workflows/token-logs-fetch.md diff --git a/.github/workflows/claude-token-optimizer.lock.yml b/.github/workflows/claude-token-optimizer.lock.yml index f04877ee44..ca020064c8 100644 --- a/.github/workflows/claude-token-optimizer.lock.yml +++ b/.github/workflows/claude-token-optimizer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"d28ca01966ea04e0f3dbad739cdce71c88eef80ccc8091c3cbff3401dac2e05c","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"dbff5ee16cfc21a95e26ce60664927bc565c0ad0b4ea980493be8dfb278f7302","strict":true,"agent_id":"copilot"} name: "Claude Token Optimizer" "on": @@ -144,14 +144,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' + cat << 'GH_AW_PROMPT_39ebff004f890f10_EOF' - GH_AW_PROMPT_b4eb75949c6211e2_EOF + GH_AW_PROMPT_39ebff004f890f10_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' + cat << 'GH_AW_PROMPT_39ebff004f890f10_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -183,13 +183,13 @@ jobs: {{/if}} - GH_AW_PROMPT_b4eb75949c6211e2_EOF + GH_AW_PROMPT_39ebff004f890f10_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_b4eb75949c6211e2_EOF' + cat << 'GH_AW_PROMPT_39ebff004f890f10_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/claude-token-optimizer.md}} - GH_AW_PROMPT_b4eb75949c6211e2_EOF + GH_AW_PROMPT_39ebff004f890f10_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -327,7 +327,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Find and download artifacts from the most expensive Claude workflow - run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer-claude\n\necho \"đŸ“Ĩ Loading Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer-claude/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer-claude/claude-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-optimizer-claude/claude-runs-raw.json > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer-claude/claude-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Claude runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Claude runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer-claude/claude-runs.json > /tmp/token-optimizer-claude/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer-claude/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer-claude/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run\nARTIFACT_DIR=\"/tmp/token-optimizer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer-claude/token-usage.jsonl\n echo \"Records: $(wc -l < /tmp/token-optimizer-claude/token-usage.jsonl)\"\n\n # Pre-compute Anthropic-specific metrics\n echo \"📊 Computing Anthropic cache efficiency metrics...\"\n awk '\n BEGIN { ti=0; to=0; cr=0; cw=0; tr=0 }\n {\n if (match($0, /\"input_tokens\" *: *([0-9]+)/, m)) ti += m[1]+0\n if (match($0, /\"output_tokens\" *: *([0-9]+)/, m)) to += m[1]+0\n if (match($0, /\"cache_read_tokens\" *: *([0-9]+)/, m)) cr += m[1]+0\n if (match($0, /\"cache_write_tokens\" *: *([0-9]+)/, m)) cw += m[1]+0\n tr += 1\n }\n END {\n total = ti + to + cr + cw\n if (tr == 0) exit\n printf \"Requests: %d\\n\", tr\n printf \"Input tokens: %d\\n\", ti\n printf \"Output tokens: %d\\n\", to\n printf \"Cache read tokens: %d\\n\", cr\n printf \"Cache write tokens: %d\\n\", cw\n printf \"Total tokens: %d\\n\", total\n if (ti + cr > 0) printf \"Cache hit rate: %.1f%%\\n\", (cr / (ti + cr)) * 100\n if (ti + cw > 0) printf \"Cache write rate: %.1f%%\\n\", (cw / (ti + cw)) * 100\n if (cw > 0) printf \"Cache read/write ratio: %.2f\\n\", (cr / cw)\n }' /tmp/token-optimizer-claude/token-usage.jsonl > /tmp/token-optimizer-claude/cache-metrics.txt\n cat /tmp/token-optimizer-claude/cache-metrics.txt\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer-claude/token-usage.jsonl\n touch /tmp/token-optimizer-claude/cache-metrics.txt\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer-claude/workflow-source.md\nelse\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer-claude/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source\nif [ -f /tmp/token-optimizer-claude/workflow-source.md ]; then\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer-claude/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer-claude/declared-tools.txt || true\nfi\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer-claude\n\n# Try to use pre-fetched logs from the Token Logs Fetch workflow to avoid redundant API calls\nTODAY=$(date -u +%Y-%m-%d)\nFETCH_RUN_ID=$(gh run list \\\n --workflow \"token-logs-fetch.lock.yml\" \\\n --status success \\\n --limit 1 \\\n --json databaseId \\\n --jq '.[0].databaseId' 2>/dev/null || echo \"\")\nUSED_CACHE=false\nif [ -n \"$FETCH_RUN_ID\" ]; then\n CACHE_TMP=\"/tmp/token-logs-cache-claude-optimizer\"\n mkdir -p \"$CACHE_TMP\"\n gh run download \"$FETCH_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"cache-memory\" \\\n --dir \"$CACHE_TMP\" \\\n 2>/dev/null || true\n CACHE_DATE=$(cat \"$CACHE_TMP/token-logs/fetch-date.txt\" 2>/dev/null || echo \"\")\n if [ \"$CACHE_DATE\" = \"$TODAY\" ] && [ -s \"$CACHE_TMP/token-logs/claude-runs.json\" ]; then\n echo \"✅ Using pre-fetched logs from Token Logs Fetch run $FETCH_RUN_ID (date: $CACHE_DATE)\"\n cp \"$CACHE_TMP/token-logs/claude-runs.json\" /tmp/token-optimizer-claude/claude-runs.json\n USED_CACHE=true\n else\n echo \"ℹī¸ No valid cached logs found (cache date: ${CACHE_DATE:-none}, today: $TODAY)\"\n fi\nfi\n\nif [ \"$USED_CACHE\" != \"true\" ]; then\n echo \"đŸ“Ĩ Loading Claude workflow runs from last 24 hours...\"\n gh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer-claude/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer-claude/claude-runs-raw.json\n\n # Extract runs array from the JSON output\n jq '.runs // []' /tmp/token-optimizer-claude/claude-runs-raw.json > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer-claude/claude-runs.json\nfi\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Claude runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Claude runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n sort_by(.workflow_name) |\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer-claude/claude-runs.json > /tmp/token-optimizer-claude/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer-claude/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer-claude/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run\nARTIFACT_DIR=\"/tmp/token-optimizer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer-claude/token-usage.jsonl\n echo \"Records: $(wc -l < /tmp/token-optimizer-claude/token-usage.jsonl)\"\n\n # Pre-compute Anthropic-specific metrics\n echo \"📊 Computing Anthropic cache efficiency metrics...\"\n awk '\n BEGIN { ti=0; to=0; cr=0; cw=0; tr=0 }\n {\n if (match($0, /\"input_tokens\" *: *([0-9]+)/, m)) ti += m[1]+0\n if (match($0, /\"output_tokens\" *: *([0-9]+)/, m)) to += m[1]+0\n if (match($0, /\"cache_read_tokens\" *: *([0-9]+)/, m)) cr += m[1]+0\n if (match($0, /\"cache_write_tokens\" *: *([0-9]+)/, m)) cw += m[1]+0\n tr += 1\n }\n END {\n total = ti + to + cr + cw\n if (tr == 0) exit\n printf \"Requests: %d\\n\", tr\n printf \"Input tokens: %d\\n\", ti\n printf \"Output tokens: %d\\n\", to\n printf \"Cache read tokens: %d\\n\", cr\n printf \"Cache write tokens: %d\\n\", cw\n printf \"Total tokens: %d\\n\", total\n if (ti + cr > 0) printf \"Cache hit rate: %.1f%%\\n\", (cr / (ti + cr)) * 100\n if (ti + cw > 0) printf \"Cache write rate: %.1f%%\\n\", (cw / (ti + cw)) * 100\n if (cw > 0) printf \"Cache read/write ratio: %.2f\\n\", (cr / cw)\n }' /tmp/token-optimizer-claude/token-usage.jsonl > /tmp/token-optimizer-claude/cache-metrics.txt\n cat /tmp/token-optimizer-claude/cache-metrics.txt\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer-claude/token-usage.jsonl\n touch /tmp/token-optimizer-claude/cache-metrics.txt\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer-claude/workflow-source.md\nelse\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer-claude/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source\nif [ -f /tmp/token-optimizer-claude/workflow-source.md ]; then\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer-claude/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer-claude/declared-tools.txt || true\nfi\n" - name: Configure Git credentials env: @@ -378,12 +378,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_0fb88f09872c1369_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_12e7e3b2b944d6ca_EOF' {"create_issue":{"close_older_issues":true,"expires":168,"labels":["automated-analysis","token-optimization","claude","cost-reduction"],"max":1,"title_prefix":"⚡ Claude Token Optimization: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_0fb88f09872c1369_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_12e7e3b2b944d6ca_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_971214b094014a4d_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_163d89fa6c431e34_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"⚡ Claude Token Optimization: \". Labels [\"automated-analysis\" \"token-optimization\" \"claude\" \"cost-reduction\"] will be automatically added." @@ -391,8 +391,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_971214b094014a4d_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_ad5d398c6bc28877_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_163d89fa6c431e34_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_1f62702e2eb2fc94_EOF' { "create_issue": { "defaultMax": 1, @@ -485,7 +485,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_ad5d398c6bc28877_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_1f62702e2eb2fc94_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -555,7 +555,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_c6bfa07f5408b430_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_38aabebdf2375b48_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -596,7 +596,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_c6bfa07f5408b430_EOF + GH_AW_MCP_CONFIG_38aabebdf2375b48_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/claude-token-optimizer.md b/.github/workflows/claude-token-optimizer.md index 97c9f3fba5..84c90247fc 100644 --- a/.github/workflows/claude-token-optimizer.md +++ b/.github/workflows/claude-token-optimizer.md @@ -61,16 +61,45 @@ steps: set -euo pipefail mkdir -p /tmp/token-optimizer-claude - echo "đŸ“Ĩ Loading Claude workflow runs from last 24 hours..." - gh aw logs \ - --engine claude \ - --start-date -1d \ - --json \ - -c 300 \ - > /tmp/token-optimizer-claude/claude-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-optimizer-claude/claude-runs-raw.json - - # Extract runs array from the JSON output - jq '.runs // []' /tmp/token-optimizer-claude/claude-runs-raw.json > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-optimizer-claude/claude-runs.json + # Try to use pre-fetched logs from the Token Logs Fetch workflow to avoid redundant API calls + TODAY=$(date -u +%Y-%m-%d) + FETCH_RUN_ID=$(gh run list \ + --workflow "token-logs-fetch.lock.yml" \ + --status success \ + --limit 1 \ + --json databaseId \ + --jq '.[0].databaseId' 2>/dev/null || echo "") + USED_CACHE=false + if [ -n "$FETCH_RUN_ID" ]; then + CACHE_TMP="/tmp/token-logs-cache-claude-optimizer" + mkdir -p "$CACHE_TMP" + gh run download "$FETCH_RUN_ID" \ + --repo "$GITHUB_REPOSITORY" \ + --name "cache-memory" \ + --dir "$CACHE_TMP" \ + 2>/dev/null || true + CACHE_DATE=$(cat "$CACHE_TMP/token-logs/fetch-date.txt" 2>/dev/null || echo "") + if [ "$CACHE_DATE" = "$TODAY" ] && [ -s "$CACHE_TMP/token-logs/claude-runs.json" ]; then + echo "✅ Using pre-fetched logs from Token Logs Fetch run $FETCH_RUN_ID (date: $CACHE_DATE)" + cp "$CACHE_TMP/token-logs/claude-runs.json" /tmp/token-optimizer-claude/claude-runs.json + USED_CACHE=true + else + echo "ℹī¸ No valid cached logs found (cache date: ${CACHE_DATE:-none}, today: $TODAY)" + fi + fi + + if [ "$USED_CACHE" != "true" ]; then + echo "đŸ“Ĩ Loading Claude workflow runs from last 24 hours..." + gh aw logs \ + --engine claude \ + --start-date -1d \ + --json \ + -c 300 \ + > /tmp/token-optimizer-claude/claude-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-optimizer-claude/claude-runs-raw.json + + # Extract runs array from the JSON output + jq '.runs // []' /tmp/token-optimizer-claude/claude-runs-raw.json > /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-optimizer-claude/claude-runs.json + fi RUN_COUNT=$(jq 'length' /tmp/token-optimizer-claude/claude-runs.json 2>/dev/null || echo 0) echo "Found ${RUN_COUNT} Claude runs" diff --git a/.github/workflows/claude-token-usage-analyzer.lock.yml b/.github/workflows/claude-token-usage-analyzer.lock.yml index f4363eb968..e0696d559e 100644 --- a/.github/workflows/claude-token-usage-analyzer.lock.yml +++ b/.github/workflows/claude-token-usage-analyzer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"6d66eade0456e72f7633fe59372e82e86d56afc2d374492975124f67ea898cf1","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"8e6be7e2956872fe478a9ab8396eb583429c408d43b0bd1956735df464e90baf","strict":true,"agent_id":"copilot"} name: "Claude Token Usage Analyzer" "on": @@ -132,14 +132,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_e1a5813608bb58e3_EOF' + cat << 'GH_AW_PROMPT_17d5d1cbaeff7d93_EOF' - GH_AW_PROMPT_e1a5813608bb58e3_EOF + GH_AW_PROMPT_17d5d1cbaeff7d93_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_e1a5813608bb58e3_EOF' + cat << 'GH_AW_PROMPT_17d5d1cbaeff7d93_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -171,13 +171,13 @@ jobs: {{/if}} - GH_AW_PROMPT_e1a5813608bb58e3_EOF + GH_AW_PROMPT_17d5d1cbaeff7d93_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_e1a5813608bb58e3_EOF' + cat << 'GH_AW_PROMPT_17d5d1cbaeff7d93_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/claude-token-usage-analyzer.md}} - GH_AW_PROMPT_e1a5813608bb58e3_EOF + GH_AW_PROMPT_17d5d1cbaeff7d93_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -310,7 +310,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Download Claude workflow runs (last 24h) - run: "set -euo pipefail\nmkdir -p /tmp/token-analyzer-claude\n\necho \"đŸ“Ĩ Downloading Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-analyzer-claude/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-analyzer-claude/claude-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-analyzer-claude/claude-runs-raw.json > /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-analyzer-claude/claude-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"✅ Found ${RUN_COUNT} Claude workflow runs\"\n\n# Download token-usage.jsonl artifacts for per-model breakdown\nARTIFACT_DIR=\"/tmp/token-analyzer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading token-usage.jsonl artifacts...\"\njq -r '.[0:50][]?.database_id' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null > /tmp/token-analyzer-claude/run-ids.txt || true\nwhile read -r run_id; do\n run_dir=\"$ARTIFACT_DIR/$run_id\"\n mkdir -p \"$run_dir\"\n gh run download \"$run_id\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$run_dir\" \\\n 2>/dev/null || true\ndone < /tmp/token-analyzer-claude/run-ids.txt\n\n# Count how many token-usage.jsonl files we got\nJSONL_COUNT=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | wc -l)\necho \"✅ Downloaded ${JSONL_COUNT} token-usage.jsonl artifacts\"\n\n# Merge all token-usage.jsonl files annotated with run_id\nMERGED_FILE=\"/tmp/token-analyzer-claude/token-usage-merged.jsonl\"\n> \"$MERGED_FILE\"\nfind \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" > /tmp/token-analyzer-claude/jsonl-files.txt 2>/dev/null || true\nwhile read -r f; do\n run_id=$(echo \"$f\" | grep -oP '(?<=/artifacts/)\\d+(?=/)' || true)\n while IFS= read -r line; do\n if [ -n \"$line\" ]; then\n echo \"${line}\" | jq --arg run_id \"$run_id\" '. + {run_id: $run_id}' >> \"$MERGED_FILE\" 2>/dev/null || true\n fi\n done < \"$f\"\ndone < /tmp/token-analyzer-claude/jsonl-files.txt\n\nRECORD_COUNT=$(wc -l < \"$MERGED_FILE\" 2>/dev/null || echo 0)\necho \"✅ Merged ${RECORD_COUNT} token usage records\"\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-analyzer-claude\n\n# Try to use pre-fetched logs from the Token Logs Fetch workflow to avoid redundant API calls\nTODAY=$(date -u +%Y-%m-%d)\nFETCH_RUN_ID=$(gh run list \\\n --workflow \"token-logs-fetch.lock.yml\" \\\n --status success \\\n --limit 1 \\\n --json databaseId \\\n --jq '.[0].databaseId' 2>/dev/null || echo \"\")\nUSED_CACHE=false\nif [ -n \"$FETCH_RUN_ID\" ]; then\n CACHE_TMP=\"/tmp/token-logs-cache-claude-analyzer\"\n mkdir -p \"$CACHE_TMP\"\n gh run download \"$FETCH_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"cache-memory\" \\\n --dir \"$CACHE_TMP\" \\\n 2>/dev/null || true\n CACHE_DATE=$(cat \"$CACHE_TMP/token-logs/fetch-date.txt\" 2>/dev/null || echo \"\")\n if [ \"$CACHE_DATE\" = \"$TODAY\" ] && [ -s \"$CACHE_TMP/token-logs/claude-runs.json\" ]; then\n echo \"✅ Using pre-fetched logs from Token Logs Fetch run $FETCH_RUN_ID (date: $CACHE_DATE)\"\n cp \"$CACHE_TMP/token-logs/claude-runs.json\" /tmp/token-analyzer-claude/claude-runs.json\n USED_CACHE=true\n else\n echo \"ℹī¸ No valid cached logs found (cache date: ${CACHE_DATE:-none}, today: $TODAY)\"\n fi\nfi\n\nif [ \"$USED_CACHE\" != \"true\" ]; then\n echo \"đŸ“Ĩ Downloading Claude workflow runs from last 24 hours...\"\n gh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-analyzer-claude/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-analyzer-claude/claude-runs-raw.json\n\n # Extract runs array from the JSON output\n jq '.runs // []' /tmp/token-analyzer-claude/claude-runs-raw.json > /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-analyzer-claude/claude-runs.json\nfi\n\nRUN_COUNT=$(jq 'length' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo 0)\necho \"✅ Found ${RUN_COUNT} Claude workflow runs\"\n\n# Download token-usage.jsonl artifacts for per-model breakdown\nARTIFACT_DIR=\"/tmp/token-analyzer-claude/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading token-usage.jsonl artifacts...\"\njq -r '.[0:50][]?.database_id' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null > /tmp/token-analyzer-claude/run-ids.txt || true\nwhile read -r run_id; do\n run_dir=\"$ARTIFACT_DIR/$run_id\"\n mkdir -p \"$run_dir\"\n gh run download \"$run_id\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$run_dir\" \\\n 2>/dev/null || true\ndone < /tmp/token-analyzer-claude/run-ids.txt\n\n# Count how many token-usage.jsonl files we got\nJSONL_COUNT=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | wc -l)\necho \"✅ Downloaded ${JSONL_COUNT} token-usage.jsonl artifacts\"\n\n# Merge all token-usage.jsonl files annotated with run_id\nMERGED_FILE=\"/tmp/token-analyzer-claude/token-usage-merged.jsonl\"\n> \"$MERGED_FILE\"\nfind \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" > /tmp/token-analyzer-claude/jsonl-files.txt 2>/dev/null || true\nwhile read -r f; do\n run_id=$(echo \"$f\" | grep -oP '(?<=/artifacts/)\\d+(?=/)' || true)\n while IFS= read -r line; do\n if [ -n \"$line\" ]; then\n echo \"${line}\" | jq --arg run_id \"$run_id\" '. + {run_id: $run_id}' >> \"$MERGED_FILE\" 2>/dev/null || true\n fi\n done < \"$f\"\ndone < /tmp/token-analyzer-claude/jsonl-files.txt\n\nRECORD_COUNT=$(wc -l < \"$MERGED_FILE\" 2>/dev/null || echo 0)\necho \"✅ Merged ${RECORD_COUNT} token usage records\"\n" - name: Configure Git credentials env: @@ -361,12 +361,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_a4ba8bab8dcca375_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_e591f4f8252fc42c_EOF' {"create_issue":{"close_older_issues":true,"expires":48,"labels":["automated-analysis","token-usage","claude"],"max":1,"title_prefix":"📊 Claude Token Usage Report: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_a4ba8bab8dcca375_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_e591f4f8252fc42c_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_e2f42f9d919138fa_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_ec4b56ef535d93ce_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"📊 Claude Token Usage Report: \". Labels [\"automated-analysis\" \"token-usage\" \"claude\"] will be automatically added." @@ -374,8 +374,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_e2f42f9d919138fa_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_89ae148174e0a909_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_ec4b56ef535d93ce_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_3f99af1cbefc5c06_EOF' { "create_issue": { "defaultMax": 1, @@ -468,7 +468,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_89ae148174e0a909_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_3f99af1cbefc5c06_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -538,7 +538,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_d12389cf810a9482_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_959b0238f0b52450_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -579,7 +579,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_d12389cf810a9482_EOF + GH_AW_MCP_CONFIG_959b0238f0b52450_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/claude-token-usage-analyzer.md b/.github/workflows/claude-token-usage-analyzer.md index 491a9e2cd6..497784da70 100644 --- a/.github/workflows/claude-token-usage-analyzer.md +++ b/.github/workflows/claude-token-usage-analyzer.md @@ -53,16 +53,45 @@ steps: set -euo pipefail mkdir -p /tmp/token-analyzer-claude - echo "đŸ“Ĩ Downloading Claude workflow runs from last 24 hours..." - gh aw logs \ - --engine claude \ - --start-date -1d \ - --json \ - -c 300 \ - > /tmp/token-analyzer-claude/claude-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-analyzer-claude/claude-runs-raw.json - - # Extract runs array from the JSON output - jq '.runs // []' /tmp/token-analyzer-claude/claude-runs-raw.json > /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-analyzer-claude/claude-runs.json + # Try to use pre-fetched logs from the Token Logs Fetch workflow to avoid redundant API calls + TODAY=$(date -u +%Y-%m-%d) + FETCH_RUN_ID=$(gh run list \ + --workflow "token-logs-fetch.lock.yml" \ + --status success \ + --limit 1 \ + --json databaseId \ + --jq '.[0].databaseId' 2>/dev/null || echo "") + USED_CACHE=false + if [ -n "$FETCH_RUN_ID" ]; then + CACHE_TMP="/tmp/token-logs-cache-claude-analyzer" + mkdir -p "$CACHE_TMP" + gh run download "$FETCH_RUN_ID" \ + --repo "$GITHUB_REPOSITORY" \ + --name "cache-memory" \ + --dir "$CACHE_TMP" \ + 2>/dev/null || true + CACHE_DATE=$(cat "$CACHE_TMP/token-logs/fetch-date.txt" 2>/dev/null || echo "") + if [ "$CACHE_DATE" = "$TODAY" ] && [ -s "$CACHE_TMP/token-logs/claude-runs.json" ]; then + echo "✅ Using pre-fetched logs from Token Logs Fetch run $FETCH_RUN_ID (date: $CACHE_DATE)" + cp "$CACHE_TMP/token-logs/claude-runs.json" /tmp/token-analyzer-claude/claude-runs.json + USED_CACHE=true + else + echo "ℹī¸ No valid cached logs found (cache date: ${CACHE_DATE:-none}, today: $TODAY)" + fi + fi + + if [ "$USED_CACHE" != "true" ]; then + echo "đŸ“Ĩ Downloading Claude workflow runs from last 24 hours..." + gh aw logs \ + --engine claude \ + --start-date -1d \ + --json \ + -c 300 \ + > /tmp/token-analyzer-claude/claude-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-analyzer-claude/claude-runs-raw.json + + # Extract runs array from the JSON output + jq '.runs // []' /tmp/token-analyzer-claude/claude-runs-raw.json > /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-analyzer-claude/claude-runs.json + fi RUN_COUNT=$(jq 'length' /tmp/token-analyzer-claude/claude-runs.json 2>/dev/null || echo 0) echo "✅ Found ${RUN_COUNT} Claude workflow runs" diff --git a/.github/workflows/copilot-token-optimizer.lock.yml b/.github/workflows/copilot-token-optimizer.lock.yml index 9e585f38b2..123e94b8c8 100644 --- a/.github/workflows/copilot-token-optimizer.lock.yml +++ b/.github/workflows/copilot-token-optimizer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"fd23e1427b2313e8891e828fe49ebfd23bdc4abc966f587a004d381370a68f13","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"6eadad6bbe15632de5d8067a8b7daa0eb6baeb44a942e2e0d55ec41d846d5b63","strict":true,"agent_id":"copilot"} name: "Copilot Token Optimizer" "on": @@ -144,14 +144,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' + cat << 'GH_AW_PROMPT_5ce9c5eb83669cda_EOF' - GH_AW_PROMPT_68c5831fe1087681_EOF + GH_AW_PROMPT_5ce9c5eb83669cda_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' + cat << 'GH_AW_PROMPT_5ce9c5eb83669cda_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -183,13 +183,13 @@ jobs: {{/if}} - GH_AW_PROMPT_68c5831fe1087681_EOF + GH_AW_PROMPT_5ce9c5eb83669cda_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_68c5831fe1087681_EOF' + cat << 'GH_AW_PROMPT_5ce9c5eb83669cda_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/copilot-token-optimizer.md}} - GH_AW_PROMPT_68c5831fe1087681_EOF + GH_AW_PROMPT_5ce9c5eb83669cda_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -327,7 +327,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Find and download artifacts from the most expensive Copilot workflow - run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer\n\necho \"đŸ“Ĩ Loading Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer/copilot-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-optimizer/copilot-runs-raw.json > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer/copilot-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Copilot runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Copilot runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer/copilot-runs.json > /tmp/token-optimizer/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run of that workflow\nARTIFACT_DIR=\"/tmp/token-optimizer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts (contains prompt and tool usage logs)\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer/token-usage.jsonl\n wc -l < /tmp/token-optimizer/token-usage.jsonl\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer/token-usage.jsonl\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer/workflow-source.md\nelse\n echo \"Workflow source not found at $WORKFLOW_MD, searching...\"\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source (if available)\nif [ -f /tmp/token-optimizer/workflow-source.md ]; then\n echo \"📋 Extracting declared tools from workflow source...\"\n # Extract tools section from frontmatter\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer/declared-tools.txt || true\n cat /tmp/token-optimizer/declared-tools.txt\nfi\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-optimizer\n\n# Try to use pre-fetched logs from the Token Logs Fetch workflow to avoid redundant API calls\nTODAY=$(date -u +%Y-%m-%d)\nFETCH_RUN_ID=$(gh run list \\\n --workflow \"token-logs-fetch.lock.yml\" \\\n --status success \\\n --limit 1 \\\n --json databaseId \\\n --jq '.[0].databaseId' 2>/dev/null || echo \"\")\nUSED_CACHE=false\nif [ -n \"$FETCH_RUN_ID\" ]; then\n CACHE_TMP=\"/tmp/token-logs-cache-optimizer\"\n mkdir -p \"$CACHE_TMP\"\n gh run download \"$FETCH_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"cache-memory\" \\\n --dir \"$CACHE_TMP\" \\\n 2>/dev/null || true\n CACHE_DATE=$(cat \"$CACHE_TMP/token-logs/fetch-date.txt\" 2>/dev/null || echo \"\")\n if [ \"$CACHE_DATE\" = \"$TODAY\" ] && [ -s \"$CACHE_TMP/token-logs/copilot-runs.json\" ]; then\n echo \"✅ Using pre-fetched logs from Token Logs Fetch run $FETCH_RUN_ID (date: $CACHE_DATE)\"\n cp \"$CACHE_TMP/token-logs/copilot-runs.json\" /tmp/token-optimizer/copilot-runs.json\n USED_CACHE=true\n else\n echo \"ℹī¸ No valid cached logs found (cache date: ${CACHE_DATE:-none}, today: $TODAY)\"\n fi\nfi\n\nif [ \"$USED_CACHE\" != \"true\" ]; then\n echo \"đŸ“Ĩ Loading Copilot workflow runs from last 24 hours...\"\n gh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-optimizer/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-optimizer/copilot-runs-raw.json\n\n # Extract runs array from the JSON output\n jq '.runs // []' /tmp/token-optimizer/copilot-runs-raw.json > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-optimizer/copilot-runs.json\nfi\n\nRUN_COUNT=$(jq 'length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0)\necho \"Found ${RUN_COUNT} Copilot runs\"\n\nif [ \"$RUN_COUNT\" -eq 0 ]; then\n echo \"No Copilot runs found, nothing to optimize\"\n exit 0\nfi\n\n# Find the most expensive workflow (by total tokens across all its runs)\necho \"🔍 Identifying most expensive workflow...\"\njq -r '\n sort_by(.workflow_name) |\n group_by(.workflow_name) |\n map({\n workflow: .[0].workflow_name,\n total_tokens: (map(.token_usage) | add),\n total_cost: 0,\n run_count: length,\n avg_tokens: ((map(.token_usage) | add) / length),\n run_ids: map(.database_id),\n latest_run_id: (sort_by(.created_at) | last | .database_id),\n latest_run_url: (sort_by(.created_at) | last | .url)\n }) |\n sort_by(.total_tokens) | reverse | .[0]\n' /tmp/token-optimizer/copilot-runs.json > /tmp/token-optimizer/top-workflow.json\n\nWORKFLOW_NAME=$(jq -r '.workflow' /tmp/token-optimizer/top-workflow.json)\nLATEST_RUN_ID=$(jq -r '.latest_run_id' /tmp/token-optimizer/top-workflow.json)\necho \"Most expensive workflow: $WORKFLOW_NAME (run: $LATEST_RUN_ID)\"\necho \"WORKFLOW_NAME=$WORKFLOW_NAME\" >> \"$GITHUB_ENV\"\n\n# Download the firewall-audit-logs artifact from the latest run of that workflow\nARTIFACT_DIR=\"/tmp/token-optimizer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading firewall-audit-logs from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$ARTIFACT_DIR\" \\\n 2>/dev/null || true\n\n# Also download agent artifacts (contains prompt and tool usage logs)\necho \"đŸ“Ĩ Downloading agent artifacts from run $LATEST_RUN_ID...\"\ngh run download \"$LATEST_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"agent\" \\\n --dir \"$ARTIFACT_DIR/agent\" \\\n 2>/dev/null || true\n\n# Find token-usage.jsonl\nUSAGE_FILE=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | head -1)\nif [ -n \"$USAGE_FILE\" ]; then\n echo \"Found token-usage.jsonl: $USAGE_FILE\"\n cp \"$USAGE_FILE\" /tmp/token-optimizer/token-usage.jsonl\n wc -l < /tmp/token-optimizer/token-usage.jsonl\nelse\n echo \"No token-usage.jsonl found in artifacts\"\n touch /tmp/token-optimizer/token-usage.jsonl\nfi\n\n# Find the workflow markdown source\nWORKFLOW_MD_NAME=$(echo \"$WORKFLOW_NAME\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\nWORKFLOW_MD=\".github/workflows/${WORKFLOW_MD_NAME}.md\"\nif [ -f \"$WORKFLOW_MD\" ]; then\n echo \"Found workflow source: $WORKFLOW_MD\"\n cp \"$WORKFLOW_MD\" /tmp/token-optimizer/workflow-source.md\nelse\n echo \"Workflow source not found at $WORKFLOW_MD, searching...\"\n FOUND_MD=$(find .github/workflows -name \"*.md\" -exec grep -l \"^name: $WORKFLOW_NAME\" {} \\; 2>/dev/null | head -1 || true)\n if [ -n \"$FOUND_MD\" ]; then\n echo \"Found: $FOUND_MD\"\n cp \"$FOUND_MD\" /tmp/token-optimizer/workflow-source.md\n fi\nfi\n\n# Extract declared tools from workflow source (if available)\nif [ -f /tmp/token-optimizer/workflow-source.md ]; then\n echo \"📋 Extracting declared tools from workflow source...\"\n # Extract tools section from frontmatter\n sed -n '/^---$/,/^---$/p' /tmp/token-optimizer/workflow-source.md | \\\n grep -A20 \"^tools:\" | head -30 > /tmp/token-optimizer/declared-tools.txt || true\n cat /tmp/token-optimizer/declared-tools.txt\nfi\n" - name: Configure Git credentials env: @@ -378,12 +378,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_178afd5b56c5bba7_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_948280de2275be42_EOF' {"create_issue":{"close_older_issues":true,"expires":168,"labels":["automated-analysis","token-optimization","copilot","cost-reduction"],"max":1,"title_prefix":"⚡ Copilot Token Optimization: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_178afd5b56c5bba7_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_948280de2275be42_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_cec4f6a3637a6d3b_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_743d8b22383899ed_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"⚡ Copilot Token Optimization: \". Labels [\"automated-analysis\" \"token-optimization\" \"copilot\" \"cost-reduction\"] will be automatically added." @@ -391,8 +391,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_cec4f6a3637a6d3b_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_2089a1213782993a_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_743d8b22383899ed_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_9d0d6fbaccddcacf_EOF' { "create_issue": { "defaultMax": 1, @@ -485,7 +485,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_2089a1213782993a_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_9d0d6fbaccddcacf_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -555,7 +555,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_27cc3fbbc713df4f_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_dd0e368aa164a954_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -596,7 +596,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_27cc3fbbc713df4f_EOF + GH_AW_MCP_CONFIG_dd0e368aa164a954_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/copilot-token-optimizer.md b/.github/workflows/copilot-token-optimizer.md index 457c7258f1..aca7e99311 100644 --- a/.github/workflows/copilot-token-optimizer.md +++ b/.github/workflows/copilot-token-optimizer.md @@ -61,16 +61,45 @@ steps: set -euo pipefail mkdir -p /tmp/token-optimizer - echo "đŸ“Ĩ Loading Copilot workflow runs from last 24 hours..." - gh aw logs \ - --engine copilot \ - --start-date -1d \ - --json \ - -c 300 \ - > /tmp/token-optimizer/copilot-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-optimizer/copilot-runs-raw.json - - # Extract runs array from the JSON output - jq '.runs // []' /tmp/token-optimizer/copilot-runs-raw.json > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-optimizer/copilot-runs.json + # Try to use pre-fetched logs from the Token Logs Fetch workflow to avoid redundant API calls + TODAY=$(date -u +%Y-%m-%d) + FETCH_RUN_ID=$(gh run list \ + --workflow "token-logs-fetch.lock.yml" \ + --status success \ + --limit 1 \ + --json databaseId \ + --jq '.[0].databaseId' 2>/dev/null || echo "") + USED_CACHE=false + if [ -n "$FETCH_RUN_ID" ]; then + CACHE_TMP="/tmp/token-logs-cache-optimizer" + mkdir -p "$CACHE_TMP" + gh run download "$FETCH_RUN_ID" \ + --repo "$GITHUB_REPOSITORY" \ + --name "cache-memory" \ + --dir "$CACHE_TMP" \ + 2>/dev/null || true + CACHE_DATE=$(cat "$CACHE_TMP/token-logs/fetch-date.txt" 2>/dev/null || echo "") + if [ "$CACHE_DATE" = "$TODAY" ] && [ -s "$CACHE_TMP/token-logs/copilot-runs.json" ]; then + echo "✅ Using pre-fetched logs from Token Logs Fetch run $FETCH_RUN_ID (date: $CACHE_DATE)" + cp "$CACHE_TMP/token-logs/copilot-runs.json" /tmp/token-optimizer/copilot-runs.json + USED_CACHE=true + else + echo "ℹī¸ No valid cached logs found (cache date: ${CACHE_DATE:-none}, today: $TODAY)" + fi + fi + + if [ "$USED_CACHE" != "true" ]; then + echo "đŸ“Ĩ Loading Copilot workflow runs from last 24 hours..." + gh aw logs \ + --engine copilot \ + --start-date -1d \ + --json \ + -c 300 \ + > /tmp/token-optimizer/copilot-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-optimizer/copilot-runs-raw.json + + # Extract runs array from the JSON output + jq '.runs // []' /tmp/token-optimizer/copilot-runs-raw.json > /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-optimizer/copilot-runs.json + fi RUN_COUNT=$(jq 'length' /tmp/token-optimizer/copilot-runs.json 2>/dev/null || echo 0) echo "Found ${RUN_COUNT} Copilot runs" diff --git a/.github/workflows/copilot-token-usage-analyzer.lock.yml b/.github/workflows/copilot-token-usage-analyzer.lock.yml index af26d0d589..5990ee4b03 100644 --- a/.github/workflows/copilot-token-usage-analyzer.lock.yml +++ b/.github/workflows/copilot-token-usage-analyzer.lock.yml @@ -26,7 +26,7 @@ # Imports: # - shared/reporting.md # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"b289a6f4ddae47c218302a21a6199546f19abebf8650b1963e2c8699302c4666","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"bb3e0ddc54c3b2b84499160d1c1db0297adfa5cf06b0b7b5a771e9d9da4857ff","strict":true,"agent_id":"copilot"} name: "Copilot Token Usage Analyzer" "on": @@ -132,14 +132,14 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_ac218341b6979b04_EOF' + cat << 'GH_AW_PROMPT_daf57289ac6aa438_EOF' - GH_AW_PROMPT_ac218341b6979b04_EOF + GH_AW_PROMPT_daf57289ac6aa438_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" - cat << 'GH_AW_PROMPT_ac218341b6979b04_EOF' + cat << 'GH_AW_PROMPT_daf57289ac6aa438_EOF' Tools: create_issue, missing_tool, missing_data, noop @@ -171,13 +171,13 @@ jobs: {{/if}} - GH_AW_PROMPT_ac218341b6979b04_EOF + GH_AW_PROMPT_daf57289ac6aa438_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_ac218341b6979b04_EOF' + cat << 'GH_AW_PROMPT_daf57289ac6aa438_EOF' {{#runtime-import .github/workflows/shared/reporting.md}} {{#runtime-import .github/workflows/copilot-token-usage-analyzer.md}} - GH_AW_PROMPT_ac218341b6979b04_EOF + GH_AW_PROMPT_daf57289ac6aa438_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -310,7 +310,7 @@ jobs: - env: GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} name: Download Copilot workflow runs (last 24h) - run: "set -euo pipefail\nmkdir -p /tmp/token-analyzer\n\necho \"đŸ“Ĩ Downloading Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-analyzer/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-analyzer/copilot-runs-raw.json\n\n# Extract runs array from the JSON output\njq '.runs // []' /tmp/token-analyzer/copilot-runs-raw.json > /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-analyzer/copilot-runs.json\n\nRUN_COUNT=$(jq 'length' /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo 0)\necho \"✅ Found ${RUN_COUNT} Copilot workflow runs\"\n\n# Download token-usage.jsonl artifacts for per-model breakdown\n# We look for the firewall-audit-logs artifact which contains token-usage.jsonl\nARTIFACT_DIR=\"/tmp/token-analyzer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading token-usage.jsonl artifacts...\"\njq -r '.[0:50][]?.database_id' /tmp/token-analyzer/copilot-runs.json 2>/dev/null > /tmp/token-analyzer/run-ids.txt || true\nwhile read -r run_id; do\n run_dir=\"$ARTIFACT_DIR/$run_id\"\n mkdir -p \"$run_dir\"\n gh run download \"$run_id\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$run_dir\" \\\n 2>/dev/null || true\ndone < /tmp/token-analyzer/run-ids.txt\n\n# Count how many token-usage.jsonl files we got\nJSONL_COUNT=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | wc -l)\necho \"✅ Downloaded ${JSONL_COUNT} token-usage.jsonl artifacts\"\n\n# Merge all token-usage.jsonl files into a single aggregate file annotated with run_id\nMERGED_FILE=\"/tmp/token-analyzer/token-usage-merged.jsonl\"\n> \"$MERGED_FILE\"\nfind \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" > /tmp/token-analyzer/jsonl-files.txt 2>/dev/null || true\nwhile read -r f; do\n run_id=$(echo \"$f\" | grep -oP '(?<=/artifacts/)\\d+(?=/)' || true)\n while IFS= read -r line; do\n if [ -n \"$line\" ]; then\n echo \"${line}\" | jq --arg run_id \"$run_id\" '. + {run_id: $run_id}' >> \"$MERGED_FILE\" 2>/dev/null || true\n fi\n done < \"$f\"\ndone < /tmp/token-analyzer/jsonl-files.txt\n\nRECORD_COUNT=$(wc -l < \"$MERGED_FILE\" 2>/dev/null || echo 0)\necho \"✅ Merged ${RECORD_COUNT} token usage records\"\n" + run: "set -euo pipefail\nmkdir -p /tmp/token-analyzer\n\n# Try to use pre-fetched logs from the Token Logs Fetch workflow to avoid redundant API calls\nTODAY=$(date -u +%Y-%m-%d)\nFETCH_RUN_ID=$(gh run list \\\n --workflow \"token-logs-fetch.lock.yml\" \\\n --status success \\\n --limit 1 \\\n --json databaseId \\\n --jq '.[0].databaseId' 2>/dev/null || echo \"\")\nUSED_CACHE=false\nif [ -n \"$FETCH_RUN_ID\" ]; then\n CACHE_TMP=\"/tmp/token-logs-cache-analyzer\"\n mkdir -p \"$CACHE_TMP\"\n gh run download \"$FETCH_RUN_ID\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"cache-memory\" \\\n --dir \"$CACHE_TMP\" \\\n 2>/dev/null || true\n CACHE_DATE=$(cat \"$CACHE_TMP/token-logs/fetch-date.txt\" 2>/dev/null || echo \"\")\n if [ \"$CACHE_DATE\" = \"$TODAY\" ] && [ -s \"$CACHE_TMP/token-logs/copilot-runs.json\" ]; then\n echo \"✅ Using pre-fetched logs from Token Logs Fetch run $FETCH_RUN_ID (date: $CACHE_DATE)\"\n cp \"$CACHE_TMP/token-logs/copilot-runs.json\" /tmp/token-analyzer/copilot-runs.json\n USED_CACHE=true\n else\n echo \"ℹī¸ No valid cached logs found (cache date: ${CACHE_DATE:-none}, today: $TODAY)\"\n fi\nfi\n\nif [ \"$USED_CACHE\" != \"true\" ]; then\n echo \"đŸ“Ĩ Downloading Copilot workflow runs from last 24 hours...\"\n gh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-analyzer/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-analyzer/copilot-runs-raw.json\n\n # Extract runs array from the JSON output\n jq '.runs // []' /tmp/token-analyzer/copilot-runs-raw.json > /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-analyzer/copilot-runs.json\nfi\n\nRUN_COUNT=$(jq 'length' /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo 0)\necho \"✅ Found ${RUN_COUNT} Copilot workflow runs\"\n\n# Download token-usage.jsonl artifacts for per-model breakdown\n# We look for the firewall-audit-logs artifact which contains token-usage.jsonl\nARTIFACT_DIR=\"/tmp/token-analyzer/artifacts\"\nmkdir -p \"$ARTIFACT_DIR\"\n\necho \"đŸ“Ĩ Downloading token-usage.jsonl artifacts...\"\njq -r '.[0:50][]?.database_id' /tmp/token-analyzer/copilot-runs.json 2>/dev/null > /tmp/token-analyzer/run-ids.txt || true\nwhile read -r run_id; do\n run_dir=\"$ARTIFACT_DIR/$run_id\"\n mkdir -p \"$run_dir\"\n gh run download \"$run_id\" \\\n --repo \"$GITHUB_REPOSITORY\" \\\n --name \"firewall-audit-logs\" \\\n --dir \"$run_dir\" \\\n 2>/dev/null || true\ndone < /tmp/token-analyzer/run-ids.txt\n\n# Count how many token-usage.jsonl files we got\nJSONL_COUNT=$(find \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" 2>/dev/null | wc -l)\necho \"✅ Downloaded ${JSONL_COUNT} token-usage.jsonl artifacts\"\n\n# Merge all token-usage.jsonl files into a single aggregate file annotated with run_id\nMERGED_FILE=\"/tmp/token-analyzer/token-usage-merged.jsonl\"\n> \"$MERGED_FILE\"\nfind \"$ARTIFACT_DIR\" -name \"token-usage.jsonl\" > /tmp/token-analyzer/jsonl-files.txt 2>/dev/null || true\nwhile read -r f; do\n run_id=$(echo \"$f\" | grep -oP '(?<=/artifacts/)\\d+(?=/)' || true)\n while IFS= read -r line; do\n if [ -n \"$line\" ]; then\n echo \"${line}\" | jq --arg run_id \"$run_id\" '. + {run_id: $run_id}' >> \"$MERGED_FILE\" 2>/dev/null || true\n fi\n done < \"$f\"\ndone < /tmp/token-analyzer/jsonl-files.txt\n\nRECORD_COUNT=$(wc -l < \"$MERGED_FILE\" 2>/dev/null || echo 0)\necho \"✅ Merged ${RECORD_COUNT} token usage records\"\n" - name: Configure Git credentials env: @@ -361,12 +361,12 @@ jobs: mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/safeoutputs mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_34f7182c6d0b277b_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_5e7995fc41d2308e_EOF' {"create_issue":{"close_older_issues":true,"expires":48,"labels":["automated-analysis","token-usage","copilot"],"max":1,"title_prefix":"📊 Copilot Token Usage Report: "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} - GH_AW_SAFE_OUTPUTS_CONFIG_34f7182c6d0b277b_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_5e7995fc41d2308e_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_840971bf025c07cc_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_01fe7c132b6ba579_EOF' { "description_suffixes": { "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"📊 Copilot Token Usage Report: \". Labels [\"automated-analysis\" \"token-usage\" \"copilot\"] will be automatically added." @@ -374,8 +374,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_840971bf025c07cc_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_b0e902b7f47a2fc6_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_01fe7c132b6ba579_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_73af6f249a088d12_EOF' { "create_issue": { "defaultMax": 1, @@ -468,7 +468,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_b0e902b7f47a2fc6_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_73af6f249a088d12_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -538,7 +538,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_b6b35d61ba8b5d52_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_fa6396237d6c74c6_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -579,7 +579,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_b6b35d61ba8b5d52_EOF + GH_AW_MCP_CONFIG_fa6396237d6c74c6_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/copilot-token-usage-analyzer.md b/.github/workflows/copilot-token-usage-analyzer.md index 2b85b75157..bd44d072f1 100644 --- a/.github/workflows/copilot-token-usage-analyzer.md +++ b/.github/workflows/copilot-token-usage-analyzer.md @@ -53,16 +53,45 @@ steps: set -euo pipefail mkdir -p /tmp/token-analyzer - echo "đŸ“Ĩ Downloading Copilot workflow runs from last 24 hours..." - gh aw logs \ - --engine copilot \ - --start-date -1d \ - --json \ - -c 300 \ - > /tmp/token-analyzer/copilot-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-analyzer/copilot-runs-raw.json - - # Extract runs array from the JSON output - jq '.runs // []' /tmp/token-analyzer/copilot-runs-raw.json > /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-analyzer/copilot-runs.json + # Try to use pre-fetched logs from the Token Logs Fetch workflow to avoid redundant API calls + TODAY=$(date -u +%Y-%m-%d) + FETCH_RUN_ID=$(gh run list \ + --workflow "token-logs-fetch.lock.yml" \ + --status success \ + --limit 1 \ + --json databaseId \ + --jq '.[0].databaseId' 2>/dev/null || echo "") + USED_CACHE=false + if [ -n "$FETCH_RUN_ID" ]; then + CACHE_TMP="/tmp/token-logs-cache-analyzer" + mkdir -p "$CACHE_TMP" + gh run download "$FETCH_RUN_ID" \ + --repo "$GITHUB_REPOSITORY" \ + --name "cache-memory" \ + --dir "$CACHE_TMP" \ + 2>/dev/null || true + CACHE_DATE=$(cat "$CACHE_TMP/token-logs/fetch-date.txt" 2>/dev/null || echo "") + if [ "$CACHE_DATE" = "$TODAY" ] && [ -s "$CACHE_TMP/token-logs/copilot-runs.json" ]; then + echo "✅ Using pre-fetched logs from Token Logs Fetch run $FETCH_RUN_ID (date: $CACHE_DATE)" + cp "$CACHE_TMP/token-logs/copilot-runs.json" /tmp/token-analyzer/copilot-runs.json + USED_CACHE=true + else + echo "ℹī¸ No valid cached logs found (cache date: ${CACHE_DATE:-none}, today: $TODAY)" + fi + fi + + if [ "$USED_CACHE" != "true" ]; then + echo "đŸ“Ĩ Downloading Copilot workflow runs from last 24 hours..." + gh aw logs \ + --engine copilot \ + --start-date -1d \ + --json \ + -c 300 \ + > /tmp/token-analyzer/copilot-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-analyzer/copilot-runs-raw.json + + # Extract runs array from the JSON output + jq '.runs // []' /tmp/token-analyzer/copilot-runs-raw.json > /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-analyzer/copilot-runs.json + fi RUN_COUNT=$(jq 'length' /tmp/token-analyzer/copilot-runs.json 2>/dev/null || echo 0) echo "✅ Found ${RUN_COUNT} Copilot workflow runs" diff --git a/.github/workflows/token-logs-fetch.lock.yml b/.github/workflows/token-logs-fetch.lock.yml new file mode 100644 index 0000000000..9178204048 --- /dev/null +++ b/.github/workflows/token-logs-fetch.lock.yml @@ -0,0 +1,1183 @@ +# ___ _ _ +# / _ \ | | (_) +# | |_| | __ _ ___ _ __ | |_ _ ___ +# | _ |/ _` |/ _ \ '_ \| __| |/ __| +# | | | | (_| | __/ | | | |_| | (__ +# \_| |_/\__, |\___|_| |_|\__|_|\___| +# __/ | +# _ _ |___/ +# | | | | / _| | +# | | | | ___ _ __ _ __| |_| | _____ ____ +# | |/\| |/ _ \ '__| |/ /| _| |/ _ \ \ /\ / / ___| +# \ /\ / (_) | | | | ( | | | | (_) \ V V /\__ \ +# \/ \/ \___/|_| |_|\_\|_| |_|\___/ \_/\_/ |___/ +# +# This file was automatically generated by gh-aw. DO NOT EDIT. +# +# To update this file, edit the corresponding .md file and run: +# gh aw compile +# Not all edits will cause changes to this file. +# +# For more information: https://github.github.com/gh-aw/introduction/overview/ +# +# Pre-fetches Copilot and Claude workflow run logs daily and stores them in cache-memory to avoid redundant API calls and rate-limiting in downstream token analysis and optimization workflows +# +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"77d36911c8e8f38e7a1eb9aa895af361b0136b7088d2ff848d490476f794c270","strict":true,"agent_id":"copilot"} + +name: "Token Logs Fetch" +"on": + schedule: + - cron: "54 7 * * 1-5" + # Friendly format: daily around 08:45 on weekdays (scattered) + workflow_dispatch: + inputs: + aw_context: + default: "" + description: Agent caller context (used internally by Agentic Workflows). + required: false + type: string + +permissions: {} + +concurrency: + group: "gh-aw-${{ github.workflow }}" + +run-name: "Token Logs Fetch" + +jobs: + activation: + runs-on: ubuntu-slim + permissions: + contents: read + outputs: + comment_id: "" + comment_repo: "" + lockdown_check_failed: ${{ steps.generate_aw_info.outputs.lockdown_check_failed == 'true' }} + model: ${{ steps.generate_aw_info.outputs.model }} + steps: + - name: Checkout actions folder + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + repository: github/gh-aw + sparse-checkout: | + actions + persist-credentials: false + - name: Setup Scripts + uses: ./actions/setup + with: + destination: ${{ runner.temp }}/gh-aw/actions + - name: Generate agentic run info + id: generate_aw_info + env: + GH_AW_INFO_ENGINE_ID: "copilot" + GH_AW_INFO_ENGINE_NAME: "GitHub Copilot CLI" + GH_AW_INFO_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || 'auto' }} + GH_AW_INFO_VERSION: "latest" + GH_AW_INFO_AGENT_VERSION: "latest" + GH_AW_INFO_WORKFLOW_NAME: "Token Logs Fetch" + GH_AW_INFO_EXPERIMENTAL: "false" + GH_AW_INFO_SUPPORTS_TOOLS_ALLOWLIST: "true" + GH_AW_INFO_STAGED: "false" + GH_AW_INFO_ALLOWED_DOMAINS: '["defaults"]' + GH_AW_INFO_FIREWALL_ENABLED: "true" + GH_AW_INFO_AWF_VERSION: "v0.25.13" + GH_AW_INFO_AWMG_VERSION: "" + GH_AW_INFO_FIREWALL_TYPE: "squid" + GH_AW_COMPILED_STRICT: "true" + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_aw_info.cjs'); + await main(core, context); + - name: Checkout .github and .agents folders + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + sparse-checkout: | + .github + .agents + actions/setup + sparse-checkout-cone-mode: true + fetch-depth: 1 + - name: Check workflow lock file + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_WORKFLOW_FILE: "token-logs-fetch.lock.yml" + GH_AW_CONTEXT_WORKFLOW_REF: "${{ github.workflow_ref }}" + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/check_workflow_timestamp_api.cjs'); + await main(); + - name: Create prompt with built-in context + env: + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + GH_AW_SAFE_OUTPUTS: ${{ runner.temp }}/gh-aw/safeoutputs/outputs.jsonl + GH_AW_GITHUB_ACTOR: ${{ github.actor }} + GH_AW_GITHUB_EVENT_COMMENT_ID: ${{ github.event.comment.id }} + GH_AW_GITHUB_EVENT_DISCUSSION_NUMBER: ${{ github.event.discussion.number }} + GH_AW_GITHUB_EVENT_ISSUE_NUMBER: ${{ github.event.issue.number }} + GH_AW_GITHUB_EVENT_PULL_REQUEST_NUMBER: ${{ github.event.pull_request.number }} + GH_AW_GITHUB_REPOSITORY: ${{ github.repository }} + GH_AW_GITHUB_RUN_ID: ${{ github.run_id }} + GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }} + # poutine:ignore untrusted_checkout_exec + run: | + bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh + { + cat << 'GH_AW_PROMPT_564883dfc94bb1c9_EOF' + + GH_AW_PROMPT_564883dfc94bb1c9_EOF + cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" + cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" + cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" + cat "${RUNNER_TEMP}/gh-aw/prompts/cache_memory_prompt.md" + cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" + cat << 'GH_AW_PROMPT_564883dfc94bb1c9_EOF' + + Tools: create_issue, missing_tool, missing_data, noop + GH_AW_PROMPT_564883dfc94bb1c9_EOF + cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_auto_create_issue.md" + cat << 'GH_AW_PROMPT_564883dfc94bb1c9_EOF' + + + The following GitHub context information is available for this workflow: + {{#if __GH_AW_GITHUB_ACTOR__ }} + - **actor**: __GH_AW_GITHUB_ACTOR__ + {{/if}} + {{#if __GH_AW_GITHUB_REPOSITORY__ }} + - **repository**: __GH_AW_GITHUB_REPOSITORY__ + {{/if}} + {{#if __GH_AW_GITHUB_WORKSPACE__ }} + - **workspace**: __GH_AW_GITHUB_WORKSPACE__ + {{/if}} + {{#if __GH_AW_GITHUB_EVENT_ISSUE_NUMBER__ }} + - **issue-number**: #__GH_AW_GITHUB_EVENT_ISSUE_NUMBER__ + {{/if}} + {{#if __GH_AW_GITHUB_EVENT_DISCUSSION_NUMBER__ }} + - **discussion-number**: #__GH_AW_GITHUB_EVENT_DISCUSSION_NUMBER__ + {{/if}} + {{#if __GH_AW_GITHUB_EVENT_PULL_REQUEST_NUMBER__ }} + - **pull-request-number**: #__GH_AW_GITHUB_EVENT_PULL_REQUEST_NUMBER__ + {{/if}} + {{#if __GH_AW_GITHUB_EVENT_COMMENT_ID__ }} + - **comment-id**: __GH_AW_GITHUB_EVENT_COMMENT_ID__ + {{/if}} + {{#if __GH_AW_GITHUB_RUN_ID__ }} + - **workflow-run-id**: __GH_AW_GITHUB_RUN_ID__ + {{/if}} + + + GH_AW_PROMPT_564883dfc94bb1c9_EOF + cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" + cat << 'GH_AW_PROMPT_564883dfc94bb1c9_EOF' + + {{#runtime-import .github/workflows/token-logs-fetch.md}} + GH_AW_PROMPT_564883dfc94bb1c9_EOF + } > "$GH_AW_PROMPT" + - name: Interpolate variables and render templates + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/interpolate_prompt.cjs'); + await main(); + - name: Substitute placeholders + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + GH_AW_ALLOWED_EXTENSIONS: '' + GH_AW_CACHE_DESCRIPTION: '' + GH_AW_CACHE_DIR: '/tmp/gh-aw/cache-memory/' + GH_AW_GITHUB_ACTOR: ${{ github.actor }} + GH_AW_GITHUB_EVENT_COMMENT_ID: ${{ github.event.comment.id }} + GH_AW_GITHUB_EVENT_DISCUSSION_NUMBER: ${{ github.event.discussion.number }} + GH_AW_GITHUB_EVENT_ISSUE_NUMBER: ${{ github.event.issue.number }} + GH_AW_GITHUB_EVENT_PULL_REQUEST_NUMBER: ${{ github.event.pull_request.number }} + GH_AW_GITHUB_REPOSITORY: ${{ github.repository }} + GH_AW_GITHUB_RUN_ID: ${{ github.run_id }} + GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }} + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + + const substitutePlaceholders = require('${{ runner.temp }}/gh-aw/actions/substitute_placeholders.cjs'); + + // Call the substitution function + return await substitutePlaceholders({ + file: process.env.GH_AW_PROMPT, + substitutions: { + GH_AW_ALLOWED_EXTENSIONS: process.env.GH_AW_ALLOWED_EXTENSIONS, + GH_AW_CACHE_DESCRIPTION: process.env.GH_AW_CACHE_DESCRIPTION, + GH_AW_CACHE_DIR: process.env.GH_AW_CACHE_DIR, + GH_AW_GITHUB_ACTOR: process.env.GH_AW_GITHUB_ACTOR, + GH_AW_GITHUB_EVENT_COMMENT_ID: process.env.GH_AW_GITHUB_EVENT_COMMENT_ID, + GH_AW_GITHUB_EVENT_DISCUSSION_NUMBER: process.env.GH_AW_GITHUB_EVENT_DISCUSSION_NUMBER, + GH_AW_GITHUB_EVENT_ISSUE_NUMBER: process.env.GH_AW_GITHUB_EVENT_ISSUE_NUMBER, + GH_AW_GITHUB_EVENT_PULL_REQUEST_NUMBER: process.env.GH_AW_GITHUB_EVENT_PULL_REQUEST_NUMBER, + GH_AW_GITHUB_REPOSITORY: process.env.GH_AW_GITHUB_REPOSITORY, + GH_AW_GITHUB_RUN_ID: process.env.GH_AW_GITHUB_RUN_ID, + GH_AW_GITHUB_WORKSPACE: process.env.GH_AW_GITHUB_WORKSPACE + } + }); + - name: Validate prompt placeholders + env: + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + # poutine:ignore untrusted_checkout_exec + run: bash ${RUNNER_TEMP}/gh-aw/actions/validate_prompt_placeholders.sh + - name: Print prompt + env: + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + # poutine:ignore untrusted_checkout_exec + run: bash ${RUNNER_TEMP}/gh-aw/actions/print_prompt_summary.sh + - name: Upload activation artifact + if: success() + uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7 + with: + name: activation + path: | + /tmp/gh-aw/aw_info.json + /tmp/gh-aw/aw-prompts/prompt.txt + retention-days: 1 + + agent: + needs: activation + runs-on: ubuntu-latest + permissions: + actions: read + contents: read + copilot-requests: write + concurrency: + group: "gh-aw-copilot-${{ github.workflow }}" + env: + DEFAULT_BRANCH: ${{ github.event.repository.default_branch }} + GH_AW_ASSETS_ALLOWED_EXTS: "" + GH_AW_ASSETS_BRANCH: "" + GH_AW_ASSETS_MAX_SIZE_KB: 0 + GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs + GH_AW_WORKFLOW_ID_SANITIZED: tokenlogsfetch + outputs: + checkout_pr_success: ${{ steps.checkout-pr.outputs.checkout_pr_success || 'true' }} + effective_tokens: ${{ steps.parse-mcp-gateway.outputs.effective_tokens }} + has_patch: ${{ steps.collect_output.outputs.has_patch }} + inference_access_error: ${{ steps.detect-inference-error.outputs.inference_access_error || 'false' }} + model: ${{ needs.activation.outputs.model }} + output: ${{ steps.collect_output.outputs.output }} + output_types: ${{ steps.collect_output.outputs.output_types }} + steps: + - name: Checkout actions folder + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + repository: github/gh-aw + sparse-checkout: | + actions + persist-credentials: false + - name: Setup Scripts + uses: ./actions/setup + with: + destination: ${{ runner.temp }}/gh-aw/actions + - name: Set runtime paths + id: set-runtime-paths + run: | + echo "GH_AW_SAFE_OUTPUTS=${RUNNER_TEMP}/gh-aw/safeoutputs/outputs.jsonl" >> "$GITHUB_OUTPUT" + echo "GH_AW_SAFE_OUTPUTS_CONFIG_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/config.json" >> "$GITHUB_OUTPUT" + echo "GH_AW_SAFE_OUTPUTS_TOOLS_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/tools.json" >> "$GITHUB_OUTPUT" + - name: Checkout repository + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - name: Create gh-aw temp directory + run: bash ${RUNNER_TEMP}/gh-aw/actions/create_gh_aw_tmp_dir.sh + - name: Configure gh CLI for GitHub Enterprise + run: bash ${RUNNER_TEMP}/gh-aw/actions/configure_gh_for_ghe.sh + env: + GH_TOKEN: ${{ github.token }} + - env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + name: Install gh-aw CLI + run: | + if gh extension list | grep -q "github/gh-aw"; then + gh extension upgrade gh-aw || true + else + gh extension install github/gh-aw + fi + gh aw --version + - env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + name: Fetch Copilot and Claude workflow run logs + run: "set -euo pipefail\nmkdir -p /tmp/token-logs\n\necho \"đŸ“Ĩ Fetching Copilot workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine copilot \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-logs/copilot-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-logs/copilot-runs-raw.json\n\njq '.runs // []' /tmp/token-logs/copilot-runs-raw.json > /tmp/token-logs/copilot-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-logs/copilot-runs.json\necho \"✅ Copilot runs: $(jq 'length' /tmp/token-logs/copilot-runs.json)\"\n\necho \"đŸ“Ĩ Fetching Claude workflow runs from last 24 hours...\"\ngh aw logs \\\n --engine claude \\\n --start-date -1d \\\n --json \\\n -c 300 \\\n > /tmp/token-logs/claude-runs-raw.json 2>/dev/null || echo '{\"runs\":[]}' > /tmp/token-logs/claude-runs-raw.json\n\njq '.runs // []' /tmp/token-logs/claude-runs-raw.json > /tmp/token-logs/claude-runs.json 2>/dev/null || echo \"[]\" > /tmp/token-logs/claude-runs.json\necho \"✅ Claude runs: $(jq 'length' /tmp/token-logs/claude-runs.json)\"" + + # Cache memory file share configuration from frontmatter processed below + - name: Create cache-memory directory + run: bash ${RUNNER_TEMP}/gh-aw/actions/create_cache_memory_dir.sh + - name: Restore cache-memory file share data + uses: actions/cache/restore@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 + with: + key: memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-${{ github.run_id }} + path: /tmp/gh-aw/cache-memory + restore-keys: | + memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}- + - name: Setup cache-memory git repository + env: + GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory + GH_AW_MIN_INTEGRITY: none + run: bash ${RUNNER_TEMP}/gh-aw/actions/setup_cache_memory_git.sh + - name: Configure Git credentials + env: + REPO_NAME: ${{ github.repository }} + SERVER_URL: ${{ github.server_url }} + run: | + git config --global user.email "github-actions[bot]@users.noreply.github.com" + git config --global user.name "github-actions[bot]" + git config --global am.keepcr true + # Re-authenticate git with GitHub token + SERVER_URL_STRIPPED="${SERVER_URL#https://}" + git remote set-url origin "https://x-access-token:${{ github.token }}@${SERVER_URL_STRIPPED}/${REPO_NAME}.git" + echo "Git configured with standard GitHub Actions identity" + - name: Checkout PR branch + id: checkout-pr + if: | + github.event.pull_request || github.event.issue.pull_request + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + with: + github-token: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/checkout_pr_branch.cjs'); + await main(); + - name: Install GitHub Copilot CLI + run: ${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh latest + env: + GH_HOST: github.com + - name: Install AWF binary + run: bash ${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh v0.25.13 + - name: Determine automatic lockdown mode for GitHub MCP Server + id: determine-automatic-lockdown + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }} + GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }} + with: + script: | + const determineAutomaticLockdown = require('${{ runner.temp }}/gh-aw/actions/determine_automatic_lockdown.cjs'); + await determineAutomaticLockdown(github, context, core); + - name: Download container images + run: bash ${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh ghcr.io/github/gh-aw-firewall/agent:0.25.13 ghcr.io/github/gh-aw-firewall/api-proxy:0.25.13 ghcr.io/github/gh-aw-firewall/squid:0.25.13 ghcr.io/github/gh-aw-mcpg:v0.2.12 ghcr.io/github/github-mcp-server:v0.32.0 node:lts-alpine + - name: Write Safe Outputs Config + run: | + mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs + mkdir -p /tmp/gh-aw/safeoutputs + mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_9f109b086ddbc660_EOF' + {"create_issue":{"labels":["token-logs-fetch"],"max":1,"title_prefix":"[token-logs-fetch]"},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"true"}} + GH_AW_SAFE_OUTPUTS_CONFIG_9f109b086ddbc660_EOF + - name: Write Safe Outputs Tools + run: | + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_c4497f70f215a2ea_EOF' + { + "description_suffixes": { + "create_issue": " CONSTRAINTS: Maximum 1 issue(s) can be created. Title will be prefixed with \"[token-logs-fetch]\". Labels [\"token-logs-fetch\"] will be automatically added." + }, + "repo_params": {}, + "dynamic_tools": [] + } + GH_AW_SAFE_OUTPUTS_TOOLS_META_c4497f70f215a2ea_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_fa3ea862e417a214_EOF' + { + "create_issue": { + "defaultMax": 1, + "fields": { + "body": { + "required": true, + "type": "string", + "sanitize": true, + "maxLength": 65000 + }, + "labels": { + "type": "array", + "itemType": "string", + "itemSanitize": true, + "itemMaxLength": 128 + }, + "parent": { + "issueOrPRNumber": true + }, + "repo": { + "type": "string", + "maxLength": 256 + }, + "temporary_id": { + "type": "string" + }, + "title": { + "required": true, + "type": "string", + "sanitize": true, + "maxLength": 128 + } + } + }, + "missing_data": { + "defaultMax": 20, + "fields": { + "alternatives": { + "type": "string", + "sanitize": true, + "maxLength": 256 + }, + "context": { + "type": "string", + "sanitize": true, + "maxLength": 256 + }, + "data_type": { + "type": "string", + "sanitize": true, + "maxLength": 128 + }, + "reason": { + "type": "string", + "sanitize": true, + "maxLength": 256 + } + } + }, + "missing_tool": { + "defaultMax": 20, + "fields": { + "alternatives": { + "type": "string", + "sanitize": true, + "maxLength": 512 + }, + "reason": { + "required": true, + "type": "string", + "sanitize": true, + "maxLength": 256 + }, + "tool": { + "type": "string", + "sanitize": true, + "maxLength": 128 + } + } + }, + "noop": { + "defaultMax": 1, + "fields": { + "message": { + "required": true, + "type": "string", + "sanitize": true, + "maxLength": 65000 + } + } + } + } + GH_AW_SAFE_OUTPUTS_VALIDATION_fa3ea862e417a214_EOF + node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs + - name: Generate Safe Outputs MCP Server Config + id: safe-outputs-config + run: | + # Generate a secure random API key (360 bits of entropy, 40+ chars) + # Mask immediately to prevent timing vulnerabilities + API_KEY=$(openssl rand -base64 45 | tr -d '/+=') + echo "::add-mask::${API_KEY}" + + PORT=3001 + + # Set outputs for next steps + { + echo "safe_outputs_api_key=${API_KEY}" + echo "safe_outputs_port=${PORT}" + } >> "$GITHUB_OUTPUT" + + echo "Safe Outputs MCP server will run on port ${PORT}" + + - name: Start Safe Outputs MCP HTTP Server + id: safe-outputs-start + env: + DEBUG: '*' + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + GH_AW_SAFE_OUTPUTS_PORT: ${{ steps.safe-outputs-config.outputs.safe_outputs_port }} + GH_AW_SAFE_OUTPUTS_API_KEY: ${{ steps.safe-outputs-config.outputs.safe_outputs_api_key }} + GH_AW_SAFE_OUTPUTS_TOOLS_PATH: ${{ runner.temp }}/gh-aw/safeoutputs/tools.json + GH_AW_SAFE_OUTPUTS_CONFIG_PATH: ${{ runner.temp }}/gh-aw/safeoutputs/config.json + GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs + run: | + # Environment variables are set above to prevent template injection + export DEBUG + export GH_AW_SAFE_OUTPUTS + export GH_AW_SAFE_OUTPUTS_PORT + export GH_AW_SAFE_OUTPUTS_API_KEY + export GH_AW_SAFE_OUTPUTS_TOOLS_PATH + export GH_AW_SAFE_OUTPUTS_CONFIG_PATH + export GH_AW_MCP_LOG_DIR + + bash ${RUNNER_TEMP}/gh-aw/actions/start_safe_outputs_server.sh + + - name: Start MCP Gateway + id: start-mcp-gateway + env: + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + GH_AW_SAFE_OUTPUTS_API_KEY: ${{ steps.safe-outputs-start.outputs.api_key }} + GH_AW_SAFE_OUTPUTS_PORT: ${{ steps.safe-outputs-start.outputs.port }} + GITHUB_MCP_GUARD_MIN_INTEGRITY: ${{ steps.determine-automatic-lockdown.outputs.min_integrity }} + GITHUB_MCP_GUARD_REPOS: ${{ steps.determine-automatic-lockdown.outputs.repos }} + GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + run: | + set -eo pipefail + mkdir -p /tmp/gh-aw/mcp-config + + # Export gateway environment variables for MCP config and gateway script + export MCP_GATEWAY_PORT="80" + export MCP_GATEWAY_DOMAIN="host.docker.internal" + MCP_GATEWAY_API_KEY=$(openssl rand -base64 45 | tr -d '/+=') + echo "::add-mask::${MCP_GATEWAY_API_KEY}" + export MCP_GATEWAY_API_KEY + export MCP_GATEWAY_PAYLOAD_DIR="/tmp/gh-aw/mcp-payloads" + mkdir -p "${MCP_GATEWAY_PAYLOAD_DIR}" + export MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD="524288" + export DEBUG="*" + + export GH_AW_ENGINE="copilot" + export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.12' + + mkdir -p /home/runner/.copilot + cat << GH_AW_MCP_CONFIG_23d1a6d7f0f43aca_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + { + "mcpServers": { + "github": { + "type": "stdio", + "container": "ghcr.io/github/github-mcp-server:v0.32.0", + "env": { + "GITHUB_HOST": "\${GITHUB_SERVER_URL}", + "GITHUB_PERSONAL_ACCESS_TOKEN": "\${GITHUB_MCP_SERVER_TOKEN}", + "GITHUB_READ_ONLY": "1", + "GITHUB_TOOLSETS": "context,repos,issues,pull_requests" + }, + "guard-policies": { + "allow-only": { + "min-integrity": "$GITHUB_MCP_GUARD_MIN_INTEGRITY", + "repos": "$GITHUB_MCP_GUARD_REPOS" + } + } + }, + "safeoutputs": { + "type": "http", + "url": "http://host.docker.internal:$GH_AW_SAFE_OUTPUTS_PORT", + "headers": { + "Authorization": "\${GH_AW_SAFE_OUTPUTS_API_KEY}" + }, + "guard-policies": { + "write-sink": { + "accept": [ + "*" + ] + } + } + } + }, + "gateway": { + "port": $MCP_GATEWAY_PORT, + "domain": "${MCP_GATEWAY_DOMAIN}", + "apiKey": "${MCP_GATEWAY_API_KEY}", + "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" + } + } + GH_AW_MCP_CONFIG_23d1a6d7f0f43aca_EOF + - name: Download activation artifact + uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 + with: + name: activation + path: /tmp/gh-aw + - name: Clean git credentials + continue-on-error: true + run: bash ${RUNNER_TEMP}/gh-aw/actions/clean_git_credentials.sh + - name: Execute GitHub Copilot CLI + id: agentic_execution + # Copilot CLI tool arguments (sorted): + timeout-minutes: 15 + run: | + set -o pipefail + touch /tmp/gh-aw/agent-step-summary.md + # shellcheck disable=SC1003 + sudo -E awf --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" --env-all --exclude-env COPILOT_GITHUB_TOKEN --exclude-env GITHUB_MCP_SERVER_TOKEN --exclude-env MCP_GATEWAY_API_KEY --allow-domains api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.com --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --audit-dir /tmp/gh-aw/sandbox/firewall/audit --enable-host-access --image-tag 0.25.13 --skip-pull --enable-api-proxy \ + -- /bin/bash -c '/usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --allow-all-tools --add-dir /tmp/gh-aw/cache-memory/ --allow-all-paths --add-dir "${GITHUB_WORKSPACE}" --prompt "$(cat /tmp/gh-aw/aw-prompts/prompt.txt)"' 2>&1 | tee -a /tmp/gh-aw/agent-stdio.log + env: + COPILOT_AGENT_RUNNER_TYPE: STANDALONE + COPILOT_GITHUB_TOKEN: ${{ github.token }} + COPILOT_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || '' }} + GH_AW_MCP_CONFIG: /home/runner/.copilot/mcp-config.json + GH_AW_PHASE: agent + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + GH_AW_VERSION: dev + GITHUB_API_URL: ${{ github.api_url }} + GITHUB_AW: true + GITHUB_HEAD_REF: ${{ github.head_ref }} + GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + GITHUB_REF_NAME: ${{ github.ref_name }} + GITHUB_SERVER_URL: ${{ github.server_url }} + GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md + GITHUB_WORKSPACE: ${{ github.workspace }} + GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com + GIT_AUTHOR_NAME: github-actions[bot] + GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com + GIT_COMMITTER_NAME: github-actions[bot] + S2STOKENS: true + XDG_CONFIG_HOME: /home/runner + - name: Detect inference access error + id: detect-inference-error + if: always() + continue-on-error: true + run: bash ${RUNNER_TEMP}/gh-aw/actions/detect_inference_access_error.sh + - name: Configure Git credentials + env: + REPO_NAME: ${{ github.repository }} + SERVER_URL: ${{ github.server_url }} + run: | + git config --global user.email "github-actions[bot]@users.noreply.github.com" + git config --global user.name "github-actions[bot]" + git config --global am.keepcr true + # Re-authenticate git with GitHub token + SERVER_URL_STRIPPED="${SERVER_URL#https://}" + git remote set-url origin "https://x-access-token:${{ github.token }}@${SERVER_URL_STRIPPED}/${REPO_NAME}.git" + echo "Git configured with standard GitHub Actions identity" + - name: Copy Copilot session state files to logs + if: always() + continue-on-error: true + run: bash ${RUNNER_TEMP}/gh-aw/actions/copy_copilot_session_state.sh + - name: Stop MCP Gateway + if: always() + continue-on-error: true + env: + MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }} + MCP_GATEWAY_API_KEY: ${{ steps.start-mcp-gateway.outputs.gateway-api-key }} + GATEWAY_PID: ${{ steps.start-mcp-gateway.outputs.gateway-pid }} + run: | + bash ${RUNNER_TEMP}/gh-aw/actions/stop_mcp_gateway.sh "$GATEWAY_PID" + - name: Redact secrets in logs + if: always() + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/redact_secrets.cjs'); + await main(); + env: + GH_AW_SECRET_NAMES: 'GH_AW_GITHUB_MCP_SERVER_TOKEN,GH_AW_GITHUB_TOKEN,GITHUB_TOKEN' + SECRET_GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }} + SECRET_GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }} + SECRET_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + - name: Append agent step summary + if: always() + run: bash ${RUNNER_TEMP}/gh-aw/actions/append_agent_step_summary.sh + - name: Copy Safe Outputs + if: always() + env: + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + run: | + mkdir -p /tmp/gh-aw + cp "$GH_AW_SAFE_OUTPUTS" /tmp/gh-aw/safeoutputs.jsonl 2>/dev/null || true + - name: Ingest agent output + id: collect_output + if: always() + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + GH_AW_ALLOWED_DOMAINS: "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.com" + GITHUB_SERVER_URL: ${{ github.server_url }} + GITHUB_API_URL: ${{ github.api_url }} + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/collect_ndjson_output.cjs'); + await main(); + - name: Parse agent logs for step summary + if: always() + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_AGENT_OUTPUT: /tmp/gh-aw/sandbox/agent/logs/ + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_copilot_log.cjs'); + await main(); + - name: Parse MCP Gateway logs for step summary + if: always() + id: parse-mcp-gateway + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_mcp_gateway_log.cjs'); + await main(); + - name: Print firewall logs + if: always() + continue-on-error: true + env: + AWF_LOGS_DIR: /tmp/gh-aw/sandbox/firewall/logs + run: | + # Fix permissions on firewall logs so they can be uploaded as artifacts + # AWF runs with sudo, creating files owned by root + sudo chmod -R a+r /tmp/gh-aw/sandbox/firewall/logs 2>/dev/null || true + # Only run awf logs summary if awf command exists (it may not be installed if workflow failed before install step) + if command -v awf &> /dev/null; then + awf logs summary | tee -a "$GITHUB_STEP_SUMMARY" + else + echo 'AWF binary not installed, skipping firewall log summary' + fi + - name: Parse token usage for step summary + if: always() + continue-on-error: true + run: bash ${RUNNER_TEMP}/gh-aw/actions/parse_token_usage.sh + - name: Write agent output placeholder if missing + if: always() + run: | + if [ ! -f /tmp/gh-aw/agent_output.json ]; then + echo '{"items":[]}' > /tmp/gh-aw/agent_output.json + fi + - name: Commit cache-memory changes + if: always() + env: + GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory + run: bash ${RUNNER_TEMP}/gh-aw/actions/commit_cache_memory_git.sh + - name: Upload cache-memory data as artifact + uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7 + if: always() + with: + name: cache-memory + path: /tmp/gh-aw/cache-memory + - name: Upload agent artifacts + if: always() + continue-on-error: true + uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7 + with: + name: agent + path: | + /tmp/gh-aw/aw-prompts/prompt.txt + /tmp/gh-aw/sandbox/agent/logs/ + /tmp/gh-aw/redacted-urls.log + /tmp/gh-aw/mcp-logs/ + /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent-stdio.log + /tmp/gh-aw/agent/ + /tmp/gh-aw/safeoutputs.jsonl + /tmp/gh-aw/agent_output.json + /tmp/gh-aw/aw-*.patch + /tmp/gh-aw/aw-*.bundle + if-no-files-found: ignore + - name: Upload firewall audit logs + if: always() + continue-on-error: true + uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7 + with: + name: firewall-audit-logs + path: | + /tmp/gh-aw/sandbox/firewall/logs/ + /tmp/gh-aw/sandbox/firewall/audit/ + if-no-files-found: ignore + + conclusion: + needs: + - activation + - agent + - detection + - safe_outputs + - update_cache_memory + if: always() && (needs.agent.result != 'skipped' || needs.activation.outputs.lockdown_check_failed == 'true') + runs-on: ubuntu-slim + permissions: + contents: read + issues: write + concurrency: + group: "gh-aw-conclusion-token-logs-fetch" + cancel-in-progress: false + outputs: + noop_message: ${{ steps.noop.outputs.noop_message }} + tools_reported: ${{ steps.missing_tool.outputs.tools_reported }} + total_count: ${{ steps.missing_tool.outputs.total_count }} + steps: + - name: Checkout actions folder + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + repository: github/gh-aw + sparse-checkout: | + actions + persist-credentials: false + - name: Setup Scripts + uses: ./actions/setup + with: + destination: ${{ runner.temp }}/gh-aw/actions + - name: Download agent output artifact + id: download-agent-output + continue-on-error: true + uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 + with: + name: agent + path: /tmp/gh-aw/ + - name: Setup agent output environment variable + id: setup-agent-output-env + if: steps.download-agent-output.outcome == 'success' + run: | + mkdir -p /tmp/gh-aw/ + find "/tmp/gh-aw/" -type f -print + echo "GH_AW_AGENT_OUTPUT=/tmp/gh-aw/agent_output.json" >> "$GITHUB_OUTPUT" + - name: Process No-Op Messages + id: noop + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} + GH_AW_NOOP_MAX: "1" + GH_AW_WORKFLOW_NAME: "Token Logs Fetch" + GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }} + GH_AW_AGENT_CONCLUSION: ${{ needs.agent.result }} + GH_AW_NOOP_REPORT_AS_ISSUE: "true" + with: + github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_noop_message.cjs'); + await main(); + - name: Record Missing Tool + id: missing_tool + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} + GH_AW_MISSING_TOOL_CREATE_ISSUE: "true" + GH_AW_WORKFLOW_NAME: "Token Logs Fetch" + with: + github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/missing_tool.cjs'); + await main(); + - name: Handle Agent Failure + id: handle_agent_failure + if: always() + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} + GH_AW_WORKFLOW_NAME: "Token Logs Fetch" + GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }} + GH_AW_AGENT_CONCLUSION: ${{ needs.agent.result }} + GH_AW_WORKFLOW_ID: "token-logs-fetch" + GH_AW_ENGINE_ID: "copilot" + GH_AW_CHECKOUT_PR_SUCCESS: ${{ needs.agent.outputs.checkout_pr_success }} + GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} + GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} + GH_AW_GROUP_REPORTS: "false" + GH_AW_FAILURE_REPORT_AS_ISSUE: "true" + GH_AW_TIMEOUT_MINUTES: "15" + with: + github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_agent_failure.cjs'); + await main(); + + detection: + needs: agent + if: > + always() && needs.agent.result != 'skipped' && (needs.agent.outputs.output_types != '' || needs.agent.outputs.has_patch == 'true') + runs-on: ubuntu-latest + permissions: + contents: read + copilot-requests: write + outputs: + detection_conclusion: ${{ steps.detection_conclusion.outputs.conclusion }} + detection_success: ${{ steps.detection_conclusion.outputs.success }} + steps: + - name: Checkout actions folder + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + repository: github/gh-aw + sparse-checkout: | + actions + persist-credentials: false + - name: Setup Scripts + uses: ./actions/setup + with: + destination: ${{ runner.temp }}/gh-aw/actions + - name: Download agent output artifact + id: download-agent-output + continue-on-error: true + uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 + with: + name: agent + path: /tmp/gh-aw/ + - name: Setup agent output environment variable + id: setup-agent-output-env + if: steps.download-agent-output.outcome == 'success' + run: | + mkdir -p /tmp/gh-aw/ + find "/tmp/gh-aw/" -type f -print + echo "GH_AW_AGENT_OUTPUT=/tmp/gh-aw/agent_output.json" >> "$GITHUB_OUTPUT" + - name: Checkout repository for patch context + if: needs.agent.outputs.has_patch == 'true' + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + # --- Threat Detection --- + - name: Download container images + run: bash ${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh ghcr.io/github/gh-aw-firewall/agent:0.25.13 ghcr.io/github/gh-aw-firewall/api-proxy:0.25.13 ghcr.io/github/gh-aw-firewall/squid:0.25.13 + - name: Check if detection needed + id: detection_guard + if: always() + env: + OUTPUT_TYPES: ${{ needs.agent.outputs.output_types }} + HAS_PATCH: ${{ needs.agent.outputs.has_patch }} + run: | + if [[ -n "$OUTPUT_TYPES" || "$HAS_PATCH" == "true" ]]; then + echo "run_detection=true" >> "$GITHUB_OUTPUT" + echo "Detection will run: output_types=$OUTPUT_TYPES, has_patch=$HAS_PATCH" + else + echo "run_detection=false" >> "$GITHUB_OUTPUT" + echo "Detection skipped: no agent outputs or patches to analyze" + fi + - name: Clear MCP configuration for detection + if: always() && steps.detection_guard.outputs.run_detection == 'true' + run: | + rm -f /tmp/gh-aw/mcp-config/mcp-servers.json + rm -f /home/runner/.copilot/mcp-config.json + rm -f "$GITHUB_WORKSPACE/.gemini/settings.json" + - name: Prepare threat detection files + if: always() && steps.detection_guard.outputs.run_detection == 'true' + run: | + mkdir -p /tmp/gh-aw/threat-detection/aw-prompts + cp /tmp/gh-aw/aw-prompts/prompt.txt /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt 2>/dev/null || true + cp /tmp/gh-aw/agent_output.json /tmp/gh-aw/threat-detection/agent_output.json 2>/dev/null || true + for f in /tmp/gh-aw/aw-*.patch; do + [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true + done + for f in /tmp/gh-aw/aw-*.bundle; do + [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true + done + echo "Prepared threat detection files:" + ls -la /tmp/gh-aw/threat-detection/ 2>/dev/null || true + - name: Setup threat detection + if: always() && steps.detection_guard.outputs.run_detection == 'true' + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + WORKFLOW_NAME: "Token Logs Fetch" + WORKFLOW_DESCRIPTION: "Pre-fetches Copilot and Claude workflow run logs daily and stores them in cache-memory to avoid redundant API calls and rate-limiting in downstream token analysis and optimization workflows" + HAS_PATCH: ${{ needs.agent.outputs.has_patch }} + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/setup_threat_detection.cjs'); + await main(); + - name: Ensure threat-detection directory and log + if: always() && steps.detection_guard.outputs.run_detection == 'true' + run: | + mkdir -p /tmp/gh-aw/threat-detection + touch /tmp/gh-aw/threat-detection/detection.log + - name: Install GitHub Copilot CLI + run: ${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh latest + env: + GH_HOST: github.com + - name: Install AWF binary + run: bash ${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh v0.25.13 + - name: Execute GitHub Copilot CLI + if: always() && steps.detection_guard.outputs.run_detection == 'true' + id: detection_agentic_execution + # Copilot CLI tool arguments (sorted): + timeout-minutes: 20 + run: | + set -o pipefail + touch /tmp/gh-aw/agent-step-summary.md + # shellcheck disable=SC1003 + sudo -E awf --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" --env-all --exclude-env COPILOT_GITHUB_TOKEN --allow-domains api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,github.com,host.docker.internal,telemetry.enterprise.githubcopilot.com --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --audit-dir /tmp/gh-aw/sandbox/firewall/audit --enable-host-access --image-tag 0.25.13 --skip-pull --enable-api-proxy \ + -- /bin/bash -c '/usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --allow-all-tools --add-dir "${GITHUB_WORKSPACE}" --prompt "$(cat /tmp/gh-aw/aw-prompts/prompt.txt)"' 2>&1 | tee -a /tmp/gh-aw/threat-detection/detection.log + env: + COPILOT_AGENT_RUNNER_TYPE: STANDALONE + COPILOT_GITHUB_TOKEN: ${{ github.token }} + COPILOT_MODEL: ${{ vars.GH_AW_MODEL_DETECTION_COPILOT || '' }} + GH_AW_PHASE: detection + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + GH_AW_VERSION: dev + GITHUB_API_URL: ${{ github.api_url }} + GITHUB_AW: true + GITHUB_HEAD_REF: ${{ github.head_ref }} + GITHUB_REF_NAME: ${{ github.ref_name }} + GITHUB_SERVER_URL: ${{ github.server_url }} + GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md + GITHUB_WORKSPACE: ${{ github.workspace }} + GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com + GIT_AUTHOR_NAME: github-actions[bot] + GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com + GIT_COMMITTER_NAME: github-actions[bot] + S2STOKENS: true + XDG_CONFIG_HOME: /home/runner + - name: Upload threat detection log + if: always() && steps.detection_guard.outputs.run_detection == 'true' + uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7 + with: + name: detection + path: /tmp/gh-aw/threat-detection/detection.log + if-no-files-found: ignore + - name: Parse and conclude threat detection + id: detection_conclusion + if: always() + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + RUN_DETECTION: ${{ steps.detection_guard.outputs.run_detection }} + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_threat_detection_results.cjs'); + await main(); + + safe_outputs: + needs: + - agent + - detection + if: (!cancelled()) && needs.agent.result != 'skipped' && needs.detection.result == 'success' + runs-on: ubuntu-slim + permissions: + contents: read + issues: write + timeout-minutes: 15 + env: + GH_AW_CALLER_WORKFLOW_ID: "${{ github.repository }}/token-logs-fetch" + GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens }} + GH_AW_ENGINE_ID: "copilot" + GH_AW_ENGINE_MODEL: ${{ needs.agent.outputs.model }} + GH_AW_WORKFLOW_ID: "token-logs-fetch" + GH_AW_WORKFLOW_NAME: "Token Logs Fetch" + outputs: + code_push_failure_count: ${{ steps.process_safe_outputs.outputs.code_push_failure_count }} + code_push_failure_errors: ${{ steps.process_safe_outputs.outputs.code_push_failure_errors }} + create_discussion_error_count: ${{ steps.process_safe_outputs.outputs.create_discussion_error_count }} + create_discussion_errors: ${{ steps.process_safe_outputs.outputs.create_discussion_errors }} + created_issue_number: ${{ steps.process_safe_outputs.outputs.created_issue_number }} + created_issue_url: ${{ steps.process_safe_outputs.outputs.created_issue_url }} + process_safe_outputs_processed_count: ${{ steps.process_safe_outputs.outputs.processed_count }} + process_safe_outputs_temporary_id_map: ${{ steps.process_safe_outputs.outputs.temporary_id_map }} + steps: + - name: Checkout actions folder + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + repository: github/gh-aw + sparse-checkout: | + actions + persist-credentials: false + - name: Setup Scripts + uses: ./actions/setup + with: + destination: ${{ runner.temp }}/gh-aw/actions + - name: Download agent output artifact + id: download-agent-output + continue-on-error: true + uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 + with: + name: agent + path: /tmp/gh-aw/ + - name: Setup agent output environment variable + id: setup-agent-output-env + if: steps.download-agent-output.outcome == 'success' + run: | + mkdir -p /tmp/gh-aw/ + find "/tmp/gh-aw/" -type f -print + echo "GH_AW_AGENT_OUTPUT=/tmp/gh-aw/agent_output.json" >> "$GITHUB_OUTPUT" + - name: Configure GH_HOST for enterprise compatibility + id: ghes-host-config + shell: bash + run: | + # Derive GH_HOST from GITHUB_SERVER_URL so the gh CLI targets the correct + # GitHub instance (GHES/GHEC). On github.com this is a harmless no-op. + GH_HOST="${GITHUB_SERVER_URL#https://}" + GH_HOST="${GH_HOST#http://}" + echo "GH_HOST=${GH_HOST}" >> "$GITHUB_ENV" + - name: Process Safe Outputs + id: process_safe_outputs + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 + env: + GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} + GH_AW_ALLOWED_DOMAINS: "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.com" + GITHUB_SERVER_URL: ${{ github.server_url }} + GITHUB_API_URL: ${{ github.api_url }} + GH_AW_SAFE_OUTPUTS_HANDLER_CONFIG: "{\"create_issue\":{\"labels\":[\"token-logs-fetch\"],\"max\":1,\"title_prefix\":\"[token-logs-fetch]\"},\"missing_data\":{},\"missing_tool\":{},\"noop\":{\"max\":1,\"report-as-issue\":\"true\"}}" + with: + github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io); + const { main } = require('${{ runner.temp }}/gh-aw/actions/safe_output_handler_manager.cjs'); + await main(); + - name: Upload Safe Output Items + if: always() + uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7 + with: + name: safe-output-items + path: /tmp/gh-aw/safe-output-items.jsonl + if-no-files-found: ignore + + update_cache_memory: + needs: + - agent + - detection + if: > + always() && (needs.detection.result == 'success' || needs.detection.result == 'skipped') && + needs.agent.result == 'success' + runs-on: ubuntu-slim + permissions: + contents: read + env: + GH_AW_WORKFLOW_ID_SANITIZED: tokenlogsfetch + steps: + - name: Checkout actions folder + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + repository: github/gh-aw + sparse-checkout: | + actions + persist-credentials: false + - name: Setup Scripts + uses: ./actions/setup + with: + destination: ${{ runner.temp }}/gh-aw/actions + - name: Download cache-memory artifact (default) + id: download_cache_default + uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 + continue-on-error: true + with: + name: cache-memory + path: /tmp/gh-aw/cache-memory + - name: Check if cache-memory folder has content (default) + id: check_cache_default + shell: bash + run: | + if [ -d "/tmp/gh-aw/cache-memory" ] && [ "$(ls -A /tmp/gh-aw/cache-memory 2>/dev/null)" ]; then + echo "has_content=true" >> "$GITHUB_OUTPUT" + else + echo "has_content=false" >> "$GITHUB_OUTPUT" + fi + - name: Save cache-memory to cache (default) + if: steps.check_cache_default.outputs.has_content == 'true' + uses: actions/cache/save@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 + with: + key: memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-${{ github.run_id }} + path: /tmp/gh-aw/cache-memory + diff --git a/.github/workflows/token-logs-fetch.md b/.github/workflows/token-logs-fetch.md new file mode 100644 index 0000000000..1619a991d2 --- /dev/null +++ b/.github/workflows/token-logs-fetch.md @@ -0,0 +1,91 @@ +--- +name: Token Logs Fetch +description: Pre-fetches Copilot and Claude workflow run logs daily and stores them in cache-memory to avoid redundant API calls and rate-limiting in downstream token analysis and optimization workflows +on: + schedule: + - cron: "daily around 08:45 on weekdays" + workflow_dispatch: + +permissions: + contents: read + actions: read + +engine: copilot +features: + copilot-requests: true + +tools: + bash: + - "*" + cache-memory: true + +safe-outputs: + noop: + +network: defaults + +timeout-minutes: 15 + +steps: + - name: Install gh-aw CLI + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + run: | + if gh extension list | grep -q "github/gh-aw"; then + gh extension upgrade gh-aw || true + else + gh extension install github/gh-aw + fi + gh aw --version + - name: Fetch Copilot and Claude workflow run logs + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + run: | + set -euo pipefail + mkdir -p /tmp/token-logs + + echo "đŸ“Ĩ Fetching Copilot workflow runs from last 24 hours..." + gh aw logs \ + --engine copilot \ + --start-date -1d \ + --json \ + -c 300 \ + > /tmp/token-logs/copilot-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-logs/copilot-runs-raw.json + + jq '.runs // []' /tmp/token-logs/copilot-runs-raw.json > /tmp/token-logs/copilot-runs.json 2>/dev/null || echo "[]" > /tmp/token-logs/copilot-runs.json + echo "✅ Copilot runs: $(jq 'length' /tmp/token-logs/copilot-runs.json)" + + echo "đŸ“Ĩ Fetching Claude workflow runs from last 24 hours..." + gh aw logs \ + --engine claude \ + --start-date -1d \ + --json \ + -c 300 \ + > /tmp/token-logs/claude-runs-raw.json 2>/dev/null || echo '{"runs":[]}' > /tmp/token-logs/claude-runs-raw.json + + jq '.runs // []' /tmp/token-logs/claude-runs-raw.json > /tmp/token-logs/claude-runs.json 2>/dev/null || echo "[]" > /tmp/token-logs/claude-runs.json + echo "✅ Claude runs: $(jq 'length' /tmp/token-logs/claude-runs.json)" +--- + +# Token Logs Fetch + +Pre-fetched workflow run logs are available at `/tmp/token-logs/`: + +- `/tmp/token-logs/copilot-runs.json` — Copilot workflow runs from the last 24 hours +- `/tmp/token-logs/claude-runs.json` — Claude workflow runs from the last 24 hours + +Your task is to cache these files for use by downstream token analysis and optimization workflows: + +```bash +mkdir -p /tmp/gh-aw/cache-memory/token-logs +cp /tmp/token-logs/copilot-runs.json /tmp/gh-aw/cache-memory/token-logs/ +cp /tmp/token-logs/claude-runs.json /tmp/gh-aw/cache-memory/token-logs/ +date -u +%Y-%m-%d > /tmp/gh-aw/cache-memory/token-logs/fetch-date.txt +echo "Cached logs for $(cat /tmp/gh-aw/cache-memory/token-logs/fetch-date.txt)" +``` + +Once the files are cached, call noop. + +```json +{"noop": {"message": "Token logs fetched and cached for downstream analysis workflows"}} +```