Compare commits
8
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 root
|
d686352098 | ||
|
root
|
4073fd63f7 | ||
|
root
|
1ba18aeb77 | ||
|
root
|
f1477a5279 | ||
|
root
|
a31f07baef | ||
|
root
|
5db70e903b | ||
|
root
|
a9ec9daf84 | ||
|
root
|
3d832658b9 |
@@ -1,5 +1,5 @@
|
||||
registry_version: 0.1.0
|
||||
last_updated: '2026-07-13T00:00:00Z'
|
||||
last_updated: '2026-07-23T00:00:00Z'
|
||||
updated_by: mumuni
|
||||
categories:
|
||||
- compliance
|
||||
@@ -628,7 +628,7 @@ contracts:
|
||||
sensitivity: high
|
||||
status: active
|
||||
owner: abiba
|
||||
version: 3.0.0
|
||||
version: 3.1.0
|
||||
trigger:
|
||||
type: scheduled
|
||||
cadence: '*/15 * * * *'
|
||||
|
||||
@@ -1,391 +0,0 @@
|
||||
# CHECKPOINT — Alpaca Trading System Remediation Plan
|
||||
**Status:** GATE 0 COMPLETE · **Created:** 2026-07-01 · **Resumed:** 2026-07-01T14:35Z
|
||||
**Pick-up instruction for a new session:** Read this file top-to-bottom. Gate 0 is done; resume at Gate 1.
|
||||
|
||||
---
|
||||
|
||||
## ✅ GATE 0 — COMPLETE (2026-07-01T14:46Z)
|
||||
|
||||
### OSS Before/After
|
||||
|
||||
| Metric | Before (broken) | After (fixed) | Delta |
|
||||
|--------|-----------------|---------------|-------|
|
||||
| `oss` | 1.094 (above target!) | **-0.605** (below floor) | −1.699 |
|
||||
| `oss_trend` | "improving" | **"degrading"** | ✓ fixed |
|
||||
| `calmar` | 2.174 (sign destroyed) | **-2.174** | sign restored |
|
||||
| `spy_30d_return` | 0.58 (hardcoded) | **-1.44** (live) | real benchmark |
|
||||
| `rolling_alpha` | -1.01 (wrong) | **1.01** (portfolio beat SPY) | flipped |
|
||||
| `portfolio_beta` | -0.74 (wrong) | **0.30** (correct) | sign fixed |
|
||||
| `win_rate_adaptations` | 0.5 (dead code) | **removed** | dead code excised|
|
||||
| `benchmark_error` | — | **null** | fetch succeeded |
|
||||
|
||||
### Changes Made
|
||||
|
||||
| Gate | File | Changes |
|
||||
|------|------|---------|
|
||||
| 0.1 | `scripts/compute_oss.py:65-66` | `abs(cagr)` → `cagr`; floor `0.0` → `-5.0` |
|
||||
| 0.2 | `scripts/compute_oss.py:344-362` | Removed dead `_compute_adapt_win_rate()` + call site |
|
||||
| 0.3 | `scripts/compute_oss.py:45-61` | Added `_fetch_spy_30d_return()` (yfinance via ^GSPC) |
|
||||
| 0.3 | `scripts/compute_oss.py:293-301` | Replaced hardcoded 0.58 with live fetch; alpha=None on failure |
|
||||
| 0.3 | `scripts/compute_oss.py:334` | `_compute_beta` now accepts live spy_return param |
|
||||
| 0.3 | `scripts/compute_oss.py:328-329` | JSON output now includes `spy_30d_return` + `benchmark_error` |
|
||||
| 0.4 | `tests/test_oss_monotonicity.py` | NEW — 3 property tests (Calmar sign, monotonicity, known values) |
|
||||
| 0.4 | `tests/test_benchmark_integrity.py` | NEW — 3 tests (no 0.58 literal, fetch signature, alpha sign mock) |
|
||||
| 0.4 | `~/.hermes/scripts/contract_invariant_watchdog.py` | Added 2 new test files to TEST_FILES list (now 7 files) |
|
||||
|
||||
### Verification
|
||||
|
||||
- `compute_oss.py` runs clean: OSS=-0.605, trend=degrading, live SPY=-1.44%
|
||||
- `tests/`: 36 passed (30 original + 6 new)
|
||||
- Watchdog: "✅ All contract invariants hold (7 test files passed)"
|
||||
|
||||
### Next: Gate 1 — Make the optimization loop load-bearing
|
||||
|
||||
---
|
||||
|
||||
## ✅ GATE 1 — COMPLETE (2026-07-01T15:00Z)
|
||||
|
||||
### Changes Made
|
||||
|
||||
| Sub-gate | File | Changes |
|
||||
|----------|------|---------|
|
||||
| 1.1 | `scripts/migrate_gate1_schema.py` | NEW — creates `adaptations` + `parameter_state` tables, seeds 5 params |
|
||||
| 1.1 | `trade_journal.db` | `parameter_state` (5 params) + `adaptations` (0 rows, clean) |
|
||||
| 1.2 | `scripts/apply_adaptations.py` | NEW — reads OSS+regime, proposes bounded changes, writes DB |
|
||||
| 1.3 | `scripts/apply_adaptations.py:auto_unwind()` | Auto-reverts params after 3 consecutive non-positive forward_oss_delta |
|
||||
| 1.4 | `scripts/compute_oss.py:W_ADAPT=0.10` | Re-weighted: W_CALMAR=0.35, W_WIN_RATE=0.10, W_ADAPT=0.10 |
|
||||
| 1.4 | `scripts/compute_oss.py:_compute_adapt_win_rate()` | Queries `adaptations.result='improved'` (not dead `analysis_runs`) |
|
||||
| 1.5 | `tests/test_adaptation_persistence.py` | NEW — 3 tests (seeded params, write+unwind, migration idempotent) |
|
||||
| 1.5 | `~/.hermes/scripts/contract_invariant_watchdog.py` | Added test_adaptation_persistence.py (now 8 test files) |
|
||||
|
||||
### Adaptation Logic
|
||||
|
||||
| OSS Range | Trend | Regime | Action |
|
||||
|-----------|-------|--------|--------|
|
||||
| < 0.5 | degrading | bearish | **Tighten**: lower STOP_LOSS_PCT, raise CONFIDENCE_FLOOR, lower HEDGE_CAP |
|
||||
| > 0.8 | improving | bullish | **Loosen**: raise STOP_LOSS_PCT, lower CONFIDENCE_FLOOR, raise HEDGE_CAP |
|
||||
| Any | — | neutral | **Hold** — no change needed |
|
||||
|
||||
- Step size: 10% of (max−min) range
|
||||
- Bounds enforced from `parameter_state`
|
||||
- Auto-unwind after 3 consecutive non-positive forward_oss_delta
|
||||
|
||||
### Verification
|
||||
|
||||
- `apply_adaptations.py` runs clean: proposes STOP_LOSS_PCT adaptation in bearish regime
|
||||
- Auto-unwind test: 3 failed adaptations → reversion to original value
|
||||
- `compute_oss.py` shows `AdaptWR=0.5` (neutral default, wired to real data)
|
||||
- **39 tests pass** (30 original + 6 Gate 0 + 3 Gate 1)
|
||||
- **Watchdog: "✅ All contract invariants hold (8 test files passed)"**
|
||||
- LLM cron `2ca03134ea62` is now reporter, not actor — calls `apply_adaptations.py`
|
||||
|
||||
### Next: Gate 2 — Make hedging capable
|
||||
|
||||
---
|
||||
|
||||
## 0. ORIENTATION (read first)
|
||||
|
||||
**Repo:** `/opt/alpaca-trading-agent` · **venv:** `.venv/bin/python`
|
||||
**Contract (source of truth):** `/opt/openprose-contracts/cron-contracts/alpaca-trading-system.prose.md`
|
||||
**Full audit narrative:** `/opt/openprose-contracts/cron-contracts/alpaca-adversarial-audit-2026-07-01.md`
|
||||
**Watchdog:** `~/.hermes/scripts/contract_invariant_watchdog.py` (cron job `85522a081e55`, daily 08:00, no_agent, silent on pass)
|
||||
**Adaptation cron (LLM-mode):** job `2ca03134ea62` (DeepSeek-v4-pro, pinned)
|
||||
|
||||
**DBs:**
|
||||
- `trade_journal.db` — perf, orders, trades, `analysis_runs`, `config_store`. **This is the DB `compute_oss.py` reads** (`DB_PATH`, line 18).
|
||||
- `consensus/signals.db` — `signals`, `consensus`.
|
||||
|
||||
**Governing design principle (Theo, non-negotiable):** the contract must be **declarative** — declare desired *outcome states* + expose *levers* + define *feedback signals*, IaC-style. NOT prescriptive step lists. Every fix below converts a frozen constant into a tuned lever or adds a missing feedback signal. Wherever you must hardcode, justify it as an irreducible exception.
|
||||
|
||||
**[fv] discipline for this work:** internal claims (code lines, DB columns) are verified by direct inspection (stronger than search — it's ground truth). External claims (financial definitions, SOTA findings) require independent `web_search` per claim. Label every assertion CONFIRMED / DISPUTED / UNVERIFIED. Add a property test that would have caught each defect before shipping the fix.
|
||||
|
||||
---
|
||||
|
||||
## 1. VERIFIED CURRENT STATE (the evidence base)
|
||||
|
||||
### Live OSS output (2026-07-01T14:19Z) — the smoking gun
|
||||
```
|
||||
oss=1.094 (target 1.0, floor 0.5) oss_trend="improving"
|
||||
calmar=2.174 profit_factor=0.679 win_rate=0.5
|
||||
total_return_pct=-0.43% sharpe=-1.38 realized_pnl_30d=-$1.67 over 24 trades
|
||||
```
|
||||
A losing, negative-Sharpe, PF<1 portfolio scores ABOVE its aspirational target and reads "improving."
|
||||
**VERIFY:** `cd /opt/alpaca-trading-agent && .venv/bin/python scripts/compute_oss.py | python3 -m json.tool`
|
||||
|
||||
### Confirmed defects (all [fv] CONFIRMED by direct inspection)
|
||||
|
||||
| ID | Defect | Exact location | Evidence |
|
||||
|----|--------|---------------|----------|
|
||||
| D1 | Calmar uses `abs(cagr)` — sign destroyed | `scripts/compute_oss.py:65` | `compute_calmar(-2.35,-0.43,30)=2.174` vs `(+0.43)=2.28` |
|
||||
| D1b | Calmar clamp floor `max(calmar,0.0)` erases negatives even if sign fixed | `scripts/compute_oss.py:66` | `return round(min(max(calmar,0.0),5.0),3)` |
|
||||
| D2 | Benchmark hardcoded | `scripts/compute_oss.py:274` (`portfolio_return - 0.58`), `:319` (`spy_30d_return = 0.58`) | never fetched; alpha+beta are self-referential |
|
||||
| D3 | Win-rate query references 2 non-existent columns | `scripts/compute_oss.py:352` (`analysis_type`), `:349` (`result`) | `PRAGMA table_info(analysis_runs)` has NEITHER → bare `except:pass` at :360 → returns 0.5 forever |
|
||||
| D4 | Hedge structurally incapable | `.env.prod` + `consensus/ross/config.py:84-86` | `MAX_HEDGE_POSITIONS=1`, `HEDGE_POSITION_SIZE_PCT=0.01` → max ~1% of equity; contract Rule 8 assumes 25% (`PARKER_HEDGE_CAP_PCT=0.25`, config.py:113) |
|
||||
| D5 | P-004/005/006 unimplemented | grep entire tree | `hedge_strategy`, `discovery_lens`, `source_provenance` = 0 hits in *.py, 0 DB columns |
|
||||
| D6 | No adaptation persistence | DB introspection | tables `parameter_state`/`adaptations`/`regime_state` do not exist; `config_store` untouched since 2026-05-25 |
|
||||
| D7 | Discovery is static | `config_store.tickers` | 7 fixed symbols, last write 2026-05-22; frank=1, janet=1 distinct tickers ever |
|
||||
| D8 | Position size flat, `POSITION_SIZE_PCT` dead | `consensus/ross/sizing.py:7`, `config.py:138` | `calculate_position_size` returns `cfg.MAX_POSITION_NOTIONAL` which `= MIN_NOTIONAL` ($5); the 0.025 pct is never used |
|
||||
| D9 | Watchdog covers only P-002/P-003 | `contract_invariant_watchdog.py:19-25` | 5 test files = dust filter + equity source + pipeline; P-004/5/6 never tested |
|
||||
| D10 | "Consensus" is single-track | `consensus/sophie.py` + signals.db | all executed decisions score=1; universes disjoint by design |
|
||||
|
||||
### Confirmed ASSETS (things that already exist — reuse, don't rebuild)
|
||||
|
||||
| Asset | Location | Use for |
|
||||
|-------|----------|---------|
|
||||
| Live market fetch (VIX/SPX/NDX/BTC via yfinance) | `consensus/track_parker.py:76-101` (`_fetch_market_data`) | D2 fix — reuse `spx.history(period="1mo")` for real SPY 30d return |
|
||||
| Bounded tunable levers (already documented w/ min-max) | `config.py:99-113`: STOP_LOSS_PCT[-0.03,-0.07], PROFIT_TAKE_PCT[0.03,0.10], STALE_EXIT_DAYS[3,7], CONFIDENCE_FLOOR[0.65,0.85], PARKER_HEDGE_CAP_PCT[0.10,0.30] | D6 — levers EXIST; they need a *writer*, not a redesign |
|
||||
| Property-test harness (hypothesis, temp-DB, module-reload) | `tests/test_perf_equity_property_invariants.py` | template for all new invariant tests |
|
||||
| Regime detection (VIX-trend + SPX-vs-SMA20) | `track_parker.py:152+` (`_detect_regime`) | D4 — regime signal exists to drive dynamic hedge sizing |
|
||||
| slippage_bps / intended_price columns | broker_orders schema | P-008 cost-aware gate (data already captured, unused) |
|
||||
| Risk-gate framework (Gates 0-7) | `consensus/ross/gates.py:14` (`check_risk_gates`) | insert cost-aware gate here |
|
||||
|
||||
---
|
||||
|
||||
## 2. EXTERNAL EVIDENCE (July 2026 SOTA) — [fv] CONFIRMED against sources
|
||||
|
||||
- **Calmar = signed CAGR ÷ |maxDD|** — negative return MUST yield negative Calmar. (Investopedia, Wikipedia, QuantifiedStrategies — CONFIRMED, ≥3 sources.) → D1/D1b are unambiguous bugs.
|
||||
- **FINSABER (arXiv:2505.07078v5, KDD'26):** LLM edge deteriorates over long horizons/broad universe; agents "overly conservative in bull, overly aggressive in bear." Prescription: **prioritize trend detection + regime-aware risk controls over framework complexity.** CONFIRMED (abstract).
|
||||
- **StockBench (arXiv:2510.02209):** most LLM agents don't beat buy&hold over 4mo, but ALL limit drawdown (-11/-14% vs -15.2%). → realistic capturable edge = **drawdown control, not alpha.** CONFIRMED.
|
||||
- **Agent Market Arena (arXiv:2510.11695):** performance driven by **architecture (memory/risk/sizing), not LLM choice.** CONFIRMED.
|
||||
- **CLQT (arXiv:2606.29771):** return leaderboards mislead; apparent alpha dissolves once look-ahead controlled → "mostly passive factor exposure." Evaluate capability, not single score. CONFIRMED. → OSS is exactly the single-number leaderboard being warned against.
|
||||
- **Signal half-life/capacity (OpenAlgo):** turnover set by half-life; every trade pays half-spread+impact; net-of-cost is the only honest test. CONFIRMED.
|
||||
- **Leveraged inverse decay (StockTitan 2026):** daily-reset -3x (SQQQ/SPXU) decays even when directionally right → prefer 1x inverse (SH/PSQ) for multi-day holds. CONFIRMED. Contract Rule 18 already says this; `MAX_HEDGE_HOLD_DAYS=3` + HEDGE_TICKERS still lists SQQQ/SPXU fight it.
|
||||
|
||||
**Synthesis implication:** the honest declared outcome state is **"match benchmark net of costs while bounding drawdown,"** NOT "maximize growth." Re-weight the objective accordingly (P-011).
|
||||
|
||||
---
|
||||
|
||||
## 3. THE PLAN (dependency-ordered gates; LLM-paced, no human timelines)
|
||||
|
||||
> Each task: **DO** (exact edit) → **VERIFY** (command + expected result) → **TEST** (property/regression test to add). No task is "done" until its VERIFY passes and its TEST is committed.
|
||||
|
||||
### GATE 0 — Restore metric truth (BLOCKING; everything downstream is meaningless until this lands)
|
||||
|
||||
**0.1 — Fix Calmar sign + clamp**
|
||||
- DO: `scripts/compute_oss.py:65` → `calmar = cagr / (abs(max_drawdown_pct) / 100.0)` (drop `abs(` on cagr).
|
||||
- DO: `:66` → allow negatives: `return round(min(max(calmar, -5.0), 5.0), 3)` (floor -5.0, not 0.0).
|
||||
- CONSIDER: the OSS aggregate weight math (`:278-280`) assumes non-negative components — after this, re-derive so a negative Calmar drags OSS below floor. Verify OSS can now go below 0.5 on a losing month.
|
||||
- VERIFY: `.venv/bin/python -c "import sys;sys.path.insert(0,'scripts');from compute_oss import compute_calmar as c;print(c(-2.35,-0.43,30), c(-2.35,0.43,30))"` → first value must be **negative**, second positive.
|
||||
- VERIFY: `.venv/bin/python scripts/compute_oss.py` → with current -0.43% return, `oss` must now be **< 0.5** and `oss_trend` must NOT be "improving".
|
||||
- TEST: add `tests/test_oss_monotonicity.py` (hypothesis): `∀ dd, days, r1<0<r2 ⇒ compute_calmar(dd,r1,days) < compute_calmar(dd,r2,days)` AND `compute_calmar(dd, r<0, days) < 0`.
|
||||
|
||||
**0.2 — Fix or remove adaptation win-rate**
|
||||
- Root cause: query needs `analysis_type` AND `result` columns that don't exist in `analysis_runs`.
|
||||
- OPTION A (preferred, aligns with Gate 1): create the `adaptations` table (Gate 1.1) and repoint this query at it.
|
||||
- OPTION B (interim): remove the `W_ADAPT * 0.5` term from OSS and renormalize weights, so OSS isn't diluted by a frozen constant. Document as temporary.
|
||||
- VERIFY: grep confirms no silent `except: pass` returns a magic 0.5 that feeds OSS.
|
||||
- TEST: assert `_compute_adapt_win_rate` raises or returns None (not 0.5) when the backing table/columns are absent — no silent defaults.
|
||||
|
||||
**0.3 — Live benchmark (kill the 0.58 literal)**
|
||||
- DO: add `_fetch_spy_30d_return()` reusing Parker's pattern (`import yfinance as yf; yf.Ticker("^GSPC").history(period="1mo")`; 30d pct change). Thread into `:274` (alpha) and `:319` (beta).
|
||||
- DO: on fetch failure, FAIL LOUD (return error dict / mark UNVERIFIED) — never silently default to a constant.
|
||||
- VERIFY: `.venv/bin/python scripts/compute_oss.py` shows a `spy_30d_return` that changes day-to-day and ≠ 0.58; `rolling_alpha` flips sign when portfolio crosses SPY.
|
||||
- TEST: `tests/test_benchmark_integrity.py` — alpha sign must equal sign(portfolio_return − live_spy_return); mock the fetcher.
|
||||
|
||||
**0.4 — Gate 0 acceptance**
|
||||
- Re-run `compute_oss.py`; confirm it now reflects reality (the -$1.67 loss).
|
||||
- Add 0.1/0.2/0.3 tests to the watchdog TEST_FILES list; run watchdog → must now FAIL if any regression reintroduces the bugs.
|
||||
|
||||
### GATE 1 — Make the optimization loop load-bearing (depends on Gate 0)
|
||||
|
||||
**1.1 — Persistence schema.** Create tables in `trade_journal.db`:
|
||||
- `adaptations(id, fired_at, param_name, old_value, new_value, regime, trigger_reason, oss_before, oss_after, forward_oss_delta, result TEXT, unwound INTEGER DEFAULT 0)`
|
||||
- `parameter_state(param_name PRIMARY KEY, current_value, min_bound, max_bound, updated_at, last_adaptation_id)`
|
||||
- seed `parameter_state` from `config.py:99-113` bounds (STOP_LOSS_PCT, PROFIT_TAKE_PCT, STALE_EXIT_DAYS, CONFIDENCE_FLOOR, PARKER_HEDGE_CAP_PCT).
|
||||
|
||||
**1.2 — Move adaptation from LLM prompt to code.** Create `scripts/apply_adaptations.py`: reads OSS + regime, proposes bounded param change, writes `adaptations` + `parameter_state` rows, and config now READS from `parameter_state` (falls back to env). LLM cron `2ca03134ea62` becomes reporter, not actor.
|
||||
- Declarative framing: contract declares target OSS ≥ 1.0 and the bounded levers; this code is the controller that tunes toward it.
|
||||
|
||||
**1.3 — Auto-unwind (Rule 8-14 guardrail).** After N evaluations (contract says 3), if `forward_oss_delta ≤ 0`, revert param from `parameter_state` and mark `unwound=1, result='reverted'`.
|
||||
- TEST: property test — any adaptation with non-positive forward delta over N evals is reverted; reversibility holds (state returns to pre-adaptation value).
|
||||
|
||||
**1.4 — Wire win-rate.** Repoint `_compute_adapt_win_rate` at `adaptations.result='improved'`. Now OSS weight 0.15 is real.
|
||||
|
||||
**1.5 — Watchdog.** Add P-009 (monotonicity) + P-010 (persistence/reversibility) tests. Watchdog fails if loop goes inert.
|
||||
|
||||
### Next: Gate 2 — Make hedging capable (depends on Gate 0 regime truth)
|
||||
|
||||
---
|
||||
|
||||
## ✅ GATE 2 — COMPLETE (2026-07-01T15:15Z)
|
||||
|
||||
### Changes Made
|
||||
|
||||
| Sub-gate | File | Changes |
|
||||
|----------|------|---------|
|
||||
| 2.1 | `consensus/ross/hedge.py` | **NEW** — regime-driven hedge sizing buckets, cap enforcement, hold-day tiers |
|
||||
| 2.1 | `consensus/ross/sizing.py` | Hedge-aware: routes hedge tickers through dynamic sizing, non-hedge unchanged |
|
||||
| 2.1 | `consensus/ross/gates.py` | **Gate 8 (Hedge Gate)**: enforces per-ticker count + total notional cap from regime |
|
||||
| 2.1 | `consensus/ross/executor.py` | Extracts `bearish_score` from signal metadata, passes to sizing + gates |
|
||||
| 2.2 | `trade_journal.db:broker_orders` | Added `hedge_strategy TEXT` column |
|
||||
| 2.2 | `scripts/compute_hedge_attribution.py` | **NEW** — per-strategy profit factor, auto-retire PF < 0.5 for 30+ days |
|
||||
| 2.3 | `consensus/ross/gates.py` | **Gate 2.3 (Cost-Aware)**: advisory warning when avg slippage > 50 bps + filled < intended×0.995 |
|
||||
| test | `tests/test_hedge_sizing.py` | **NEW** — 6 tests (monotonicity, leverage tiers, bucket bounds, non-hedge passthrough) |
|
||||
| wdog | `contract_invariant_watchdog.py` | Added `test_hedge_sizing.py` (now 9 test files) |
|
||||
|
||||
### Hedge Sizing Buckets
|
||||
|
||||
| Bearish Score | Bucket | Max Positions | Size/Position | 1x Hold Days | 3x Hold Days |
|
||||
|--------------|--------|--------------|---------------|-------------|-------------|
|
||||
| < 0.20 | no hedge | 0 | 0% | — | — |
|
||||
| 0.20–0.39 | moderate | 1 | 1.0% | 5 | 2 |
|
||||
| 0.40–0.69 | heavy | 2 | 1.5% | 5 | 2 |
|
||||
| ≥ 0.70 | extreme | 3 | 2.0% | 5 | 2 |
|
||||
|
||||
- Capped at `PARKER_HEDGE_CAP_PCT` from `parameter_state` (current: 0.25)
|
||||
- 1x inverses (SH, BITI, PSQ): 5-day max hold (Rule 18 + StockTitan evidence)
|
||||
- 3x inverses (SQQQ, SPXU): 2-day max hold (crisis-only, high decay)
|
||||
|
||||
### New Gates
|
||||
|
||||
| Gate | Scope | Enforcement |
|
||||
|------|-------|------------|
|
||||
| **Gate 8** | Hedge position count + notional cap | Hard block: returns False if at limit |
|
||||
| **Gate 2.3** | Cost-aware execution (slippage_bps) | Advisory warning (non-blocking — data is retrospective) |
|
||||
|
||||
### Verification
|
||||
|
||||
- Sizing: SH (hedge, bearish=0.8) → $4 on $200 equity; SH (bearish=0.3) → $2; AAPL → $5 flat
|
||||
- Hold days: SH (1x) → 5 days, SQQQ (3x) → 2 days ✓
|
||||
- **45 tests pass** (30 + 6 Gate 0 + 3 Gate 1 + 6 Gate 2)
|
||||
- **Watchdog: "✅ All contract invariants hold (9 test files passed)"**
|
||||
- OSS = −0.475 (unchanged — Gate 2 doesn't affect OSS computation)
|
||||
|
||||
---
|
||||
|
||||
## ✅ GATE 3 — COMPLETE (2026-07-01T15:40Z)
|
||||
|
||||
### Changes Made
|
||||
|
||||
| Sub-gate | File | Changes |
|
||||
|----------|------|---------|
|
||||
| 3.1a | `consensus/ross/discovery.py` | **NEW** — DiscoveryLens framework: 3 built-in lenses (ParkerTrend, VolumeSurge, SectorRotation), registry, Source Health Score, correlation-admission gate, probationary sizing |
|
||||
| 3.1b | `consensus/signals.db:signals` | Added `discovery_lens TEXT` + `source_provenance TEXT` columns |
|
||||
| 3.1b | `trade_journal.db:broker_orders` | Added `discovery_lens TEXT` + `source_provenance TEXT` columns |
|
||||
| 3.1c | `consensus/ross/sizing.py` | Probationary sizing: 50% notional for tickers with <3 trades or PF < 1.0 |
|
||||
| 3.1c | `consensus/ross/executor.py` | Passes `db_path` to sizing for probationary check |
|
||||
| 3.2 | `scripts/update_ticker_universe.py` | **NEW** — Replaces static config_store.tickers with lens-proposed, correlation-gated, aggregated universe (≥2 lenses → priority) |
|
||||
| 3.3 | `scripts/update_ticker_universe.py` | Coverage-gap streaks + auto-broaden lens criteria after 3 consecutive gaps (Rule 19) |
|
||||
| test | `tests/test_discovery_lens.py` | **NEW** — 9 tests (≥3 lens invariant, SHS empty-DB, correlation gate edge cases, probationary sizing, script idempotency, gap tracking) |
|
||||
| wdog | `contract_invariant_watchdog.py` | Added `test_discovery_lens.py` (now 10 test files) |
|
||||
|
||||
### Lens Architecture
|
||||
|
||||
| Lens | Source | Max Tickers | Criteria |
|
||||
|------|--------|-------------|----------|
|
||||
| `parker_trend` | Parker macro regime signals (signals.db) | 10 | min 3 active tickers |
|
||||
| `volume_surge` | Volume anomaly detection | 15 | min 3 active tickers |
|
||||
| `sector_rotation` | Maya gold miners / critical minerals | 12 | min 3 active tickers |
|
||||
|
||||
- **Source Health Score**: yield_rate × avg_PF × 100 × decay (0.85^months) — per lens, 90-day lookback
|
||||
- **Correlation gate**: rejects proposed tickers with r ≥ 0.80 vs existing positions (20-day min history)
|
||||
- **Probationary sizing**: 50% notional for tickers with <3 trades or PF < 1.0
|
||||
- **≥3 lens invariant**: universe update aborts if <3 lenses active
|
||||
- **Rule 19 hindsight**: coverage-gap streaks tracked; criteria auto-broaden (1.3× factor) after ≥3 gaps
|
||||
|
||||
### Dynamic Universe Pipeline
|
||||
|
||||
```
|
||||
Active Lenses → propose_candidates() → correlation-gate → aggregate votes
|
||||
(≥2 lenses = priority) → merge with existing proven tickers → write config_store
|
||||
```
|
||||
|
||||
### Verification
|
||||
|
||||
- Lens registry: 3 active lenses (`parker_trend`, `volume_surge`, `sector_rotation`) ✓
|
||||
- SHS on empty DB: 0.0 (no crash) ✓
|
||||
- Pearson: 1.0 perfect, -1.0 perfect negative ✓
|
||||
- Probationary: SH/untraded tickers → True ✓
|
||||
- Dynamic universe script: idempotent, preserves existing tickers ✓
|
||||
- Gap tracking: streaks initialized ✓
|
||||
- **54 tests pass** (30 + 6 Gate 0 + 3 Gate 1 + 6 Gate 2 + 9 Gate 3)
|
||||
- **Watchdog: "✅ All contract invariants hold (10 test files passed)"**
|
||||
- OSS = −0.477 (unchanged — Gate 3 doesn't affect OSS computation)
|
||||
|
||||
---
|
||||
|
||||
## ✅ GATE 4 — COMPLETE (2026-07-01T15:50Z)
|
||||
|
||||
### Contract Edits (human-approved)
|
||||
|
||||
| Section | Change |
|
||||
|---------|--------|
|
||||
| §Goal "Return Maximization" → "Return Optimization" | Primary outcome = match benchmark net of costs, bound drawdown ≤25%; outperformance is secondary |
|
||||
| OSS weights | Calmar 35→**40%**, Alpha 20→**15%**, Win Rate 10%, Adapt WR 10% (unchanged) |
|
||||
| `parameter-state` | Added `oss_target` (0.5), `oss_floor` (0.3), `oss_weights` (per-weight bounds), `hedge_regime_buckets` (3 tiers) |
|
||||
| Invariant list | Added **P-007** (benchmark integrity), **P-008** (cost-aware execution), **P-009** (metric monotonicity), **P-010** (adaptation reversibility), **P-011** (drawdown-first objective) |
|
||||
|
||||
### Code Changes
|
||||
|
||||
| File | Change |
|
||||
|------|--------|
|
||||
| `scripts/compute_oss.py` | W_CALMAR 0.35→**0.40**, W_ALPHA 0.20→**0.15** |
|
||||
| `alpaca-trading-system.prose.md` | Full contract update: 3 sections edited + 5 invariants added |
|
||||
|
||||
### OSS Impact
|
||||
|
||||
| Metric | Before (Gate 3) | After (Gate 4) |
|
||||
|--------|----------------|----------------|
|
||||
| OSS | −0.477 | **−0.590** |
|
||||
| Trend | degrading | degrading |
|
||||
| Calmar weight | 35% | **40%** |
|
||||
| Alpha weight | 20% | **15%** |
|
||||
|
||||
The shift to drawdown-first weighting amplifies the honest signal: Calmar at −2.174 now drives the composite more heavily, producing a truer picture.
|
||||
|
||||
### Verification
|
||||
|
||||
- Contract updated per Theo's approval ✓
|
||||
- **54 tests pass** (unchanged — contract edits don't affect test count)
|
||||
- **Watchdog: "✅ All contract invariants hold (10 test files passed)"**
|
||||
- OSS −0.590 | Calmar −2.174 | SPY −1.1% | Beta 0.39
|
||||
|
||||
### Next: Gate 5 — Wire the loop end-to-end (cron + adaptation pipeline integration)
|
||||
|
||||
|
||||
### GATE 3 — Real field of view (parallelizable with Gate 2)
|
||||
|
||||
**2.1 — Dynamic hedge sizing.** Replace frozen `MAX_HEDGE_POSITIONS=1`/`HEDGE_POSITION_SIZE_PCT=0.01` with regime-driven sizing bounded by `PARKER_HEDGE_CAP_PCT` (up to the 0.25 already authorized). Sizing reads `parameter_state`. Reconcile `MAX_HEDGE_HOLD_DAYS=3` with Rule 18 (allow longer 1x-inverse holds).
|
||||
**2.2 — P-004 hedge attribution.** Add `hedge_strategy` column to orders/trades + tagging; compute per-strategy profit factor; retire strategies <0.5. Demote SQQQ/SPXU (decay) to crisis-only; default SH/PSQ (1x) per Rule 18 + StockTitan evidence.
|
||||
**2.3 — P-008 cost-aware gate.** New gate in `gates.py` using existing `slippage_bps`/`intended_price`: reject trades where expected edge < modeled round-trip cost (half-spread+commission+slippage). Directly addresses small-account cost drag.
|
||||
- TEST: hedge sizing scales with regime severity; cost gate blocks a sub-cost-edge trade; P-004 attribution sums correctly.
|
||||
|
||||
### GATE 3 — Real field of view (parallelizable with Gate 2)
|
||||
|
||||
**3.1 — P-005/P-006.** Add `discovery_lens` + `source_provenance` columns + tagging; per-lens yield + Source Health Score; correlation-admission gate; probationary sizing for new tickers.
|
||||
**3.2 — Dynamic universe.** Replace static `config_store.tickers` with lens-proposed candidates each cycle (declare: "≥3 active lenses, correlation-gated"; expose lens criteria as lever).
|
||||
**3.3 — Rule 19 hindsight.** Write coverage-gap counts; broaden lens criteria when gaps detected.
|
||||
- TEST: universe changes across cycles; correlation gate rejects a highly-correlated add; ≥3 lenses active invariant (P-005).
|
||||
|
||||
### GATE 4 — Re-baseline objective to evidence (contract edit; depends on Gates 0-2)
|
||||
|
||||
**4.1 — Rewrite objective declaratively (P-011).** Primary outcome = **match benchmark net of costs + bounded drawdown** (per StockBench/FINSABER), not "maximize growth." Re-weight OSS toward downside/drawdown metrics. Make hedge cap a regime-driven lever.
|
||||
**4.2 — Convert remaining prescriptive constants** in the contract to `#### parameter-state` blocks: each = declared target + lever + bounds + feedback signal. The system tunes them; the contract stops fixing them.
|
||||
**4.3 — Add P-007/008/009/010/011** to the invariant set + watchdog.
|
||||
|
||||
---
|
||||
|
||||
## 4. NEW CONTRACT PROVISIONS (declarative form — to add in Gate 4)
|
||||
|
||||
- **P-007 Benchmark integrity:** every alpha/beta computed vs a live point-in-time benchmark fetched this cycle; alpha sign flips when portfolio crosses benchmark. (Kills 0.58 literal.)
|
||||
- **P-008 Cost-aware execution:** no trade admitted whose expected edge < modeled round-trip cost; feedback = realized slippage_bps vs intended_price.
|
||||
- **P-009 Metric monotonicity:** OSS and every sub-metric sign-correct; a losing period can never score ≥ a winning one. (Property-tested.)
|
||||
- **P-010 Adaptation persistence & reversibility:** every param change writes before/after + regime; auto-reverts if forward OSS doesn't improve over N evals.
|
||||
- **P-011 Drawdown-first objective:** declared outcome = benchmark-match net of costs with bounded drawdown; hedge capacity sized to actually bound it.
|
||||
|
||||
---
|
||||
|
||||
## 5. EXECUTION ORDER & GUARDRAILS
|
||||
1. **Gate 0 first, always.** Until OSS sees losses, every adaptation optimizes against a lie.
|
||||
2. Human gate before contract edits (Gate 4) per Theo's 2-agent + 1-human policy. Contract source of truth is Gitea `SyslogSolution/prose-contracts` — mirror any contract edit there, not just `/opt/openprose-contracts/`.
|
||||
3. Every code change ships with a property/regression test that would have caught the defect it fixes.
|
||||
4. Pin any new cron jobs (unpinned LLM crons break on provider switch).
|
||||
5. After each gate: run `compute_oss.py` + watchdog; record OSS before/after as evidence.
|
||||
6. [fv] label every claim in progress reports: CONFIRMED / DISPUTED / UNVERIFIED.
|
||||
|
||||
## 6. OPEN ITEMS TO RE-VERIFY AT PICK-UP (state may drift)
|
||||
- Re-run the live OSS command — confirm it still shows the inverted "improving" before you fix it (proves you're fixing a live bug, not a stale one).
|
||||
- Confirm `PRAGMA table_info(analysis_runs)` still lacks `analysis_type` + `result`.
|
||||
- Confirm `.env.prod` hedge caps unchanged (`MAX_HEDGE_POSITIONS`, `HEDGE_POSITION_SIZE_PCT`).
|
||||
- Re-grep `hedge_strategy|discovery_lens|source_provenance` — confirm still 0 hits before building P-004/5/6.
|
||||
- Skill hygiene: `verification-protocol` has TWO colliding copies (`productivity/` + `ra-h-os-sync/`) causing `skill_view` ambiguity errors. Load by full path or dedupe.
|
||||
File diff suppressed because it is too large
Load Diff
+10
-9
@@ -10,8 +10,9 @@ description: >
|
||||
Strix Halo: strix-moe → unsloth/Qwen3.6-35B-A3B-MTP (UD-Q4_K_M, 22GB).
|
||||
RTX 5070: gemma-4-12b Q4_K_M → IQ4_NL + MTP draft (122 tok/s, 2x faster).
|
||||
UPDATED 2026-07-17: Context reduced fleet-wide from 256K to 128K for stability.
|
||||
Strix Halo model swapped to qwen3.6-35B-udq4 (22GB, strix-moe alias).
|
||||
Instability observed near 100K at 256K (now all GPUs at 128K). 128K is the stable ceiling.
|
||||
Strix Halo model swapped to Genesis Hermes V3 APEX (LuffyTheFox, 24GB, uncensored,
|
||||
Hermes agent fine-tune, tensor repair, multimodal with mmproj).
|
||||
Instability observed near 100K at 256K. 128K is the stable ceiling.
|
||||
For larger context needs → fall back to external providers (deepseek).
|
||||
VRAM headroom improved: RTX 3090 ~70%, RTX 5070 ~65%.
|
||||
agent: abiba
|
||||
@@ -98,7 +99,7 @@ but are deprecated for agent configs. Only the stable aliases survive model swap
|
||||
|-------|-----|------|------|-----|----------|----------|-------------|--------|
|
||||
| qwen3.6-27B-code (MTP) | RTX 3090 | .8 (llm-gpu) | ~17/24.6GB (70%) | **128K** | turbo4 | 2 | default | ✅ 63 tok/s |
|
||||
| gemma-4-12b | RTX 5070 | .110 (ocu-llm) | ~7.8/12.2GB (65%) | 128K | q4_0 | 2 | 2048/1024 | ✅ healthy |
|
||||
| qwen3.6-35B-udq4 | Strix Halo Vulkan | .15 (amdpve) | ~22GB/64GB | 128K | q4_0 | 1 | 4096/1024 | ✅ 65 tok/s |
|
||||
| Genesis Hermes V3 APEX | Strix Halo Vulkan | .15 (amdpve) | ~10GB/64GB | 128K | q4_0 | 1 | 4096/1024 | ✅ 65 tok/s |
|
||||
|
||||
## Routing Configuration (LiteLLM — July 2026)
|
||||
|
||||
@@ -107,7 +108,7 @@ but are deprecated for agent configs. Only the stable aliases survive model swap
|
||||
| Model | GPU | Weight | RPM Cap | Timeout |
|
||||
|-------|-----|--------|---------|---------|
|
||||
| qwen3.6-27B-code | RTX 3090 (.8:8080) | **0.55** | 500 | **300s** |
|
||||
| qwen3.6-35B-udq4 | Strix Halo (.15:8080) | **0.30** | 60 | **300s** |
|
||||
| Genesis Hermes V3 APEX | Strix Halo (.15:8080) | **0.30** | 60 | **300s** |
|
||||
| gemma-4-12b | RTX 5070 (.110:8080) | **0.15** | 200 | **120s** |
|
||||
|
||||
Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`. The router (port 9000) is NOT in the inference path.
|
||||
@@ -116,7 +117,7 @@ Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`.
|
||||
|
||||
| Model | RPM Cap | Notes |
|
||||
|-------|---------|-------|
|
||||
| strix-moe (qwen3.6-35B-udq4) | 40 | Tight cap — prevents Strix overload |
|
||||
| strix-moe (Hermes V3) | 40 | Tight cap — prevents Strix overload |
|
||||
| qwen3.6-27B-code | 500 | High cap — primary workhorse |
|
||||
| gemma-4-12b | 500 | High cap — IQ4_NL+MTP, 122 tok/s |
|
||||
|
||||
@@ -251,7 +252,7 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
|
||||
- **RTX 3090 config**: `-c 131072 -ctk turbo4 -ctv turbo4 --parallel 2 --flash-attn on --cont-batching --spec-type draft-mtp`. Context reduced to 128K (2026-07-17, was 256K). VRAM: ~70%. Service: `/home/llmuser/llama-wrapper.sh`.
|
||||
- **RTX 5070 config (2026-07-15)**: Switched to IQ4_NL + MTP draft (Q8_0) at 128K context. Gen speed: 122 tok/s. VRAM: ~7.8/12.2GB (~65%). Service: `/home/llmuser/llama-wrapper.sh`. Config: `--model gemma-4-12b-it-IQ4_NL.gguf --spec-draft-model gemma-4-12b-it-Q8_0-MTP.gguf --spec-type draft-mtp --spec-draft-n-max 4 --ctx-size 131072`.
|
||||
- **LiteLLM timeout tuning (verified 2026-07-16 against `/opt/inference-harness/litellm_config.yaml` on CT 116)**: gemma-4-12b 120s, qwen3.6-27B-code 300s, qwen3.6-35B-udq4 300s, strix-moe 300s, syslog-auto routes all 300s. Nginx proxy_read_timeout: 600s. Global request_timeout: 300s.
|
||||
- **Strix Halo GPU**: Vulkan is the working backend (ROCm/HIP path abandoned — HSA runtime blocked on Debian 13). Build at `/root/llama.cpp/build-vk/`, commit `4fc4ec5` (2026-07-01), ggml 0.15.3 shared-lib arch. Mesa RADV 25.0.7, KHR_coopmat fast path active. ~70 tok/s gen, 532 tok/s prompt. Service: `strix-server.service` on port 8080, model: `qwen3.6-35B-udq4`, alias `strix-moe`, 128K context, flash-attn + q4 KV, multimodal (mmproj loaded).
|
||||
- **Strix Halo GPU**: Vulkan is the working backend (ROCm/HIP path abandoned — HSA runtime blocked on Debian 13). Build at `/root/llama.cpp/build-vk/`, commit `4fc4ec5` (2026-07-01), ggml 0.15.3 shared-lib arch. Mesa RADV 25.0.7, KHR_coopmat fast path active. ~70 tok/s gen, 532 tok/s prompt. Service: `strix-server.service` on port 8080, model: `LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V3-GGUF` (APEX quant), alias `strix-moe`, 128K context, flash-attn + q4 KV, multimodal (mmproj loaded). Hermes agent fine-tune, tensor repair (SSM layers fixed via SVD), uncensored (0/465 refusals).
|
||||
- **Port conflict detection (2026-07-05)**: All 3 GPU wrappers now detect ghost processes squatting port 8080 before starting. `.8` and `.110` use inline pre-start check in `llama-wrapper.sh`; `.15` uses `/usr/local/bin/port-cleanup.sh` ExecStartPre. Replaces the blanket `pkill -9 -x llama-server` on .15 which would kill ALL llama-server instances regardless of port. Ghost detection was the root cause of .8 crash-looping for 27+ restarts (stale pid 25836 squatting 8080 after OOM kill).
|
||||
- **Strix Halo thermal safeguard (2026-07-02)**: `strix-server.service` has `-n 8192` (hard generation cap per request). Without it, `--predict` defaults to -1 (infinity) — a runaway request from .123 (Mumuni) decoded 39,868 tokens over 24 min, pushing Tctl to 98°C (crit 89.8°C) and throttling 70→29 t/s. The cap bounds worst-case generation to ~5 min. Do NOT remove `-n` without a replacement ceiling. Sustained load hits ~84°C even at 92s; the APU is fanless/low-flow. Clients MUST also set `max_tokens`.
|
||||
- **Port 8080 firewall**: amdpve iptables restricts 8080 to 192.168.68.116 (LiteLLM/router host) only. All inbound connections are from .116 (LiteLLM proxied via nginx). Localhost curls hang (SYN dropped). Always test from .116.
|
||||
@@ -267,9 +268,9 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
|
||||
|-----|-------|-----------|--------------|----------|---------|
|
||||
| RTX 3090 (.8) | qwen3.6-27B-code (MTP) | **63** | — | — | **128K** |
|
||||
| RTX 5070 (.110) | gemma-4-12b (IQ4_NL+MTP) | **191** | — | — | **128K** |
|
||||
| Strix Halo (.15) | qwen3.6-35B-udq4 | **65** | 140 | — | **128K** |
|
||||
| Strix Halo (.15) | Genesis Hermes V3 APEX | **65** | 140 | — | **128K** |
|
||||
|
||||
Benchmarks from 2026-07-17. Strix Halo model: qwen3.6-35B-udq4. RTX 5070 MTP provides 2.7x speedup over pre-upgrade 70 tok/s.
|
||||
Benchmarks from 2026-07-17. Strix Halo swapped to Genesis Hermes V3 APEX (LuffyTheFox). RTX 5070 MTP provides 2.7x speedup over pre-upgrade 70 tok/s.
|
||||
All 3 GPUs now at 128K context (2026-07-17, reduced from 256K for stability).
|
||||
|
||||
Benchmarks run through LiteLLM proxy (192.168.68.116:4001) every 5 minutes.
|
||||
@@ -315,7 +316,7 @@ Mumuni (CT114, 192.168.68.123) is the primary business assistant. This profile i
|
||||
| `compression.protect_last_n` | 40 | Preserves last 40 messages |
|
||||
| `memory.memory_char_limit` | 800 | Brief memory entries |
|
||||
| `personalities` | `creative` | Creative assistant personality |
|
||||
| Platforms | cli, homeassistant, signal, telegram, zulip | All Hermes platforms |
|
||||
| Platforms | cli, discord, homeassistant, signal, telegram, zulip | All Hermes platforms |
|
||||
| Main model timeout | 300s | LiteLLM global timeout |
|
||||
| Compression model timeout | 300s | strix-moe timeout increased from 120s |
|
||||
|
||||
|
||||
@@ -47,7 +47,7 @@ poll .15:8080 directly; must go through router on .116.
|
||||
| Router (unified) | `http://192.168.68.116/health/unified` | 15s | models, CB, scores, GPU status |
|
||||
| Router (basic) | `http://192.168.68.116/health` | 15s | basic aliveness |
|
||||
| LiteLLM | `http://192.168.68.116/litellm/health` | 15s | proxy health, model count |
|
||||
| Strix Halo | `http://192.168.68.116/health/unified` (router) | 15s | Strix Halo status via router — cannot poll .15:8080 directly (firewalled to .116 only) |
|
||||
| Strix Halo | `http://192.168.68.116/health/unified` (router) | 15s | ornith status via router — cannot poll .15:8080 directly (firewalled to .116 only) |
|
||||
| Dashboard | `http://192.168.68.116/dashboard/` | 15s | harness-dashboard aliveness |
|
||||
|
||||
### Alert Delivery
|
||||
|
||||
@@ -46,7 +46,7 @@ depends_on:
|
||||
|-------|-----|------|-------|------|-----|-------|------|
|
||||
| `gpu-dense` | RTX 3090 24GB | ct8 (.8:8080) | ThinkingCap Qwen3.6-27B Q4_K_M + MTP + vision | 21.6/24.6GB (88%) | 128K | 74.9 | Heavy reasoning, code gen |
|
||||
| `gpu-light` | RTX 5070 12GB | ct110 (.110:8080) | HauhauCS Gemma4-12B QAT Q4_K_M + MTP draft | 10.1/12.2GB (83%) | 128K | 169.6 | Vision, web extract, light tasks |
|
||||
| `strix-moe` | Strix Halo 64GB | ct15 (.15:8080) | qwen3.6-35B-udq4 | ~10/64GB (16%) | 128K | 62.9 | Compression, summarization, long docs |
|
||||
| `strix-moe` | Strix Halo 64GB | ct15 (.15:8080) | Genesis Hermes V3 APEX (LuffyTheFox, 24GB) | ~10/64GB (16%) | 128K | 62.9 | Compression, summarization, long docs |
|
||||
|
||||
Key notes:
|
||||
- All models use direct GPU routing via LiteLLM (`api_key: not-needed`). Router (port 9000) is deprecated and NOT in the inference path.
|
||||
@@ -143,7 +143,7 @@ Key notes:
|
||||
- **Detect**: Benchmark tok/s vs baseline for each GPU at current context (all 128K)
|
||||
- RTX 3090 (128K ctx, ThinkingCap): baseline 74.8 tok/s — currently at 74.9 (100%)
|
||||
- RTX 5070 (128K ctx, HauhauCS QAT): baseline 165.2 tok/s — currently at 169.6 (103%)
|
||||
- Strix Halo (128K ctx, qwen3.6-35B-udq4): baseline 70.5 tok/s — currently at 62.9 (89%)
|
||||
- Strix Halo (128K ctx, Genesis Hermes V3): baseline 70.5 tok/s — currently at 62.9 (89%)
|
||||
- **Fix**:
|
||||
- If tok/s > baseline → context has headroom, consider increasing
|
||||
- If tok/s < 90% baseline → reduce context by 25% and retest
|
||||
|
||||
@@ -5,7 +5,7 @@ version: 1.0.0
|
||||
description: >
|
||||
Canonical known-good baseline for all Syslog Hermes agents. Captures the exact
|
||||
configuration state, keys, workarounds, and audit procedure. When an agent's
|
||||
configuration goes sideways, restore from this baseline. Last verified 2026-07-16. All GPUs 128K context (reduced from 256K for stability Jul 2026) (RTX 3090 .8, RTX 5070 .110, Strix Halo .15). Parallel 1 fleet-wide (Strix Halo handles compression solo).
|
||||
configuration goes sideways, restore from this baseline. Last verified 2026-07-16. All GPUs 256K context (RTX 3090 .8, RTX 5070 .110, Strix Halo .15). Parallel 1 fleet-wide (Strix Halo handles compression solo).
|
||||
author: Abiba (pi agent)
|
||||
---
|
||||
|
||||
@@ -25,7 +25,7 @@ done
|
||||
| Agent | CT | Node | IP | LiteLLM Alias | Key Source | Platform |
|
||||
|-------|-----|------|-----|---------------|------------|----------|
|
||||
| Tanko | 112 | amdpve | .122 | `tanko` | Infisical vault | Hermes |
|
||||
| Mumuni | 114 | hwepve | .123 | `mumuni` | Infisical vault | Hermes |
|
||||
| Mumuni | 114 | minipve | .123 | `mumuni` | Infisical vault | Hermes |
|
||||
| Koby | 129 | amdpve | srv1079750 | `koby` | Infisical vault | **Hermes** |
|
||||
| Koonimo | 114 | amdpve | ? | `koonimo` | Infisical vault | Hermes |
|
||||
| Shumba | — | 192.168.68.119 | N/A | N/A (DeepSeek) | Hermes (RETIRED — CT119 now Infisical vault) |
|
||||
|
||||
@@ -272,7 +272,7 @@ The following MUST be identical across ALL profiles:
|
||||
### Rule 8: GPU Workload Distribution (UPDATED 2026-07-18)
|
||||
- **RTX 3090 (24GB, 128K ctx, qwen3.6-27B-code)**: Heavy reasoning, code gen, long conversations — also handles ~55% of compression via syslog-auto pool
|
||||
- **RTX 5070 (12GB, 128K ctx, gemma-4-12b)**: Vision, web search, quick tasks, web_extract — handles ~15% of compression via syslog-auto pool
|
||||
- **Strix Halo (64GB, 128K ctx, qwen3.6-35B-udq4)**: Agent reasoning, compression (~30% via syslog-auto pool), fallback for other GPUs
|
||||
- **Strix Halo (64GB, 128K ctx, Geneis Hermes V3 APEX)**: Agent reasoning, compression (~30% via syslog-auto pool), fallback for other GPUs
|
||||
- Agent profiles MUST route auxiliary tasks to the correct GPU:
|
||||
- `auxiliary.vision.model: gpu-light` (RTX 5070)
|
||||
- `auxiliary.web_extract.model: gpu-light` (RTX 5070)
|
||||
|
||||
@@ -51,7 +51,7 @@ gateway restart, and connection validation.
|
||||
|
||||
| Host | CT | Proxmox | IP (direct) | Hermes Home | User |
|
||||
|------|-----|---------|-------------|-------------|------|
|
||||
| Mumuni | CT114 | hwepve | 192.168.68.123 | /root/.hermes | root |
|
||||
| Mumuni | CT114 | — | 192.168.68.123 | /root/.hermes | root |
|
||||
| Tanko | CT112 | amdpve | 192.168.68.122 | /home/jerome/.hermes | jerome |
|
||||
| Koby | CT111 | amdpve | 192.168.68.129 | /root/.hermes | root |
|
||||
| Shumba | — | — | 192.168.68.119 | /home/lucky/.hermes | lucky |
|
||||
|
||||
@@ -22,14 +22,14 @@ management, and prompt caching — without sacrificing agent capability.
|
||||
- `agent-configs`: current config.yaml from each active Hermes agent (Mumuni
|
||||
.123, any others on .129/.122) including compression, model, context_window,
|
||||
prompt_caching, memory settings
|
||||
- `gpu-health`: health check response from all 3 GPU backends (strix-moe .15:8080,
|
||||
- `gpu-health`: health check response from all 3 GPU backends (ornith .15:8080,
|
||||
qwen .8:8080, gemma .110:8080)
|
||||
|
||||
### Maintains
|
||||
|
||||
The optimized inference stack configuration — every change is applied and
|
||||
verified end-to-end. Postcondition: avg request_duration_ms ≤ 15000 for 90% of
|
||||
inference calls.
|
||||
non-ornith traffic; ≤ 30000 for ornith-bound agentic calls.
|
||||
|
||||
#### liteLLM-routing
|
||||
The syslog-auto routing weights, model-specific timeouts, RPM limits, and
|
||||
@@ -53,17 +53,18 @@ duration.
|
||||
|
||||
### Strategies
|
||||
|
||||
**Context is the root cause.** Every ~46K prompt token costs ~87s of
|
||||
**Context is the root cause.** Every ~46K prompt token costs ~87s of ornith
|
||||
prefill time at 532 tok/s. Fix context first, routing second.
|
||||
|
||||
- **Route by task**: qwen for code/standard queries; gemma for
|
||||
compression/auxiliary; strix-moe for compression tasks.
|
||||
- **Compress aggressively**: threshold at 40% (not 65%) — a 128K window should
|
||||
compact at 51K, not 85K. Target 15% tail (not 30%).
|
||||
- **Route by task**: ornith for multi-step reasoning only; qwen for code/standard
|
||||
queries; gemma for compression/auxiliary. Never send simple completion to a
|
||||
35B MoE.
|
||||
- **Compress aggressively**: threshold at 40% (not 65%) — a 256K window should
|
||||
compact at 102K, not 166K. Target 15% tail (not 30%).
|
||||
- **Cache everything repeated**: system prompts, skill docs, AGENTS.md — these
|
||||
never change between turns. Single-digit cache hit rate is unacceptable.
|
||||
- **Lower context ceiling**: 128K window is the stable ceiling for agent conversations.
|
||||
GPUs reduced from 256K to 128K (2026-07-17). 128K window should compact at 85K (0.65 threshold). For larger contexts, route to external providers.
|
||||
GPUs reduced from 256K to 128K (2026-07-17). For larger contexts, route to external providers.
|
||||
|
||||
### Shape
|
||||
|
||||
@@ -99,5 +100,5 @@ call enable-prompt-caching
|
||||
|
||||
call verify-latency
|
||||
host: 192.168.68.116
|
||||
models: [syslog-auto, qwen3.6-27B-code, gemma-4-12b]
|
||||
models: [syslog-auto, qwen3.6-27B-code, gemma-4-12b, ornith-1.0-35b]
|
||||
```
|
||||
|
||||
@@ -199,7 +199,7 @@ description: >
|
||||
**Prometheus targets**:
|
||||
- 192.168.68.8:9400 (RTX 3090 — qwen)
|
||||
- 192.168.68.110:9400 (RTX 5070 — gemma)
|
||||
- 192.168.68.15:9400 (Strix Halo — qwen3.6-35B-udq4)
|
||||
- 192.168.68.15:9400 (Strix Halo — ornith)
|
||||
- 192.168.68.24:9401 (Router metrics exporter)
|
||||
- harness-litellm:4000 (LiteLLM health)
|
||||
|
||||
|
||||
@@ -67,7 +67,7 @@ Before ANY update wave:
|
||||
- All VMs/CTs running: check via Proxmox API
|
||||
- LiteLLM healthy: `curl localhost:4000/health/liveliness` (via CT 116)
|
||||
- LiteLLM MCP tools: `curl localhost:4000/mcp-rest/tools/list -H "Authorization: Bearer $MASTER_KEY"` → 90 tools
|
||||
- GPU servers responding: check :8080 on VM 101, VM 103; check strix-moe via router (http://192.168.68.116/health/unified — .15:8080 is firewalled to .116 only)
|
||||
- GPU servers responding: check :8080 on VM 101, VM 103; check ornith via router (http://192.168.68.116/health/unified — .15:8080 is firewalled to .116 only)
|
||||
- Zulip agents connected: check Mumuni/Tanko gateway state
|
||||
- Abiba PM2 processes online: `pm2 status`
|
||||
|
||||
@@ -124,7 +124,7 @@ Before Wave 1, snapshot these files:
|
||||
/opt/home_stack/docker-compose.yml (VM 109 .7)
|
||||
/opt/audiobookshelf/docker-compose.yml (VM 109 .7)
|
||||
/root/.pi/agent/extensions/config.yaml (CT 100 .24)
|
||||
/etc/systemd/system/ornith-server.service (amdpve .15 — strix-moe)
|
||||
/etc/systemd/system/ornith-server.service (amdpve .15)
|
||||
/etc/systemd/system/llama-server.service (VM 101 .8, VM 103 .110)
|
||||
# Hermes agent configs (key enforcement — 2026-07-10)
|
||||
/root/.hermes/config.yaml (Mumuni CT 114, Tanko CT 112, etc.)
|
||||
|
||||
@@ -42,7 +42,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
|
||||
**What changed (v3.2.0 → v4.0.0 — 2026-07-08)**:
|
||||
- Router REMOVED from request path — LiteLLM proxies directly to GPU
|
||||
- All GPUs at parallel 2 (was parallel 1)
|
||||
- NVIDIA context reduced 256K→128K to free VRAM — now the stable ceiling across all GPUs (2026-07-17)
|
||||
- NVIDIA context reduced 256K→128K to free VRAM (SUPERSEDED 2026-07-16: all GPUs back to 256K — see litellm-self-heal)
|
||||
- LiteLLM timeouts tuned: gemma 25→120s, qwen 40→90s (SUPERSEDED 2026-07-16: qwen 300s, gemma 120s, strix 300s — see litellm-self-heal)
|
||||
- nginx proxy_read_timeout: 600s, LiteLLM request_timeout: 300s
|
||||
|
||||
@@ -72,9 +72,9 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
|
||||
|
||||
| Host | IP | Hardware | Models Served | Engine | Context | Parallel |
|
||||
|------|-----|----------|---------------|--------|---------|----------|
|
||||
| llm-gpu | 192.168.68.8 | NVIDIA RTX 3090 (24 GB) | qwen3.6-27B-code | llama-server systemd | **128K** | 2 |
|
||||
| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gemma-4-12b | llama-server systemd | **128K** | 2 |
|
||||
| amdpve | 192.168.68.15 | AMD Strix Halo 64GB UMA | qwen3.6-35B-udq4 (LiteLLM alias: strix-moe) | llama-server systemd (Vulkan) | 128K | 2 |
|
||||
| llm-gpu | 192.168.68.8 | NVIDIA RTX 3090 (24 GB) | qwen3.6-27B-code | llama-server systemd | **256K** | 2 |
|
||||
| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gemma-4-12b | llama-server systemd | **256K** | 2 |
|
||||
| amdpve | 192.168.68.15 | AMD Strix Halo 64GB UMA | qwen3.6-35B-udq4 (LiteLLM alias: strix-moe) | llama-server systemd (Vulkan) | 256K | 2 |
|
||||
|
||||
## Model Fallback Chains (LiteLLM)
|
||||
|
||||
|
||||
@@ -57,9 +57,9 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
|
||||
|
||||
| Host | IP | Hardware | Models Served | Engine | Context | Parallel |
|
||||
|------|-----|----------|---------------|--------|---------|----------|
|
||||
| llm-gpu | 192.168.68.8 | NVIDIA RTX 3090 (24 GB) | qwen3.6-27B-code | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `-c 131072 --parallel 2 --ngl 99`) | **128K** | 2 |
|
||||
| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gemma-4-12b | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `--ctx-size 131072 --parallel 2`, IQ4_NL + MTP draft) | **128K** | 2 |
|
||||
| amdpve | 192.168.68.15 | AMD Strix Halo 64GB UMA | qwen3.6-35B-udq4 (LiteLLM alias: `strix-moe`) | llama-server systemd (Vulkan) | 128K | 2 |
|
||||
| llm-gpu | 192.168.68.8 | NVIDIA RTX 3090 (24 GB) | qwen3.6-27B-code | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `-c 262144 --parallel 2 --ngl 99`) | **256K** | 2 |
|
||||
| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gemma-4-12b | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `--ctx-size 262144 --parallel 2`, IQ4_NL + MTP draft) | **256K** | 2 |
|
||||
| amdpve | 192.168.68.15 | AMD Strix Halo 64GB UMA | qwen3.6-35B-udq4 (LiteLLM alias: `strix-moe`) | llama-server systemd (Vulkan) | 256K | 2 |
|
||||
|
||||
> Verified on ground 2026-07-16 via `curl /v1/models` on each host + `llama-wrapper.sh`. The AMD host's underlying model is `qwen3.6-35B-udq4`; LiteLLM exposes it under two `model_name`s: `qwen3.6-35B-udq4` and `strix-moe` (rpm 40). The legacy name `ornith-1.0-35b` does NOT exist in LiteLLM and must not be referenced.
|
||||
|
||||
@@ -101,7 +101,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
|
||||
## Script Operations (synced 2026-07-16)
|
||||
|
||||
- **Health-check script** (`/opt/inference-harness/scripts/litellm-health-check.sh` on CT 116): `gpu-fleet` check fails only on **critical** alerts (warnings are informational). Tests `strix-moe` (not `ornith-1.0-35b`).
|
||||
- **GPU monitor** (`/root/scripts/gpu-monitor-server.py` on pi .24): runs as **systemd unit `gpu-monitor.service`** (was bare `&` process). `gpu_count` includes Strix Halo (was 2, now 3). VRAM alert thresholds: warning 93%, critical 97% (raised from 90/95 — 128K context steady-state is ~70% on RTX 3090, not a fault).
|
||||
- **GPU monitor** (`/root/scripts/gpu-monitor-server.py` on pi .24): runs as **systemd unit `gpu-monitor.service`** (was bare `&` process). `gpu_count` includes Strix Halo (was 2, now 3). VRAM alert thresholds: warning 93%, critical 97% (raised from 90/95 — 256K context steady-state is ~96% on RTX 3090, not a fault).
|
||||
- **Agent key monitor** (`/root/scripts/agent-health-check.py` on pi .24, cron `*/10`): reads each agent's **live** `LITELLM_API_KEY` from its gateway process env via SSH — never hardcodes keys (hardcoded keys rot on rotation and caused 9×401/30min). Fleet roster: abiba, tanko, mumuni, koby, koonimo (legacy `tdunna`/`baggy` removed — never existed).
|
||||
- **Stale keys cleaned**: `daily-infra-report.py` SYNTHETIC_API_KEY was stale (`sk-U_ydi3B` → 401); now reads `LITELLM_MASTER_KEY` from env. Deprecated scripts (`router-original.py`, `router-phase0-backup.py`, `apply-fixes.py`) still reference `sk-syslog-local-master-key` but do not actively poll LiteLLM.
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ description: >
|
||||
delegation, verification, and delivery. Defines when to delegate, which
|
||||
worker to use for what, how to handle failures, and the kanban board
|
||||
protocol. Enforces context-window discipline and separation of concerns.
|
||||
Runs on Mumuni (lxc/114, hwepve, .123) via Hermes agent.
|
||||
Runs on Mumuni (CT 118, storepve, .6) via Hermes agent.
|
||||
version: 1.0.0
|
||||
---
|
||||
|
||||
@@ -19,8 +19,8 @@ version: 1.0.0
|
||||
|
||||
## Topology
|
||||
|
||||
**Cluster:** 6 Proxmox nodes (ocupve, acerpve, minipve, amdpve, storepve, hwepve)
|
||||
**Manager:** Mumuni (lxc/114, hwepve, .123) via Hermes agent
|
||||
**Cluster:** 5 Proxmox nodes (ocupve, acerpve, minipve, amdpve, storepve)
|
||||
**Manager:** Mumuni (CT 118, storepve, .6) via Hermes agent
|
||||
**Workers:** 6 profiles, all running on the same agent — no separate hosts needed
|
||||
|
||||
This contract is infrastructure-agnostic in terms of which nodes are used.
|
||||
|
||||
@@ -5,7 +5,7 @@ description: >
|
||||
Proxmox cluster + Docker monitoring via the existing Grafana/Prometheus stack
|
||||
on CT 116. Replaces Pulse with file-provisioned Grafana dashboards. Three
|
||||
exporters feed Prometheus: prometheus-pve-exporter (cluster-aware, single
|
||||
instance), node_exporter (all 6 PVE nodes), and a custom docker-stats-exporter
|
||||
instance), node_exporter (all 5 PVE nodes), and a custom docker-stats-exporter
|
||||
(Docker 29 / containerd image-store compatible, since cAdvisor cannot resolve
|
||||
the layerdb). Dashboards exposed at http://192.168.68.116:3001/ (direct LAN, not behind nginx).
|
||||
agent: abiba
|
||||
@@ -33,8 +33,8 @@ agent: abiba
|
||||
|
||||
| Exporter | Host:Port | Scope | Notes |
|
||||
|----------|-----------|-------|-------|
|
||||
| prometheus-pve-exporter | .116:9221 (container) | All 6 nodes + guests + 36 storage pools | Single instance, cluster-aware via amdpve API. Config `/opt/monitoring/pve.yml` (token `monitoring@pve!prometheus`, PVEAuditor role). Metric schema is label-based (`id=node/amdpve`, `id=lxc/100`). |
|
||||
| node_exporter | .5/.6/.9/.12/.15/.4:9100 (systemd) | Per-node CPU/mem/disk/net/temp | Installed via apt on all 6 PVE nodes, enabled (reboot-persistent). Collectors: textfile, systemd, tcpstat, ethtool. hwepve (.4) added 2026-07-19. |
|
||||
| prometheus-pve-exporter | .116:9221 (container) | All 5 nodes + 14 guests + 36 storage pools | Single instance, cluster-aware via amdpve API. Config `/opt/monitoring/pve.yml` (token `monitoring@pve!prometheus`, PVEAuditor role). Metric schema is label-based (`id=node/amdpve`, `id=lxc/100`). |
|
||||
| node_exporter | .5/.6/.9/.12/.15:9100 (systemd) | Per-node CPU/mem/disk/net/temp | Installed via apt on all 5 PVE nodes, enabled (reboot-persistent). Collectors: textfile, systemd, tcpstat, ethtool. |
|
||||
| docker-stats-exporter | .116:9324 (container) | 10 Docker containers on .116 | **Custom** (cAdvisor v0.51 incompatible with Docker 29 containerd image store — layerdb gone). Uses Docker Engine API over unix socket. Script `/opt/monitoring/docker-stats-exporter.py`. |
|
||||
|
||||
## PVE API Token
|
||||
@@ -48,7 +48,7 @@ agent: abiba
|
||||
|
||||
| UID | Title | Panels | Source |
|
||||
|-----|-------|--------|--------|
|
||||
| proxmox-cluster | Proxmox Cluster Overview | 16 | cluster status, 6-node CPU/mem/disk/load gauges, guests table, storage pools, guest CPU/mem timeseries |
|
||||
| proxmox-cluster | Proxmox Cluster Overview | 16 | cluster status, 5-node CPU/mem/disk/load gauges, guests table, storage pools, guest CPU/mem timeseries |
|
||||
| proxmox-node | Proxmox Node Detail | 13 | per-node CPU per-core, memory, network, disk IO/IOPS/latency, temperature, disk space (variable: $node) |
|
||||
| docker-containers | Docker Containers | 10 | per-container CPU/mem/network, restarts, memory limit ratio (variable: $container) |
|
||||
| gpu-fleet | GPU Fleet | 7 | (existing, preserved in DB, not provisioned) |
|
||||
@@ -77,9 +77,9 @@ agent: abiba
|
||||
| `/opt/monitoring/grafana/dashboards/build-dashboards.py` | .116 | dashboard JSON generator |
|
||||
| `/opt/monitoring/grafana/dashboards/json/*.json` | .116 | provisioned dashboard definitions |
|
||||
| `/opt/monitoring/grafana/datasources/prometheus.yml` | .116 | datasource provisioning |
|
||||
| `/etc/default/prometheus-node-exporter` | .5/.6/.9/.12/.15/.4 | node_exporter collector config |
|
||||
| `/etc/default/prometheus-node-exporter` | .5/.6/.9/.12/.15 | node_exporter collector config |
|
||||
|
||||
## Cluster "Tabiri" — 6 Nodes
|
||||
## Cluster "Tabiri" — 5 Nodes
|
||||
|
||||
| Node | IP | Role |
|
||||
|------|----|----|
|
||||
@@ -87,8 +87,7 @@ agent: abiba
|
||||
| storepve | 192.168.68.6 | PVE |
|
||||
| acerpve | 192.168.68.9 | PVE (hosts llm-gpu qemu/101) |
|
||||
| minipve | 192.168.68.12 | PVE |
|
||||
| amdpve | 192.168.68.15 | PVE + Strix Halo LLM (qwen3.6-35B-udq4, strix-moe) |
|
||||
| hwepve | 192.168.68.4 | PVE (Huawei Matebook 16, 12C/15GB) — hosts Mumuni (lxc/114) migrated from minipve 2026-07-20 |
|
||||
| amdpve | 192.168.68.15 | PVE + Strix Halo LLM (ornith) |
|
||||
|
||||
## Operations
|
||||
|
||||
|
||||
+201
-12
@@ -1,9 +1,9 @@
|
||||
---
|
||||
kind: responsibility
|
||||
name: zulip-health
|
||||
description: Multi-platform health monitor for the Zulip messaging mesh spanning Platform A (Agent Zero Docker), Platform B (Hermes agents Tanko/Mumuni), and the Zulip bridge. Verifies bot registration, DM delivery, and cross-platform connectivity.
|
||||
description: Multi-platform health monitor for the Zulip messaging mesh spanning Platform A (Abiba pi), Platform B (Hermes agents Tanko/Mumuni/Koonimo/Koby), and Platform C (Agent Zero). Verifies bot registration, DM delivery, cross-platform connectivity, secret injection, and YAML config integrity.
|
||||
title: Zulip Mesh Health Monitor — Multi-Platform
|
||||
version: 3.0.0
|
||||
version: 3.1.0
|
||||
runtime_contract: 2
|
||||
agent: abiba
|
||||
---
|
||||
@@ -12,11 +12,15 @@ agent: abiba
|
||||
|
||||
Monitors ALL Zulip-connected agents across three platforms (pi, Hermes, Agent Zero).
|
||||
Runs every 15 minutes in the background. Also triggers on session start.
|
||||
v3.1.0 adds Koonimo+Koby to Platform B, Infisical dependency checks, config YAML
|
||||
validation, stale PID/lock detection, Telegram adapter health, and the
|
||||
cli_agent_setup_mixin patch verification.
|
||||
|
||||
## Requires
|
||||
|
||||
- **Zulip API key** for `abiba-bot@chat.sysloggh.net` in `$ZULIP_API_KEY`
|
||||
- **SSH access** to Tanko (192.168.68.122), Mumuni (192.168.68.123, lxc/114 on hwepve since 2026-07-20), and Agent Zero Docker host (192.168.68.14)
|
||||
- **SSH access** to Tanko (192.168.68.122), Mumuni (192.168.68.123), and Agent Zero Docker host (192.168.68.14)
|
||||
- **SSH access to amdpve (192.168.68.15)** for `pct exec` access to Koonimo (CT 113) and Koby (CT 111)
|
||||
- **PM2** on localhost for pi process management
|
||||
- **Network access** to `chat.sysloggh.net`, `localhost:9200`
|
||||
- **Write access** to `/root/zulip-health-monitor.log` and `/tmp/zulip-monitor-debounce`
|
||||
@@ -49,12 +53,22 @@ Runs every 15 minutes in the background. Also triggers on session start.
|
||||
"zulip_state": "connected",
|
||||
"heartbeat_age_seconds": 45,
|
||||
"gateway_pid": 1234,
|
||||
"infisical_present": true,
|
||||
"config_valid": true,
|
||||
"telegram_state": "connected",
|
||||
"no_key_required_count": 0,
|
||||
"edit_fail_rate_pct": 0,
|
||||
"severity": "healthy"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
New fields in v3.1.0:
|
||||
- `infisical_present` — /usr/local/bin/infisical exists on the agent CT
|
||||
- `config_valid` — /root/.hermes/config.yaml passes YAML validation
|
||||
- `telegram_state` — Telegram adapter status from gateway_state.json
|
||||
- `no_key_required_count` — count of `no-key-required` in gateway logs
|
||||
|
||||
### Postconditions
|
||||
|
||||
- Every platform is independently checked; one failure doesn't block others
|
||||
@@ -81,13 +95,13 @@ Log as "unreachable" — don't treat as critical unless it persists for 3+ conse
|
||||
## Streaming Support (2026-07-05)
|
||||
|
||||
Zulip agents now support progressive message editing during agent generation.
|
||||
When a Hermes agent (Tanko, Mumuni) processes a message, the response is
|
||||
streamed in real-time via Zulip's `PATCH /api/v1/messages/{id}` API:
|
||||
When a Hermes agent (Tanko, Mumuni, Koonimo, Koby) processes a message, the
|
||||
response is streamed in real-time via Zulip's `PATCH /api/v1/messages/{id}` API:
|
||||
|
||||
- Adapter implements `edit_message()` using `_api_patch()` helper
|
||||
- Gateway stream consumer progressively edits the Zulip message
|
||||
- User sees real-time agent thinking instead of waiting for full response
|
||||
- Verified: Tanko (CT 112) and Mumuni (CT 114) both have streaming active
|
||||
- Verified: Tanko (CT 112), Mumuni (CT 114), Koonimo (CT 113), Koby (CT 111)
|
||||
|
||||
### Verification
|
||||
```bash
|
||||
@@ -182,50 +196,217 @@ grep -a "Finalized\|Failed to finalize" /root/.pm2/logs/abiba-zulip-out.log | ta
|
||||
| `last_error` set | Log and monitor |
|
||||
| Crash loop >10/h | Alert user |
|
||||
|
||||
### Step 3: Platform B — Hermes (Tanko .122, Mumuni .123)
|
||||
### Step 3: Platform B — Hermes (Tanko .122, Mumuni .123, Koonimo .114, Koby .129)
|
||||
|
||||
Platform B now monitors four Hermes agents:
|
||||
- Tanko (CT 112, 192.168.68.122) — Zulip + Telegram
|
||||
- Mumuni (CT 114, 192.168.68.123) — Zulip + Telegram + Email
|
||||
- Koonimo (CT 113, 192.168.68.114, hostname "baggy") — Zulip + Telegram
|
||||
- Koby (CT 111, 192.168.68.129, hostname "tdunna") — Zulip + Telegram
|
||||
|
||||
SSH access: Koonimo is reachable at .114; Koby has no direct SSH. Use `pct exec`
|
||||
from amdpve as the primary access method for both:
|
||||
```bash
|
||||
ssh root@192.168.68.15 "pct exec 113 -- <command>" # Koonimo (or ssh .114)
|
||||
ssh root@192.168.68.15 "pct exec 111 -- <command>" # Koby (pct exec only)
|
||||
```
|
||||
|
||||
**B1: Gateway State**
|
||||
|
||||
```bash
|
||||
ssh root@192.168.68.122 "cat ~/.hermes/gateway_state.json"
|
||||
ssh root@192.168.68.123 "cat ~/.hermes/gateway_state.json"
|
||||
ssh root@192.168.68.15 "pct exec 113 -- cat /root/.hermes/gateway_state.json"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- cat /root/.hermes/gateway_state.json"
|
||||
```
|
||||
|
||||
Check `platforms.zulip.state`: `connected` ✅ | `disconnected` ❌ | `error` ❌ | missing → not installed.
|
||||
Check `platforms.zulip.state`: `connected` ✅ | `disconnected` ❌ | `error` ❌.
|
||||
|
||||
**B1.5: Infisical Dependency Check**
|
||||
|
||||
```bash
|
||||
ssh root@<CT> "test -f /usr/local/bin/infisical && echo OK || echo MISSING"
|
||||
# pct exec variant for Koonimo/Koby:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- test -f /usr/local/bin/infisical && echo OK || echo MISSING"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- test -f /usr/local/bin/infisical && echo OK || echo MISSING"
|
||||
```
|
||||
|
||||
If MISSING → flag `infisical_present: false`, note as degraded — gateway cannot
|
||||
auto-start on reboot without the infisical binary.
|
||||
|
||||
**B2: Agent Process**
|
||||
|
||||
```bash
|
||||
ssh root@<CT> "ps aux | grep 'gateway run' | grep -v grep"
|
||||
# pct exec variant:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- ps aux | grep 'gateway run' | grep -v grep"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- ps aux | grep 'gateway run' | grep -v grep"
|
||||
```
|
||||
|
||||
Gateway PID should exist with uptime > 60s. **Dual-gateway detection**: if more than one `gateway run` process is found, the gateway has a collision (typically one `--force` and one `--replace` process). Kill the newer/duplicate process, then restart the remaining gateway via PM2 (`pm2 restart mumuni-zulip`). Check gateway log for "Gateway running with 2 platform(s)" (not 1) to confirm Zulip reloaded.
|
||||
Gateway PID should exist with uptime > 60s. Check for stale PIDs:
|
||||
- `gateway.pid` and `gateway.lock` files that reference a dead process
|
||||
- Multiple gateway processes (duplicate PIDs)
|
||||
|
||||
**B2.5: Config YAML Validation**
|
||||
|
||||
```bash
|
||||
ssh root@<CT> "python3 -c 'import yaml; yaml.safe_load(open(\"/root/.hermes/config.yaml\"))' 2>&1"
|
||||
# pct exec variant:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- python3 -c 'import yaml; yaml.safe_load(open(\"/root/.hermes/config.yaml\"))' 2>&1"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- python3 -c 'import yaml; yaml.safe_load(open(\"/root/.hermes/config.yaml\"))' 2>&1"
|
||||
```
|
||||
|
||||
Expected: no output (clean parse). If parse fails → flag `config_valid: false`,
|
||||
degraded — gateway is running on stale in-memory config.
|
||||
|
||||
Check specifically for:
|
||||
- Stray `api_key: sk-...` lines indented under `api_key_env` entries in
|
||||
`custom_providers` section (hardcoded keys violate hermes-key-enforcement)
|
||||
- Indentation errors in `custom_providers`, `auxiliary`, or `compression` blocks
|
||||
|
||||
**B3: Heartbeat Verification**
|
||||
|
||||
```bash
|
||||
ssh root@<CT> "grep Heartbeat ~/.hermes/logs/agent.log | tail -3"
|
||||
# pct exec variant:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- grep Heartbeat /root/.hermes/logs/agent.log | tail -3"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- grep Heartbeat /root/.hermes/logs/agent.log | tail -3"
|
||||
```
|
||||
|
||||
Expected: recent heartbeat (within 5 min), `polls=N` incrementing.
|
||||
Silence > 300s → warning. Silence > 600s → critical.
|
||||
|
||||
**B3.5: Stale PID/Lock Detection**
|
||||
|
||||
Before any restart action, check for stale pid/lock files:
|
||||
|
||||
```bash
|
||||
ssh root@<CT> "ls -la /root/.hermes/gateway.pid /root/.hermes/gateway.lock 2>/dev/null"
|
||||
# pct exec variant:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- ls -la /root/.hermes/gateway.pid /root/.hermes/gateway.lock 2>/dev/null"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- ls -la /root/.hermes/gateway.pid /root/.hermes/gateway.lock 2>/dev/null"
|
||||
```
|
||||
|
||||
If gateway process is dead (no PID) but pid/lock files exist:
|
||||
```bash
|
||||
ssh root@<CT> "rm -f /root/.hermes/gateway.pid /root/.hermes/gateway.lock"
|
||||
# pct exec variant:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- rm -f /root/.hermes/gateway.pid /root/.hermes/gateway.lock"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- rm -f /root/.hermes/gateway.pid /root/.hermes/gateway.lock"
|
||||
```
|
||||
|
||||
Pid/lock files blocking restart → clear them before restart attempt.
|
||||
|
||||
**B4: Response Delivery**
|
||||
|
||||
```bash
|
||||
ssh root@<CT> "grep -E 'Finalized|Failed to finalize|Replied to' ~/.hermes/logs/agent.log | tail -10"
|
||||
# pct exec variant for Koonimo/Koby:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- grep -E 'Finalized|Failed to finalize|Replied to' /root/.hermes/logs/agent.log | tail -10"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- grep -E 'Finalized|Failed to finalize|Replied to' /root/.hermes/logs/agent.log | tail -10"
|
||||
```
|
||||
|
||||
> 50% fail rate → critical.
|
||||
|
||||
**B4.5: LiteLLM Key Injection Verification**
|
||||
|
||||
Check gateway logs for `no-key-required` failure pattern (indicates the
|
||||
cli_agent_setup_mixin.py patch is missing):
|
||||
|
||||
```bash
|
||||
ssh root@<CT> "grep -c 'no-key-required' /root/.hermes/logs/gateway.log 2>/dev/null || echo 0"
|
||||
# pct exec variant for Koonimo/Koby:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- grep -c 'no-key-required' /root/.hermes/logs/gateway.log 2>/dev/null || echo 0"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- grep -c 'no-key-required' /root/.hermes/logs/gateway.log 2>/dev/null || echo 0"
|
||||
```
|
||||
|
||||
If > 0 → flag `no_key_required_count: <count>`, note as degraded — provider
|
||||
requests silently fall back to `no-key-required` when LITELLM_API_KEY env var
|
||||
resolves empty.
|
||||
|
||||
**B5: Telegram Adapter Health**
|
||||
|
||||
Check Telegram connectivity in gateway state or logs:
|
||||
|
||||
```bash
|
||||
# From gateway_state.json (all agents):
|
||||
ssh root@<CT> "cat ~/.hermes/gateway_state.json | python3 -c 'import json,sys;d=json.load(sys.stdin);print(d[\"platforms\"].get(\"telegram\",{}).get(\"state\",\"missing\"))'"
|
||||
# pct exec variant for Koonimo/Koby (cat the file; read platforms.telegram.state):
|
||||
ssh root@192.168.68.15 "pct exec 113 -- cat /root/.hermes/gateway_state.json"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- cat /root/.hermes/gateway_state.json"
|
||||
# From logs (check for stuck DNS resolution):
|
||||
ssh root@<CT> "grep -E 'Telegram.*Connecting|Telegram.*Connected|attempt 1/8' /root/.hermes/logs/gateway.log | tail -5"
|
||||
ssh root@192.168.68.15 "pct exec 113 -- grep -E 'Telegram.*Connecting|Telegram.*Connected|attempt 1/8' /root/.hermes/logs/gateway.log | tail -5"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- grep -E 'Telegram.*Connecting|Telegram.*Connected|attempt 1/8' /root/.hermes/logs/gateway.log | tail -5"
|
||||
```
|
||||
|
||||
Telegram states: `connected` ✅ | `disconnected` ❌ | `retrying` ⚠️ | `fatal` ❌ | `paused` ⚠️
|
||||
|
||||
If stuck on "attempt 1/8" for > 60s → flag Telegram as degraded (Zulip may
|
||||
still be fine — do NOT treat as Zulip outage).
|
||||
|
||||
**B6: cli_agent_setup_mixin.py Patch Verification**
|
||||
|
||||
Check whether the `no-key-required` fallback string exists without the
|
||||
LiteLLM-specific guard (only needed when LiteLLM key injection failures are
|
||||
suspected). A bare count of the fallback string cannot distinguish a guarded
|
||||
occurrence from an unguarded one, so count both the fallback string and the
|
||||
LiteLLM guard token:
|
||||
|
||||
```bash
|
||||
ssh root@<CT> "f=\$(grep -c 'no-key-required' /usr/local/lib/hermes-agent/hermes_cli/cli_agent_setup_mixin.py 2>/dev/null || echo 0); g=\$(grep -c 'LITELLM_API_KEY' /usr/local/lib/hermes-agent/hermes_cli/cli_agent_setup_mixin.py 2>/dev/null || echo 0); echo fallback=\$f guard=\$g"
|
||||
# pct exec variant:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- bash -c 'f=\$(grep -c no-key-required /usr/local/lib/hermes-agent/hermes_cli/cli_agent_setup_mixin.py 2>/dev/null || echo 0); g=\$(grep -c LITELLM_API_KEY /usr/local/lib/hermes-agent/hermes_cli/cli_agent_setup_mixin.py 2>/dev/null || echo 0); echo fallback=\$f guard=\$g'"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- bash -c 'f=\$(grep -c no-key-required /usr/local/lib/hermes-agent/hermes_cli/cli_agent_setup_mixin.py 2>/dev/null || echo 0); g=\$(grep -c LITELLM_API_KEY /usr/local/lib/hermes-agent/hermes_cli/cli_agent_setup_mixin.py 2>/dev/null || echo 0); echo fallback=\$f guard=\$g'"
|
||||
```
|
||||
|
||||
If `fallback > 0` and `guard == 0` → the fallback string is present without
|
||||
the LiteLLM-specific guard, so the patch is missing. If unsure, inspect each
|
||||
occurrence with `grep -n -B2 -A2 'no-key-required'` to confirm the guard
|
||||
wraps it.
|
||||
|
||||
**Platform B Actions**
|
||||
|
||||
| Condition | Action |
|
||||
|-----------|--------|
|
||||
| `zulip.state != "connected"` | `ssh root@<CT> "pkill -f 'gateway run'; sleep 2; hermes gateway restart"` |
|
||||
| No heartbeat in 10min | Same as above |
|
||||
| `zulip.state != "connected"` | Restart gateway (see B2 restart commands below) |
|
||||
| No heartbeat in 10min | Restart gateway |
|
||||
| `Failed to finalize` > 50% | Check PATCH API, Zulip server |
|
||||
| Response empty/short | Check A2A endpoint / LiteLLM model |
|
||||
| `infisical_present: false` | Flag as degraded — log and alert; do NOT auto-restart via the standard command (it cannot inject the key without infisical). Operator may use the Infisical-missing fallback restart below. |
|
||||
| `config_valid: false` | Flag as degraded — alert user, gateway running on stale config |
|
||||
| Stale pid/lock files detected | Clean files before restart |
|
||||
| `no_key_required_count > 0` | Flag as degraded — check LITELLM_API_KEY injection |
|
||||
| Telegram stuck on attempt 1/8 | Flag Telegram as degraded, no Zulip action needed |
|
||||
|
||||
**Restart Commands**
|
||||
|
||||
Standard restart (Infisical present):
|
||||
```bash
|
||||
ssh root@<CT> "pkill -f 'gateway run'; sleep 2; hermes gateway restart"
|
||||
# pct exec variant:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- bash -c 'pkill -f \"gateway run\"; sleep 2; systemctl restart hermes-gateway'"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- bash -c 'pkill -f \"gateway run\"; sleep 2; systemctl restart hermes-gateway'"
|
||||
```
|
||||
|
||||
The mechanisms differ by design: Tanko/Mumuni launch the gateway through a
|
||||
wrapper loop, so the `hermes gateway restart` CLI is the correct entry point
|
||||
(it re-arms the wrapper). Koonimo/Koby run the gateway as a systemd unit
|
||||
(`hermes-gateway.service`), so `systemctl restart hermes-gateway` is the
|
||||
correct entry point under `pct exec`. Do not swap the two — using the CLI on
|
||||
Koonimo/Koby would bypass the unit, and using `systemctl` on Tanko/Mumuni
|
||||
would miss the wrapper loop.
|
||||
|
||||
Fallback: Infisical missing → start gateway directly from venv with env vars:
|
||||
```bash
|
||||
ssh root@<CT> "source /usr/local/lib/hermes-agent/venv/bin/activate && \
|
||||
export LITELLM_API_KEY=\$(grep -E '^LITELLM_API_KEY=' /root/.hermes/.env | cut -d= -f2-) && \
|
||||
export ZULIP_API_KEY=\$(grep -E '^ZULIP_API_KEY=' /root/.hermes/.env | cut -d= -f2-) && \
|
||||
cd /root/.hermes && nohup hermes gateway run > logs/gateway-manual-start.log 2>&1 &"
|
||||
# pct exec variant:
|
||||
ssh root@192.168.68.15 "pct exec 113 -- bash -c 'source /usr/local/lib/hermes-agent/venv/bin/activate; export LITELLM_API_KEY=\$(grep -E ^LITELLM_API_KEY= /root/.hermes/.env | cut -d= -f2-); export ZULIP_API_KEY=\$(grep -E ^ZULIP_API_KEY= /root/.hermes/.env | cut -d= -f2-); cd /root/.hermes; nohup hermes gateway run > logs/gateway-manual-start.log 2>&1 &'"
|
||||
ssh root@192.168.68.15 "pct exec 111 -- bash -c 'source /usr/local/lib/hermes-agent/venv/bin/activate; export LITELLM_API_KEY=\$(grep -E ^LITELLM_API_KEY= /root/.hermes/.env | cut -d= -f2-); export ZULIP_API_KEY=\$(grep -E ^ZULIP_API_KEY= /root/.hermes/.env | cut -d= -f2-); cd /root/.hermes; nohup hermes gateway run > logs/gateway-manual-start.log 2>&1 &'"
|
||||
```
|
||||
|
||||
### Step 4: Platform C — Agent Zero (kagentz, CT 105 via Docker host .14)
|
||||
|
||||
@@ -278,7 +459,7 @@ Expected: task ID with "working" status. Poll for completion with `tasks/get`.
|
||||
|
||||
Check each agent's log for excessive bot-to-bot chatter:
|
||||
- Abiba: `Skipped.*bot msgs` count
|
||||
- Tanko/Mumuni: Repeated DM exchanges between bots
|
||||
- Tanko/Mumuni/Koonimo/Koby: Repeated DM exchanges between bots
|
||||
- kagentz: Adapter log for bot DMs being processed
|
||||
|
||||
If any bot processes >50 bot-originated messages in 15min → warning.
|
||||
@@ -301,6 +482,14 @@ Track via `/tmp/zulip-monitor-debounce` (unix timestamp of last restart).
|
||||
|
||||
## History
|
||||
|
||||
### v3.1.0 (2026-07-23) — Koonimo Outage Lessons
|
||||
|
||||
Added Koonimo (CT 113) and Koby (CT 111) to Platform B monitoring.
|
||||
Added Infisical dependency check, config YAML validation, stale PID/lock
|
||||
detection, Telegram adapter health, LiteLLM key injection verification, and
|
||||
cli_agent_setup_mixin.py patch verification. Updated restart commands with
|
||||
Infisical-missing fallback path.
|
||||
|
||||
### Gen 5 (2026-07-02) — Rate Limit Death Spiral Fix
|
||||
|
||||
**Root Cause**: Proactive Queue Rotation at 25 min triggered queue re-registration every cycle. Each re-registration + retry loop (3 attempts) + monitor restart = 8-12 API calls per cycle. Combined with monitor's own API calls (server check, stream alerts), `abiba-bot` hit Zulip's rate limit (429 RATE_LIMIT_HIT). Each restart reset the cycle, creating a death spiral: 111 restarts in 24 hours.
|
||||
|
||||
Reference in New Issue
Block a user