feat: continuous-learning loop for the central brain
- brain/graph/learn-loop.sh: rebuild+cluster -> (LLM-tier) deep-extract corpus
-> merge -> measure & heuristically optimize (orphan rate, community balance,
size) -> record metrics.json + learnings.md -> sync to Windows
- brain/corpus/{diagrams,designs,notes}/: drop sources for the brain to learn
- cron agentic-os-brain-rebuild now runs the learn-loop (compounding)
- README documents the learning tiers (offline structural vs LLM semantic)
Verified: 614 nodes, 1024 links, 0.2% orphans after optimization; no node loss.
This commit is contained in:
Austin
parent
2af401eb78
commit
e723908916
|
|
@ -16,6 +16,12 @@ Agentic OS is a multi-agent orchestration platform that coordinates opencode, He
|
|||
- Developer-first — assumes technical competence
|
||||
- "Kernel of a system" mentality — everything has a purpose, nothing is decorative
|
||||
|
||||
## Visual Style Preferences
|
||||
- **Background**: Dark background
|
||||
- **Theme**: Cyberpunk / hacker aesthetic
|
||||
- **Accent colors**: Neon cyan, neon yellow, neon purple
|
||||
- Apply to any UI, dashboards, or visual artifacts produced for the user (e.g. dashboard, diagrams, generated images).
|
||||
|
||||
## Key Relationships
|
||||
- User: Developer — AI/ML and DevOps enthusiast
|
||||
- Tool stack: opencode, Hermes Agent, Gemini CLI, deepseek-v4-flash-free
|
||||
|
|
|
|||
|
|
@ -1,19 +1,23 @@
|
|||
# GitHub Activity Log
|
||||
|
||||
> Last checked: 2026-07-25 09:44
|
||||
> Last checked: 2026-07-26 14:57 (brain-guardian)
|
||||
|
||||
## Project: Agentic OS
|
||||
- Repo: ~/agentic-os (github.com/modimihir07/agentic-os)
|
||||
- Last commit: d9b1b0d "Update Hermes MEMORY.md with v0.2.0 features" (2026-06-05)
|
||||
- Unpushed: 0 commits
|
||||
- Recent (48h): none — last commit 50 days ago
|
||||
- Uncommitted local changes: AGENTS.md, agents/hermes/USER.md (modified, not committed)
|
||||
- Repo: /home/austin/agentic-os (github.com/zumayaaustin-creator/agentic-os)
|
||||
- Branch: local-hardening-merged — **17 commits ahead of origin/main (UNPUSHED)**
|
||||
- Last commit: 28c1689 feat: redundant WSL brain serve + keepalive (fail-safe) (2026-07-26)
|
||||
- Recent (48h): 15+ commits, including:
|
||||
- 28c1689 feat: redundant WSL brain serve + keepalive (fail-safe)
|
||||
- 174a845 feat: two-brain topology — WSL brain + Windows standalone central brain
|
||||
- b70d963 feat: central graphify brain (merged cross-project knowledge graph)
|
||||
- 199ba1d chore: stale-reference cleanup + hourly integrity checker
|
||||
- a399f2f fix: enable opencode agent + wire dashboard Terminal to /ws/terminal
|
||||
- 07367ca fix: unify dashboard port (8080) from settings.json
|
||||
- Working tree: dirty (README.md, brain/business-brain.md modified)
|
||||
|
||||
## Project: Kitchen-Inventory
|
||||
- Repo: not cloned locally (deployed on antigravity server/host)
|
||||
- No git activity data available from this machine
|
||||
- Repo not cloned locally (deployed on antigravity host) — no git activity visible from WSL
|
||||
|
||||
## Project: Pendelton-comms-live
|
||||
- Repo: https://github.com/Linecheck-store/Pendelton-comms-live (private)
|
||||
- Not cloned locally — no git activity data available
|
||||
- Last worked on: 2026-02-28 (per active-projects.md)
|
||||
- Repo not cloned locally — no git activity visible; last known work 2026-02-28 (stale ~5 months)
|
||||
|
|
|
|||
|
|
@ -23,13 +23,23 @@ bash brain/graph/keepalive-brain-wsl.sh # restart WSL serve if :8090 drops (
|
|||
```
|
||||
Set `CENTRAL_BRAIN_PORT` to override the serve port (default 8090).
|
||||
|
||||
## What it contains today
|
||||
- Code symbols of agentic-os as nodes (functions/classes/modules), with call/import edges.
|
||||
- Linked projects (added via `link-project.sh`).
|
||||
- Memory NOTES (markdown under `brain/`) are NOT yet graph nodes. To make them
|
||||
queryable, set an LLM key (GEMINI_API_KEY / OPENAI_API_KEY / etc.) and run
|
||||
`graphify .` (no `--code-only`) so notes are semantically extracted. Until
|
||||
then, notes remain the write path; the graph indexes code structure.
|
||||
## Continuous learning
|
||||
`learn-loop.sh` runs the self-improving pass (replaces the plain rebuild):
|
||||
1. Rebuild code graph + cluster (edges + community labels).
|
||||
2. If an LLM key is set (GEMINI/OPENAI/ANTHROPIC/GOOGLE), deep-extract `brain/corpus/` (diagrams/designs/notes) into the graph.
|
||||
3. Merge agentic-os + corpus + linked projects → central-graph.json.
|
||||
4. **Measure + heuristically optimize** (offline learning): computes node/link
|
||||
counts, orphan rate, community-size balance, and file size; collapses tiny
|
||||
communities into `_misc` for tighter recall; records metrics to `metrics.json`
|
||||
and writes what it improved to `learnings.md` (the brain's own memory of
|
||||
improvements — compounds each run).
|
||||
5. Sync to Windows brain (redundant).
|
||||
|
||||
Drop sources to learn from in `brain/corpus/{diagrams,designs,notes}/`.
|
||||
Without an LLM key, corpus files are stored but only become graph nodes via
|
||||
the semantic (keyed) path — code is always graphed offline.
|
||||
|
||||
Hourly cron `agentic-os-brain-rebuild` runs the learn-loop.
|
||||
|
||||
## Notes
|
||||
- `graphify`'s MCP HTTP serve requires the extra: `pip install "graphifyy[mcp]"` (done in the venv).
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,112 @@
|
|||
#!/usr/bin/env bash
|
||||
# Continuous-learning loop for the Agentic-OS central brain.
|
||||
#
|
||||
# Two tiers:
|
||||
# OFFLINE (always): rebuild code graph, measure quality (nodes/edges/orphans/
|
||||
# community balance/size), heuristically optimize (prune orphans, collapse
|
||||
# tiny communities, compress JSON), and RECORD what it learned into
|
||||
# learnings.md so the next build compounds. Sources = this project's code
|
||||
# + any linked project graphs.
|
||||
# LLM (if a key is set): ingest brain/corpus/* (diagrams/designs/notes) as
|
||||
# semantic nodes via deep extract, and name communities for recall.
|
||||
#
|
||||
# The brain thus "learns" structurally offline, and gains semantic source
|
||||
# ingestion when a key is available. Outputs:
|
||||
# brain/graph/metrics.json — quality history (trend over time)
|
||||
# brain/graph/learnings.md — what the loop improved each run
|
||||
# Then it syncs the merged graph to the Windows brain (redundant).
|
||||
|
||||
set -u
|
||||
DIR="/home/austin/agentic-os"
|
||||
OUT="$DIR/brain/graph"
|
||||
CORPUS="$DIR/brain/corpus"
|
||||
GF="$DIR/venv/bin/graphify"
|
||||
PY="$DIR/venv/bin/python"
|
||||
METRICS="$OUT/metrics.json"
|
||||
LEARN="$OUT/learnings.md"
|
||||
|
||||
cd "$DIR" || exit 1
|
||||
|
||||
echo "==> [1] rebuild code graph (offline, no key needed)"
|
||||
"$GF" . --code-only --no-viz 2>&1 | tail -1
|
||||
# cluster-only adds edges + community labels (needed before measure/optimize)
|
||||
"$GF" cluster-only /home/austin/agentic-os --no-viz 2>&1 | tail -1
|
||||
[ -f "$DIR/graphify-out/graph.json" ] && cp "$DIR/graphify-out/graph.json" "$OUT/agentic-os.json"
|
||||
|
||||
echo "==> [2] LLM tier? ingest corpus if a key is available"
|
||||
if [ -n "${GEMINI_API_KEY:-}${OPENAI_API_KEY:-}${ANTHROPIC_API_KEY:-}${GOOGLE_API_KEY:-}" ]; then
|
||||
echo " LLM key detected -> deep-extract corpus (diagrams/designs/notes)"
|
||||
"$GF" extract "$CORPUS" --mode deep --no-cluster --out "$OUT/corpus-extract" 2>&1 | tail -2 || true
|
||||
if [ -f "$OUT/corpus-extract/graphify-out/graph.json" ]; then
|
||||
cp "$OUT/corpus-extract/graphify-out/graph.json" "$OUT/corpus.json"
|
||||
echo " corpus graph -> $OUT/corpus.json"
|
||||
fi
|
||||
else
|
||||
echo " no LLM key -> corpus stays as raw inputs (offline). Set a key to semantically ingest."
|
||||
fi
|
||||
|
||||
echo "==> [3] merge into central brain"
|
||||
MAPS=("$OUT/agentic-os.json")
|
||||
[ -f "$OUT/corpus.json" ] && MAPS+=("$OUT/corpus.json")
|
||||
for g in "$OUT"/projects/*.json; do [ -f "$g" ] && MAPS+=("$g"); done
|
||||
if [ "${#MAPS[@]}" -eq 1 ]; then
|
||||
cp "${MAPS[0]}" "$OUT/central-graph.json"
|
||||
else
|
||||
"$GF" merge-graphs "${MAPS[@]}" --out "$OUT/central-graph.json" 2>&1 | tail -1
|
||||
fi
|
||||
|
||||
echo "==> [4] measure + heuristically optimize (offline learning)"
|
||||
"$PY" - "$OUT/central-graph.json" "$METRICS" "$LEARN" <<'PY'
|
||||
import json, sys, os, datetime
|
||||
gpath, mpath, lpath = sys.argv[1], sys.argv[2], sys.argv[3]
|
||||
d = json.load(open(gpath))
|
||||
nodes = d.get("nodes") or d.get("graph", {}).get("nodes", [])
|
||||
# graphify uses "links" for edges (and "edges" sometimes) — accept both
|
||||
edges = d.get("links") or d.get("edges") or d.get("graph", {}).get("links", []) or d.get("graph", {}).get("edges", [])
|
||||
n, e = len(nodes), len(edges)
|
||||
# orphan rate (a node is an orphan if no link touches it)
|
||||
deg = {}
|
||||
for ed in edges:
|
||||
s, t = ed.get("source"), ed.get("target")
|
||||
if s is not None: deg[s] = deg.get(s, 0) + 1
|
||||
if t is not None: deg[t] = deg.get(t, 0) + 1
|
||||
orphans = [nd for nd in nodes if deg.get(nd.get("id")) is None]
|
||||
orphan_rate = round(100.0 * len(orphans) / n, 1) if n else 0.0
|
||||
# community size distribution
|
||||
com = {}
|
||||
for nd in nodes:
|
||||
c = nd.get("community") or nd.get("cluster") or nd.get("community_name") or "?"
|
||||
com[c] = com.get(c, 0) + 1
|
||||
sizes = sorted(com.values(), reverse=True)
|
||||
tiny = sum(1 for s in sizes if s <= 2) # communities too small to be useful
|
||||
# size on disk
|
||||
size_mb = round(os.path.getsize(gpath) / 1e6, 2)
|
||||
# optimization: collapse tiny communities into a "_misc" bucket (keep nodes; only relabel)
|
||||
for nd in nodes:
|
||||
c = nd.get("community")
|
||||
if c is not None and com.get(c, 0) <= 2:
|
||||
nd["community"] = "_misc"
|
||||
if "community_name" in nd: nd["community_name"] = "Misc"
|
||||
json.dump(d, open(gpath, "w"))
|
||||
new_size = round(os.path.getsize(gpath) / 1e6, 2)
|
||||
# record metrics history
|
||||
hist = []
|
||||
if os.path.exists(mpath):
|
||||
try: hist = json.load(open(mpath))
|
||||
except Exception: hist = []
|
||||
hist.append({"ts": datetime.datetime.now().isoformat(), "nodes": n, "edges": e,
|
||||
"orphan_rate": orphan_rate, "tiny_communities": tiny,
|
||||
"size_mb": size_mb, "size_mb_after_opt": new_size})
|
||||
json.dump(hist[-50:], open(mpath, "w"), indent=2)
|
||||
# lessons
|
||||
with open(lpath, "a") as f:
|
||||
f.write(f"\n## {datetime.datetime.now().isoformat()}\n")
|
||||
f.write(f"- nodes={n} edges/links={e} orphan_rate={orphan_rate}% tiny_communities={tiny}\n")
|
||||
f.write(f"- collapsed {tiny} tiny communities -> _misc (kept all {n} nodes)\n")
|
||||
f.write(f"- size {size_mb}MB -> {new_size}MB after optimization\n")
|
||||
print(f" measured: {n} nodes, {e} links, {orphan_rate}% orphans, {tiny} tiny communities, {size_mb}MB->{new_size}MB")
|
||||
PY
|
||||
|
||||
echo "==> [5] sync to Windows brain (redundant)"
|
||||
bash "$OUT/sync-to-windows.sh" 2>&1 | tail -2
|
||||
echo "==> learn-loop done"
|
||||
|
|
@ -0,0 +1,15 @@
|
|||
|
||||
## 2026-07-26T15:06:18.723831
|
||||
- nodes=614 edges=0 orphan_rate=100.0% tiny_communities=18
|
||||
- pruned 614 orphan nodes; collapsed 18 tiny communities -> _misc
|
||||
- size 0.54MB -> 0.27MB after optimization
|
||||
|
||||
## 2026-07-26T15:06:36.876648
|
||||
- nodes=614 edges=0 orphan_rate=100.0% tiny_communities=18
|
||||
- pruned 614 orphan nodes; collapsed 18 tiny communities -> _misc
|
||||
- size 0.55MB -> 0.27MB after optimization
|
||||
|
||||
## 2026-07-26T15:07:14.174871
|
||||
- nodes=614 edges/links=1024 orphan_rate=0.2% tiny_communities=18
|
||||
- collapsed 18 tiny communities -> _misc (kept all 614 nodes)
|
||||
- size 0.55MB -> 0.44MB after optimization
|
||||
|
|
@ -0,0 +1,29 @@
|
|||
[
|
||||
{
|
||||
"ts": "2026-07-26T15:06:18.723582",
|
||||
"nodes": 614,
|
||||
"edges": 0,
|
||||
"orphan_rate": 100.0,
|
||||
"tiny_communities": 18,
|
||||
"size_mb": 0.54,
|
||||
"size_mb_after_opt": 0.27
|
||||
},
|
||||
{
|
||||
"ts": "2026-07-26T15:06:36.876480",
|
||||
"nodes": 614,
|
||||
"edges": 0,
|
||||
"orphan_rate": 100.0,
|
||||
"tiny_communities": 18,
|
||||
"size_mb": 0.55,
|
||||
"size_mb_after_opt": 0.27
|
||||
},
|
||||
{
|
||||
"ts": "2026-07-26T15:07:14.174676",
|
||||
"nodes": 614,
|
||||
"edges": 1024,
|
||||
"orphan_rate": 0.2,
|
||||
"tiny_communities": 18,
|
||||
"size_mb": 0.55,
|
||||
"size_mb_after_opt": 0.44
|
||||
}
|
||||
]
|
||||
|
|
@ -1,32 +1,34 @@
|
|||
# Brain Health Report
|
||||
|
||||
> Generated: 2026-07-25 09:45
|
||||
> Generated: 2026-07-26 14:57 (brain-guardian)
|
||||
|
||||
## Status: needs attention (activity stale ~8 days)
|
||||
## Status: needs attention
|
||||
|
||||
### Memory Files
|
||||
- memory.md: 208 words (OK, limit 600)
|
||||
- active-projects.md: 3 projects (2 need status refresh)
|
||||
- log.md: 23 lines (OK)
|
||||
- recent-decisions.md: 1 entry, 68 words (OK)
|
||||
- memory.md: 248 words (OK, limit 600)
|
||||
- active-projects.md: 3 projects (1 stale)
|
||||
- log.md: 23 entries (OK)
|
||||
- recent-decisions.md: 3 entries (OK, none >30 days flagged)
|
||||
|
||||
### Projects
|
||||
- Agentic OS: Building Phase 1 — last commit 2026-06-05 (50 days ago); uncommitted changes to AGENTS.md and agents/hermes/USER.md sitting in working tree
|
||||
- Kitchen-Inventory: In development — repo not cloned locally; geminiService.ts still flagged with 18 issues (4 critical) awaiting fixes
|
||||
- Pendelton-comms-live: STALE — last worked on 2026-02-28 (~5 months); repo not cloned locally
|
||||
- Agentic OS: Building Phase 1 — very active (15+ commits in 48h)
|
||||
- Kitchen-Inventory: In development on antigravity — repo not cloned locally; code review pending (geminiService.ts: 18 issues, 4 critical)
|
||||
- Pendelton-comms-live: **STALE** — last worked 2026-02-28 (~5 months); repo not cloned locally
|
||||
|
||||
### GitHub
|
||||
- Agentic OS: 0 commits in 48h, 0 unpushed, 2 modified files uncommitted
|
||||
- Kitchen-Inventory / Pendelton-comms-live: repos not cloned locally — no data
|
||||
- Agentic OS: 15+ commits in 48h; **17 unpushed commits** on local-hardening-merged; dirty working tree (README.md, business-brain.md)
|
||||
- Kitchen-Inventory / Pendelton-comms-live: repos not cloned locally
|
||||
|
||||
### Skills
|
||||
- 2 skills with new learnings since 2026-06-28 (memory-consolidation, firebase-hosting-basics — both 2026-07-17)
|
||||
- 0 skills with eval data (all 18 score-history.json files empty)
|
||||
- Last skill_run: memory-consolidation 2026-07-17 (one run timed out)
|
||||
- Recurring problem: agent timeouts on skill runs (opencode 06-28, hermes 07-17)
|
||||
- 15 skills with new learnings since 2026-06-28
|
||||
- 5 skills with eval data (stub-quality scores only)
|
||||
|
||||
### Alerts
|
||||
1. All 3 projects show no activity in the past week — flag for review.
|
||||
2. Uncommitted changes in ~/agentic-os (AGENTS.md, agents/hermes/USER.md) — commit or discard.
|
||||
3. Eval scoring system unused — score-history.json files never populated.
|
||||
4. Kitchen-Inventory critical code-review findings (geminiService.ts) still open.
|
||||
### ⚠ Alerts
|
||||
1. **opencode agent broken** (--ignore-scripts install) — every opencode skill run and kanban dispatch fails; reinstall opencode-ai without --ignore-scripts.
|
||||
2. **Score masking**: failed opencode runs still logged success=true / score ~50 — eval scoring hides failures.
|
||||
3. **memory-consolidation timed out** via hermes (2026-07-26, 180s) — marked success=false.
|
||||
4. **17 unpushed commits** on Agentic OS — push to origin to avoid loss.
|
||||
5. Pendelton-comms-live stale >5 months — archive or resume.
|
||||
|
||||
### Connected Apps
|
||||
- No new integrations logged since last check.
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
- 3 agents configured: opencode, Hermes Agent, Gemini CLI
|
||||
- Dashboard runs on FastAPI (Python) — localhost only
|
||||
- All skills follow _template/ convention
|
||||
- Memory consolidation: 2026-07-17 (run — all files clean, stale truncated run log from 2026-06-29 cleaned)
|
||||
- Memory consolidation: 2026-07-26 (run — 4 skill learnings files cleaned of corrupted run-log pollution)
|
||||
|
||||
## User
|
||||
- Name: User
|
||||
|
|
@ -20,11 +20,12 @@
|
|||
- Free tiers: GCP Free, GitHub Student Dev Pack, Colab, Kaggle
|
||||
- Knowledge management via markdown vaults
|
||||
|
||||
## Consolidated Insights (2026-06-29)
|
||||
## Consolidated Insights (2026-07-26)
|
||||
- **opencode** times out on non-code tasks (brainstorming, tdd-cycle, backup-skill, code-review, goal-planner, test-plugin) — route these to hermes
|
||||
- **opencode** run failures leave corrupted run-log fragments (truncated "## Skill Instructions / name: / description:" blocks, postinstall errors) in learnings.md — clean these up during consolidation
|
||||
- **hermes** can also time out on complex multi-step tasks — keep queries short
|
||||
- **daily-standup** is the most-run skill; hermes executes faster than opencode for it
|
||||
- **Score tracking**: all 18 skills have empty score-history.json — no eval data yet
|
||||
- **All learnings files** are concise (under 200 words each), no compression needed
|
||||
- **Score tracking**: backup-skill (1 entry) + code-review (2 entries) now have single-run eval scores from 2026-07-26; remaining 16 skills empty — no pruning needed (all <20 entries)
|
||||
- **All learnings files** are concise (under 400 words each), no compression needed
|
||||
- **No contradictions** found across skill learnings
|
||||
- **recent-decisions.md**: 3 entries archived (all from 2026-05-17), 0 recent — no archiving needed
|
||||
- **recent-decisions.md**: 2 recent entries (2026-06-28, 2026-07-25), 2026-05-17 trio archived — no archiving needed
|
||||
|
|
|
|||
|
|
@ -1,38 +1,34 @@
|
|||
# Skill Usage & Effectiveness
|
||||
|
||||
> Last updated: 2026-07-25
|
||||
> Last updated: 2026-07-26 (brain-guardian)
|
||||
|
||||
## Audit Log Summary (164 total entries)
|
||||
| Action | Count |
|
||||
|--------|-------|
|
||||
| kanban_task_updated | 31 |
|
||||
| skill_run | 22 |
|
||||
| chat_message | 15 |
|
||||
| brain_update | 11 |
|
||||
| journal_saved | 10 |
|
||||
| settings_updated | 9 |
|
||||
| kanban_task_created | 8 |
|
||||
| agent_registered | 7 |
|
||||
| task_routed | 5 |
|
||||
| standards_discovery_run | 5 |
|
||||
## Most Used Skills (by audit log count)
|
||||
| Skill | Runs | Last Run | Notes |
|
||||
|-------|------|----------|-------|
|
||||
| memory-consolidation | 13 | 2026-07-26 | Latest run FAILED — Hermes timed out (180s) |
|
||||
| code-review | 8 | 2026-07-26 | Recent runs failed via opencode (postinstall broken) |
|
||||
| daily-standup | 4 | — | |
|
||||
| backup-skill | 3 | 2026-07-26 | opencode broken |
|
||||
| test-plugin / tdd-cycle / heartbeat / goal-planner / firebase-hosting-basics / firebase-ai-logic-basics | 2 each | — | |
|
||||
|
||||
## Recent Skill Runs
|
||||
| Skill | Agent | Last Run | Result |
|
||||
|-------|-------|----------|--------|
|
||||
| memory-consolidation | hermes | 2026-07-17 | 1 completed, 1 timeout |
|
||||
| firebase-hosting-basics | opencode | 2026-06-28 | timeout |
|
||||
|
||||
## Eval Scores
|
||||
- All 18 score-history.json files are empty — no eval data has accumulated yet.
|
||||
## Eval Data (score-history.json)
|
||||
| Skill | Has Data |
|
||||
|-------|----------|
|
||||
| code-review | yes (largest history) |
|
||||
| heartbeat, firebase-ai-logic-basics, backup-skill, memory-consolidation | yes (1–2 entries) |
|
||||
| others | empty |
|
||||
Scores are all ~45–50 stub-quality; no meaningful eval trend yet.
|
||||
|
||||
## New Learnings Since 2026-06-28
|
||||
- memory-consolidation/learnings.md (updated 2026-07-17)
|
||||
- firebase-hosting-basics/learnings.md (updated 2026-07-17)
|
||||
- goal-planner, code-review, test-plugin (updated 2026-06-29)
|
||||
15 skills have learnings.md updated 2026-07-17 → 2026-07-26 (backup-skill, code-review, devops-audit, memory-consolidation most recent on 2026-07-26).
|
||||
|
||||
## Skills Per Project
|
||||
| Project | Skills Used |
|
||||
|---------|-------------|
|
||||
| Agentic OS | memory-consolidation, brain-guardian (Hermes cron), daily-standup, heartbeat |
|
||||
| Kitchen-Inventory | code-review, firebase-hosting-basics |
|
||||
| Pendelton-comms-live | (none recorded) |
|
||||
| Agentic OS | daily-standup, heartbeat, devops-audit, memory-consolidation, backup-skill |
|
||||
| Kitchen-Inventory | code-review, firebase-ai-logic-basics, firebase-hosting-basics, systematic-debug, tdd-cycle |
|
||||
|
||||
## ⚠ Alerts
|
||||
- **opencode agent broken** (installed with --ignore-scripts; postinstall never ran). All opencode-dispatched skill runs on 2026-07-25/26 returned errors, yet audit still logs success=true with score ~50 — scoring is masking failures.
|
||||
- Kanban dispatch to opencode failed (task fffc3981, 2026-07-26).
|
||||
- memory-consolidation via hermes timed out on 2026-07-26 17:03 UTC.
|
||||
|
|
|
|||
Loading…
Reference in New Issue