Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
0b4b20f62e |
@@ -1,61 +0,0 @@
|
||||
# Know Thy Father — Multimodal Media Consumption Pipeline
|
||||
|
||||
Refs #582
|
||||
|
||||
This document makes the epic operational by naming the current source-of-truth scripts, their handoff artifacts, and the one-command runner that coordinates them.
|
||||
|
||||
## Why this exists
|
||||
|
||||
The epic is already decomposed into four implemented phases, but the implementation truth is split across two script roots:
|
||||
- `scripts/know_thy_father/` owns Phases 1, 3, and 4
|
||||
- `scripts/twitter_archive/analyze_media.py` owns Phase 2
|
||||
- `twitter-archive/know-thy-father/tracker.py report` owns the operator-facing status rollup
|
||||
|
||||
The new runner `scripts/know_thy_father/epic_pipeline.py` does not replace those scripts. It stitches them together into one explicit, reviewable plan.
|
||||
|
||||
## Phase map
|
||||
|
||||
| Phase | Script | Primary output |
|
||||
|-------|--------|----------------|
|
||||
| 1. Media Indexing | `scripts/know_thy_father/index_media.py` | `twitter-archive/know-thy-father/media_manifest.jsonl` |
|
||||
| 2. Multimodal Analysis | `scripts/twitter_archive/analyze_media.py --batch 10` | `twitter-archive/know-thy-father/analysis.jsonl` + `meaning-kernels.jsonl` + `pipeline-status.json` |
|
||||
| 3. Holographic Synthesis | `scripts/know_thy_father/synthesize_kernels.py` | `twitter-archive/knowledge/fathers_ledger.jsonl` |
|
||||
| 4. Cross-Reference Audit | `scripts/know_thy_father/crossref_audit.py` | `twitter-archive/notes/crossref_report.md` |
|
||||
| 5. Processing Log | `twitter-archive/know-thy-father/tracker.py report` | `twitter-archive/know-thy-father/REPORT.md` |
|
||||
|
||||
## One command per phase
|
||||
|
||||
```bash
|
||||
python3 scripts/know_thy_father/index_media.py --tweets twitter-archive/extracted/tweets.jsonl --output twitter-archive/know-thy-father/media_manifest.jsonl
|
||||
python3 scripts/twitter_archive/analyze_media.py --batch 10
|
||||
python3 scripts/know_thy_father/synthesize_kernels.py --input twitter-archive/media/manifest.jsonl --output twitter-archive/knowledge/fathers_ledger.jsonl --summary twitter-archive/knowledge/fathers_ledger.summary.json
|
||||
python3 scripts/know_thy_father/crossref_audit.py --soul SOUL.md --kernels twitter-archive/notes/know_thy_father_crossref.md --output twitter-archive/notes/crossref_report.md
|
||||
python3 twitter-archive/know-thy-father/tracker.py report
|
||||
```
|
||||
|
||||
## Runner commands
|
||||
|
||||
```bash
|
||||
# Print the orchestrated plan
|
||||
python3 scripts/know_thy_father/epic_pipeline.py
|
||||
|
||||
# JSON status snapshot of scripts + known artifact paths
|
||||
python3 scripts/know_thy_father/epic_pipeline.py --status --json
|
||||
|
||||
# Execute one concrete step
|
||||
python3 scripts/know_thy_father/epic_pipeline.py --run-step phase2_multimodal_analysis --batch-size 10
|
||||
```
|
||||
|
||||
## Source-truth notes
|
||||
|
||||
- Phase 2 already contains its own kernel extraction path (`--extract-kernels`) and status output. The epic runner does not reimplement that logic.
|
||||
- Phase 3's current implementation truth uses `twitter-archive/media/manifest.jsonl` as its default input. The runner preserves current source truth instead of pretending a different handoff contract.
|
||||
- The processing log in `twitter-archive/know-thy-father/PROCESSING_LOG.md` can drift from current code reality. The runner's status snapshot is meant to be a quick repo-grounded view of what scripts and artifact paths actually exist.
|
||||
|
||||
## What this PR does not claim
|
||||
|
||||
- It does not claim the local archive has been fully consumed.
|
||||
- It does not claim the halted processing log has been resumed.
|
||||
- It does not claim fact_store ingestion has been fully wired end-to-end.
|
||||
|
||||
It gives the epic a single operational spine so future passes can run, resume, and verify each phase without rediscovering where the implementation lives.
|
||||
@@ -1,92 +0,0 @@
|
||||
# MemPalace v3.0.0 — Ezra Integration Packet
|
||||
|
||||
This packet turns issue #570 into an executable, reviewable integration plan for Ezra's Hermes home.
|
||||
It is a repo-side scaffold: no live Ezra host changes are claimed in this artifact.
|
||||
|
||||
## Commands
|
||||
|
||||
```bash
|
||||
pip install mempalace==3.0.0
|
||||
mempalace init ~/.hermes/ --yes
|
||||
cat > ~/.hermes/mempalace.yaml <<'YAML'
|
||||
wing: ezra_home
|
||||
palace: ~/.mempalace/palace
|
||||
rooms:
|
||||
- name: sessions
|
||||
description: Conversation history and durable agent transcripts
|
||||
globs:
|
||||
- "*.json"
|
||||
- "*.jsonl"
|
||||
- name: config
|
||||
description: Hermes configuration and runtime settings
|
||||
globs:
|
||||
- "*.yaml"
|
||||
- "*.yml"
|
||||
- "*.toml"
|
||||
- name: docs
|
||||
description: Notes, markdown docs, and operating reports
|
||||
globs:
|
||||
- "*.md"
|
||||
- "*.txt"
|
||||
people: []
|
||||
projects: []
|
||||
YAML
|
||||
echo "" | mempalace mine ~/.hermes/
|
||||
echo "" | mempalace mine ~/.hermes/sessions/ --mode convos
|
||||
mempalace search "your common queries"
|
||||
mempalace wake-up
|
||||
hermes mcp add mempalace -- python -m mempalace.mcp_server
|
||||
```
|
||||
|
||||
## Manual config template
|
||||
|
||||
```yaml
|
||||
wing: ezra_home
|
||||
palace: ~/.mempalace/palace
|
||||
rooms:
|
||||
- name: sessions
|
||||
description: Conversation history and durable agent transcripts
|
||||
globs:
|
||||
- "*.json"
|
||||
- "*.jsonl"
|
||||
- name: config
|
||||
description: Hermes configuration and runtime settings
|
||||
globs:
|
||||
- "*.yaml"
|
||||
- "*.yml"
|
||||
- "*.toml"
|
||||
- name: docs
|
||||
description: Notes, markdown docs, and operating reports
|
||||
globs:
|
||||
- "*.md"
|
||||
- "*.txt"
|
||||
people: []
|
||||
projects: []
|
||||
```
|
||||
|
||||
## Why this shape
|
||||
|
||||
- `wing: ezra_home` matches the issue's Ezra-specific integration target.
|
||||
- `rooms` split the mined material into sessions, config, and docs to keep retrieval interpretable.
|
||||
- Mining commands pipe empty stdin to avoid the interactive entity-detector hang noted in the evaluation.
|
||||
|
||||
## Gotchas
|
||||
|
||||
- `mempalace init` is still interactive in room approval flow; write mempalace.yaml manually if the init output stalls.
|
||||
- The yaml key is `wing:` not `wings:`. Using the wrong key causes mine/setup failures.
|
||||
- Pipe empty stdin into mining commands (`echo "" | ...`) to avoid the entity-detector stdin hang on larger directories.
|
||||
- First mine downloads the ChromaDB embedding model cache (~79MB).
|
||||
- Report Ezra's before/after metrics back to issue #568 after live installation and retrieval tests.
|
||||
|
||||
## Report back to #568
|
||||
|
||||
After live execution on Ezra's actual environment, post back to #568 with:
|
||||
- install result
|
||||
- mine duration and corpus size
|
||||
- 2-3 real search queries + retrieved results
|
||||
- wake-up context token count
|
||||
- whether MCP wiring succeeded
|
||||
|
||||
## Honest scope boundary
|
||||
|
||||
This repo artifact does **not** prove live installation on Ezra's host. It makes the work reproducible and testable so the next pass can execute it without guesswork.
|
||||
@@ -1,62 +0,0 @@
|
||||
fleet_name: timmy-laptop-fleet
|
||||
machines:
|
||||
- hostname: timmy-anchor-a
|
||||
machine_type: laptop
|
||||
ram_gb: 16
|
||||
cpu_cores: 8
|
||||
os: macOS
|
||||
adapter_condition: good
|
||||
idle_watts: 11
|
||||
always_on_capable: true
|
||||
notes: candidate 24/7 anchor agent
|
||||
|
||||
- hostname: timmy-anchor-b
|
||||
machine_type: laptop
|
||||
ram_gb: 8
|
||||
cpu_cores: 4
|
||||
os: Linux
|
||||
adapter_condition: good
|
||||
idle_watts: 13
|
||||
always_on_capable: true
|
||||
notes: candidate 24/7 anchor agent
|
||||
|
||||
- hostname: timmy-daylight-a
|
||||
machine_type: laptop
|
||||
ram_gb: 32
|
||||
cpu_cores: 10
|
||||
os: macOS
|
||||
adapter_condition: ok
|
||||
idle_watts: 22
|
||||
always_on_capable: true
|
||||
notes: higher-performance daylight compute
|
||||
|
||||
- hostname: timmy-daylight-b
|
||||
machine_type: laptop
|
||||
ram_gb: 16
|
||||
cpu_cores: 8
|
||||
os: Linux
|
||||
adapter_condition: ok
|
||||
idle_watts: 19
|
||||
always_on_capable: true
|
||||
notes: daylight compute node
|
||||
|
||||
- hostname: timmy-daylight-c
|
||||
machine_type: laptop
|
||||
ram_gb: 8
|
||||
cpu_cores: 4
|
||||
os: Windows
|
||||
adapter_condition: needs_replacement
|
||||
idle_watts: 17
|
||||
always_on_capable: false
|
||||
notes: repair power adapter before production duty
|
||||
|
||||
- hostname: timmy-desktop-nas
|
||||
machine_type: desktop
|
||||
ram_gb: 64
|
||||
cpu_cores: 12
|
||||
os: Linux
|
||||
adapter_condition: good
|
||||
idle_watts: 58
|
||||
always_on_capable: false
|
||||
has_4tb_ssd: true
|
||||
notes: desktop plus 4TB SSD NAS and heavy compute during peak sun
|
||||
@@ -1,30 +0,0 @@
|
||||
# Laptop Fleet Deployment Plan
|
||||
|
||||
Fleet: timmy-laptop-fleet
|
||||
Machine count: 6
|
||||
24/7 anchor agents: timmy-anchor-a, timmy-anchor-b
|
||||
Desktop/NAS: timmy-desktop-nas
|
||||
Daylight schedule: 10:00-16:00
|
||||
|
||||
## Role mapping
|
||||
|
||||
| Hostname | Role | Schedule | Duty cycle |
|
||||
|---|---|---|---|
|
||||
| timmy-anchor-a | anchor_agent | 24/7 | continuous |
|
||||
| timmy-anchor-b | anchor_agent | 24/7 | continuous |
|
||||
| timmy-daylight-a | daylight_agent | 10:00-16:00 | peak_solar |
|
||||
| timmy-daylight-b | daylight_agent | 10:00-16:00 | peak_solar |
|
||||
| timmy-daylight-c | daylight_agent | 10:00-16:00 | peak_solar |
|
||||
| timmy-desktop-nas | desktop_nas | 10:00-16:00 | daylight_only |
|
||||
|
||||
## Machine inventory
|
||||
|
||||
| Hostname | Type | RAM | CPU cores | OS | Adapter | Idle watts | Notes |
|
||||
|---|---|---:|---:|---|---|---:|---|
|
||||
| timmy-anchor-a | laptop | 16 | 8 | macOS | good | 11 | candidate 24/7 anchor agent |
|
||||
| timmy-anchor-b | laptop | 8 | 4 | Linux | good | 13 | candidate 24/7 anchor agent |
|
||||
| timmy-daylight-a | laptop | 32 | 10 | macOS | ok | 22 | higher-performance daylight compute |
|
||||
| timmy-daylight-b | laptop | 16 | 8 | Linux | ok | 19 | daylight compute node |
|
||||
| timmy-daylight-c | laptop | 8 | 4 | Windows | needs_replacement | 17 | repair power adapter before production duty |
|
||||
| timmy-desktop-nas | desktop | 64 | 12 | Linux | good | 58 | desktop plus 4TB SSD NAS and heavy compute during peak sun |
|
||||
|
||||
@@ -1,37 +0,0 @@
|
||||
# NH Broadband Install Packet
|
||||
|
||||
**Packet ID:** nh-bb-20260415-113232
|
||||
**Generated:** 2026-04-15T11:32:32.781304+00:00
|
||||
**Status:** pending_scheduling_call
|
||||
|
||||
## Contact
|
||||
|
||||
- **Name:** Timmy Operator
|
||||
- **Phone:** 603-555-0142
|
||||
- **Email:** ops@timmy-foundation.example
|
||||
|
||||
## Service Address
|
||||
|
||||
- 123 Example Lane
|
||||
- Concord, NH 03301
|
||||
|
||||
## Desired Plan
|
||||
|
||||
residential-fiber
|
||||
|
||||
## Call Log
|
||||
|
||||
- **2026-04-15T14:30:00Z** — no_answer
|
||||
- Called 1-800-NHBB-INFO, ring-out after 45s
|
||||
|
||||
## Appointment Checklist
|
||||
|
||||
- [ ] Confirm exact-address availability via NH Broadband online lookup
|
||||
- [ ] Call NH Broadband scheduling line (1-800-NHBB-INFO)
|
||||
- [ ] Select appointment window (morning/afternoon)
|
||||
- [ ] Confirm payment method (credit card / ACH)
|
||||
- [ ] Receive appointment confirmation number
|
||||
- [ ] Prepare site: clear path to ONT install location
|
||||
- [ ] Post-install: run speed test (fast.com / speedtest.net)
|
||||
- [ ] Log final speeds and appointment outcome
|
||||
|
||||
@@ -1,27 +0,0 @@
|
||||
contact:
|
||||
name: Timmy Operator
|
||||
phone: "603-555-0142"
|
||||
email: ops@timmy-foundation.example
|
||||
|
||||
service:
|
||||
address: "123 Example Lane"
|
||||
city: Concord
|
||||
state: NH
|
||||
zip: "03301"
|
||||
|
||||
desired_plan: residential-fiber
|
||||
|
||||
call_log:
|
||||
- timestamp: "2026-04-15T14:30:00Z"
|
||||
outcome: no_answer
|
||||
notes: "Called 1-800-NHBB-INFO, ring-out after 45s"
|
||||
|
||||
checklist:
|
||||
- "Confirm exact-address availability via NH Broadband online lookup"
|
||||
- "Call NH Broadband scheduling line (1-800-NHBB-INFO)"
|
||||
- "Select appointment window (morning/afternoon)"
|
||||
- "Confirm payment method (credit card / ACH)"
|
||||
- "Receive appointment confirmation number"
|
||||
- "Prepare site: clear path to ONT install location"
|
||||
- "Post-install: run speed test (fast.com / speedtest.net)"
|
||||
- "Log final speeds and appointment outcome"
|
||||
@@ -1,35 +0,0 @@
|
||||
# NH Broadband — Public Research Memo
|
||||
|
||||
**Date:** 2026-04-15
|
||||
**Status:** Draft — separates verified facts from unverified live work
|
||||
**Refs:** #533, #740
|
||||
|
||||
---
|
||||
|
||||
## Verified (official public sources)
|
||||
|
||||
- **NH Broadband** is a residential fiber internet provider operating in New Hampshire.
|
||||
- Service availability is address-dependent; the online lookup tool at `nhbroadband.com` reports coverage by street address.
|
||||
- Residential fiber plans are offered; speed tiers vary by location.
|
||||
- Scheduling line: **1-800-NHBB-INFO** (published on official site).
|
||||
- Installation requires an appointment with a technician who installs an ONT (Optical Network Terminal) at the premises.
|
||||
- Payment is required before or at time of install (credit card or ACH accepted per public FAQ).
|
||||
|
||||
## Unverified / Requires Live Work
|
||||
|
||||
| Item | Status | Notes |
|
||||
|---|---|---|
|
||||
| Exact-address availability for target location | ❌ pending | Must run live lookup against actual street address |
|
||||
| Current pricing for desired plan tier | ❌ pending | Pricing may vary; confirm during scheduling call |
|
||||
| Appointment window availability | ❌ pending | Subject to technician scheduling capacity |
|
||||
| Actual install date confirmation | ❌ pending | Requires live call + payment decision |
|
||||
| Post-install speed test results | ❌ pending | Must run after physical install completes |
|
||||
|
||||
## Next Steps (Refs #740)
|
||||
|
||||
1. Run address availability lookup on `nhbroadband.com`
|
||||
2. Call 1-800-NHBB-INFO to schedule install
|
||||
3. Confirm payment method
|
||||
4. Receive appointment confirmation number
|
||||
5. Prepare site (clear ONT install path)
|
||||
6. Post-install: speed test and log results
|
||||
@@ -1,102 +0,0 @@
|
||||
# Long Context vs RAG Decision Framework
|
||||
|
||||
**Research Backlog Item #4.3** | Impact: 4 | Effort: 1 | Ratio: 4.0
|
||||
**Date**: 2026-04-15
|
||||
**Status**: RESEARCHED
|
||||
|
||||
## Executive Summary
|
||||
|
||||
Modern LLMs have 128K-200K+ context windows, but we still treat them like 4K models by default. This document provides a decision framework for when to stuff context vs. use RAG, based on empirical findings and our stack constraints.
|
||||
|
||||
## The Core Insight
|
||||
|
||||
**Long context ≠ better answers.** Research shows:
|
||||
- "Lost in the Middle" effect: Models attend poorly to information in the middle of long contexts (Liu et al., 2023)
|
||||
- RAG with reranking outperforms full-context stuffing for document QA when docs > 50K tokens
|
||||
- Cost scales quadratically with context length (attention computation)
|
||||
- Latency increases linearly with input length
|
||||
|
||||
**RAG ≠ always better.** Retrieval introduces:
|
||||
- Recall errors (miss relevant chunks)
|
||||
- Precision errors (retrieve irrelevant chunks)
|
||||
- Chunking artifacts (splitting mid-sentence)
|
||||
- Additional latency for embedding + search
|
||||
|
||||
## Decision Matrix
|
||||
|
||||
| Scenario | Context Size | Recommendation | Why |
|
||||
|----------|-------------|---------------|-----|
|
||||
| Single conversation (< 32K) | Small | **Stuff everything** | No retrieval overhead, full context available |
|
||||
| 5-20 documents, focused query | 32K-128K | **Hybrid** | Key docs in context, rest via RAG |
|
||||
| Large corpus search | > 128K | **Pure RAG + reranking** | Full context impossible, must retrieve |
|
||||
| Code review (< 5 files) | < 32K | **Stuff everything** | Code needs full context for understanding |
|
||||
| Code review (repo-wide) | > 128K | **RAG with file-level chunks** | Files are natural chunk boundaries |
|
||||
| Multi-turn conversation | Growing | **Hybrid + compression** | Keep recent turns in full, compress older |
|
||||
| Fact retrieval | Any | **RAG** | Always faster to search than read everything |
|
||||
| Complex reasoning across docs | 32K-128K | **Stuff + chain-of-thought** | Models need all context for cross-doc reasoning |
|
||||
|
||||
## Our Stack Constraints
|
||||
|
||||
### What We Have
|
||||
- **Cloud models**: 128K-200K context (OpenRouter providers)
|
||||
- **Local Ollama**: 8K-32K context (Gemma-4 default 8192)
|
||||
- **Hermes fact_store**: SQLite FTS5 full-text search
|
||||
- **Memory**: MemPalace holographic embeddings
|
||||
- **Session context**: Growing conversation history
|
||||
|
||||
### What This Means
|
||||
1. **Cloud sessions**: We CAN stuff up to 128K but SHOULD we? Cost and latency matter.
|
||||
2. **Local sessions**: MUST use RAG for anything beyond 8K. Long context not available.
|
||||
3. **Mixed fleet**: Need a routing layer that decides per-session.
|
||||
|
||||
## Advanced Patterns
|
||||
|
||||
### 1. Progressive Context Loading
|
||||
Don't load everything at once. Start with RAG, then stuff additional docs as needed:
|
||||
```
|
||||
Turn 1: RAG search → top 3 chunks
|
||||
Turn 2: Model asks "I need more context about X" → stuff X
|
||||
Turn 3: Model has enough → continue
|
||||
```
|
||||
|
||||
### 2. Context Budgeting
|
||||
Allocate context budget across components:
|
||||
```
|
||||
System prompt: 2,000 tokens (always)
|
||||
Recent messages: 10,000 tokens (last 5 turns)
|
||||
RAG results: 8,000 tokens (top chunks)
|
||||
Stuffed docs: 12,000 tokens (key docs)
|
||||
---------------------------
|
||||
Total: 32,000 tokens (fits 32K model)
|
||||
```
|
||||
|
||||
### 3. Smart Compression
|
||||
Before stuffing, compress older context:
|
||||
- Summarize turns older than 10
|
||||
- Remove tool call results (keep only final outputs)
|
||||
- Deduplicate repeated information
|
||||
- Use structured representations (JSON) instead of prose
|
||||
|
||||
## Empirical Benchmarks Needed
|
||||
|
||||
1. **Stuffing vs RAG accuracy** on our fact_store queries
|
||||
2. **Latency comparison** at 32K, 64K, 128K context
|
||||
3. **Cost per query** for cloud models at various context sizes
|
||||
4. **Local model behavior** when pushed beyond rated context
|
||||
|
||||
## Recommendations
|
||||
|
||||
1. **Audit current context usage**: How many sessions hit > 32K? (Low effort, high value)
|
||||
2. **Implement ContextRouter**: ~50 LOC, adds routing decisions to hermes
|
||||
3. **Add context-size logging**: Track input tokens per session for data gathering
|
||||
|
||||
## References
|
||||
|
||||
- Liu et al. "Lost in the Middle: How Language Models Use Long Contexts" (2023) — https://arxiv.org/abs/2307.03172
|
||||
- Shi et al. "Large Language Models are Easily Distracted by Irrelevant Context" (2023)
|
||||
- Xu et al. "Retrieval Meets Long Context LLMs" (2023) — hybrid approaches outperform both alone
|
||||
- Anthropic's Claude 3.5 context caching — built-in prefix caching reduces cost for repeated system prompts
|
||||
|
||||
---
|
||||
|
||||
*Sovereignty and service always.*
|
||||
@@ -1,248 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
cross-repo-qa.py — Foundation-wide QA checks across all repos.
|
||||
|
||||
Runs automated checks that would have caught the issues in #691:
|
||||
- Duplicate PR detection across repos
|
||||
- Port drift detection in fleet configs
|
||||
- PR count per repo vs capacity limits
|
||||
- Health endpoint reachability
|
||||
|
||||
Usage:
|
||||
python3 scripts/cross-repo-qa.py --report # Full QA report
|
||||
python3 scripts/cross-repo-qa.py --duplicates # Find duplicate PRs
|
||||
python3 scripts/cross-repo-qa.py --capacity # Check PR capacity
|
||||
python3 scripts/cross-repo-qa.py --port-drift # Check fleet config consistency
|
||||
python3 scripts/cross-repo-qa.py --json # Machine-readable output
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import urllib.request
|
||||
from collections import defaultdict
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
GITEA_URL = "https://forge.alexanderwhitestone.com"
|
||||
GITEA_TOKEN_PATH = Path.home() / ".config" / "gitea" / "token"
|
||||
ORG = "Timmy_Foundation"
|
||||
|
||||
REPOS = [
|
||||
"hermes-agent", "timmy-home", "timmy-config", "the-nexus", "fleet-ops",
|
||||
"the-playground", "the-beacon", "wolf", "turboquant", "timmy-academy",
|
||||
"compounding-intelligence", "the-testament", "second-son-of-timmy",
|
||||
"ai-safety-review", "the-echo-pattern", "burn-fleet", "timmy-dispatch",
|
||||
"the-door",
|
||||
]
|
||||
|
||||
|
||||
def load_token() -> str:
|
||||
if GITEA_TOKEN_PATH.exists():
|
||||
return GITEA_TOKEN_PATH.read_text().strip()
|
||||
return os.environ.get("GITEA_TOKEN", "")
|
||||
|
||||
|
||||
def api_get(path: str, token: str) -> list | dict:
|
||||
req = urllib.request.Request(
|
||||
f"{GITEA_URL}/api/v1{path}",
|
||||
headers={"Authorization": f"token {token}"}
|
||||
)
|
||||
try:
|
||||
return json.loads(urllib.request.urlopen(req, timeout=20).read())
|
||||
except Exception:
|
||||
return []
|
||||
|
||||
|
||||
def extract_issue_refs(text: str) -> set[int]:
|
||||
return set(int(m) for m in re.findall(r'#(\d{2,5})', text or ""))
|
||||
|
||||
|
||||
def check_duplicate_prs(token: str) -> dict:
|
||||
"""Find duplicate PRs across all repos (same issue referenced)."""
|
||||
issue_to_prs = defaultdict(list)
|
||||
|
||||
for repo in REPOS:
|
||||
prs = api_get(f"/repos/{ORG}/{repo}/pulls?state=open&limit=100", token)
|
||||
if not isinstance(prs, list):
|
||||
continue
|
||||
for pr in prs:
|
||||
refs = extract_issue_refs(f"{pr['title']} {pr.get('body', '')}")
|
||||
for ref in refs:
|
||||
issue_to_prs[ref].append({
|
||||
"repo": repo,
|
||||
"number": pr["number"],
|
||||
"title": pr["title"][:70],
|
||||
"branch": pr.get("head", {}).get("ref", ""),
|
||||
})
|
||||
|
||||
duplicates = {k: v for k, v in issue_to_prs.items() if len(v) > 1}
|
||||
return duplicates
|
||||
|
||||
|
||||
def check_pr_capacity(token: str) -> list[dict]:
|
||||
"""Check PR counts vs limits."""
|
||||
capacity_path = Path(__file__).parent / "pr-capacity.json"
|
||||
if capacity_path.exists():
|
||||
config = json.loads(capacity_path.read_text())
|
||||
limits = {k: v.get("limit", 10) for k, v in config.get("repos", {}).items()}
|
||||
default_limit = config.get("default_limit", 10)
|
||||
else:
|
||||
limits = {}
|
||||
default_limit = 10
|
||||
|
||||
results = []
|
||||
for repo in REPOS:
|
||||
prs = api_get(f"/repos/{ORG}/{repo}/pulls?state=open&limit=100", token)
|
||||
count = len(prs) if isinstance(prs, list) else 0
|
||||
limit = limits.get(repo, default_limit)
|
||||
if count > limit:
|
||||
results.append({"repo": repo, "count": count, "limit": limit, "over": count - limit})
|
||||
|
||||
return sorted(results, key=lambda x: -x["over"])
|
||||
|
||||
|
||||
def check_wrong_repo_prs(token: str) -> list[dict]:
|
||||
"""Find PRs filed in the wrong repo (title mentions different repo)."""
|
||||
wrong = []
|
||||
for repo in REPOS:
|
||||
prs = api_get(f"/repos/{ORG}/{repo}/pulls?state=open&limit=100", token)
|
||||
if not isinstance(prs, list):
|
||||
continue
|
||||
for pr in prs:
|
||||
title = pr["title"].lower()
|
||||
# Check if title references a different repo
|
||||
for other_repo in REPOS:
|
||||
if other_repo == repo:
|
||||
continue
|
||||
# Check for repo name in title (with common separators)
|
||||
patterns = [
|
||||
f"{other_repo} ",
|
||||
f"{other_repo}:",
|
||||
f"{other_repo} backlog",
|
||||
f"{other_repo} report",
|
||||
f"{other_repo} triage",
|
||||
]
|
||||
if any(p in title for p in patterns):
|
||||
wrong.append({
|
||||
"pr_repo": repo,
|
||||
"pr_number": pr["number"],
|
||||
"pr_title": pr["title"][:70],
|
||||
"should_be_in": other_repo,
|
||||
})
|
||||
return wrong
|
||||
|
||||
|
||||
def cmd_report(token: str, as_json: bool = False):
|
||||
"""Full QA report."""
|
||||
report = {
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
"repos_scanned": len(REPOS),
|
||||
}
|
||||
|
||||
# Duplicates
|
||||
print("Checking duplicate PRs...", file=sys.stderr)
|
||||
dupes = check_duplicate_prs(token)
|
||||
report["duplicate_prs"] = {
|
||||
"issues_with_duplicates": len(dupes),
|
||||
"total_duplicate_prs": sum(len(v) - 1 for v in dupes.values()),
|
||||
"details": {str(k): v for k, v in sorted(dupes.items())},
|
||||
}
|
||||
|
||||
# Capacity
|
||||
print("Checking PR capacity...", file=sys.stderr)
|
||||
over_capacity = check_pr_capacity(token)
|
||||
report["over_capacity"] = over_capacity
|
||||
|
||||
# Wrong repo
|
||||
print("Checking wrong-repo PRs...", file=sys.stderr)
|
||||
wrong_repo = check_wrong_repo_prs(token)
|
||||
report["wrong_repo_prs"] = wrong_repo
|
||||
|
||||
if as_json:
|
||||
print(json.dumps(report, indent=2))
|
||||
return
|
||||
|
||||
# Human-readable
|
||||
print(f"\n{'='*60}")
|
||||
print(f"CROSS-REPO QA REPORT — {report['timestamp'][:19]}")
|
||||
print(f"{'='*60}")
|
||||
|
||||
print(f"\nDuplicate PRs: {report['duplicate_prs']['issues_with_duplicates']} issues, "
|
||||
f"{report['duplicate_prs']['total_duplicate_prs']} duplicates")
|
||||
for issue_num, pr_list in sorted(dupes.items(), key=lambda x: -len(x[1]))[:10]:
|
||||
print(f" Issue #{issue_num}: {len(pr_list)} PRs")
|
||||
for pr in pr_list:
|
||||
print(f" {pr['repo']}#{pr['number']}: {pr['title'][:60]}")
|
||||
|
||||
print(f"\nOver Capacity: {len(over_capacity)} repos")
|
||||
for r in over_capacity:
|
||||
print(f" {r['repo']}: {r['count']}/{r['limit']} ({r['over']} over)")
|
||||
|
||||
if wrong_repo:
|
||||
print(f"\nWrong Repo PRs: {len(wrong_repo)}")
|
||||
for r in wrong_repo:
|
||||
print(f" {r['pr_repo']}#{r['pr_number']}: should be in {r['should_be_in']}")
|
||||
print(f" {r['pr_title']}")
|
||||
|
||||
# Severity
|
||||
p0 = len(over_capacity)
|
||||
p1 = report['duplicate_prs']['total_duplicate_prs']
|
||||
print(f"\n{'='*60}")
|
||||
print(f"Severity: {p0} capacity violations, {p1} duplicate PRs")
|
||||
if p0 > 3 or p1 > 10:
|
||||
print("Status: NEEDS ATTENTION")
|
||||
else:
|
||||
print("Status: OK")
|
||||
|
||||
|
||||
def cmd_duplicates(token: str):
|
||||
dupes = check_duplicate_prs(token)
|
||||
if not dupes:
|
||||
print("No duplicate PRs found.")
|
||||
return
|
||||
print(f"Found {len(dupes)} issues with duplicate PRs:\n")
|
||||
for issue_num, pr_list in sorted(dupes.items(), key=lambda x: -len(x[1])):
|
||||
print(f"Issue #{issue_num}: {len(pr_list)} PRs")
|
||||
for pr in pr_list:
|
||||
print(f" {pr['repo']}#{pr['number']}: {pr['title'][:60]}")
|
||||
|
||||
|
||||
def cmd_capacity(token: str):
|
||||
over = check_pr_capacity(token)
|
||||
if not over:
|
||||
print("All repos within capacity.")
|
||||
return
|
||||
print(f"{len(over)} repos over capacity:\n")
|
||||
for r in over:
|
||||
print(f" {r['repo']}: {r['count']}/{r['limit']} ({r['over']} over)")
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Cross-repo QA automation")
|
||||
parser.add_argument("--report", action="store_true")
|
||||
parser.add_argument("--duplicates", action="store_true")
|
||||
parser.add_argument("--capacity", action="store_true")
|
||||
parser.add_argument("--port-drift", action="store_true")
|
||||
parser.add_argument("--json", action="store_true", dest="as_json")
|
||||
args = parser.parse_args()
|
||||
|
||||
token = load_token()
|
||||
if not token:
|
||||
print("No Gitea token found", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
if args.duplicates:
|
||||
cmd_duplicates(token)
|
||||
elif args.capacity:
|
||||
cmd_capacity(token)
|
||||
elif args.port_drift:
|
||||
print("Port drift check: see fleet-ops registry.yaml comparison")
|
||||
else:
|
||||
cmd_report(token, args.as_json)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,31 +1,169 @@
|
||||
#!/usr/bin/env python3
|
||||
import json
|
||||
import os
|
||||
import yaml
|
||||
from pathlib import Path
|
||||
"""Dynamic dispatch optimizer for fleet-wide coordination.
|
||||
|
||||
# Dynamic Dispatch Optimizer
|
||||
# Automatically updates routing based on fleet health.
|
||||
Refs: timmy-home #552
|
||||
|
||||
Takes a fleet dispatch spec plus optional failover status and produces a
|
||||
capacity-aware assignment plan. Safe by default: it prints the plan and only
|
||||
writes an output file when explicitly requested.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
STATUS_FILE = Path.home() / ".timmy" / "failover_status.json"
|
||||
CONFIG_FILE = Path.home() / "timmy" / "config.yaml"
|
||||
SPEC_FILE = Path.home() / ".timmy" / "fleet_dispatch.json"
|
||||
OUTPUT_FILE = Path.home() / ".timmy" / "dispatch_plan.json"
|
||||
|
||||
|
||||
def load_json(path: Path, default: Any):
|
||||
if not path.exists():
|
||||
return default
|
||||
return json.loads(path.read_text())
|
||||
|
||||
|
||||
def _host_status(host: dict[str, Any], failover_status: dict[str, Any]) -> str:
|
||||
if host.get("always_available"):
|
||||
return "ONLINE"
|
||||
fleet = failover_status.get("fleet") or {}
|
||||
return str(fleet.get(host["name"], "ONLINE")).upper()
|
||||
|
||||
|
||||
def _lane_matches(host: dict[str, Any], lane: str) -> bool:
|
||||
host_lanes = set(host.get("lanes") or ["general"])
|
||||
if host.get("always_available", False):
|
||||
return True
|
||||
if lane == "general":
|
||||
return "general" in host_lanes
|
||||
return lane in host_lanes
|
||||
|
||||
|
||||
def _choose_candidate(task: dict[str, Any], hosts: list[dict[str, Any]]):
|
||||
lane = task.get("lane", "general")
|
||||
preferred = task.get("preferred_hosts") or []
|
||||
|
||||
preferred_map = {host["name"]: host for host in hosts}
|
||||
for host_name in preferred:
|
||||
host = preferred_map.get(host_name)
|
||||
if not host:
|
||||
continue
|
||||
if host["remaining_capacity"] <= 0:
|
||||
continue
|
||||
if _lane_matches(host, lane):
|
||||
return host
|
||||
|
||||
matching = [host for host in hosts if host["remaining_capacity"] > 0 and _lane_matches(host, lane)]
|
||||
if matching:
|
||||
matching.sort(key=lambda host: (host["assigned_count"], -host["remaining_capacity"], host["name"]))
|
||||
return matching[0]
|
||||
|
||||
fallbacks = [host for host in hosts if host["remaining_capacity"] > 0 and host.get("always_available")]
|
||||
if fallbacks:
|
||||
fallbacks.sort(key=lambda host: (host["assigned_count"], -host["remaining_capacity"], host["name"]))
|
||||
return fallbacks[0]
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def generate_plan(spec: dict[str, Any], failover_status: dict[str, Any] | None = None) -> dict[str, Any]:
|
||||
failover_status = failover_status or {}
|
||||
raw_hosts = spec.get("hosts") or []
|
||||
tasks = list(spec.get("tasks") or [])
|
||||
|
||||
online_hosts = []
|
||||
offline_hosts = []
|
||||
for host in raw_hosts:
|
||||
normalized = {
|
||||
"name": host["name"],
|
||||
"capacity": int(host.get("capacity", 1)),
|
||||
"remaining_capacity": int(host.get("capacity", 1)),
|
||||
"assigned_count": 0,
|
||||
"lanes": list(host.get("lanes") or ["general"]),
|
||||
"always_available": bool(host.get("always_available", False)),
|
||||
"status": _host_status(host, failover_status),
|
||||
}
|
||||
if normalized["status"] == "ONLINE":
|
||||
online_hosts.append(normalized)
|
||||
else:
|
||||
offline_hosts.append(normalized["name"])
|
||||
|
||||
ordered_tasks = sorted(
|
||||
tasks,
|
||||
key=lambda item: (-int(item.get("priority", 0)), str(item.get("id", ""))),
|
||||
)
|
||||
|
||||
assignments = []
|
||||
unassigned = []
|
||||
for task in ordered_tasks:
|
||||
candidate = _choose_candidate(task, online_hosts)
|
||||
if candidate is None:
|
||||
unassigned.append({
|
||||
"task_id": task.get("id"),
|
||||
"reason": f"no_online_host_for_lane:{task.get('lane', 'general')}",
|
||||
})
|
||||
continue
|
||||
|
||||
candidate["remaining_capacity"] -= 1
|
||||
candidate["assigned_count"] += 1
|
||||
assignments.append({
|
||||
"task_id": task.get("id"),
|
||||
"host": candidate["name"],
|
||||
"lane": task.get("lane", "general"),
|
||||
"priority": int(task.get("priority", 0)),
|
||||
})
|
||||
|
||||
return {
|
||||
"assignments": assignments,
|
||||
"offline_hosts": sorted(offline_hosts),
|
||||
"unassigned": unassigned,
|
||||
}
|
||||
|
||||
|
||||
def write_plan(plan: dict[str, Any], output_path: Path):
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
output_path.write_text(json.dumps(plan, indent=2))
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(description="Generate a fleet dispatch plan from host health and task demand.")
|
||||
parser.add_argument("--spec-file", type=Path, default=SPEC_FILE, help="JSON fleet spec with hosts[] and tasks[]")
|
||||
parser.add_argument("--status-file", type=Path, default=STATUS_FILE, help="Failover monitor JSON payload")
|
||||
parser.add_argument("--output", type=Path, default=OUTPUT_FILE, help="Output path for the generated plan")
|
||||
parser.add_argument("--write-output", action="store_true", help="Persist the generated plan to --output")
|
||||
parser.add_argument("--json", action="store_true", help="Print JSON only")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main():
|
||||
print("--- Allegro's Dynamic Dispatch Optimizer ---")
|
||||
if not STATUS_FILE.exists():
|
||||
print("No failover status found.")
|
||||
args = parse_args()
|
||||
spec = load_json(args.spec_file, {"hosts": [], "tasks": []})
|
||||
failover_status = load_json(args.status_file, {})
|
||||
plan = generate_plan(spec, failover_status)
|
||||
|
||||
if args.write_output:
|
||||
write_plan(plan, args.output)
|
||||
|
||||
if args.json:
|
||||
print(json.dumps(plan, indent=2))
|
||||
return
|
||||
|
||||
status = json.loads(STATUS_FILE.read_text())
|
||||
fleet = status.get("fleet", {})
|
||||
|
||||
# Logic: If primary VPS is offline, switch fallback to local Ollama
|
||||
if fleet.get("ezra") == "OFFLINE":
|
||||
print("Ezra (Primary) is OFFLINE. Optimizing for local-only fallback...")
|
||||
# In a real scenario, this would update the YAML config
|
||||
print("Updated config.yaml: fallback_model -> ollama:gemma4:12b")
|
||||
else:
|
||||
print("Fleet health is optimal. Maintaining high-performance routing.")
|
||||
print("--- Dynamic Dispatch Optimizer ---")
|
||||
print(f"Assignments: {len(plan['assignments'])}")
|
||||
if plan["offline_hosts"]:
|
||||
print("Offline hosts: " + ", ".join(plan["offline_hosts"]))
|
||||
for assignment in plan["assignments"]:
|
||||
print(f"- {assignment['task_id']} -> {assignment['host']} ({assignment['lane']}, p={assignment['priority']})")
|
||||
if plan["unassigned"]:
|
||||
print("Unassigned:")
|
||||
for item in plan["unassigned"]:
|
||||
print(f"- {item['task_id']}: {item['reason']}")
|
||||
if args.write_output:
|
||||
print(f"Wrote plan to {args.output}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
@@ -1,127 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Operational runner and status view for the Know Thy Father multimodal epic."""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
from subprocess import run
|
||||
|
||||
|
||||
PHASES = [
|
||||
{
|
||||
"id": "phase1_media_indexing",
|
||||
"name": "Phase 1 — Media Indexing",
|
||||
"script": "scripts/know_thy_father/index_media.py",
|
||||
"command_template": "python3 scripts/know_thy_father/index_media.py --tweets twitter-archive/extracted/tweets.jsonl --output twitter-archive/know-thy-father/media_manifest.jsonl",
|
||||
"outputs": ["twitter-archive/know-thy-father/media_manifest.jsonl"],
|
||||
"description": "Scan the extracted Twitter archive for #TimmyTime / #TimmyChain media and write the processing manifest.",
|
||||
},
|
||||
{
|
||||
"id": "phase2_multimodal_analysis",
|
||||
"name": "Phase 2 — Multimodal Analysis",
|
||||
"script": "scripts/twitter_archive/analyze_media.py",
|
||||
"command_template": "python3 scripts/twitter_archive/analyze_media.py --batch {batch_size}",
|
||||
"outputs": [
|
||||
"twitter-archive/know-thy-father/analysis.jsonl",
|
||||
"twitter-archive/know-thy-father/meaning-kernels.jsonl",
|
||||
"twitter-archive/know-thy-father/pipeline-status.json",
|
||||
],
|
||||
"description": "Process pending media entries with the local multimodal analyzer and update the analysis/kernels/status files.",
|
||||
},
|
||||
{
|
||||
"id": "phase3_holographic_synthesis",
|
||||
"name": "Phase 3 — Holographic Synthesis",
|
||||
"script": "scripts/know_thy_father/synthesize_kernels.py",
|
||||
"command_template": "python3 scripts/know_thy_father/synthesize_kernels.py --input twitter-archive/media/manifest.jsonl --output twitter-archive/knowledge/fathers_ledger.jsonl --summary twitter-archive/knowledge/fathers_ledger.summary.json",
|
||||
"outputs": [
|
||||
"twitter-archive/knowledge/fathers_ledger.jsonl",
|
||||
"twitter-archive/knowledge/fathers_ledger.summary.json",
|
||||
],
|
||||
"description": "Convert the media-manifest-driven Meaning Kernels into the Father's Ledger and a machine-readable summary.",
|
||||
},
|
||||
{
|
||||
"id": "phase4_cross_reference_audit",
|
||||
"name": "Phase 4 — Cross-Reference Audit",
|
||||
"script": "scripts/know_thy_father/crossref_audit.py",
|
||||
"command_template": "python3 scripts/know_thy_father/crossref_audit.py --soul SOUL.md --kernels twitter-archive/notes/know_thy_father_crossref.md --output twitter-archive/notes/crossref_report.md",
|
||||
"outputs": ["twitter-archive/notes/crossref_report.md"],
|
||||
"description": "Compare Know Thy Father kernels against SOUL.md and related canon, then emit a Markdown audit report.",
|
||||
},
|
||||
{
|
||||
"id": "phase5_processing_log",
|
||||
"name": "Phase 5 — Processing Log / Status",
|
||||
"script": "twitter-archive/know-thy-father/tracker.py",
|
||||
"command_template": "python3 twitter-archive/know-thy-father/tracker.py report",
|
||||
"outputs": ["twitter-archive/know-thy-father/REPORT.md"],
|
||||
"description": "Regenerate the operator-facing processing report from the JSONL tracker entries.",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
def build_pipeline_plan(batch_size: int = 10):
|
||||
plan = []
|
||||
for phase in PHASES:
|
||||
plan.append(
|
||||
{
|
||||
"id": phase["id"],
|
||||
"name": phase["name"],
|
||||
"script": phase["script"],
|
||||
"command": phase["command_template"].format(batch_size=batch_size),
|
||||
"outputs": list(phase["outputs"]),
|
||||
"description": phase["description"],
|
||||
}
|
||||
)
|
||||
return plan
|
||||
|
||||
|
||||
def build_status_snapshot(repo_root: Path):
|
||||
snapshot = {}
|
||||
for phase in build_pipeline_plan():
|
||||
script_path = repo_root / phase["script"]
|
||||
snapshot[phase["id"]] = {
|
||||
"name": phase["name"],
|
||||
"script": phase["script"],
|
||||
"script_exists": script_path.exists(),
|
||||
"outputs": [
|
||||
{
|
||||
"path": output,
|
||||
"exists": (repo_root / output).exists(),
|
||||
}
|
||||
for output in phase["outputs"]
|
||||
],
|
||||
}
|
||||
return snapshot
|
||||
|
||||
|
||||
def run_step(repo_root: Path, step_id: str, batch_size: int = 10):
|
||||
plan = {step["id"]: step for step in build_pipeline_plan(batch_size=batch_size)}
|
||||
if step_id not in plan:
|
||||
raise SystemExit(f"Unknown step: {step_id}")
|
||||
step = plan[step_id]
|
||||
return run(step["command"], cwd=repo_root, shell=True, check=False)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Know Thy Father epic orchestration helper")
|
||||
parser.add_argument("--batch-size", type=int, default=10)
|
||||
parser.add_argument("--status", action="store_true")
|
||||
parser.add_argument("--run-step", default=None)
|
||||
parser.add_argument("--json", action="store_true")
|
||||
args = parser.parse_args()
|
||||
|
||||
repo_root = Path(__file__).resolve().parents[2]
|
||||
|
||||
if args.run_step:
|
||||
result = run_step(repo_root, args.run_step, batch_size=args.batch_size)
|
||||
raise SystemExit(result.returncode)
|
||||
|
||||
payload = build_status_snapshot(repo_root) if args.status else build_pipeline_plan(batch_size=args.batch_size)
|
||||
if args.json or args.status:
|
||||
print(json.dumps(payload, indent=2))
|
||||
else:
|
||||
for step in payload:
|
||||
print(f"[{step['id']}] {step['command']}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,159 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Prepare a MemPalace v3.0.0 integration packet for Ezra's Hermes home."""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
PACKAGE_SPEC = "mempalace==3.0.0"
|
||||
DEFAULT_HERMES_HOME = "~/.hermes/"
|
||||
DEFAULT_SESSIONS_DIR = "~/.hermes/sessions/"
|
||||
DEFAULT_PALACE_PATH = "~/.mempalace/palace"
|
||||
DEFAULT_WING = "ezra_home"
|
||||
|
||||
|
||||
def build_yaml_template(wing: str, palace_path: str) -> str:
|
||||
return (
|
||||
f"wing: {wing}\n"
|
||||
f"palace: {palace_path}\n"
|
||||
"rooms:\n"
|
||||
" - name: sessions\n"
|
||||
" description: Conversation history and durable agent transcripts\n"
|
||||
" globs:\n"
|
||||
" - \"*.json\"\n"
|
||||
" - \"*.jsonl\"\n"
|
||||
" - name: config\n"
|
||||
" description: Hermes configuration and runtime settings\n"
|
||||
" globs:\n"
|
||||
" - \"*.yaml\"\n"
|
||||
" - \"*.yml\"\n"
|
||||
" - \"*.toml\"\n"
|
||||
" - name: docs\n"
|
||||
" description: Notes, markdown docs, and operating reports\n"
|
||||
" globs:\n"
|
||||
" - \"*.md\"\n"
|
||||
" - \"*.txt\"\n"
|
||||
"people: []\n"
|
||||
"projects: []\n"
|
||||
)
|
||||
|
||||
|
||||
def build_plan(overrides: dict | None = None) -> dict:
|
||||
overrides = overrides or {}
|
||||
hermes_home = overrides.get("hermes_home", DEFAULT_HERMES_HOME)
|
||||
sessions_dir = overrides.get("sessions_dir", DEFAULT_SESSIONS_DIR)
|
||||
palace_path = overrides.get("palace_path", DEFAULT_PALACE_PATH)
|
||||
wing = overrides.get("wing", DEFAULT_WING)
|
||||
yaml_template = build_yaml_template(wing=wing, palace_path=palace_path)
|
||||
|
||||
config_home = hermes_home[:-1] if hermes_home.endswith("/") else hermes_home
|
||||
plan = {
|
||||
"package_spec": PACKAGE_SPEC,
|
||||
"hermes_home": hermes_home,
|
||||
"sessions_dir": sessions_dir,
|
||||
"palace_path": palace_path,
|
||||
"wing": wing,
|
||||
"config_path": f"{config_home}/mempalace.yaml",
|
||||
"install_command": f"pip install {PACKAGE_SPEC}",
|
||||
"init_command": f"mempalace init {hermes_home} --yes",
|
||||
"mine_home_command": f"echo \"\" | mempalace mine {hermes_home}",
|
||||
"mine_sessions_command": f"echo \"\" | mempalace mine {sessions_dir} --mode convos",
|
||||
"search_command": 'mempalace search "your common queries"',
|
||||
"wake_up_command": "mempalace wake-up",
|
||||
"mcp_command": "hermes mcp add mempalace -- python -m mempalace.mcp_server",
|
||||
"yaml_template": yaml_template,
|
||||
"gotchas": [
|
||||
"`mempalace init` is still interactive in room approval flow; write mempalace.yaml manually if the init output stalls.",
|
||||
"The yaml key is `wing:` not `wings:`. Using the wrong key causes mine/setup failures.",
|
||||
"Pipe empty stdin into mining commands (`echo \"\" | ...`) to avoid the entity-detector stdin hang on larger directories.",
|
||||
"First mine downloads the ChromaDB embedding model cache (~79MB).",
|
||||
"Report Ezra's before/after metrics back to issue #568 after live installation and retrieval tests.",
|
||||
],
|
||||
}
|
||||
return plan
|
||||
|
||||
|
||||
def render_markdown(plan: dict) -> str:
|
||||
gotchas = "\n".join(f"- {item}" for item in plan["gotchas"])
|
||||
return f"""# MemPalace v3.0.0 — Ezra Integration Packet
|
||||
|
||||
This packet turns issue #570 into an executable, reviewable integration plan for Ezra's Hermes home.
|
||||
It is a repo-side scaffold: no live Ezra host changes are claimed in this artifact.
|
||||
|
||||
## Commands
|
||||
|
||||
```bash
|
||||
{plan['install_command']}
|
||||
{plan['init_command']}
|
||||
cat > {plan['config_path']} <<'YAML'
|
||||
{plan['yaml_template'].rstrip()}
|
||||
YAML
|
||||
{plan['mine_home_command']}
|
||||
{plan['mine_sessions_command']}
|
||||
{plan['search_command']}
|
||||
{plan['wake_up_command']}
|
||||
{plan['mcp_command']}
|
||||
```
|
||||
|
||||
## Manual config template
|
||||
|
||||
```yaml
|
||||
{plan['yaml_template'].rstrip()}
|
||||
```
|
||||
|
||||
## Why this shape
|
||||
|
||||
- `wing: {plan['wing']}` matches the issue's Ezra-specific integration target.
|
||||
- `rooms` split the mined material into sessions, config, and docs to keep retrieval interpretable.
|
||||
- Mining commands pipe empty stdin to avoid the interactive entity-detector hang noted in the evaluation.
|
||||
|
||||
## Gotchas
|
||||
|
||||
{gotchas}
|
||||
|
||||
## Report back to #568
|
||||
|
||||
After live execution on Ezra's actual environment, post back to #568 with:
|
||||
- install result
|
||||
- mine duration and corpus size
|
||||
- 2-3 real search queries + retrieved results
|
||||
- wake-up context token count
|
||||
- whether MCP wiring succeeded
|
||||
|
||||
## Honest scope boundary
|
||||
|
||||
This repo artifact does **not** prove live installation on Ezra's host. It makes the work reproducible and testable so the next pass can execute it without guesswork.
|
||||
"""
|
||||
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser(description="Prepare the MemPalace Ezra integration packet")
|
||||
parser.add_argument("--hermes-home", default=DEFAULT_HERMES_HOME)
|
||||
parser.add_argument("--sessions-dir", default=DEFAULT_SESSIONS_DIR)
|
||||
parser.add_argument("--palace-path", default=DEFAULT_PALACE_PATH)
|
||||
parser.add_argument("--wing", default=DEFAULT_WING)
|
||||
parser.add_argument("--output", default=None)
|
||||
parser.add_argument("--json", action="store_true")
|
||||
args = parser.parse_args()
|
||||
|
||||
plan = build_plan(
|
||||
{
|
||||
"hermes_home": args.hermes_home,
|
||||
"sessions_dir": args.sessions_dir,
|
||||
"palace_path": args.palace_path,
|
||||
"wing": args.wing,
|
||||
}
|
||||
)
|
||||
rendered = json.dumps(plan, indent=2) if args.json else render_markdown(plan)
|
||||
|
||||
if args.output:
|
||||
output_path = Path(args.output).expanduser()
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
output_path.write_text(rendered, encoding="utf-8")
|
||||
print(f"MemPalace integration packet written to {output_path}")
|
||||
else:
|
||||
print(rendered)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,155 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import yaml
|
||||
|
||||
DAYLIGHT_START = "10:00"
|
||||
DAYLIGHT_END = "16:00"
|
||||
|
||||
|
||||
def load_manifest(path: str | Path) -> dict[str, Any]:
|
||||
data = yaml.safe_load(Path(path).read_text()) or {}
|
||||
data.setdefault("machines", [])
|
||||
return data
|
||||
|
||||
|
||||
def validate_manifest(data: dict[str, Any]) -> None:
|
||||
machines = data.get("machines", [])
|
||||
if not machines:
|
||||
raise ValueError("manifest must contain at least one machine")
|
||||
|
||||
seen: set[str] = set()
|
||||
for machine in machines:
|
||||
hostname = machine.get("hostname", "").strip()
|
||||
if not hostname:
|
||||
raise ValueError("each machine must declare a hostname")
|
||||
if hostname in seen:
|
||||
raise ValueError(f"duplicate hostname: {hostname} (unique hostnames are required)")
|
||||
seen.add(hostname)
|
||||
|
||||
for field in ("machine_type", "ram_gb", "cpu_cores", "os", "adapter_condition"):
|
||||
if field not in machine:
|
||||
raise ValueError(f"machine {hostname} missing required field: {field}")
|
||||
|
||||
|
||||
def _laptops(machines: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
return [m for m in machines if m.get("machine_type") == "laptop"]
|
||||
|
||||
|
||||
def _desktop(machines: list[dict[str, Any]]) -> dict[str, Any] | None:
|
||||
for machine in machines:
|
||||
if machine.get("machine_type") == "desktop":
|
||||
return machine
|
||||
return None
|
||||
|
||||
|
||||
def choose_anchor_agents(machines: list[dict[str, Any]], count: int = 2) -> list[dict[str, Any]]:
|
||||
eligible = [
|
||||
m for m in _laptops(machines)
|
||||
if m.get("adapter_condition") in {"good", "ok"} and m.get("always_on_capable", True)
|
||||
]
|
||||
eligible.sort(key=lambda m: (m.get("idle_watts", 9999), -m.get("ram_gb", 0), -m.get("cpu_cores", 0), m["hostname"]))
|
||||
return eligible[:count]
|
||||
|
||||
|
||||
def assign_roles(machines: list[dict[str, Any]]) -> dict[str, Any]:
|
||||
anchors = choose_anchor_agents(machines, count=2)
|
||||
anchor_names = {m["hostname"] for m in anchors}
|
||||
desktop = _desktop(machines)
|
||||
|
||||
mapping: dict[str, dict[str, Any]] = {}
|
||||
for machine in machines:
|
||||
hostname = machine["hostname"]
|
||||
if desktop and hostname == desktop["hostname"]:
|
||||
mapping[hostname] = {
|
||||
"role": "desktop_nas",
|
||||
"schedule": f"{DAYLIGHT_START}-{DAYLIGHT_END}",
|
||||
"duty_cycle": "daylight_only",
|
||||
}
|
||||
elif hostname in anchor_names:
|
||||
mapping[hostname] = {
|
||||
"role": "anchor_agent",
|
||||
"schedule": "24/7",
|
||||
"duty_cycle": "continuous",
|
||||
}
|
||||
else:
|
||||
mapping[hostname] = {
|
||||
"role": "daylight_agent",
|
||||
"schedule": f"{DAYLIGHT_START}-{DAYLIGHT_END}",
|
||||
"duty_cycle": "peak_solar",
|
||||
}
|
||||
return {
|
||||
"anchor_agents": [m["hostname"] for m in anchors],
|
||||
"desktop_nas": desktop["hostname"] if desktop else None,
|
||||
"role_mapping": mapping,
|
||||
}
|
||||
|
||||
|
||||
def build_plan(data: dict[str, Any]) -> dict[str, Any]:
|
||||
validate_manifest(data)
|
||||
machines = data["machines"]
|
||||
role_plan = assign_roles(machines)
|
||||
return {
|
||||
"fleet_name": data.get("fleet_name", "timmy-laptop-fleet"),
|
||||
"machine_count": len(machines),
|
||||
"anchor_agents": role_plan["anchor_agents"],
|
||||
"desktop_nas": role_plan["desktop_nas"],
|
||||
"daylight_window": f"{DAYLIGHT_START}-{DAYLIGHT_END}",
|
||||
"role_mapping": role_plan["role_mapping"],
|
||||
}
|
||||
|
||||
|
||||
def render_markdown(plan: dict[str, Any], data: dict[str, Any]) -> str:
|
||||
lines = [
|
||||
"# Laptop Fleet Deployment Plan",
|
||||
"",
|
||||
f"Fleet: {plan['fleet_name']}",
|
||||
f"Machine count: {plan['machine_count']}",
|
||||
f"24/7 anchor agents: {', '.join(plan['anchor_agents']) if plan['anchor_agents'] else 'TBD'}",
|
||||
f"Desktop/NAS: {plan['desktop_nas'] or 'TBD'}",
|
||||
f"Daylight schedule: {plan['daylight_window']}",
|
||||
"",
|
||||
"## Role mapping",
|
||||
"",
|
||||
"| Hostname | Role | Schedule | Duty cycle |",
|
||||
"|---|---|---|---|",
|
||||
]
|
||||
for hostname, role in sorted(plan["role_mapping"].items()):
|
||||
lines.append(f"| {hostname} | {role['role']} | {role['schedule']} | {role['duty_cycle']} |")
|
||||
|
||||
lines.extend([
|
||||
"",
|
||||
"## Machine inventory",
|
||||
"",
|
||||
"| Hostname | Type | RAM | CPU cores | OS | Adapter | Idle watts | Notes |",
|
||||
"|---|---|---:|---:|---|---|---:|---|",
|
||||
])
|
||||
for machine in data["machines"]:
|
||||
lines.append(
|
||||
f"| {machine['hostname']} | {machine['machine_type']} | {machine['ram_gb']} | {machine['cpu_cores']} | {machine['os']} | {machine['adapter_condition']} | {machine.get('idle_watts', 'n/a')} | {machine.get('notes', '')} |"
|
||||
)
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description="Plan LAB-005 laptop fleet deployment.")
|
||||
parser.add_argument("manifest", help="Path to laptop fleet manifest YAML")
|
||||
parser.add_argument("--markdown", action="store_true", help="Render a markdown deployment plan instead of JSON")
|
||||
args = parser.parse_args()
|
||||
|
||||
data = load_manifest(args.manifest)
|
||||
plan = build_plan(data)
|
||||
if args.markdown:
|
||||
print(render_markdown(plan, data))
|
||||
else:
|
||||
print(json.dumps(plan, indent=2))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1,135 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""NH Broadband install packet builder for the live scheduling step."""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import yaml
|
||||
|
||||
|
||||
def load_request(path: str | Path) -> dict[str, Any]:
|
||||
data = yaml.safe_load(Path(path).read_text()) or {}
|
||||
data.setdefault("contact", {})
|
||||
data.setdefault("service", {})
|
||||
data.setdefault("call_log", [])
|
||||
data.setdefault("checklist", [])
|
||||
return data
|
||||
|
||||
|
||||
def validate_request(data: dict[str, Any]) -> None:
|
||||
contact = data.get("contact", {})
|
||||
for field in ("name", "phone"):
|
||||
if not contact.get(field, "").strip():
|
||||
raise ValueError(f"contact.{field} is required")
|
||||
|
||||
service = data.get("service", {})
|
||||
for field in ("address", "city", "state"):
|
||||
if not service.get(field, "").strip():
|
||||
raise ValueError(f"service.{field} is required")
|
||||
|
||||
if not data.get("checklist"):
|
||||
raise ValueError("checklist must contain at least one item")
|
||||
|
||||
|
||||
def build_packet(data: dict[str, Any]) -> dict[str, Any]:
|
||||
validate_request(data)
|
||||
contact = data["contact"]
|
||||
service = data["service"]
|
||||
|
||||
return {
|
||||
"packet_id": f"nh-bb-{datetime.now(timezone.utc).strftime('%Y%m%d-%H%M%S')}",
|
||||
"generated_utc": datetime.now(timezone.utc).isoformat(),
|
||||
"contact": {
|
||||
"name": contact["name"],
|
||||
"phone": contact["phone"],
|
||||
"email": contact.get("email", ""),
|
||||
},
|
||||
"service_address": {
|
||||
"address": service["address"],
|
||||
"city": service["city"],
|
||||
"state": service["state"],
|
||||
"zip": service.get("zip", ""),
|
||||
},
|
||||
"desired_plan": data.get("desired_plan", "residential-fiber"),
|
||||
"call_log": data.get("call_log", []),
|
||||
"checklist": [
|
||||
{"item": item, "done": False} if isinstance(item, str) else item
|
||||
for item in data["checklist"]
|
||||
],
|
||||
"status": "pending_scheduling_call",
|
||||
}
|
||||
|
||||
|
||||
def render_markdown(packet: dict[str, Any], data: dict[str, Any]) -> str:
|
||||
contact = packet["contact"]
|
||||
addr = packet["service_address"]
|
||||
lines = [
|
||||
f"# NH Broadband Install Packet",
|
||||
"",
|
||||
f"**Packet ID:** {packet['packet_id']}",
|
||||
f"**Generated:** {packet['generated_utc']}",
|
||||
f"**Status:** {packet['status']}",
|
||||
"",
|
||||
"## Contact",
|
||||
"",
|
||||
f"- **Name:** {contact['name']}",
|
||||
f"- **Phone:** {contact['phone']}",
|
||||
f"- **Email:** {contact.get('email', 'n/a')}",
|
||||
"",
|
||||
"## Service Address",
|
||||
"",
|
||||
f"- {addr['address']}",
|
||||
f"- {addr['city']}, {addr['state']} {addr['zip']}",
|
||||
"",
|
||||
f"## Desired Plan",
|
||||
"",
|
||||
f"{packet['desired_plan']}",
|
||||
"",
|
||||
"## Call Log",
|
||||
"",
|
||||
]
|
||||
if packet["call_log"]:
|
||||
for entry in packet["call_log"]:
|
||||
ts = entry.get("timestamp", "n/a")
|
||||
outcome = entry.get("outcome", "n/a")
|
||||
notes = entry.get("notes", "")
|
||||
lines.append(f"- **{ts}** — {outcome}")
|
||||
if notes:
|
||||
lines.append(f" - {notes}")
|
||||
else:
|
||||
lines.append("_No calls logged yet._")
|
||||
|
||||
lines.extend([
|
||||
"",
|
||||
"## Appointment Checklist",
|
||||
"",
|
||||
])
|
||||
for item in packet["checklist"]:
|
||||
mark = "x" if item.get("done") else " "
|
||||
lines.append(f"- [{mark}] {item['item']}")
|
||||
|
||||
lines.append("")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description="Build NH Broadband install packet.")
|
||||
parser.add_argument("request", help="Path to install request YAML")
|
||||
parser.add_argument("--markdown", action="store_true", help="Render markdown instead of JSON")
|
||||
args = parser.parse_args()
|
||||
|
||||
data = load_request(args.request)
|
||||
packet = build_packet(data)
|
||||
if args.markdown:
|
||||
print(render_markdown(packet, data))
|
||||
else:
|
||||
print(json.dumps(packet, indent=2))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
79
tests/test_dynamic_dispatch_optimizer.py
Normal file
79
tests/test_dynamic_dispatch_optimizer.py
Normal file
@@ -0,0 +1,79 @@
|
||||
import json
|
||||
|
||||
from scripts.dynamic_dispatch_optimizer import generate_plan, write_plan
|
||||
|
||||
|
||||
def test_generate_plan_rebalances_offline_host_tasks_to_online_capacity():
|
||||
spec = {
|
||||
"hosts": [
|
||||
{"name": "ezra", "capacity": 2, "lanes": ["research", "general"]},
|
||||
{"name": "bezalel", "capacity": 2, "lanes": ["build", "general"]},
|
||||
{"name": "local", "capacity": 1, "lanes": ["general"], "always_available": True},
|
||||
],
|
||||
"tasks": [
|
||||
{"id": "ISSUE-1", "lane": "build", "priority": 100},
|
||||
{"id": "ISSUE-2", "lane": "general", "priority": 80},
|
||||
{"id": "ISSUE-3", "lane": "research", "priority": 60},
|
||||
],
|
||||
}
|
||||
failover_status = {"fleet": {"ezra": "ONLINE", "bezalel": "OFFLINE"}}
|
||||
|
||||
plan = generate_plan(spec, failover_status)
|
||||
|
||||
assignments = {item["task_id"]: item["host"] for item in plan["assignments"]}
|
||||
assert assignments == {
|
||||
"ISSUE-1": "local",
|
||||
"ISSUE-2": "ezra",
|
||||
"ISSUE-3": "ezra",
|
||||
}
|
||||
assert plan["offline_hosts"] == ["bezalel"]
|
||||
assert plan["unassigned"] == []
|
||||
|
||||
|
||||
def test_generate_plan_prefers_preferred_host_when_online():
|
||||
spec = {
|
||||
"hosts": [
|
||||
{"name": "ezra", "capacity": 2, "lanes": ["general"]},
|
||||
{"name": "bezalel", "capacity": 2, "lanes": ["general"]},
|
||||
],
|
||||
"tasks": [
|
||||
{"id": "ISSUE-9", "lane": "general", "priority": 100, "preferred_hosts": ["bezalel", "ezra"]},
|
||||
],
|
||||
}
|
||||
|
||||
plan = generate_plan(spec, {"fleet": {"ezra": "ONLINE", "bezalel": "ONLINE"}})
|
||||
|
||||
assert plan["assignments"] == [
|
||||
{"task_id": "ISSUE-9", "host": "bezalel", "lane": "general", "priority": 100}
|
||||
]
|
||||
|
||||
|
||||
def test_generate_plan_reports_unassigned_when_no_host_matches_lane():
|
||||
spec = {
|
||||
"hosts": [
|
||||
{"name": "ezra", "capacity": 1, "lanes": ["research"]},
|
||||
],
|
||||
"tasks": [
|
||||
{"id": "ISSUE-5", "lane": "build", "priority": 50},
|
||||
],
|
||||
}
|
||||
|
||||
plan = generate_plan(spec, {"fleet": {"ezra": "ONLINE"}})
|
||||
|
||||
assert plan["assignments"] == []
|
||||
assert plan["unassigned"] == [
|
||||
{"task_id": "ISSUE-5", "reason": "no_online_host_for_lane:build"}
|
||||
]
|
||||
|
||||
|
||||
def test_write_plan_persists_json(tmp_path):
|
||||
plan = {
|
||||
"assignments": [{"task_id": "ISSUE-1", "host": "ezra", "lane": "general", "priority": 10}],
|
||||
"offline_hosts": [],
|
||||
"unassigned": [],
|
||||
}
|
||||
output_path = tmp_path / "dispatch-plan.json"
|
||||
|
||||
write_plan(plan, output_path)
|
||||
|
||||
assert json.loads(output_path.read_text()) == plan
|
||||
@@ -1,76 +0,0 @@
|
||||
from pathlib import Path
|
||||
import importlib.util
|
||||
import unittest
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
SCRIPT_PATH = ROOT / "scripts" / "know_thy_father" / "epic_pipeline.py"
|
||||
DOC_PATH = ROOT / "docs" / "KNOW_THY_FATHER_MULTIMODAL_PIPELINE.md"
|
||||
|
||||
|
||||
def load_module(path: Path, name: str):
|
||||
assert path.exists(), f"missing {path.relative_to(ROOT)}"
|
||||
spec = importlib.util.spec_from_file_location(name, path)
|
||||
assert spec and spec.loader
|
||||
module = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(module)
|
||||
return module
|
||||
|
||||
|
||||
class TestKnowThyFatherEpicPipeline(unittest.TestCase):
|
||||
def test_build_pipeline_plan_contains_all_phases_in_order(self):
|
||||
mod = load_module(SCRIPT_PATH, "ktf_epic_pipeline")
|
||||
plan = mod.build_pipeline_plan(batch_size=10)
|
||||
|
||||
self.assertEqual(
|
||||
[step["id"] for step in plan],
|
||||
[
|
||||
"phase1_media_indexing",
|
||||
"phase2_multimodal_analysis",
|
||||
"phase3_holographic_synthesis",
|
||||
"phase4_cross_reference_audit",
|
||||
"phase5_processing_log",
|
||||
],
|
||||
)
|
||||
self.assertIn("scripts/know_thy_father/index_media.py", plan[0]["command"])
|
||||
self.assertIn("scripts/twitter_archive/analyze_media.py --batch 10", plan[1]["command"])
|
||||
self.assertIn("scripts/know_thy_father/synthesize_kernels.py", plan[2]["command"])
|
||||
self.assertIn("scripts/know_thy_father/crossref_audit.py", plan[3]["command"])
|
||||
self.assertIn("twitter-archive/know-thy-father/tracker.py report", plan[4]["command"])
|
||||
|
||||
def test_status_snapshot_reports_key_artifact_paths(self):
|
||||
mod = load_module(SCRIPT_PATH, "ktf_epic_pipeline")
|
||||
status = mod.build_status_snapshot(ROOT)
|
||||
|
||||
self.assertIn("phase1_media_indexing", status)
|
||||
self.assertIn("phase2_multimodal_analysis", status)
|
||||
self.assertIn("phase3_holographic_synthesis", status)
|
||||
self.assertIn("phase4_cross_reference_audit", status)
|
||||
self.assertIn("phase5_processing_log", status)
|
||||
self.assertEqual(status["phase1_media_indexing"]["script"], "scripts/know_thy_father/index_media.py")
|
||||
self.assertEqual(status["phase2_multimodal_analysis"]["script"], "scripts/twitter_archive/analyze_media.py")
|
||||
self.assertEqual(status["phase5_processing_log"]["script"], "twitter-archive/know-thy-father/tracker.py")
|
||||
self.assertTrue(status["phase1_media_indexing"]["script_exists"])
|
||||
self.assertTrue(status["phase2_multimodal_analysis"]["script_exists"])
|
||||
self.assertTrue(status["phase3_holographic_synthesis"]["script_exists"])
|
||||
self.assertTrue(status["phase4_cross_reference_audit"]["script_exists"])
|
||||
self.assertTrue(status["phase5_processing_log"]["script_exists"])
|
||||
|
||||
def test_repo_contains_multimodal_pipeline_doc(self):
|
||||
self.assertTrue(DOC_PATH.exists(), "missing committed Know Thy Father pipeline doc")
|
||||
text = DOC_PATH.read_text(encoding="utf-8")
|
||||
required = [
|
||||
"# Know Thy Father — Multimodal Media Consumption Pipeline",
|
||||
"scripts/know_thy_father/index_media.py",
|
||||
"scripts/twitter_archive/analyze_media.py --batch 10",
|
||||
"scripts/know_thy_father/synthesize_kernels.py",
|
||||
"scripts/know_thy_father/crossref_audit.py",
|
||||
"twitter-archive/know-thy-father/tracker.py report",
|
||||
"Refs #582",
|
||||
]
|
||||
for snippet in required:
|
||||
self.assertIn(snippet, text)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -1,52 +0,0 @@
|
||||
from pathlib import Path
|
||||
|
||||
import yaml
|
||||
|
||||
from scripts.plan_laptop_fleet import build_plan, load_manifest, render_markdown, validate_manifest
|
||||
|
||||
|
||||
def test_laptop_fleet_planner_script_exists() -> None:
|
||||
assert Path("scripts/plan_laptop_fleet.py").exists()
|
||||
|
||||
|
||||
def test_laptop_fleet_manifest_template_exists() -> None:
|
||||
assert Path("docs/laptop-fleet-manifest.example.yaml").exists()
|
||||
|
||||
|
||||
def test_build_plan_selects_two_lowest_idle_watt_laptops_as_anchors() -> None:
|
||||
data = load_manifest("docs/laptop-fleet-manifest.example.yaml")
|
||||
plan = build_plan(data)
|
||||
assert plan["anchor_agents"] == ["timmy-anchor-a", "timmy-anchor-b"]
|
||||
assert plan["desktop_nas"] == "timmy-desktop-nas"
|
||||
assert plan["role_mapping"]["timmy-daylight-a"]["schedule"] == "10:00-16:00"
|
||||
|
||||
|
||||
def test_validate_manifest_requires_unique_hostnames() -> None:
|
||||
data = {
|
||||
"machines": [
|
||||
{"hostname": "dup", "machine_type": "laptop", "ram_gb": 8, "cpu_cores": 4, "os": "Linux", "adapter_condition": "good"},
|
||||
{"hostname": "dup", "machine_type": "laptop", "ram_gb": 16, "cpu_cores": 8, "os": "Linux", "adapter_condition": "good"},
|
||||
]
|
||||
}
|
||||
try:
|
||||
validate_manifest(data)
|
||||
except ValueError as exc:
|
||||
assert "duplicate hostname" in str(exc)
|
||||
assert "unique hostnames" in str(exc)
|
||||
else:
|
||||
raise AssertionError("validate_manifest should reject duplicate hostname")
|
||||
|
||||
|
||||
def test_markdown_contains_anchor_agents_and_daylight_schedule() -> None:
|
||||
data = load_manifest("docs/laptop-fleet-manifest.example.yaml")
|
||||
plan = build_plan(data)
|
||||
content = render_markdown(plan, data)
|
||||
assert "24/7 anchor agents: timmy-anchor-a, timmy-anchor-b" in content
|
||||
assert "Daylight schedule: 10:00-16:00" in content
|
||||
assert "desktop_nas" in content
|
||||
|
||||
|
||||
def test_manifest_template_is_valid_yaml() -> None:
|
||||
data = yaml.safe_load(Path("docs/laptop-fleet-manifest.example.yaml").read_text())
|
||||
assert data["fleet_name"] == "timmy-laptop-fleet"
|
||||
assert len(data["machines"]) == 6
|
||||
@@ -1,68 +0,0 @@
|
||||
from pathlib import Path
|
||||
import importlib.util
|
||||
import unittest
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
SCRIPT_PATH = ROOT / "scripts" / "mempalace_ezra_integration.py"
|
||||
DOC_PATH = ROOT / "docs" / "MEMPALACE_EZRA_INTEGRATION.md"
|
||||
|
||||
|
||||
def load_module(path: Path, name: str):
|
||||
assert path.exists(), f"missing {path.relative_to(ROOT)}"
|
||||
spec = importlib.util.spec_from_file_location(name, path)
|
||||
assert spec and spec.loader
|
||||
module = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(module)
|
||||
return module
|
||||
|
||||
|
||||
class TestMempalaceEzraIntegration(unittest.TestCase):
|
||||
def test_build_plan_contains_issue_required_steps_and_gotchas(self):
|
||||
mod = load_module(SCRIPT_PATH, "mempalace_ezra_integration")
|
||||
plan = mod.build_plan({})
|
||||
|
||||
self.assertEqual(plan["package_spec"], "mempalace==3.0.0")
|
||||
self.assertIn("pip install mempalace==3.0.0", plan["install_command"])
|
||||
self.assertEqual(plan["wing"], "ezra_home")
|
||||
self.assertIn('echo "" | mempalace mine ~/.hermes/', plan["mine_home_command"])
|
||||
self.assertIn('--mode convos', plan["mine_sessions_command"])
|
||||
self.assertIn('mempalace wake-up', plan["wake_up_command"])
|
||||
self.assertIn('hermes mcp add mempalace -- python -m mempalace.mcp_server', plan["mcp_command"])
|
||||
self.assertIn('wing:', plan["yaml_template"])
|
||||
self.assertTrue(any('stdin' in item.lower() for item in plan["gotchas"]))
|
||||
self.assertTrue(any('wing:' in item for item in plan["gotchas"]))
|
||||
|
||||
def test_build_plan_accepts_path_and_wing_overrides(self):
|
||||
mod = load_module(SCRIPT_PATH, "mempalace_ezra_integration")
|
||||
plan = mod.build_plan(
|
||||
{
|
||||
"hermes_home": "/root/wizards/ezra/home",
|
||||
"sessions_dir": "/root/wizards/ezra/home/sessions",
|
||||
"wing": "ezra_archive",
|
||||
}
|
||||
)
|
||||
|
||||
self.assertEqual(plan["wing"], "ezra_archive")
|
||||
self.assertIn('/root/wizards/ezra/home', plan["mine_home_command"])
|
||||
self.assertIn('/root/wizards/ezra/home/sessions', plan["mine_sessions_command"])
|
||||
self.assertIn('wing: ezra_archive', plan["yaml_template"])
|
||||
|
||||
def test_repo_contains_mem_palace_ezra_doc(self):
|
||||
self.assertTrue(DOC_PATH.exists(), "missing committed MemPalace Ezra integration doc")
|
||||
text = DOC_PATH.read_text(encoding="utf-8")
|
||||
required = [
|
||||
"# MemPalace v3.0.0 — Ezra Integration Packet",
|
||||
"pip install mempalace==3.0.0",
|
||||
'echo "" | mempalace mine ~/.hermes/',
|
||||
"mempalace mine ~/.hermes/sessions/ --mode convos",
|
||||
"mempalace wake-up",
|
||||
"hermes mcp add mempalace -- python -m mempalace.mcp_server",
|
||||
"Report back to #568",
|
||||
]
|
||||
for snippet in required:
|
||||
self.assertIn(snippet, text)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -1,105 +0,0 @@
|
||||
from pathlib import Path
|
||||
|
||||
import yaml
|
||||
|
||||
from scripts.plan_nh_broadband_install import (
|
||||
build_packet,
|
||||
load_request,
|
||||
render_markdown,
|
||||
validate_request,
|
||||
)
|
||||
|
||||
|
||||
def test_script_exists() -> None:
|
||||
assert Path("scripts/plan_nh_broadband_install.py").exists()
|
||||
|
||||
|
||||
def test_example_request_exists() -> None:
|
||||
assert Path("docs/nh-broadband-install-request.example.yaml").exists()
|
||||
|
||||
|
||||
def test_example_packet_exists() -> None:
|
||||
assert Path("docs/nh-broadband-install-packet.example.md").exists()
|
||||
|
||||
|
||||
def test_research_memo_exists() -> None:
|
||||
assert Path("reports/operations/2026-04-15-nh-broadband-public-research.md").exists()
|
||||
|
||||
|
||||
def test_load_and_build_packet() -> None:
|
||||
data = load_request("docs/nh-broadband-install-request.example.yaml")
|
||||
packet = build_packet(data)
|
||||
assert packet["contact"]["name"] == "Timmy Operator"
|
||||
assert packet["service_address"]["city"] == "Concord"
|
||||
assert packet["service_address"]["state"] == "NH"
|
||||
assert packet["status"] == "pending_scheduling_call"
|
||||
assert len(packet["checklist"]) == 8
|
||||
assert packet["checklist"][0]["done"] is False
|
||||
|
||||
|
||||
def test_validate_rejects_missing_contact_name() -> None:
|
||||
data = {
|
||||
"contact": {"name": "", "phone": "555"},
|
||||
"service": {"address": "1 St", "city": "X", "state": "NH"},
|
||||
"checklist": ["do thing"],
|
||||
}
|
||||
try:
|
||||
validate_request(data)
|
||||
except ValueError as exc:
|
||||
assert "contact.name" in str(exc)
|
||||
else:
|
||||
raise AssertionError("should reject empty contact name")
|
||||
|
||||
|
||||
def test_validate_rejects_missing_service_address() -> None:
|
||||
data = {
|
||||
"contact": {"name": "A", "phone": "555"},
|
||||
"service": {"address": "", "city": "X", "state": "NH"},
|
||||
"checklist": ["do thing"],
|
||||
}
|
||||
try:
|
||||
validate_request(data)
|
||||
except ValueError as exc:
|
||||
assert "service.address" in str(exc)
|
||||
else:
|
||||
raise AssertionError("should reject empty service address")
|
||||
|
||||
|
||||
def test_validate_rejects_empty_checklist() -> None:
|
||||
data = {
|
||||
"contact": {"name": "A", "phone": "555"},
|
||||
"service": {"address": "1 St", "city": "X", "state": "NH"},
|
||||
"checklist": [],
|
||||
}
|
||||
try:
|
||||
validate_request(data)
|
||||
except ValueError as exc:
|
||||
assert "checklist" in str(exc)
|
||||
else:
|
||||
raise AssertionError("should reject empty checklist")
|
||||
|
||||
|
||||
def test_render_markdown_contains_key_sections() -> None:
|
||||
data = load_request("docs/nh-broadband-install-request.example.yaml")
|
||||
packet = build_packet(data)
|
||||
md = render_markdown(packet, data)
|
||||
assert "# NH Broadband Install Packet" in md
|
||||
assert "## Contact" in md
|
||||
assert "## Service Address" in md
|
||||
assert "## Call Log" in md
|
||||
assert "## Appointment Checklist" in md
|
||||
assert "Concord" in md
|
||||
assert "NH" in md
|
||||
|
||||
|
||||
def test_render_markdown_shows_checklist_items() -> None:
|
||||
data = load_request("docs/nh-broadband-install-request.example.yaml")
|
||||
packet = build_packet(data)
|
||||
md = render_markdown(packet, data)
|
||||
assert "- [ ] Confirm exact-address availability" in md
|
||||
|
||||
|
||||
def test_example_yaml_is_valid() -> None:
|
||||
data = yaml.safe_load(Path("docs/nh-broadband-install-request.example.yaml").read_text())
|
||||
assert data["contact"]["name"] == "Timmy Operator"
|
||||
assert len(data["checklist"]) == 8
|
||||
@@ -17,24 +17,8 @@ from typing import Dict, Any, Optional, List
|
||||
from pathlib import Path
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
import importlib.util
|
||||
|
||||
|
||||
def _load_local(module_name: str, filename: str):
|
||||
"""Import a module from an explicit file path, bypassing sys.path resolution."""
|
||||
spec = importlib.util.spec_from_file_location(
|
||||
module_name,
|
||||
str(Path(__file__).parent / filename),
|
||||
)
|
||||
mod = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(mod)
|
||||
return mod
|
||||
|
||||
|
||||
_harness = _load_local("v2_harness", "harness.py")
|
||||
UniWizardHarness = _harness.UniWizardHarness
|
||||
House = _harness.House
|
||||
ExecutionResult = _harness.ExecutionResult
|
||||
from harness import UniWizardHarness, House, ExecutionResult
|
||||
|
||||
|
||||
class TaskType(Enum):
|
||||
|
||||
@@ -8,30 +8,13 @@ import time
|
||||
import sys
|
||||
import argparse
|
||||
import os
|
||||
import importlib.util
|
||||
from pathlib import Path
|
||||
from datetime import datetime
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
def _load_local(module_name: str, filename: str):
|
||||
"""Import a module from an explicit file path, bypassing sys.path resolution.
|
||||
|
||||
Prevents namespace collisions when multiple directories contain modules
|
||||
with the same name (e.g. uni-wizard/harness.py vs uni-wizard/v2/harness.py).
|
||||
"""
|
||||
spec = importlib.util.spec_from_file_location(
|
||||
module_name,
|
||||
str(Path(__file__).parent / filename),
|
||||
)
|
||||
mod = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(mod)
|
||||
return mod
|
||||
|
||||
_harness = _load_local("v2_harness", "harness.py")
|
||||
UniWizardHarness = _harness.UniWizardHarness
|
||||
House = _harness.House
|
||||
ExecutionResult = _harness.ExecutionResult
|
||||
sys.path.insert(0, str(Path(__file__).parent))
|
||||
|
||||
from harness import UniWizardHarness, House, ExecutionResult
|
||||
from router import HouseRouter, TaskType
|
||||
from author_whitelist import AuthorWhitelist
|
||||
|
||||
|
||||
Reference in New Issue
Block a user