feat: compact and other improvements by adamdotdevin · Pull Request #1 · anomalyco/opencode

adamdotdevin · 2025-05-02T20:24:33Z

No description provided.

## Summary This PR implements dual model support (main + turbo) for cost-optimized operations and adds model sorting functionality. ### Key Changes #### Dual Model Support - Added `turbo_model` and `turbo_cost_threshold` config options - New dual-pane model selector (Tab to switch panes) - Visual indicators: ⚡ (turbo), 🧠 (reasoning), 🔧 (tools) - Smart turbo model selection with fallback logic - Fixed Anthropic auth showing incorrect turbo status #### Model Sorting - Added `release_date` and `last_updated` fields to model schema - Press 'S' to cycle through sort modes: Name, Last Updated, Release Date - Stable multi-level sorting with consistent ordering - Helps discover newest models and track updates ### Impact Enables cost optimization for PRs anomalyco#269 (status verbs) and anomalyco#275 (window titles) to use configured turbo models instead of hardcoded ones. ### Demo https://github.com/user-attachments/assets/d076e840-d790-4e23-8cf7-a179282d1f0b

…ompaction feat: intelligent compaction with model-initiated trigger, handoff prompts, and persistent memory

- Add VoyageEmbeddingProvider for Voyage AI embeddings - Add MemoryStore with high-level store/search/list API - Configure Nebius cloud API for Qwen3-Embedding-8B (#1 on MTEB) - Fix LocalEmbeddingProvider to support both /v1/embeddings and /embeddings - Fix QdrantVectorStorage to set collection on existing collections Model: Qwen3-Embedding-8B (70.58 MTEB score, 99% zero-shot, 4096 dims) Provider: Nebius API (https://api.tokenfactory.nebius.com/v1) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

- Finding #1: re-sync active sessions after disposal by saving fullSyncedSessions before clear and calling result.session.sync() after successful bootstrap - Finding anomalyco#2: cap retries at 5 with exponential backoff (2s/4s/8s/16s/30s) and generation counter to cancel stale retries when newer disposal arrives - Finding anomalyco#3: move Instance.provide() inside while loop so each event stream reconnect iteration gets fresh context - Finding anomalyco#4: remove unconditional startEventStream(process.cwd()); add events RPC method; thread calls it only when not in external transport mode - Finding anomalyco#5: replace manual new Promise+setTimeout with sleep() from node:timers/promises - Finding anomalyco#6: reload() aborts current event stream and conditionally restarts it

…mmand-guard Fill documentation gaps identified by security review: - security.mdx: add Subprocess Isolation section (OPENCODE_SPAWN_SANDBOX, bwrap/unshare mechanism, what is and isn't sandboxed, how to enable); add Managed / Enterprise Config section (config precedence ladder, /etc/opencode/ as immutable security boundary, container usage, --dangerously-open bypass); add Read-Only Commands section (/review fully read-only, /learn AGENTS.md-only, blocklist details and limitations); add Instruction and Skill URLs note under Tool Execution - FORK-CHANGES.md: expand Feature anomalyco#1 to cover subprocess sandbox and command-guard; add util/fetch.ts, bash.ts, process.ts, flag.ts to key files table - SECURITY-ANALYSIS.md: add command-guard to Current Mitigations table - tool/AGENTS.md: add Command Guard section documenting assertReadOnlyShell, assertLearnPath, assertLearnTask, and the blocklist limitation Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

jeffreyschultz · 2026-03-19T21:26:22Z

Added --help support to guards command

jeffreyschultz · 2026-03-20T01:39:27Z

Successfully archived agent-ops-enhancement effort to .agents/planning/archive/agent-ops-enhancement/

Archive includes:

planning/ - Complete epic hierarchy with all features and user stories
work/ - Decision log and execution outputs

Index automatically updated with completion timestamp.

feat: add cloud infrastructure security skill

* feat(commands): add /context-budget optimizer command Adds a command that audits context window token consumption across agents, skills, rules, MCP servers, and CLAUDE.md files. Detects bloated agent descriptions, redundant components, MCP over-subscription, and CLAUDE.md bloat. Produces a prioritized report with specific token savings per optimization. Directly relevant to anomalyco#434 (agent descriptions too verbose, ~26k tokens causing performance warnings). * fix: address review feedback on context-budget command - Add $ARGUMENTS to enable --verbose flag passthrough - Fix MCP token estimate: 45 tools × ~500 tokens = ~22,500 (was ~2,200) - Fix heavy agents example: all 3 now exceed 200-line threshold - Fix description threshold: warning at >30 words, fail at >50 words - Add Step 4 instructions (was empty) - Fix audit cadence: "quarterly" → "regularly" + "monthly" consistently - Fix Output Format heading level under Step 4 - Replace "Antigravity" with generic "harness versions" - Recalculate total overhead to match corrected MCP numbers * fix: correct MCP tool count and savings percentage in sample output - Fix MCP tool count: table now shows 87 tools matching the issues section (was 45 in table vs 87 in issues) - Fix savings percentage: 5,100 / 66,400 = 7.7% (was 20.6%) - Recalculate total overhead and effective context to match * fix: correct sample output arithmetic - Fix total overhead: 66,400 → 66,100 to match component table sum (12,400 + 6,200 + 2,800 + 43,500 + 1,200 = 66,100) - Fix MCP savings: ~1,500 → ~27,500 tokens (55 tools × 500 tokens/tool) to match the per-tool formula defined in Step 1 - Reorder optimizations by savings (MCP removal is now anomalyco#1) - Fix total savings and percentage (31,100 / 66,100 = 47.0%) * fix: distinguish always-on vs on-demand agent overhead Agent descriptions are always loaded into Task tool routing context, but the full agent body is only loaded when invoked. The audit now measures both: description-only tokens as always-on overhead and full-file tokens as worst-case overhead. This resolves the contradiction between Step 1 (counting full files) and Tip 1 (saying only descriptions are loaded per session). * fix: simplify agent accounting and resolve inconsistencies - Revert to single agent overhead metric (full file tokens) — simpler and matches what the report actually displays - Add back 200-line threshold for heavy agents in Step 1 - Fix heavy agents action to match issue type (split/trim, not description-only) - Remove .agents/skills/ scan path (doesn't exist in ECC repo) - Consolidate description threshold to single 30-word check * fix: add model assumption and verbose mode activation - Step 4: assume 200K context window by default (Claude has no way to introspect its model at runtime) - Step 4: add explicit instruction to check $ARGUMENTS for --verbose flag and include additional output when present * fix: handle .agents/skills/ duplicates in skill scan Skills scan now checks .agents/skills/ for Codex harness copies and skips identical duplicates to avoid double-counting overhead. * fix: add savings estimate to heavy agents action for consistency * feat(skills): add context-budget backing skill, slim command to delegator * fix: use structurally detectable classification criteria instead of session frequency --------- Co-authored-by: vazidmansuri005 <vazidmansuri005@users.noreply.github.com>

* feat: add pending instinct TTL pruning and /prune command Pending instincts generated by the observer accumulate indefinitely with no cleanup mechanism. This adds lifecycle management: - `instinct-cli.py prune` — delete pending instincts older than 30 days (configurable via --max-age). Supports --dry-run and --quiet flags. - Enhanced `status` command — shows pending count, warns at 5+, highlights instincts expiring within 7 days. - `observer-loop.sh` — runs prune before each analysis cycle. - `/prune` slash command — user-facing command for manual pruning. Design rationale: council consensus (4/4) rejected auto-promote in favor of TTL-based garbage collection. Frequency of observation does not establish correctness. Unreviewed pending instincts auto-delete after 30 days; if the pattern is real, the observer will regenerate it. Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * fix: remove duplicate functions, broaden extension filter, fix prune output - Remove duplicate _collect_pending_dirs and _parse_created_date defs - Use ALLOWED_INSTINCT_EXTENSIONS (.md/.yaml/.yml) instead of .md-only - Track actually-deleted items separately from expired for accurate output - Update README.md and AGENTS.md command counts: 59 → 60 Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * fix: address Copilot and CodeRabbit review findings - Use is_dir() instead of exists() for pending path checks - Change > to >= for --max-age boundary (--max-age 0 now prunes all) - Use CLV2_PYTHON_CMD env var in observer-loop.sh prune call - Remove unused source_dupes variable - Remove extraneous f-string prefix on static string Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering> * fix: update AGENTS.md project structure command count 59 → 60 Co-Authored-By: Claude <noreply@anthropic.com> * fix: address cubic and coderabbit review findings - Fix status early return skipping pending instinct warnings (cubic anomalyco#1) - Exclude already-expired items from expiring-soon filter (cubic anomalyco#2) - Warn on unparseable pending instinct age instead of silent skip (cubic anomalyco#4) - Log prune failures to observer.log instead of silencing (cubic anomalyco#5) Co-Authored-By: Claude <noreply@anthropic.com> * fix: YAML single-quote unescaping, f-string cleanup, add /prune to README - Fix single-quoted YAML unescaping: use '' doubling (YAML spec) not backslash escaping which only applies to double-quoted strings (greptile P1) - Remove extraneous f-string prefix on static string (coderabbit) - Add /prune to README command catalog and file tree (cubic) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Happy <yesreply@happy.engineering>

chore: prepare elastic-ramen for open source release

adamdotdevin added 8 commits May 2, 2025 15:20

feat: better logs page

66e3852

feat: better diagnostic visuals in status bar

ce77826

feat: write to context.md by default

4f2671f

feat: compact command with auto-compact

8dd8cbf

fix: anthropic non-empty blocks

31b20b0

fix: bedrock context window

7c4a9a0

fix: diagnostics tool init

f9e8fb3

chore: cleanup and logging

2a16b94

adamdotdevin merged commit 0095832 into dev May 2, 2025

adamdotdevin deleted the compact branch May 2, 2025 20:24

VictorTaelin mentioned this pull request Aug 12, 2025

Is it possible to select the reasoning effort of GPT-5 in OpenCode? #1858

Closed

nikhilmaddirala mentioned this pull request Aug 18, 2025

[Feature Request] Add User Controls for Context Management #1990

Open

rekram1-node pushed a commit to drevantonder/opencode that referenced this pull request Aug 31, 2025

Simplify anomalyco#1

b0dc09b

rekram1-node mentioned this pull request Sep 14, 2025

fix: token counting visual bug #2587

Merged

ghost mentioned this pull request Oct 29, 2025

Paste bug #3542

Closed

This was referenced Nov 3, 2025

fix: Clipboard image paste fails with AI_DownloadError due to binary corruption and encoding mismatch #3816

Closed

fix: correct clipboard image encoding and binary handling #3817

Merged

opencode-agent bot mentioned this pull request Dec 4, 2025

core: refactor provider and model system #5033

Merged

ariane-emory mentioned this pull request Dec 7, 2025

fix: improve sidebar working directory colour contrast with modified files (resolves #5184 #5188

Merged

junjieit mentioned this pull request Dec 11, 2025

[object Object] error output when running opencode over SSH #5206

Open

nathabonfim59 mentioned this pull request Dec 24, 2025

Web UI fails to load - JS module blocked due to incorrect MIME type #6122

Closed

burgercrisis mentioned this pull request Dec 30, 2025

Bash Fork Issues - Investigation Included #6488

Open

lsj5031 mentioned this pull request Jan 7, 2026

Bug: Excessive Sandbox Acquisitions Causing Long Workflow Delays #7254

Closed

practicusai mentioned this pull request Jan 10, 2026

clipboard copy not works in remote SSH console. #2773

Closed

marcelloceschia mentioned this pull request Mar 7, 2026

feat(bedrock): add prompt caching support for custom ARNs and inferen… #16504

Open

6 tasks

hupapaliuli mentioned this pull request Mar 8, 2026

充值20美刀后，按照https://opencode.ai/zen的充值操作后，opencode仍旧报错：Free usage exceeded, add credits https://opencode.ai/zen [retrying in 17h 42m attempt #1] #16568

Closed

yehudacohen mentioned this pull request Mar 8, 2026

fix: default provider request timeout to 300000ms (5 minutes) #16599

Open

6 tasks

ZZjames mentioned this pull request Mar 12, 2026

终端ui会一直渲染 #17122

Open

Shiva108 mentioned this pull request Mar 13, 2026

Claude models return "Cannot read properties of undefined (reading 'input_tokens')" via OpenCode Zen API #17411

Open

dawidbednarczyk mentioned this pull request Mar 15, 2026

[Bug]: Session processor retries indefinitely with unbounded exponential backoff — no max retries or circuit breaker #17648

Open

jaybinks mentioned this pull request Mar 16, 2026

opencode - Github Enterprise - Too Many Requests: quota exceeded [retrying in ~2 weeks attempt #1] #17682

Open

atharvau mentioned this pull request Mar 23, 2026

fix(app): warn on oversized prompt attachments #18730

Draft

nabilfreeman mentioned this pull request Mar 23, 2026

Auto-compaction triggers at ~200k tokens instead of model's actual context window (1M) #15871

Open

rjmorales13 mentioned this pull request Mar 23, 2026

feat(plugin): add chat.model hook for dynamic model routing for token savings #18826

Closed

6 tasks

This was referenced Mar 24, 2026

feat: make rate limit retry message more user-friendly #19003

Closed

feat: make rate limit retry message more user-friendly #19004

Open

FlorianB-DE mentioned this pull request Mar 29, 2026

ollama launch opencode requires all previously used models #19907

Closed

fastdrumr mentioned this pull request Mar 31, 2026

[FEATURE]: Request GitHub Copilot auto model routing API access + chat.model plugin hook #20235

Open

1 task

bussnet mentioned this pull request Apr 1, 2026

Azure AI Claude rejects requests after tool abort: assistant message prefill not supported #19517

Open

Shaik121 mentioned this pull request Apr 1, 2026

feat(app): view archived sessions & unarchive #15250

Open

6 tasks

wahyuabrory mentioned this pull request Apr 1, 2026

[FEATURE]: Silent result collection for background tasks to avoid consuming LLM turns #20460

Open

1 task

aiml-gmlee mentioned this pull request Apr 3, 2026

feat(opencode): add Kiro provider #20491

Open

6 tasks

tbarron-xyz mentioned this pull request Apr 5, 2026

Concurrent sessions working on different repos interfer each other #4251

Open

divitkashyap mentioned this pull request Apr 7, 2026

fix(opencode): ensure standard PATH directories for bash tool on macOS #21347

Open

4 tasks

andreipromarketing-dev pushed a commit to andreipromarketing-dev/opencode that referenced this pull request Apr 7, 2026

Merge pull request anomalyco#1 from pangerlkr/pangerlkr-patch-1

5a26daf

feat: add cloud infrastructure security skill

flash1293 added a commit to flash1293/opencode that referenced this pull request Apr 9, 2026

Merge pull request anomalyco#1 from elastic/chore/remove-unused-packages

5f3a59b

chore: prepare elastic-ramen for open source release

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: compact and other improvements#1

feat: compact and other improvements#1
adamdotdevin merged 8 commits intodevfrom
compact

adamdotdevin commented May 2, 2025

Uh oh!

jeffreyschultz commented Mar 19, 2026

Uh oh!

jeffreyschultz commented Mar 20, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

adamdotdevin commented May 2, 2025

Uh oh!

jeffreyschultz commented Mar 19, 2026

Uh oh!

jeffreyschultz commented Mar 20, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants