Skip to content

Add robust AI runtime validation, retries and email coverage; harden model client and ingest logic #43

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Rohan5commit merged 2 commits into from
May 19, 2026
Merged

Add robust AI runtime validation, retries and email coverage; harden model client and ingest logic #43

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a6cf956
Rename emergency distilled retry step id to avoid workflow id collision
Rohan5commit May 19, 2026
123bc94
Merge branch 'main' into codex/document-ai-bot-functionality-and-chan…
Rohan5commit May 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 43 additions & 29 deletions .github/workflows/daily_trading_bot.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,6 +233,36 @@ jobs:
cat results/ai_runtime_plan.json


- name: Validate Cerebrium primary configuration
id: validate_cerebrium_config
if: ${{ steps.install_base_dependencies.outcome == 'success' && !(github.event_name == 'workflow_dispatch' && inputs.run_in_lightning_studio) && ((github.event_name != 'workflow_dispatch') || (github.event_name == 'workflow_dispatch' && !inputs.disable_ai_trading)) }}
run: |
configured_inference_url="${CEREBRIUM_INFERENCE_URL}"
if [ -z "${configured_inference_url}" ]; then
configured_inference_url="${CEREBRIUM_TRAINED_MODEL_URL}"
fi
if [ -z "${configured_inference_url}" ]; then
configured_inference_url="${TRAINED_MODEL_INFERENCE_URL}"
fi
if [ -n "${configured_inference_url}" ]; then
echo "has_inference_url=true" >> "$GITHUB_OUTPUT"
echo "inference_url_source=configured"
else
echo "has_inference_url=false" >> "$GITHUB_OUTPUT"
echo "inference_url_source=missing"
echo "AI primary inference URL is missing across CEREBRIUM_INFERENCE_URL/CEREBRIUM_TRAINED_MODEL_URL/TRAINED_MODEL_INFERENCE_URL" >&2
fi
{
echo "runtime_mode=${runtime_mode}"
echo "selected_backend=${selected_backend}"
echo "selected_compute_name="
echo "selected_disk_gb=0"
echo "reason=${reason}"
} >> "$GITHUB_OUTPUT"
python -c 'import json, os, pathlib; payload={"runtime_mode": os.environ["runtime_mode"], "selected_backend": os.environ["selected_backend"], "selected_compute_name": "", "selected_disk_gb": 0, "reason": os.environ["reason"], "preflight": {"router_policy": "cerebrium_primary_then_distilled"}}; pathlib.Path("results/ai_runtime_plan.json").write_text(json.dumps(payload, indent=2)+"\n", encoding="utf-8"); print(json.dumps(payload, indent=2))'
cat results/ai_runtime_plan.json


- name: Validate Cerebrium primary configuration
id: validate_cerebrium_config
if: ${{ steps.install_base_dependencies.outcome == 'success' && !(github.event_name == 'workflow_dispatch' && inputs.run_in_lightning_studio) && ((github.event_name != 'workflow_dispatch') || (github.event_name == 'workflow_dispatch' && !inputs.disable_ai_trading)) }}
Expand Down Expand Up @@ -270,6 +300,14 @@ jobs:
echo "AI reason: ${{ steps.plan_ai_runtime.outputs.reason }}"
echo "AI inference URL configured: ${{ steps.validate_cerebrium_config.outputs.has_inference_url }}"

- name: Emit AI runtime decision
if: ${{ steps.install_base_dependencies.outcome == 'success' && !(github.event_name == 'workflow_dispatch' && inputs.run_in_lightning_studio) && ((github.event_name != 'workflow_dispatch') || (github.event_name == 'workflow_dispatch' && !inputs.disable_ai_trading)) }}
run: |
echo "AI runtime mode: ${{ steps.plan_ai_runtime.outputs.runtime_mode }}"
echo "AI backend: ${{ steps.plan_ai_runtime.outputs.selected_backend }}"
echo "AI reason: ${{ steps.plan_ai_runtime.outputs.reason }}"
echo "AI inference URL configured: ${{ steps.validate_cerebrium_config.outputs.has_inference_url }}"

- name: Warm Cerebrium inference app
id: warm_cerebrium_inference
if: ${{ steps.install_base_dependencies.outcome == 'success' && !(github.event_name == 'workflow_dispatch' && inputs.run_in_lightning_studio) && ((github.event_name != 'workflow_dispatch') || (github.event_name == 'workflow_dispatch' && !inputs.disable_ai_trading)) && steps.plan_ai_runtime.outputs.runtime_mode == 'cerebrium_full' && steps.validate_cerebrium_config.outputs.has_inference_url == 'true' }}
Expand Down Expand Up @@ -503,31 +541,7 @@ jobs:
python main.py daily_job

- name: Run AI Trading Bot (Emergency Distilled Retry)
id: run_ai_bot_distilled_retry
if: ${{ always() && steps.install_base_dependencies.outcome == 'success' && !(github.event_name == 'workflow_dispatch' && inputs.run_in_lightning_studio) && ((github.event_name != 'workflow_dispatch') || (github.event_name == 'workflow_dispatch' && !inputs.disable_ai_trading)) && steps.run_ai_bot_distilled_local.outcome == 'failure' }}
continue-on-error: true
timeout-minutes: 60
env:
SMTP_SERVER: ${{ secrets.SMTP_SERVER }}
SMTP_PORT: ${{ secrets.SMTP_PORT }}
SENDER_EMAIL: ${{ secrets.SENDER_EMAIL }}
SENDER_PASSWORD: ${{ secrets.SENDER_PASSWORD }}
RECIPIENT_EMAIL: ${{ secrets.RECIPIENT_EMAIL }}
TRAINED_MODEL_API_KEY: ${{ secrets.TRAINED_MODEL_API_KEY }}
TWELVEDATA_API_KEYS: ${{ secrets.TWELVEDATA_API_KEYS }}
ARM_LIVE_TRADING: ${{ secrets.ARM_LIVE_TRADING }}
LOG_LEVEL: ${{ secrets.LOG_LEVEL }}
DISABLE_CORE_TRADING: "1"
AI_RUNTIME_MODE: "distilled_local"
AI_ROUTER_REASON: "distilled_emergency_retry_after_failure"
TRAINED_MODEL_TIMEOUT_SECONDS: "450"
TRAINED_MODEL_MAX_RETRIES: "1"
run: |
python quant_platform/scripts/prepare_ai_only_retry.py --results-dir results
python main.py daily_job

- name: Run AI Trading Bot (Emergency Distilled Retry)
id: run_ai_bot_distilled_retry
id: run_ai_bot_distilled_emergency_retry
if: ${{ always() && steps.install_base_dependencies.outcome == 'success' && !(github.event_name == 'workflow_dispatch' && inputs.run_in_lightning_studio) && ((github.event_name != 'workflow_dispatch') || (github.event_name == 'workflow_dispatch' && !inputs.disable_ai_trading)) && steps.run_ai_bot_distilled_local.outcome == 'failure' }}
continue-on-error: true
timeout-minutes: 60
Expand All @@ -551,7 +565,7 @@ jobs:
python main.py daily_job

- name: Send AI Failure Report
if: ${{ always() && !(github.event_name == 'workflow_dispatch' && inputs.run_in_lightning_studio) && ((github.event_name != 'workflow_dispatch') || (github.event_name == 'workflow_dispatch' && !inputs.disable_ai_trading)) && (((steps.plan_ai_runtime.outputs.runtime_mode == 'cerebrium_full' && steps.validate_cerebrium_config.outputs.has_inference_url == 'true') && (steps.warm_cerebrium_inference.outcome == 'failure' || steps.verify_cerebrium_predict.outcome == 'failure' || (steps.run_ai_bot_cerebrium.outcome == 'failure' && steps.run_ai_bot_cerebrium_retry.outcome != 'success')) && steps.run_ai_bot_distilled_local.outcome == 'failure' && steps.run_ai_bot_distilled_retry.outcome != 'success') || ((steps.plan_ai_runtime.outputs.runtime_mode == 'lightning_full') && (steps.launch_lightning_inference.outcome == 'failure' || steps.run_ai_bot_in_lightning_studio.outcome == 'failure') && steps.run_ai_bot_distilled_local.outcome == 'failure' && steps.run_ai_bot_distilled_retry.outcome != 'success') || ((steps.plan_ai_runtime.outputs.runtime_mode == 'distilled_local') && steps.run_ai_bot_distilled_local.outcome == 'failure' && steps.run_ai_bot_distilled_retry.outcome != 'success')) }}
if: ${{ always() && !(github.event_name == 'workflow_dispatch' && inputs.run_in_lightning_studio) && ((github.event_name != 'workflow_dispatch') || (github.event_name == 'workflow_dispatch' && !inputs.disable_ai_trading)) && (((steps.plan_ai_runtime.outputs.runtime_mode == 'cerebrium_full' && steps.validate_cerebrium_config.outputs.has_inference_url == 'true') && (steps.warm_cerebrium_inference.outcome == 'failure' || steps.verify_cerebrium_predict.outcome == 'failure' || (steps.run_ai_bot_cerebrium.outcome == 'failure' && steps.run_ai_bot_cerebrium_retry.outcome != 'success')) && steps.run_ai_bot_distilled_local.outcome == 'failure' && steps.run_ai_bot_distilled_emergency_retry.outcome != 'success') || ((steps.plan_ai_runtime.outputs.runtime_mode == 'lightning_full') && (steps.launch_lightning_inference.outcome == 'failure' || steps.run_ai_bot_in_lightning_studio.outcome == 'failure') && steps.run_ai_bot_distilled_local.outcome == 'failure' && steps.run_ai_bot_distilled_emergency_retry.outcome != 'success') || ((steps.plan_ai_runtime.outputs.runtime_mode == 'distilled_local') && steps.run_ai_bot_distilled_local.outcome == 'failure' && steps.run_ai_bot_distilled_emergency_retry.outcome != 'success')) }}
continue-on-error: true
env:
SMTP_SERVER: ${{ secrets.SMTP_SERVER }}
Expand All @@ -569,7 +583,7 @@ jobs:
RUN_AI_CEREBRIUM_OUTCOME: ${{ steps.run_ai_bot_cerebrium.outcome }}
RUN_AI_CEREBRIUM_RETRY_OUTCOME: ${{ steps.run_ai_bot_cerebrium_retry.outcome }}
RUN_AI_DISTILLED_OUTCOME: ${{ steps.run_ai_bot_distilled_local.outcome }}
RUN_AI_DISTILLED_RETRY_OUTCOME: ${{ steps.run_ai_bot_distilled_retry.outcome }}
RUN_AI_DISTILLED_RETRY_OUTCOME: ${{ steps.run_ai_bot_distilled_emergency_retry.outcome }}
run: |
source_step="Run AI Trading Bot"
detail="AI daily job failed before sending its report email. Run: ${RUN_URL}"
Expand Down Expand Up @@ -673,7 +687,7 @@ jobs:
RUN_AI_CEREBRIUM_RETRY_OUTCOME: ${{ steps.run_ai_bot_cerebrium_retry.outcome }}
RUN_AI_STUDIO_OUTCOME: ${{ steps.run_ai_bot_in_lightning_studio.outcome }}
RUN_AI_DISTILLED_OUTCOME: ${{ steps.run_ai_bot_distilled_local.outcome }}
RUN_AI_DISTILLED_RETRY_OUTCOME: ${{ steps.run_ai_bot_distilled_retry.outcome }}
RUN_AI_DISTILLED_RETRY_OUTCOME: ${{ steps.run_ai_bot_distilled_emergency_retry.outcome }}
run: |
core_ok="false"
ai_ok="false"
Expand Down Expand Up @@ -731,7 +745,7 @@ jobs:
RUN_AI_CEREBRIUM_OUTCOME: ${{ steps.run_ai_bot_cerebrium.outcome }}
RUN_AI_CEREBRIUM_RETRY_OUTCOME: ${{ steps.run_ai_bot_cerebrium_retry.outcome }}
RUN_AI_DISTILLED_OUTCOME: ${{ steps.run_ai_bot_distilled_local.outcome }}
RUN_AI_DISTILLED_RETRY_OUTCOME: ${{ steps.run_ai_bot_distilled_retry.outcome }}
RUN_AI_DISTILLED_RETRY_OUTCOME: ${{ steps.run_ai_bot_distilled_emergency_retry.outcome }}
run: |
rc=0
if [ "${BASE_DEPS_OUTCOME}" != "success" ]; then
Expand Down