Claude Evolution System
Self-improving AI development environment. Discovers new capabilities, evaluates them against a scoring framework, and integrates approved tools on cron.
- Autonomous capability discovery pipeline
- 5-criterion evaluation scoring framework
- Auto-integration of approved capabilities
- Multi-model orchestration (Claude, Codex, Gemini)
Activity Timeline
-
The contemporary-models check covered 2 providers with 0 updates; Gemini 4 Argon is already tracked in pending evaluations.
The version tracker stopped without writes because the CLI reports 2.1.309 while its state records 2.1.310. The script lacks a downgrade guard, and the reinstall is left to the owner.
-
v2.1.310 classified from release notes as one improvement bundle, with a comparison report, discovery file and Discord summary.
The bundle includes the Monitor tool on Bedrock, Vertex and Foundry, lower compaction memory in non-interactive sessions, a clearer MCP elicitation timeout and a Linux sandbox message naming the AppArmor user-namespace restriction. An autonomous executor run committed b08d512.
-
Claude Code 2.1.309 investigated from release notes only; report filed and Discord summary posted.
The 2.1.309 notes say sandboxed commands can no longer modify the mcp-config file and disabled MCP servers are not reconnected in print and SDK sessions.
-
Release notes for v2.1.301 to v2.1.308 reviewed; tracked version moved from 2.1.300 to 2.1.308.
Two discovery files cover v2.1.304's auto-mode classifier model setting and /auto-mode-setup, and v2.1.302's headless fork default, hook cap and retry-watchdog changes. No model launch fell in the range; v2.1.303 and v2.1.308 are fixes only.
-
3 commits: two tooling changes plus the 2026-10-21 autonomous executor run.
Commit fa7bb92 lists optimized prompts without stripping the internal `_latest`, and c210f99 parses skill frontmatter on real delimiter lines. Commit 8b6700d recorded the autonomous executor run for 2026-10-21.
-
Investigated Claude Code v2.1.299 to v2.1.300 from cached notes; versions state and capability registry updated.
Flagged that transcripts now record each request's system prompt, tools and parameters, and that updatedInput from PreToolUse and PermissionRequest hooks is now validated. A Discord summary was posted, and the autonomous executor run was committed as a9e15fc.
-
Compared Claude Code v2.1.299 with the v2.1.296 baseline and logged one new evaluation discovery.
Idle compaction and CLAUDE_CODE_DISABLE_FILE_MENTIONS were flagged for owner decision. A permissions probe showed the Bash grant checks compound commands as a whole.
-
bq-4939's count of 147 'unindexed' helpers was flagged as a script artefact; the index reports 113 helpers.
Two bq-4939 cache passes, a miss then a hit, both reported 55 stale helpers and 5,540 overlap pairs, none over 70 percent. An autonomous executor run was committed as 79882cf. The contemporary-models check covered 2 models and found no updates.
-
Two cache measurements showed a miss then a hit on the same key; commit abf0db2 records an autonomous executor run.
The helper-analysis BACKLOG item was ticked with a backup, and an index-count discrepancy was flagged. The executor commit's subject names Claude Code v2.1.224.
-
A cache miss created a maintenance item; the repeat run hit and created none.
The helper analysis also found 92 helpers missing an 'Updated' field. The autonomous executor's 2026-10-11 run was committed as 694e2e5.
-
The tracker covered 2.1.295 and 2.1.296, filed one pending evaluation and posted a Discord status.
versions.json now records 2.1.296 as current and 2.1.294 as previous, and the registry gained a 2.1.295 to 2.1.296 section after a backup. Flagged items are release-note claims, none reproduced, including a hook onFailure block that could make the MCP-pinning and secrets guards fail closed.
-
Release-notes-only investigation of Claude Code v2.1.292–2.1.294 and the Haiku 5.5 launch; nothing reproduced.
Prompt and agent hooks written as instructions no longer enforce what they should block in v2.1.294, and local stdio MCP servers now negotiate protocol 2026-07-28 by default. Haiku 5.5 costs $0.10/$0.50 per million tokens; its impact on Haiku-pinned agents is unverified.
-
Executor run applied registry corrections and processed a handoff cycle.
One commit recorded the completed executor run and its handoff cycle. The registry holds 26 agents and 74 skills, with 86 evaluations pending.
-
Version analysis of Claude Code v2.1.289 through v2.1.291 completed; v2.1.290 contained about 170 changes.
A model-roster check identified GPT-6.1 Sol (released 2026-09-29) and Gemini 4 Argon (released 2026-09-30). The autonomous executor's 2026-10-06 run was logged with an ultraplan-guidance removal task.
-
Model availability matrix updated for GPT-6.1 Sol, Gemini 4 Argon and Gemini 3.8 Flash.
Gemini 4 Argon was logged as a September 2026 frontier-reasoning model. A backwards 2.1.288 vs 2.1.289 version check caused a duplicate report; version-tracker.sh needs a semver comparison guard.
-
Model landscape updated; Claude Code v2.1.289 investigated, with 29 release items documented.
GPT-6.1 Sol (2026-09-29) was identified as the latest GPT model and Gemini 3.8 Flash as current, with Gemini 4 announced but unscheduled. In Claude Code v2.1.289, bash deny-rule sandbox hardening stood out as the key security improvement.
-
Version 2.1.288 was classified with one IMPROVEMENT discovery filed, and GPT-6.1 Sol was logged as a new October 2026 release.
The v2.1.288 investigation identified API-timeout resume, a SIGTERM handling fix, fail-closed hook behavior, and path-scoped Write/Edit rules. Versions 2.1.217–256 and 2.1.261–265 remain undocumented.
-
Decisions ledger shipped: 30 cards in 3 decks render 28 reviewable decisions.
The decisions come from 58 ledger rows covering July 26-27, and verdicts are written to an append-only file. Prior-art research on 40+ session-analysis tools found 3 with LLM-based semantic classification and 1 multi-vendor tool, but none combining both.
-
Kernel-stop fix for the /insights step staged and verified; autonomous executor processed backlog.
A kernel-stop fix for the weekly-insights /insights step was staged and verified. An autonomous executor run processed backlog items and updated registries.
-
Capability discovery classified 120 items for Claude Code v2.1.285; a card-batch freshness check found post-draft edits touching 20 of 31 items.
The discovery pass sorted the 120 items across feature categories and updated the Discord channel. The freshness check found four target files edited after drafting: CLAUDE.md, polaris-session, publication-review, and codex-goal.
-
Claude Sonnet 5.5 logged as the new default; bq-1462 rollback fix ready for handback.
A model-release check identified Claude Sonnet 5.5 (1M context) as the new default and found GPT-7 still unannounced. The bq-1462 rollback fix finished validation with fixture proofs and an Opus cross-check. A three-patch sol-writes-confinement SIGKILL fix passed isolated testing and awaits enactment.
-
Agents d4b and d3 completed approval-executor spec drafting, both simulation-validated.
Spec drafting finished with 16 registry landings and 11 workspace landings. Evolution-executor-fix-v3 was deployed with background review watchers and heartbeat ledger monitors under the warm-keeper doctrine.
-
A detector-rules analysis identified 9 patches for pane busy-state detection failures.
A commit addressed the CLI 2.1.283 escape-marker removal. A model audit documented GPT-6 Astra, GPT-Live-1 for real-time voice, GPT-6 Sol and Luna, and Google's Gemini 3.8 Flash.
-
Roster verification found GPT-6 Sol and Luna, released September 22.
The contemporary-models.json file was updated with the latest OpenAI releases. An autonomous executor run was logged at 06:30Z.
-
176-item changelog reviewed for new settings and security changes.
The analysis identified a new attribution:false setting and cron-layer enhancements. Security changes include rm -rf prompting in auto and bypass modes and --bg requiring workspace trust.
-
Version registry updated for v2.1.280 and Opus 5.5 launch ($4/$20 per MTok, 1M context).
6 discovery files created for new version. Release report generated. state/versions.json updated with history entry.
-
37/37 and 7/7 tests passing for bq-2235; dispatcher stale-row recirculation bug found.
Model release sweep confirmed GPT-6 Astra (Sept 3–4), GPT-Live-1 voice (Sept 10), Gemini 3.8 Flash/Live. 70 evaluations still pending in queue.
-
Daily executor completed; GPT-6 Astra, GPT-5.6 Sol, Gemini 3.8 Flash confirmed current. 26 agents, 71 skills, 70 pending evaluations.
Autonomous executor ran 2026-09-21 with execution log capture. Model freshness check confirmed GPT-6 Astra, GPT-5.6 Sol, and Gemini 3.8 Flash current. Registry: 26 agents, 71 skills, 70 pending evaluations.
-
Context window tuned from 131072 to 65536 tokens (OOM recovery). Court-residuals-wave-0919e: 11 escalation checks, 34-item test suite passing.
OOM recovery prompted the context window reduction. The court-residuals-wave-0919e commission completed with all 34 test suite items passing across 11 escalation checks.
-
11 court-residual checks passed; executor ran daily; 70 evaluations in backlog.
Autonomous executor logged its daily run. Backlog-recovery work moved 11 court-residual checks from unsatisfied to passing with findings archived.
-
11 escalation items cleared, 34/34 tests green; GPT-Live-1 GA date discrepancy found.
Wave 0918 processed 11 items through four test iterations. Model verification flagged a nine-day GA date discrepancy on GPT-Live-1 (listed 2026-09-01, actual 2026-09-10).
-
Backlog recovery: 11 checks passed, baseline re-frozen. GPT-Live-1 date corrected to Sept 10.
Court-residuals-wave-0919e: 11 checks passed with annotation fixes, test suite baseline re-frozen. Model verification session found GPT-Live-1 release date was logged as 2026-09-01; actual release was September 10.
-
Three blocking findings in v2.1.278 changelog; unsandboxed Bash execution path discovered in cron fallback.
ANTHROPIC_BASE_URL proxy broken in 275, TaskOutput removed in 277, skills/plugins auto-sync broken in 275. Evolution-daily cron fallback executes Bash via env -u CLAUDECODE when codex quota exhausted, bypassing disabled-Bash restrictions.
-
Investigation Runner wired to Discord #general with Pro/codex escalation; GPT-6 Astra and Gemini 3.8 Flash confirmed live.
Investigation Runner configured with WebFetch, Grep, Glob, Read, and optional Pro/codex-council escalation for Discord #general. Discovery policy documented prioritizing publication-grade sources. GPT-6 Astra (1.05M context) and Gemini 3.8 Flash confirmed current.
-
Gemini 3.8 Flash detected and promoted; status poller confirmed live.
Gemini 3.8 Flash (released Sept 2–3) was detected by model monitoring and promoted from the monitor list to active models. Status system investigation confirmed the 2026-08-12 poller fix is live; cron references remain stale.
-
Agent census: 35 catalogued, name collision found; 15 rationalization findings staged.
35 agent definitions catalogued; workspace codex-researcher found to shadow global version (critical collision). 15 rationalization findings (2 P1, 6 P2, 7 P3). Weekly-insights ran zero novel findings — duplicate digest from 3 prior runs.
-
Model tracker updated with Qwen3.8 and SenseNova U1.5 Lite; self-observation tab shipped.
LFM25 registry reflects latest open-weight entries. Self-observation UI (1,116 lines) completed with post-gate bugfixes. Sol-cutover remediation ongoing. 55 evals pending.
-
Daily heartbeat recorded; 55 evaluations pending in review queue.
Evolution pipeline degraded but stable. Backlog at normal steady-state size.
-
CLAUDE.md trimmed 28% (12,598→9,038 chars); v2.1.235 verified current.
Burn-guard sessions removed 4 stale facts across 19 skills. No new GA model releases. 55 pending evaluations tracked across the system.
-
Model reference table verified; Investigation Runner framework specified.
GPT-5.6 family and Gemini 3.6 Flash GA dates and pricing confirmed against live vendor docs. Discord monitoring and Brave/Exa/Pro escalation routing specified as an Investigation Runner agent framework — not yet deployed.
-
Heartbeat job templated; bq-058 security fix verified; agent specs drafted.
Daily capability discovery heartbeat job templated with Phase 1 sources defined. GPT Max synthesis bypass fix confirmed with 22/0 contract tests. Investigation Runner and Herald agent specs drafted for Discord topic processing and backlog surfacing.
-
54 pending evaluations queued; 27 agents active; idle flag raised on backlog.
Capability discovery pipeline has 54 items waiting without processing across 5 active sessions. No commits. Agent roster at 27 active with 71 registered skills.
-
Cron health: completion stamps built, 2 stuck reports cleared, 34 false alerts suppressed.
M7 completion-stamp mechanism tracks report status without production ledger writes. OAuth-orphaned reports cleared. Night-shift-sentinel alert classifier updated. Templated renderer copy discovery revises distinct session load estimate to ~130/day.
-
Cordis investigation: identity primitive confirmed, five defects traced to one root cause.
61 KB report produced. tmux 3.4 libsystemd scopes give verified 1:1 pane identity (36/36). Root cause: identity derived post-acquisition rather than at mint-time. Zombie session bg-c-bq-041 — 42 hours past TTL, 18 orphaned processes — cited as primary evidence.
-
6 pre-publish security findings surfaced; 4 commits enforcing gate behaviors.
Write-hook fail-closed, preflight refusal honesty, and private-checkout wording tightened. Two P1 findings (write-hook fail-open, owner-interest gate) and four additional P2s under active remediation; 52 evaluations pending.
-
Burn-week session running; 51 evaluations pending; grok-build flag targeted.
Autonomous executor run logged. Five ordered burn tasks initiated including grok-build flag removal and commission-orphan requeue. Infrastructure sitting at 51 pending evaluations, 27 agents, 71 skills on Claude Code v2.1.228.
-
NE-1 and NE-4 calibration experiments frozen; overthinking research commission open.
30-cell Fable ladder executed and manually audited, converging on 10 confirmed defects. Reasoning-effort research comparing Fable, Opus 5, and Sol 5.6 commissioned on inverse-scaling patterns. Evaluation backlog steady at 51 pending items.
-
Sweep-card rewritten to plain-language output; interview-mode UI approved.
v2.1.226 current, 50 evaluations pending. Sweep-card now produces narrative output rather than structured dumps. Two investigations queued: queue-burn drain-rate analysis and row-343 deep-dive with concrete options.
-
Executor run log committed; Claude Code version check initiated (8-version delta).
Commit 95edb13 records autonomous orchestrator activity for the day. Version audit covers 2.1.217–2.1.224 range since baseline 2.1.216.
-
Semantic classification layer for nightly cron jobs went live at 93.1%/86.2% accuracy.
Hybrid GPT-5.6 Luna approach activated for closure-verify and silence-sweep paths; all misclassifications conservative-direction. False-claim audit corrected post 067. Dispatch bug identified: 18 of 146 closed items remain dispatchable.