Catch up field brief, catalog Kimi K3, and wire live daily recurrence.
Add 2026-08-03 week catch-up brief with Kimi K3 as S1 strategic (collection deferred on ~1454 GiB vs 850 GiB soft quota), document recurrence ops, and add a workstation due-notice consumer cron helper. Production schedule was applied to railiance ConfigMap and Temporal (weekdays 07:30 Europe/Berlin).
This commit is contained in:
parent
441de11a3e
commit
70cbfe0c6c
10 changed files with 389 additions and 38 deletions
3
.gitignore
vendored
3
.gitignore
vendored
|
|
@ -162,3 +162,6 @@ cython_debug/
|
|||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
|
||||
|
||||
# local consumer logs / notes
|
||||
.local/
|
||||
|
|
|
|||
9
SCOPE.md
9
SCOPE.md
|
|
@ -91,14 +91,15 @@ Git holds briefs, schemas, policies, and catalog metadata. Model weight blobs st
|
|||
|
||||
| Area | Status |
|
||||
| ---- | ------ |
|
||||
| Overall | **Operable lab** — foundation + daily rhythm + R-spine reserve (2026-07-28) |
|
||||
| Overall | **Operable lab** — foundation + **live** weekday brief schedule + R-spine reserve |
|
||||
| INTENT / SCOPE | Drafted |
|
||||
| Baseline survey | `research/2026-07-24-baseline-field-survey.md` |
|
||||
| Briefs | Playbook + briefs for 2026-07-24 and 2026-07-28 |
|
||||
| Briefs | 2026-07-24, 07-28, **08-03** (week catch-up); playbook + recurrence ops |
|
||||
| Backup storage | **VAULT HD** `D:\vault\coulomb\freedom-intelligence\`; soft quota 850 GiB |
|
||||
| Inventory | R verified (embeds, Qwen3-8B, R1-Distill-14B); S approved+deferred; W candidate |
|
||||
| Inventory | R verified; **Kimi K3** S1 approved+deferred (~1454 GiB); other S deferred; W candidate |
|
||||
| Reserve policy | Capability-first — not gated by current VRAM |
|
||||
| Activity-core | Definition **enabled**; ConfigMap entry; apply residual on railiance |
|
||||
| Activity-core | Definition **enabled on railiance**; Temporal schedule weekdays 07:30 Berlin |
|
||||
| Consumer | Workstation cron `consume-fi-brief-spawn.sh` 07:40 weekdays |
|
||||
| State Hub | Repo under **agents**; workplans finished + hub-indexed |
|
||||
| Workplans | FI-WP-0001…0003 **finished** |
|
||||
|
||||
|
|
|
|||
|
|
@ -53,17 +53,17 @@ action:
|
|||
labels: ["freedom-intelligence", "research-brief", "automated"]
|
||||
```
|
||||
|
||||
## Enable checklist (completed 2026-07-28)
|
||||
## Enable checklist
|
||||
|
||||
1. [x] FI-WP-0002-T03 resolver live (`fi_brief_status` in activity-core)
|
||||
2. [x] FI-WP-0002-T04 external definition path registered
|
||||
- Local: `ACTIVITY_DEFINITION_DIRS` includes `/home/worsch/freedom-intelligence`
|
||||
- Railiance: `actcore-external-activity-definitions` ConfigMap key
|
||||
`fi-daily-research-brief.md` in `activity-core/k8s/railiance/20-runtime.yaml`
|
||||
3. [x] Completion event proven (`fi_daily_brief` for 2026-07-24; re-verified loop)
|
||||
4. [x] `enabled: true` / `status: active` in this frontmatter
|
||||
- Railiance: ConfigMap `actcore-external-activity-definitions` key
|
||||
`fi-daily-research-brief.md` (**applied live 2026-08-03**)
|
||||
3. [x] Completion event proven (`fi_daily_brief` 2026-07-24, 07-28, 08-03)
|
||||
4. [x] `enabled: true` / `status: active`
|
||||
5. [x] Temporal schedule live: `activity-schedule-3169ab1f-882b-59c7-9763-d014dc96f4fc`
|
||||
(weekdays 07:30 Europe/Berlin; not paused; next fires from 2026-08-04)
|
||||
6. [x] Workstation consumer cron: `scripts/consume-fi-brief-spawn.sh` at 07:40
|
||||
|
||||
**Ops residual:** apply ConfigMap on railiance when cluster is reachable and
|
||||
confirm Temporal schedule `activity-schedule-fi-daily-research-brief` (or
|
||||
equivalent id from sync). Workstation cannot dry-run spawn while k8s API is
|
||||
unreachable (2026-07-28).
|
||||
Ops: `docs/recurrence-ops.md`
|
||||
|
|
|
|||
68
briefs/2026/08/2026-08-03.md
Normal file
68
briefs/2026/08/2026-08-03.md
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
---
|
||||
date: 2026-08-03
|
||||
timezone: Europe/Berlin
|
||||
author: grok
|
||||
status: final
|
||||
sources_checked:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
- briefs/2026/07/2026-07-28.md
|
||||
- public trackers (llm-stats, Artificial Analysis notes, HF moonshotai)
|
||||
- huggingface.co/moonshotai/Kimi-K3
|
||||
---
|
||||
|
||||
# Freedom Intelligence Daily Brief — 2026-08-03
|
||||
|
||||
> **Week catch-up** from 2026-07-28 (recurring automation did not fire).
|
||||
> Delta overview, not a full resurvey.
|
||||
|
||||
## Headline deltas
|
||||
|
||||
- **Kimi K3 open weights (Moonshot, ~Jul 27):** 2.8T MoE, ~1.45 TiB official tree, custom Kimi K3 License — currently **#1 open-weight** on several boards; primary strategic S1 candidate (storage exceeds 850 GiB soft quota as full tree).
|
||||
- **DeepSeek V4-Flash-0731 (Jul 31):** same cheap price/size class, large capability jump — strong open price-performance; revisit as mid-size S/W vs our R spine.
|
||||
- **Closed frontier churn:** Claude Fable 5 back after export pause; Claude Opus 5 / GPT-5.6 family / Grok 4.5 / Gemini Flash tiers all active in trackers.
|
||||
- **Lab:** FI daily brief still **due** since Jul 28 (only two prior events); R spine remains on VAULT; recurrence wiring resumed this session.
|
||||
- **Reserve action:** nominate `moonshotai/Kimi-K3` as S1 strategic with **collection deferred** pending capacity decision (full pull ≈1.45 TiB).
|
||||
|
||||
## Frontier & commercial (axis A)
|
||||
|
||||
| Item | Delta | Sources | Lab relevance |
|
||||
| ---- | ----- | ------- | ------------- |
|
||||
| Claude Fable 5 / Opus 5 | Fable restored; Opus competitive on coding/agentic | trackers / AA notes | Closed bar for harness evals via llm-connect |
|
||||
| GPT-5.6 Sol/Terra/Luna | GA; Luna deep discount end-Jul | OpenAI pricing notes | Budget routing tiers |
|
||||
| Grok 4.5 | Public coding-focused tier | xAI product notes | Compare agent coding bar |
|
||||
| Gemini 3.5/3.6 Flash class | Fast tiers shipping | Google product notes | Cheap closed automation |
|
||||
|
||||
## Edge / local / open (axis B)
|
||||
|
||||
| Item | Delta | Sources | Lab relevance |
|
||||
| ---- | ----- | ------- | ------------- |
|
||||
| **Kimi K3** | Best open general/agentic class; 2.8T / 1M ctx / vision | [HF moonshotai/Kimi-K3](https://huggingface.co/moonshotai/Kimi-K3) | S1 identity; **too large for 850 GiB soft quota** as full tree |
|
||||
| DeepSeek V4-Flash-0731 | Open MIT-class value leader after Jul 31 retrain | DeepSeek release trackers | Candidate later mid-tier collect |
|
||||
| GLM-5.2 | Still “hostable strong open” for many teams | trackers | Alternative S dense if we skip full K3 |
|
||||
| Qwen 3.7/3.8-class | Continued family updates | Alibaba trackers | Watch vs Qwen3-8B R default |
|
||||
|
||||
## Training & specialization (axis C)
|
||||
|
||||
*(none material for lab this window — no new FT stack displacement vs Unsloth/axolotl baseline)*
|
||||
|
||||
## Harness & fleet (axis D)
|
||||
|
||||
| Item | Delta | Sources | Lab relevance |
|
||||
| ---- | ----- | ------- | ------------- |
|
||||
| FI daily brief gap | No automated brief since 2026-07-28 | State Hub progress | Wire recurrence + consumer this session |
|
||||
| Agent swarm narrative (Kimi) | Product emphasis on multi-agent / long-horizon | Kimi product | Align axis D watchlist with K3 agent demos |
|
||||
|
||||
## Collection candidates
|
||||
|
||||
| id | org | name | priority | reason | approx size | license |
|
||||
| -- | --- | ---- | -------- | ------ | ----------- | ------- |
|
||||
| moonshotai__Kimi-K3__strategic | moonshotai | Kimi-K3 | high | S1 best open general/agentic; displace V3 as primary strategic identity | ~1454 GiB official | custom (Kimi K3 License) — review commercial thresholds |
|
||||
|
||||
**Decision:** catalog + **defer download** until soft-quota / disk exception. Prefer official compressed if/when published under soft quota.
|
||||
|
||||
## Lab implications
|
||||
|
||||
- Keep R spine (Qwen3-8B, R1-Distill-14B, embeds) as daily local defaults.
|
||||
- Update strategic plan: S1 = Kimi K3 (identity), not only DeepSeek-V3.
|
||||
- Unblock weekday schedule on activity-core (ConfigMap apply + sync + schedule check).
|
||||
- Llama-3.2-3B still blocked on HF token (unchanged).
|
||||
|
|
@ -99,11 +99,12 @@ export ACTIVITY_DEFINITION_DIRS=/home/worsch/freedom-intelligence
|
|||
# then: make sync-activity-definitions (with ACTCORE_DB_URL + stack)
|
||||
```
|
||||
|
||||
Production (railiance): either project
|
||||
`activity-definitions/fi-daily-research-brief.md` into ConfigMap
|
||||
`actcore-external-activity-definitions`, or mount a checkout under
|
||||
`ACTIVITY_DEFINITION_DIRS` (`/etc/activity-core/external-definitions`). Keep
|
||||
`enabled: false` until FI-WP-0002-T05 dry-run passes.
|
||||
Production (railiance): projected into ConfigMap
|
||||
`actcore-external-activity-definitions` key `fi-daily-research-brief.md`
|
||||
(**enabled 2026-08-03**; Temporal schedule weekdays 07:30 Europe/Berlin).
|
||||
|
||||
Ops runbook: `docs/recurrence-ops.md`
|
||||
Workstation due-notice cron: `scripts/consume-fi-brief-spawn.sh` (07:40 weekdays).
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
98
docs/recurrence-ops.md
Normal file
98
docs/recurrence-ops.md
Normal file
|
|
@ -0,0 +1,98 @@
|
|||
# Freedom Intelligence daily brief — recurrence ops
|
||||
|
||||
**Status:** production schedule wired 2026-08-03
|
||||
**Definition:** `activity-definitions/fi-daily-research-brief.md`
|
||||
**Playbook:** `docs/daily-brief-playbook.md`
|
||||
|
||||
---
|
||||
|
||||
## Architecture (live)
|
||||
|
||||
```text
|
||||
Temporal schedule (railiance activity-core)
|
||||
cron: 30 7 * * 1-5 Europe/Berlin
|
||||
→ fi_brief_status (state-hub)
|
||||
→ if due: activity_task_spawn (state-hub sink)
|
||||
→ workstation consumer notice (optional cron)
|
||||
→ operator/agent executes playbook in freedom-intelligence
|
||||
→ progress event fi_daily_brief → next day due=false
|
||||
```
|
||||
|
||||
| Piece | Where |
|
||||
| ----- | ----- |
|
||||
| Source of truth (def) | `freedom-intelligence/activity-definitions/fi-daily-research-brief.md` |
|
||||
| Production projection | ConfigMap `actcore-external-activity-definitions` key `fi-daily-research-brief.md` |
|
||||
| GitOps copy | `activity-core/k8s/railiance/20-runtime.yaml` (keep in sync) |
|
||||
| Resolver | activity-core `fi_brief_status` |
|
||||
| Sink | `ISSUE_SINK_TYPE=state-hub` → `activity_task_spawn` |
|
||||
| Consumer (workstation) | `scripts/consume-fi-brief-spawn.sh` (due notice; not auto-LLM) |
|
||||
|
||||
---
|
||||
|
||||
## Verify schedule
|
||||
|
||||
```bash
|
||||
# Definition present + enabled on API
|
||||
kubectl -n activity-core exec deploy/actcore-api -- \
|
||||
python3 -c "import urllib.request,json; d=json.loads(urllib.request.urlopen('http://localhost:8010/activity-definitions/').read());
|
||||
print([x for x in d if 'Freedom Intelligence' in (x.get('name') or '')])"
|
||||
|
||||
# After def change: re-project ConfigMap then
|
||||
kubectl -n activity-core exec deploy/actcore-api -- \
|
||||
python3 -c "import urllib.request; print(urllib.request.urlopen(urllib.request.Request('http://localhost:8010/admin/sync?definitions=true&schedules=true', method='POST')).read().decode())"
|
||||
```
|
||||
|
||||
Schedule id pattern: `activity-schedule-<activity-definition-uuid>`.
|
||||
|
||||
---
|
||||
|
||||
## Workstation consumer (optional but recommended)
|
||||
|
||||
After activity-core fires at 07:30, run a due-check on the workstation:
|
||||
|
||||
```cron
|
||||
# crontab -e (Europe/Berlin host clock or TZ=Europe/Berlin)
|
||||
40 7 * * 1-5 /home/worsch/freedom-intelligence/scripts/consume-fi-brief-spawn.sh
|
||||
```
|
||||
|
||||
This writes `.local/consumer-logs/DUE-YYYY-MM-DD.txt` when a brief is still due.
|
||||
An agent session or operator then runs the playbook and posts `fi_daily_brief`.
|
||||
|
||||
---
|
||||
|
||||
## Manual one-shot (if schedule missed)
|
||||
|
||||
```bash
|
||||
# Resolve activity id from API list, then:
|
||||
kubectl -n activity-core exec deploy/actcore-api -- \
|
||||
python3 -c "import urllib.request; print(urllib.request.urlopen(urllib.request.Request('http://localhost:8010/activity-definitions/<id>/trigger', method='POST')).read().decode())"
|
||||
```
|
||||
|
||||
Then execute playbook + post progress event.
|
||||
|
||||
---
|
||||
|
||||
## Update definition
|
||||
|
||||
1. Edit `activity-definitions/fi-daily-research-brief.md` in this repo
|
||||
2. Copy content into ConfigMap key (or re-apply from `activity-core` 20-runtime.yaml)
|
||||
3. Wait for volume refresh (~30–90s)
|
||||
4. `POST /admin/sync?definitions=true&schedules=true`
|
||||
5. Commit both freedom-intelligence and activity-core if 20-runtime.yaml changed
|
||||
|
||||
---
|
||||
|
||||
## Completion event (required)
|
||||
|
||||
```yaml
|
||||
event_type: fi_daily_brief
|
||||
author: <agent-or-operator>
|
||||
summary: "FI daily brief YYYY-MM-DD"
|
||||
detail:
|
||||
repo: freedom-intelligence
|
||||
date: "YYYY-MM-DD"
|
||||
path: "briefs/YYYY/MM/YYYY-MM-DD.md"
|
||||
collection_candidates: <int>
|
||||
```
|
||||
|
||||
API: `POST http://127.0.0.1:8000/progress/`
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
# Open-weight reserve status
|
||||
|
||||
**As of:** 2026-07-28
|
||||
**As of:** 2026-08-03
|
||||
**Store:** `/mnt/d/vault/coulomb/freedom-intelligence/` (`D:\vault\coulomb\freedom-intelligence\`)
|
||||
**Soft quota:** 850 GiB · **Hard stop:** 920 GiB
|
||||
|
||||
|
|
@ -10,15 +10,13 @@
|
|||
|
||||
| Class | Count | Status mix |
|
||||
| ----- | ----: | ---------- |
|
||||
| Catalog entries | 12 | see table |
|
||||
| Catalog entries | 13 | + Kimi K3 S1 |
|
||||
| **verified** on disk | 4 | R embeds + Qwen3-8B + R1-Distill-14B |
|
||||
| **approved** (pull deferred) | S giants + Llama edge | capacity / HF gate |
|
||||
| **approved** (pull deferred) | S giants + Llama edge + **Kimi K3** | capacity / HF gate |
|
||||
| **candidate** (W) | 3 | headroom-gated |
|
||||
|
||||
### Disk use (model tree)
|
||||
|
||||
Run: `du -sh /mnt/d/vault/coulomb/freedom-intelligence/models`
|
||||
|
||||
| Path | Role | Approx |
|
||||
| ---- | ---- | ------ |
|
||||
| `models/nomic-ai__nomic-embed-text-v1.5/main` | R embed | ~0.5 GiB verified |
|
||||
|
|
@ -26,26 +24,29 @@ Run: `du -sh /mnt/d/vault/coulomb/freedom-intelligence/models`
|
|||
| `models/Qwen__Qwen3-8B/main` | R instruct | ~15.3 GiB verified |
|
||||
| `models/deepseek-ai__DeepSeek-R1-Distill-Qwen-14B/main` | R reason | ~27.5 GiB verified |
|
||||
|
||||
**~45 GiB** of soft 850 GiB used by verified R spine → **~800+ GiB** headroom for S.
|
||||
**~45 GiB** used → **~800+ GiB** soft-quota headroom (insufficient for full Kimi K3 ~1454 GiB).
|
||||
|
||||
VAULT free (2026-08-03): ~1.7 TB free of 1.9 TB — full K3 would still dominate the volume and **violate soft quota**.
|
||||
|
||||
---
|
||||
|
||||
## Decision matrix (2026-07-28)
|
||||
## Decision matrix (2026-08-03)
|
||||
|
||||
| Id | Tier | Decision | Disk |
|
||||
| -- | ---- | -------- | ---- |
|
||||
| Qwen3-8B | R | **verified** | yes |
|
||||
| Llama-3.2-3B-Instruct | R | **approved** | deferred — HF gate (need token) |
|
||||
| Llama-3.2-3B-Instruct | R | **approved** | deferred — HF gate |
|
||||
| BGE-M3 | R | **verified** | yes |
|
||||
| R1-Distill-Qwen-14B | R | **verified** | yes |
|
||||
| nomic-embed-text-v1.5 | R | **verified** | yes |
|
||||
| DeepSeek-V3 | S1 | **approved**, **collection deferred** | no — capacity / compressed plan later |
|
||||
| DeepSeek-R1 full | S2 | **approved**, **collection deferred** | no — distill covers runnable reason |
|
||||
| Qwen3-72B | S4 | **approved**, **collection deferred** | no — after R; pick vs Llama-70B |
|
||||
| Llama-3.3-70B-Instruct | S4 | **approved**, **collection deferred** | no — gated + vs Qwen-72B |
|
||||
| Qwen3-14B | W | **remain candidate** | no |
|
||||
| R1-Distill-32B | W | **remain candidate** | no |
|
||||
| bge-reranker-v2-m3 | W | **remain candidate** | no |
|
||||
| **Kimi-K3** | **S1** | **approved**, **collection deferred** | no — ~1454 GiB > soft quota |
|
||||
| DeepSeek-V3 | S1→secondary | **approved**, deferred | no — K3 is primary open SOTA identity |
|
||||
| DeepSeek-R1 full | S2 | **approved**, deferred | no |
|
||||
| Qwen3-72B | S4 | **approved**, deferred | no |
|
||||
| Llama-3.3-70B-Instruct | S4 | **approved**, deferred | no |
|
||||
| Qwen3-14B | W | candidate | no |
|
||||
| R1-Distill-32B | W | candidate | no |
|
||||
| bge-reranker-v2-m3 | W | candidate | no |
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -57,15 +58,16 @@ Run: `du -sh /mnt/d/vault/coulomb/freedom-intelligence/models`
|
|||
| Edge micro-agent | Llama-3.2-3B blocked on HF auth |
|
||||
| Multilingual RAG embed | **Covered** (BGE-M3 + nomic) |
|
||||
| Local reason | **Covered** (R1-Distill-14B) |
|
||||
| Frontier-open general MoE offline | Deferred S1 (V3 class) |
|
||||
| Frontier-open general MoE offline | **Cataloged** Kimi K3 — pull blocked on capacity |
|
||||
| Full open reasoner MoE | Deferred S2 |
|
||||
|
||||
---
|
||||
|
||||
## Next pulls (operator)
|
||||
|
||||
1. Set `HF_TOKEN` and pull Llama-3.2-3B-Instruct.
|
||||
2. Reassess soft quota; pick **one** of Qwen3-72B vs Llama-3.3-70B before any S1 giant.
|
||||
3. For S1/S2: prefer **official compressed** distributions under soft quota.
|
||||
1. **Capacity decision for Kimi K3** (raise soft quota / dedicate disk / official compressed only).
|
||||
2. Set `HF_TOKEN` and pull Llama-3.2-3B-Instruct.
|
||||
3. Optional S4: one of Qwen3-72B vs Llama-3.3-70B under remaining quota.
|
||||
4. DeepSeek V4-Flash-0731 as mid open value candidate (catalog later if desired).
|
||||
|
||||
Tool: `scripts/collect_model.py` (weights-only, sequential, writes `MANIFEST.json`).
|
||||
|
|
|
|||
104
inventory/catalog/moonshotai__Kimi-K3__strategic.yaml
Normal file
104
inventory/catalog/moonshotai__Kimi-K3__strategic.yaml
Normal file
|
|
@ -0,0 +1,104 @@
|
|||
id: moonshotai__Kimi-K3__strategic
|
||||
status: approved
|
||||
name: Kimi-K3
|
||||
org: moonshotai
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/moonshotai/Kimi-K3
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/moonshotai/Kimi-K3
|
||||
project_url: https://www.kimi.com/
|
||||
paper_url: https://huggingface.co/papers/2607.24653
|
||||
license:
|
||||
spdx: LicenseRef-Kimi-K3
|
||||
url: https://huggingface.co/moonshotai/Kimi-K3
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: >
|
||||
Custom Kimi K3 License (not plain MIT/Apache). Review commercial SaaS
|
||||
revenue thresholds and attribution before external product embedding.
|
||||
Confirm card text at pin time.
|
||||
profile:
|
||||
summary: "S1 open frontier MoE (2.8T) — best open general/agentic class mid-2026."
|
||||
original_source: https://huggingface.co/moonshotai/Kimi-K3
|
||||
use_cases:
|
||||
- "Long-horizon coding and agent workflows (offline optionality)"
|
||||
- "Strategic reserve if closed APIs are unavailable or restricted"
|
||||
- "Future multi-GPU / training-facility inference when hardware catches up"
|
||||
- "Capability baseline against closed frontier for daily briefs"
|
||||
- "Native vision + 1M-context knowledge work (when runnable)"
|
||||
sweet_spots:
|
||||
- "Top open-weight intelligence class after Jul 2026 weight release"
|
||||
- "Agentic / coding / long-context open MoE identity"
|
||||
- "Displaces prior S1 DeepSeek-V3 as primary open general target"
|
||||
not_ideal_for:
|
||||
- "Current single-GPU or small multi-GPU lab serve (far beyond run envelope)"
|
||||
- "Fitting under 850 GiB soft quota at full precision (~1.45 TiB tree)"
|
||||
- "Casual always-on chat (use R spine)"
|
||||
capability_notes: >
|
||||
Moonshot Kimi K3: ~2.8T total MoE parameters, sparse activation (~16/896
|
||||
experts), Kimi Delta Attention + Attention Residuals, native multimodal,
|
||||
~1M context. Official HF tree measured ~1454 GiB (96 shards). Collection
|
||||
deferred until capacity exception or official compressed distribution.
|
||||
swot:
|
||||
strengths:
|
||||
- "Leading open-weight general/agentic capability at release"
|
||||
- "Open weights enable true offline retention optionality"
|
||||
- "Strong coding / long-horizon / vision narrative"
|
||||
weaknesses:
|
||||
- "Disk footprint (~1.45 TiB) exceeds current soft quota and most lab GPUs"
|
||||
- "Custom license with commercial thresholds"
|
||||
- "Serve cost multi-node enterprise class"
|
||||
opportunities:
|
||||
- "Hold identity in catalog; pull compressed later if published"
|
||||
- "Anchor daily briefs / evals against open SOTA"
|
||||
- "Displace V3 as primary S1 when space allows"
|
||||
threats:
|
||||
- "Quota: full pull blocks all other S niches on VAULT"
|
||||
- "Rapid supersession by K3.x or peer open giants"
|
||||
- "Third-party quant quality variance if forced to unofficial packs"
|
||||
size:
|
||||
total_bytes: 1560998984390
|
||||
total_human: "~1454 GiB official HF tree (measured 2026-08-03); compressed TBD"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 0
|
||||
min_vram_gb_fp16: 0
|
||||
notes: "Beyond current lab run envelope (multi-node). Strategic reserve only."
|
||||
axes: [A, B, C, D]
|
||||
priority: high
|
||||
collection:
|
||||
approved_by: "bernd"
|
||||
approved_at: "2026-08-03"
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- briefs/2026/08/2026-08-03.md
|
||||
- research/2026-07-24-nas-strategic-collection-plan.md
|
||||
- docs/decisions/2026-07-24-nas-strategic-reserve.md
|
||||
reason: >
|
||||
S1 strategic — best open-weight general/agentic model class after Jul 2026
|
||||
release; keep capability identity even though full tree exceeds soft quota.
|
||||
tags: [tier-s, strategic, beyond-run-envelope, moe, general, vision, kimi, s1]
|
||||
companions: []
|
||||
notes: >
|
||||
Do not bulk-download full tree under 850 GiB soft quota. Prefer official
|
||||
compressed if/when available. Revisit capacity exception with operator.
|
||||
history:
|
||||
- at: "2026-08-03"
|
||||
event: nominated
|
||||
by: grok
|
||||
detail: "Week catch-up brief — Kimi K3 open weights Jul 27 as new open SOTA."
|
||||
- at: "2026-08-03"
|
||||
event: approved
|
||||
by: bernd
|
||||
detail: "Operator direction: catalog and plan; collection deferred on capacity."
|
||||
- at: "2026-08-03"
|
||||
event: collection_deferred
|
||||
by: grok
|
||||
detail: "Official tree ~1454 GiB > soft quota 850 GiB; await capacity decision or compressed release."
|
||||
- at: "2026-08-03"
|
||||
event: profile_swot_added
|
||||
by: grok
|
||||
detail: "schema 0.2 profile + SWOT."
|
||||
|
|
@ -36,7 +36,7 @@ hundreds of GiB–TB.
|
|||
|
||||
| Priority | Capability niche | Representative targets (verify current HF id + license at pull) | Size class (order of magnitude) |
|
||||
| -------- | ---------------- | ---------------------------------------------------------------- | -------------------------------- |
|
||||
| **S1** | Best open general / MoE chat | DeepSeek-V3 / V3.2 / V4-class open MoE (latest card) | ~300–700+ GiB depending on quant/precision |
|
||||
| **S1** | Best open general / MoE chat | **Kimi K3** (`moonshotai/Kimi-K3`, Jul 2026) — primary; DeepSeek-V3/V4 secondary | K3 full ~1454 GiB (exceeds 850 GiB soft quota — capacity decision); V3/V4 class hundreds of GiB quant |
|
||||
| **S2** | Best open reasoner | DeepSeek-R1 full (or successor open reasoner) | similar large |
|
||||
| **S3** | Best open coding / SWE open weight | Top open code MoE or dense (e.g. GLM-5.x open, Qwen coder large — pick current SOTA open) | tens–hundreds GiB |
|
||||
| **S4** | Strong open dense mid-large | Qwen3-72B or Llama 3.3 70B / Llama 4 open text variant | ~40–150 GiB quant / larger fp |
|
||||
|
|
|
|||
74
scripts/consume-fi-brief-spawn.sh
Executable file
74
scripts/consume-fi-brief-spawn.sh
Executable file
|
|
@ -0,0 +1,74 @@
|
|||
#!/usr/bin/env bash
|
||||
# Workstation consumer for FI daily research brief spawns.
|
||||
#
|
||||
# activity-core emits activity_task_spawn (state-hub sink) with
|
||||
# target_repo=freedom-intelligence. This script:
|
||||
# 1) checks fi_brief_status due (or open spawn)
|
||||
# 2) reminds operator / runs playbook path
|
||||
# 3) does NOT invent brief content — open a session with the playbook
|
||||
#
|
||||
# Schedule suggestion (Europe/Berlin, after 07:30 spawn):
|
||||
# 40 7 * * 1-5 /home/worsch/freedom-intelligence/scripts/consume-fi-brief-spawn.sh
|
||||
#
|
||||
# Env:
|
||||
# STATE_HUB_URL default http://127.0.0.1:8000
|
||||
# FI_REPO default /home/worsch/freedom-intelligence
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
STATE_HUB_URL="${STATE_HUB_URL:-http://127.0.0.1:8000}"
|
||||
FI_REPO="${FI_REPO:-/home/worsch/freedom-intelligence}"
|
||||
LOG_DIR="${FI_REPO}/.local/consumer-logs"
|
||||
mkdir -p "$LOG_DIR"
|
||||
log="$LOG_DIR/$(date +%Y-%m-%d).log"
|
||||
|
||||
{
|
||||
echo "=== $(date -Is) consume-fi-brief-spawn ==="
|
||||
# Prefer activity-core resolver if available; else raw progress heuristic
|
||||
due_json=""
|
||||
if command -v uv >/dev/null 2>&1 && [[ -d /home/worsch/activity-core ]]; then
|
||||
due_json="$(
|
||||
cd /home/worsch/activity-core &&
|
||||
STATE_HUB_URL="$STATE_HUB_URL" uv run python -c "
|
||||
from activity_core.context_resolvers.state_hub import _fi_brief_status
|
||||
import json
|
||||
print(json.dumps(_fi_brief_status({'repo': 'freedom-intelligence'}), default=str))
|
||||
" 2>/dev/null || true
|
||||
)"
|
||||
fi
|
||||
|
||||
if [[ -z "$due_json" ]]; then
|
||||
echo "WARN: could not query fi_brief_status; check STATE_HUB_URL=$STATE_HUB_URL"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
echo "status: $due_json"
|
||||
due="$(python3 -c "import json,sys; d=json.loads(sys.argv[1]); print(d['items'][0]['due'])" "$due_json")"
|
||||
date_s="$(python3 -c "import json,sys; d=json.loads(sys.argv[1]); print(d['items'][0]['date'])" "$due_json")"
|
||||
|
||||
if [[ "$due" != "True" && "$due" != "true" ]]; then
|
||||
echo "not due for $date_s — exit"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
y="${date_s:0:4}"
|
||||
m="${date_s:5:2}"
|
||||
brief_path="$FI_REPO/briefs/$y/$m/$date_s.md"
|
||||
echo "DUE: produce brief at $brief_path"
|
||||
echo "Playbook: $FI_REPO/docs/daily-brief-playbook.md"
|
||||
echo "On completion POST event_type=fi_daily_brief detail.repo=freedom-intelligence detail.date=$date_s"
|
||||
|
||||
# Non-interactive marker for operators / agents
|
||||
notice="$LOG_DIR/DUE-$date_s.txt"
|
||||
cat >"$notice" <<EOF
|
||||
FI daily research brief is DUE for $date_s.
|
||||
|
||||
1. cd $FI_REPO
|
||||
2. Follow docs/daily-brief-playbook.md
|
||||
3. Write $brief_path
|
||||
4. Post State Hub progress event fi_daily_brief
|
||||
|
||||
Spawn consumer ran at $(date -Is).
|
||||
EOF
|
||||
echo "wrote $notice"
|
||||
} | tee -a "$log"
|
||||
Loading…
Add table
Add a link
Reference in a new issue