feat(docker-git): make controller limits configurable by konard · Pull Request #263 · ProverCoderAI/docker-git

konard · 2026-05-09T17:34:51Z

Summary

Updates the controller resource cap implementation after PR feedback that the default should be 90% of available limits while remaining configurable above or below that value.

Resolve controller CPU/RAM defaults to 90% of host resources before invoking Docker Compose; direct compose fallback remains bounded at 0.9 CPU / 921m RAM.
Add host CLI flags: --controller-cpu, --controller-ram, --controller-pids for docker-git, plus ./ctl up --cpu/--ram/--pids aliases.
Keep resource parsing in a pure core module and isolate host resource detection/env mutation in the shell module.
Force local controller recreation when CLI or env resource intent is supplied, so an already-running matching controller does not ignore new caps.
Extend README, help text, changeset, and regression tests.

Mathematical Guarantees

Default theorem: for host h, default controller CPU is 0.9 * h.cpuCount and default RAM is floor(0.9 * h.totalMemoryMiB)m.
Compose invariant: Docker Compose receives concrete cpus, mem_limit, memswap_limit, and pids_limit values, never percentage RAM.
Override invariant: any controller CLI/env resource intent implies controller recreate before reuse.
Safety invariant: direct compose startup remains bounded even without the host resolver (0.9 CPU, 921m RAM/swap, 4096 PIDs).

Test Plan

bun install
bun run lint
bun run check
bun run lint:effect
bun x vitest run tests/docker-git/controller-resource-limits.test.ts (10 passed)
./ctl --help
DOCKER_GIT_CONTROLLER_CPUS=75% DOCKER_GIT_CONTROLLER_MEMORY=8g DOCKER_GIT_CONTROLLER_PIDS=8192 bun --cwd packages/app scripts/print-controller-resource-env.ts (4.5, 8g, 8192 on this 6-CPU host)
bun run test (session-sync 16 passed, app 321 passed, lib 183 passed)

Closes #260

Adding .gitkeep for PR creation (default mode). This file will be removed when the task is complete. Issue: ProverCoderAI#260

Add cpus, mem_limit, memswap_limit, and pids_limit defaults to the docker-git-api controller in docker-compose.yml and docker-compose.api.yml. Each value is parameterized via a DOCKER_GIT_CONTROLLER_* env var so operators can tune them. Per-project containers already resolve a default 30% CPU/RAM cap through resolveComposeResourceLimits, but the privileged controller that orchestrates them had no caps and could consume the entire host. This closes that gap so the whole system's resource footprint stays bounded. Closes ProverCoderAI#260

konard · 2026-05-09T17:45:54Z

Working session summary

PR is ready and out of draft.

Summary

The issue (Russian: "Make a limit on the consumption of the whole system's resources") was already partially addressed for per-project containers (default 30% CPU/RAM via PR #136). The remaining gap: the privileged docker-git-api controller had no caps and could itself consume the entire host.

Changes:

docker-compose.yml and docker-compose.api.yml: added cpus, mem_limit, memswap_limit, pids_limit to the api service, parameterized via DOCKER_GIT_CONTROLLER_CPUS (default 2.0), DOCKER_GIT_CONTROLLER_MEMORY (default 4g), DOCKER_GIT_CONTROLLER_PIDS (default 4096).
README.md: documented the two-layer resource-limit story.
packages/app/tests/docker-git/controller-resource-limits.test.ts: regression test that asserts both compose files contain all four caps.
.changeset/cap-controller-resources.md: triggers a patch release.

Verification: 6/6 new tests pass, 275/275 app tests pass, 166/166 lib tests pass, typecheck clean, lint:tests clean.

PR: #263

This summary was automatically extracted from the AI working session output.

konard · 2026-05-09T17:46:02Z

🤖 Solution Draft Log

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost: $4.840903

📊 Context and tokens usage:

Claude Opus 4.7:

100.6K / 1M (10%) input tokens, 20.6K / 128K (16%) output tokens

Total: (114 new + 104.1K cache writes + 7.2M cache reads) input tokens, 20.6K output tokens, $4.743435 cost

Claude Haiku 4.5:

36.0K / 200K (18%) input tokens, 2.8K / 64K (4%) output tokens

Total: (61 new + 36.0K cache writes + 386.5K cache reads) input tokens, 2.8K output tokens, $0.097468 cost

🤖 Models used:

Tool: Anthropic Claude Code
Requested: opus
Main model: Claude Opus 4.7 (claude-opus-4-7)
Additional models:
- Claude Haiku 4.5 (claude-haiku-4-5-20251001)

📎 Log file uploaded as Gist (2582KB)

View complete solution draft log

Now working session is ended, feel free to review and add any feedback on the solution draft.

konard · 2026-05-09T17:52:19Z

🔄 Auto-restart triggered (iteration 1)

Reason: CI failures detected

Starting new session to address the issues.

Auto-restart-until-mergeable mode is active. This run will stop after 5 restart iterations.

Replace node:fs/path/url imports and the as-const cast so the test passes the Effect-TS lint profile. Reads the compose files via FileSystem/Path services with a NodeContext layer instead of readFileSync + import.meta.url.

konard · 2026-05-09T18:04:09Z

Working session summary

All 15 CI checks pass (Build, Dist deps prune, all E2E suites, Lint, Lint Effect-TS, Snapshot, Test, Types).

Summary

The "Lint Effect-TS" CI check on PR #263 was failing because the new test file packages/app/tests/docker-git/controller-resource-limits.test.ts violated the strict Effect-TS lint profile in 6 places:

node:fs, node:path, node:url direct imports (forbidden — must use @effect/platform services)
A type cast (as const) outside src/core/axioms.ts

Fix (commit 1e651a3): Rewrote the test to read compose files via FileSystem.FileSystem and Path.Path services with a NodeContext.layer, used it.effect, and replaced the as const array with a typed ReadonlyArray<string>. All 6 tests still pass and the rest of the suite (275 tests) is unaffected.

PR: #263

This summary was automatically extracted from the AI working session output.

konard · 2026-05-09T18:04:17Z

🔄 Auto-restart-until-mergeable Log (iteration 1)

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost: $1.611414

📊 Context and tokens usage:

65.8K / 1M (7%) input tokens, 9.0K / 128K (7%) output tokens

Total: (56 new + 59.3K cache writes + 2.0M cache reads) input tokens, 9.0K output tokens, $1.611414 cost

🤖 Models used:

Tool: Anthropic Claude Code
Requested: opus
Model: Claude Opus 4.7 (claude-opus-4-7)

📎 Log file uploaded as Gist (3601KB)

View complete solution draft log

Now working session is ended, feel free to review and add any feedback on the solution draft.

konard · 2026-05-09T18:06:24Z

🔄 Auto-restart triggered (iteration 2)

Reason: Uncommitted changes detected

Starting new session to address the issues.

Auto-restart-until-mergeable mode is active. This run will stop after 5 restart iterations.

konard · 2026-05-09T18:07:20Z

Working session summary

Everything is in order. Final state:

Working tree: clean (removed transient ci-logs/ debug artifacts).
PR feat(docker-git): make controller limits configurable #263: open, not a draft, mergeable, 15/15 CI checks pass, mergeStateStatus CLEAN.
Branch: up-to-date with main (no rebase/merge needed).
Solution: 5 files address issue Сделать ограничение на потребление всёй системы ресурсов #260 — caps docker-git-api controller CPU/RAM/PIDs in both compose files, with env-tunable defaults, README docs, a regression test, and a changeset.

No further work needed; the PR is ready for review.

This summary was automatically extracted from the AI working session output.

konard · 2026-05-09T18:07:28Z

🔄 Auto-restart-until-mergeable Log (iteration 2)

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost: $0.380035

📊 Context and tokens usage:

41.5K / 1M (4%) input tokens, 2.2K / 128K (2%) output tokens

Total: (16 new + 35.0K cache writes + 209.6K cache reads) input tokens, 2.2K output tokens, $0.380036 cost

🤖 Models used:

Tool: Anthropic Claude Code
Requested: opus
Model: Claude Opus 4.7 (claude-opus-4-7)

📎 Log file uploaded as Gist (3905KB)

View complete solution draft log

Now working session is ended, feel free to review and add any feedback on the solution draft.

konard · 2026-05-09T18:09:49Z

✅ Ready to merge

This pull request is now ready to be merged:

All CI checks have passed
No merge conflicts
No pending changes

Monitored by hive-mind with --auto-restart-until-mergeable flag

skulidropek · 2026-05-12T09:39:17Z

Я думаю по дефолту он должен иметь возможность к 90% лимитов, но можно настраивать и больше и меньше с помощью cli параметров

konard · 2026-05-12T09:41:49Z

🤖 AI Work Session Started

Starting automated work session at 2026-05-12T09:41:46.224Z

The PR has been converted to draft mode while work is in progress.

This comment marks the beginning of an AI work session. Please wait for the session to finish, and provide your feedback.

# Conflicts: # packages/app/src/docker-git/cli/usage.ts

konard · 2026-05-12T10:59:20Z

Working session summary

Completed and pushed to PR #263: #263

Implemented the PR feedback: controller resources now default to 90% of host CPU/RAM, while remaining configurable via docker-git --controller-cpu/--controller-ram/--controller-pids and ./ctl up --cpu/--ram/--pids. The implementation keeps parsing/resolution in pure core code and host/env mutation in shell code.

Verification passed:

bun run lint
bun run check
bun run lint:effect
focused controller resource tests: 10 passed
full bun run test: session-sync 16, app 321, lib 183 passed
GitHub PR checks: all passing
PR is marked ready, merge state is CLEAN
Working tree is clean on issue-260-ab5543061ad7

Head commit is 328ea7b33a59ddc37ed4c972774880b6a12821b9.

This summary was automatically extracted from the AI working session output.

konard · 2026-05-12T10:59:36Z

🤖 Solution Draft Log

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost estimation:

Model: GPT-5.5
Provider: OpenAI
Public pricing estimate: $40.751227

📊 Context and tokens usage:

610.4K / 1.1M (58%) input tokens, 65.8K / 128K (51%) output tokens

Total: (610.4K + 31.7M cached) input tokens, 65.8K output tokens, $40.751227 cost

🤖 Models used:

Tool: OpenAI Codex
Requested: gpt-5.5
Model: GPT-5.5 (gpt-5.5)

📎 Log file uploaded as Repository (93239KB)

View complete solution draft log

Now working session is ended, feel free to review and add any feedback on the solution draft.

konard · 2026-05-12T11:02:00Z

✅ Ready to merge

This pull request is now ready to be merged:

All CI checks have passed
No merge conflicts
No pending changes

Monitored by hive-mind with --auto-restart-until-mergeable flag

konard added 2 commits May 9, 2026 17:34

Initial commit with task details

1327326

Adding .gitkeep for PR creation (default mode). This file will be removed when the task is complete. Issue: ProverCoderAI#260

konard changed the title ~~[WIP] Сделать ограничение на потребление всёй системы ресурсов~~ feat: cap controller container CPU, RAM, and PIDs May 9, 2026

konard marked this pull request as ready for review May 9, 2026 17:45

konard marked this pull request as draft May 12, 2026 09:41

konard added 2 commits May 12, 2026 10:43

feat(docker-git): make controller limits configurable

92c5c03

Merge remote-tracking branch 'upstream/main' into issue-260-ab5543061ad7

328ea7b

# Conflicts: # packages/app/src/docker-git/cli/usage.ts

konard changed the title ~~feat: cap controller container CPU, RAM, and PIDs~~ feat(docker-git): make controller limits configurable May 12, 2026

konard marked this pull request as ready for review May 12, 2026 10:51

skulidropek merged commit 66bd05a into ProverCoderAI:main May 13, 2026
15 checks passed

Conversation

konard commented May 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Mathematical Guarantees

Test Plan

Uh oh!

konard commented May 9, 2026

Working session summary

Summary

Uh oh!

konard commented May 9, 2026

🤖 Solution Draft Log

💰 Cost: $4.840903

📊 Context and tokens usage:

🤖 Models used:

📎 Log file uploaded as Gist (2582KB)

Uh oh!

konard commented May 9, 2026

🔄 Auto-restart triggered (iteration 1)

Uh oh!

konard commented May 9, 2026

Working session summary

Summary

Uh oh!

konard commented May 9, 2026

🔄 Auto-restart-until-mergeable Log (iteration 1)

💰 Cost: $1.611414

📊 Context and tokens usage:

🤖 Models used:

📎 Log file uploaded as Gist (3601KB)

Uh oh!

konard commented May 9, 2026

🔄 Auto-restart triggered (iteration 2)

Uh oh!

konard commented May 9, 2026

Working session summary

Uh oh!

konard commented May 9, 2026

🔄 Auto-restart-until-mergeable Log (iteration 2)

💰 Cost: $0.380035

📊 Context and tokens usage:

🤖 Models used:

📎 Log file uploaded as Gist (3905KB)

Uh oh!

konard commented May 9, 2026

✅ Ready to merge

Uh oh!

skulidropek commented May 12, 2026

Uh oh!

konard commented May 12, 2026

Uh oh!

konard commented May 12, 2026

Working session summary

Uh oh!

konard commented May 12, 2026

🤖 Solution Draft Log

💰 Cost estimation:

📊 Context and tokens usage:

🤖 Models used:

📎 Log file uploaded as Repository (93239KB)

Uh oh!

konard commented May 12, 2026

✅ Ready to merge

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

konard commented May 9, 2026 •

edited

Loading