Constant High Demand Warnings #40
Description
Not sure if this a Google issue or a Conductor issue but ever since I started using Conductor I've been struggling with endless "We are currently experiencing high demand. We apologize and appreciate your patience." warnings. If I choose the stop option i see the error:
✕ [API Error: Resource exhausted. Please try again later. Please refer to
https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.]
These are happening constantly and at unlikely times so I don't think the issue is genuine (or at least not always). Often I struggle to get more than one prompt done before I get the warning. /stats claims I have plenty of usage left.
I'm running on my Google account rather than API (as a death loop ate a huge amount of credits!). Sometimes re /auth ing my account clears the issue for a couple of prompts but then it stops again. Both gemini and conductor are up to date, context usage doesn't seem to be an issue (e.g. it happens a 99% free).
Observations & Recommendations:
-
Conductor doesn't handle this situation very well. Even when I can resume a session, Conductor seems to get confused. I've also seen similar behaviour when connections are lost due to dodgy wifi etc.
-
Is conductor simply exceeding rate limits? Is there any way to throttle Conductor, even something as simple as "Max prompts per minute" setting?
Below is a full log of a session. You'll see I don't get very far. There is a /stats at the bottom saying i have lots of usage left.
chris@Chriss-MBP artist_prompt_tool % gemini
███ █████████ ██████████ ██████ ██████ █████ ██████ █████ █████
░░░███ ███░░░░░███░░███░░░░░█░░██████ ██████ ░░███ ░░██████ ░░███ ░░███
░░░███ ███ ░░░ ░███ █ ░ ░███░█████░███ ░███ ░███░███ ░███ ░███
░░░███ ░███ ░██████ ░███░░███ ░███ ░███ ░███░░███░███ ░███
███░ ░███ █████ ░███░░█ ░███ ░░░ ░███ ░███ ░███ ░░██████ ░███
███░ ░░███ ░░███ ░███ ░ █ ░███ ░███ ░███ ░███ ░░█████ ░███
███░ ░░█████████ ██████████ █████ █████ █████ █████ ░░█████ █████
░░░ ░░░░░░░░░ ░░░░░░░░░░ ░░░░░ ░░░░░ ░░░░░ ░░░░░ ░░░░░ ░░░░░
Tips for getting started:
1. Ask questions, edit files, or run commands.
2. Be specific for the best results.
3. /help for more information.
> /conductor:status
✦ I will verify the project setup and the existence of the required Conductor files.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ Shell ls -F conductor/tracks.md conductor/tech-stack.md conductor/workflow.md conductor/product.md [current working direct… │
│ │
│ conductor/product.md conductor/tracks.md │
│ conductor/tech-stack.md conductor/workflow.md │
│ │
│ ✓ ReadFile conductor/tracks.md │
│ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ I will read the plan for the active track "Minor Updates & Fixes" to gather status details.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ ReadFile conductor/.../plan.md │
│ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ Project Status: Minor Updates & Fixes
Date: Thursday, 1 January 2026
Status: In Progress
Progress: 4/12 (33%)
Current Phase: Phase 2: Admin UI & Legacy Job Migration
Current Task: Backend - Refactor SYNC_DISCOVERY and other repo tasks to use ScheduledJob table.
Next Action: Frontend - Update Admin tooltab to default to 'Scheduler' view.
Blockers: None identified.
Statistics:
* Phases: 4
* Tasks: 12
* Completed: 4
* In Progress: 1
* Pending: 7
> /conductor:implement
✦ I will verify the Conductor environment setup by checking for the required files.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ Shell ls -F conductor/tech-stack.md conductor/workflow.md conductor/product.md conductor/tracks.md [current working direct… │
│ │
│ conductor/product.md conductor/tracks.md │
│ conductor/tech-stack.md conductor/workflow.md │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ I will read the conductor/tracks.md file to identify the available tracks and their statuses.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ ReadFile conductor/tracks.md │
│ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ No track name provided. Automatically selecting the next incomplete track: 'Minor Updates & Fixes'.
I will now read the track's plan, specification, and the project workflow to begin implementation.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ ReadFile conductor/.../plan.md │
│ │
│ │
│ ✓ ReadFile conductor/.../spec.md │
│ │
│ │
│ ✓ ReadFile conductor/workflow.md │
│ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ I am implementing the track 'Minor Updates & Fixes'.
The current task is "Backend - Refactor `SYNC_DISCOVERY` and other repo tasks to use `ScheduledJob` table."
I will now start the Red Phase by exploring the codebase to understand the existing implementation of SYNC_DISCOVERY and the
ScheduledJob system, so I can write appropriate failing tests.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ SearchText 'SYNC_DISCOVERY' within ./ │
│ │
│ Found 28 matches │
│ │
│ ✓ SearchText 'class ScheduledJob' within ./ │
│ │
│ Found 4 matches │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ I will read backend/database.py to inspect the ScheduledJob model and backend/tasks/sync_tasks.py to understand the current
SYNC_DISCOVERY task definition.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ ReadFile backend/database.py │
│ │
│ │
│ ✓ ReadFile backend/tasks/sync_tasks.py │
│ │
│ │
│ ✓ ReadFile backend/services/sync_service.py │
│ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ I will read the scheduler-related files and search for the tickSync endpoint to understand how SYNC_DISCOVERY is currently
triggered and scheduled.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ ReadFile backend/routers/scheduled_jobs.py │
│ │
│ │
│ ✓ ReadFile backend/services/job_scheduler.py │
│ │
│ │
│ ✓ SearchText 'tickSync' within ./ │
│ │
│ Found 13 matches │
│ │
│ ✓ SearchText '/tick' within ./ │
│ │
│ Found 6 matches │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ I will read backend/services/system_scheduler.py and backend/routers/orchestrator.py to understand the current "tick" behavior
and how scheduled jobs are processed.
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ ReadFile backend/.../system_scheduler.py │
│ │
│ │
│ ✓ ReadFile backend/routers/orchestrator.py │
│ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✕ [API Error: Resource exhausted. Please try again later. Please refer to
https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.]
> /stats
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ Session Stats │
│ │
│ Interaction Summary │
│ Session ID: 378eec3c-66ac-496b-a454-0ae8ea86dc09 │
│ Tool Calls: 19 ( ✓ 19 x 0 ) │
│ Success Rate: 100.0% │
│ User Agreement: 100.0% (19 reviewed) │
│ │
│ Performance │
│ Wall Time: 43m 25s │
│ Agent Active: 3m 51s │
│ » API Time: 3m 41s (95.8%) │
│ » Tool Time: 9.8s (4.2%) │
│ │
│ │
│ Model Usage Reqs Usage left │
│ ──────────────────────────────────────────────────────────── │
│ gemini-2.5-flash-lite 2 99.0% (Resets in 14m) │
│ gemini-3-pro-preview 13 59.2% (Resets in 14m) │
│ gemini-2.5-flash - 99.0% (Resets in 14m) │
│ gemini-2.5-pro - 59.2% (Resets in 14m) │
│ gemini-3-flash-preview - 100.0% (Resets in 23h 33m) │
│ │
│ Usage limits span all sessions and reset daily. │
│ /auth to upgrade or switch to API key. │
│ │
│ │
│ » Tip: For a full token breakdown, run `/stats model`. │
│ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
Using: 4 GEMINI.md files | 3 MCP servers
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ > Type your message or @path/to/file