Commit Graph
216 Commits
Author SHA1 Message Date
inference-admin 1ec9657f85 Added approval date to steward policy 2026-11-16 23:22:34 +00:00
inference-admin 306b83eaa7 docs: an Operations section, the approved Steward Policy, and section index pages
The Steward Policy passed in Loomio, so it lands as operations/steward-policy.md
(verbatim from the shared draft, one garbled phrase repaired: 'finances alloas
determined by' -> 'finances allow, as determined by').

Governance and Operations now have index pages, and both are in the nav as
section overviews, so each section has a landing page instead of a bare menu.
2026-11-16 23:20:05 +00:00
inference-admin 01e18a9f8b models: the default now serves the DeepSeek V4.1 Flash 1017 snapshot
Same name, new snapshot and new rates ($0.36/$1.45/$0.04 per 1M). The id is unchanged
on purpose: 3,014 calls in two days used it, so renaming would break members' configs.
2026-11-16 15:53:13 +00:00
inference-admin 6a5acc2b82 api-access: glm-green is glm-flash-green
Same-model-two-routes reads better when both names carry the tier.
2026-11-14 18:57:48 +00:00
inference-admin 481a9f40cd api-access: -green/-tee aliases, and a table of where they point today
Names now say which route rather than how fresh a version is, and the page
answers the question the names raise: what each alias serves right now.
2026-11-14 18:47:56 +00:00
inference-admin 7f8480f13d api-access: the typical model entry uses the stable aliases
The gateway now serves four version-free names (deepseek-flash-latest,
glm-flash-latest, deepseek-flash-tee, glm-tee), added per co-op/support#47 so a
member's config survives a provider retiring a version. The example entry is what
members copy, so it should be the names that keep working; provider-prefixed ids
still work and are linked for anyone who needs a specific version.
2026-11-14 18:42:47 +00:00
inference-admin 808e54505f models: measure the Regolo context windows — all four are 262,144, not 30K/60K/100K
A member read Regolo's own catalogue, where the input-limits column reads 30K for
apertus-70b (and for the MXFP4 gpt-oss models we do not serve from Regolo), 60K for
mistral-small-4-119b and 100K for gemma4-31b, and asked whether >30K input is
possible at all on Regolo. It is: probed through the co-op gateway, every Regolo
chat model we serve accepts 262,144 tokens and rejects above it, so the ceilings are
exact rather than approximate. gemma4-31b and mistral-small-4-119b therefore move
from their catalogued 100K/60K to the measured 262K.

The 'Context figures are measured' paragraph now says what was measured, when, and
how — and names the Regolo catalogue as the source of the smaller numbers, so the
next reader comparing the two does not file the difference as a bug.
2026-11-13 18:30:42 +00:00
inference-bot 030dd1d5c4 models: add Regolo Gemma-4-31B and Mistral-Small-4-119B to the model table
Rates per Regolo's own catalog ($0.40/$0.60 and $0.20/$0.70 per 1M);
context 100K / 60K. Vision verified through the co-op gateway for both.
Mirrors the gateway config (code/litellm config.yaml, authoritative).
2026-11-13 15:30:08 +00:00
inference-admin a1b55376e4 Added Schneider blog post link 2026-11-12 16:30:08 +00:00
inference-admin f683952b49 Small tweaks and fixes 2026-11-12 04:00:20 +00:00
inference-bot 8642f5f3e9 Revert "getting-started: temporary one-word edit (deploy pipeline end-to-end test)"
This reverts commit 1d36901a5e.
2026-11-12 03:31:42 +00:00
inference-bot b295b5a5b6 publishing: fix check_toolchain dying silently on a missing package
pip show exits non-zero for an absent package; under set -euo pipefail the
command substitution aborted build.sh before the self-heal could run — the
gate then failed the deploy with no message at all. Tolerate the missing
package (that is the case being healed) and report it.
2026-11-12 03:30:11 +00:00
inference-bot 1d36901a5e getting-started: temporary one-word edit (deploy pipeline end-to-end test) 2026-11-12 03:28:03 +00:00
inference-bot 20d384be87 publishing: one canonical build venv; drift check; deploy-failure alerting
The poller's private venv (.docs-publisher/.venv-docs) diverged from the
canonical one twice, each time silently delaying a deploy. Consolidate:

- poll-watcher.sh builds with the ONE canonical venv
  (~/repos/docs/.venv-docs) while keeping its dedicated checkout (uncommitted
  edits in a working clone must never block or leak into a deploy).
- New drift check: publishing/ + mkdocs.yml are compared with the canonical
  checkout before every build; a mismatch fails the deploy loudly instead of
  shipping logic the canonical source cannot reproduce.
- Pre-deploy gate: build.sh --check-only verifies the pinned toolchain and
  every configured plugin (self-heals missing pins, fails loudly naming an
  unpinned plugin).
- Alerting: 3 consecutive deploy failures -> marker file + ONE Matrix message
  to the InferenceBot HQ room (hourly cap); counter resets on next success.
- The watcher re-execs itself when a deploy changed poll-watcher.sh, so the
  running loop always matches the deployed one.
- webhook receiver (dormant) repointed at the canonical venv too; unit files
  and README document the layout.
2026-11-12 03:23:33 +00:00
inference-bot 1691f79621 publishing: complete the pinned toolchain; build.sh self-heals missing plugins
requirements.txt pinned only mkdocs-material, so a cold venv lacked mkdocs
and mkdocs-redirects — the exact gap that silently stalled the auto-deployer
today. build.sh now gates every build on the venv: it verifies the pinned
requirements (installing anything missing or off-version — fast local no-op
when current) and fails loudly if mkdocs.yml configures a plugin that
requirements.txt does not pin. --check-only runs the gates without building,
for use as the poller's pre-deploy check.
2026-11-12 03:21:50 +00:00
inference-bot 027cf596ef Shorten and correct the agent page: single steward agent; note retired automation account 2026-11-12 03:10:41 +00:00
inference-admin 0a9ca1945a initial edits to the proposal guide 2026-11-12 02:59:58 +00:00
inference-bot a3cb6d7ec7 Update remaining root-page links to governance/ paths 2026-11-12 02:55:40 +00:00
inference-bot e84a5537d4 Fix double-prefixed relative links in governance docs 2026-11-12 02:55:31 +00:00
inference-bot 1865552390 Move redirects config to plugins section (was misplaced under theme) 2026-11-12 02:53:22 +00:00
inference-bot 4ececfa584 Move governance docs into governance/ folder with redirects; nav mirrors structure 2026-11-12 02:51:39 +00:00
inference-bot c041e88fff Add 'How to make a proposal' governance page (adapted from social.coop, credited) 2026-11-12 00:13:36 +00:00
inference-bot 2422432b85 Dark mode: search form wrapper also dark (the input's parent was still light) 2026-11-09 18:20:09 +00:00
inference-bot 5402b9e758 Dark mode: darker tab stripe (dark-border green) and darker pine search surfaces 2026-11-09 18:15:50 +00:00
inference-bot 96b1201f72 guest-access.md: dashboard self-serve invites replace the email path, note awaiting-setup state and credit return on cancel 2026-11-09 18:04:33 +00:00
inference-bot 852e52dc35 models.md: pin exact upstream versions of the default chat model and the image model
- greenpt/deepseek-v4.1-flash routes to GreenPT's base deepseek-v4.1-flash
  id, not the deepseek-v4.1-flash-1017 snapshot (17 Oct 2026) that GreenPT
  lists separately. Confirmed from the gateway registry mapping and
  GreenPT's model card / model list, 2026-11-09.
- regolo/qwen-image serves Regolo's single Qwen-Image id, which Regolo's
  catalog describes as the (2512) checkpoint — the December 2025 update,
  not the newer Qwen Image 2.1 (2026-09-20). Regolo does not list 2.1.
2026-11-09 15:44:44 +00:00
inference-bot ac75c504f6 Dark-mode search input: deep green instead of pine (stands out less) 2026-11-09 06:33:26 +00:00
inference-admin c6d03c8f85 Removing some open questions that have been closed 2026-11-09 06:28:34 +00:00
inference-bot fb14577626 Dark-mode search input: dark background with light text (was white box, light-on-light) 2026-11-09 06:27:23 +00:00
inference-bot 9119e6726a Dark header bar: #171717 with white text, matching the chat overlay's dark menu 2026-11-09 06:24:40 +00:00
inference-bot 70c87e47c2 Guest access: $5 -> $2 of credits; trim page to essentials 2026-11-08 20:12:28 +00:00
inference-bot 342c353ebc Rename 'Gift access' to 'Guest access' — pure terminology rename, page and nav moved to guest-access.md 2026-11-08 02:30:27 +00:00
inference-bot 0786d97286 Add 'Gift access' — documenting the member gift-account feature 2026-11-08 02:23:42 +00:00
inference-bot af4f96ad13 models: three member-facing embedding models (nomic un-scoped, green-embeddings added)
- tinfoil/nomic-embed-text is now member-facing ($0.016/1M per Tinfoil's
  catalog, TEE-protected, 768-dim, 8K ctx) — the model the co-op's own docs
  search runs on inside the TEE.
- greenpt/green-embeddings added ($0.20/1M, 2560-dim measured, 32K ctx) — the
  only genuinely distinct other embedding model in GreenPT's catalog.
- Embedding table now lists all three with pricing; quick-guide bullet updated.
2026-11-06 22:39:07 +00:00
inference-bot b263e125c4 models: correct audio pricing rows; add tinfoil/voxtral-small-24b
- whisper-large-v3-turbo: $0.01 per request (flat, zero per-token) — the old
  $0.05/1M-input row was stale (co-op/support#48)
- voxtral-tts: $0.002 per request (was 'listed $0 (verify on invoice)')
- new: tinfoil/voxtral-small-24b, Tinfoil's token-priced STT model
  ($0.20/1M in + $0.60/1M out), with the chunk-equivalent note for the
  transcription route and a chat-with-input_audio example
- note why dashboard audio rows read '$0.01 · 0 tokens' (Tinfoil returns no
  token usage for audio)
2026-11-06 22:33:42 +00:00
inference-bot fa4ba8d989 models: document greenpt/qwen3-embedding-8b — the member-facing embeddings API
New gateway model (code/litellm 54925ca): /v1/embeddings, GreenPT-hosted,
4096-dim (measured through the gateway), $0.25/1M input from GreenPT's own
pricing, 32K input cap (provider catalog). Not a chat model — API-only like
the audio models, hidden from the chat picker. Also states plainly that
Tinfoil's nomic-embed-text is the operator-only docs-RAG embedding, since a
member read its absence from the model list as removal.
2026-11-06 20:35:04 +00:00
inference-bot 2a89e6a19d Add the co-op meeting calendar to the homepage and Getting Started 2026-11-06 17:44:34 +00:00
inference-admin 5eacc1c116 Made explicit Nathan Schneider's founding role 2026-11-05 04:47:21 +00:00
inference-admin df722f81b0 A little tightening 2026-11-04 21:33:35 +00:00
docs-bot 278c1fda1a infrastructure: make the page member-facing; lighten the light-mode menu-bar stripe
- condense the page to what a member needs: where services run (Infomaniak),
  what backups mean to them, the .coop domain via domains.coop, mail via
  Scaleway, the Matrix space and the accounts they may meet
- drop operator detail (migration narration, DNS record inventory, scheduled-task
  internals, admin-only components, internal account/credential identifiers) to
  co-op/ops-docs; fix a heading glitch where a line began with '#infrastructure'
- brand.css: light-mode .md-tabs uses the header's pale wash #e8f5e8 (was the
  saturated --green-deep) with a warm hairline; dark scheme unchanged
2026-11-04 21:29:06 +00:00
inference-bot 869d16cc65 docs: note on Open Collective payment timing and automatic credit 2026-11-04 21:15:41 +00:00
inference-admin 07d5a60377 Adjusted framing from "private" to "ethical" 2026-11-04 20:54:48 +00:00
inference-bot 33b5cf73e8 docs site: label the site as 'docs' and link the co-op homepage
Make clear this is the documentation, not the co-op homepage:
- site_name -> 'Inference Cooperative docs' (drives the <title> and the
  header brand on every page)
- homepage h1 -> 'Inference Cooperative docs'
- footer gains a 'Co-op homepage' link to https://inference.coop/, added
  in the existing copyright.html override alongside the Gitea source link
2026-11-04 20:42:07 +00:00
inference-bot 98cd517b8a docs: rebase onto current main -- add the page to the nav and repoint the operator-runbook link
- mkdocs.yml: list 'Working with the agent' in the nav (a page not in the
  nav is hard to find).
- working-with-the-agent.md: the operator token runbook moved out of the
  published site into the git-only co-op/ops-docs, so the relative link
  (operator-token-runbook.md) would 404; point it at the runbook's new home
  in ops-docs, as infrastructure.md already does. Wording unchanged.
2026-11-04 01:17:47 +00:00
solo.ist c5fd1ba96f working-with-the-agent: apply the agent's review (fleet, two handles, allowlist mechanism, deploy policy as practiced, off-switch access caveat)
- The co-op now runs more than one isolated agent; the page covers all of
  them and names infrastructure-bot.
- Disambiguates @inference-bot (automation account) from @inferencebot
  (the steward agent members instruct).
- Names the mechanism behind "admitted members": a per-agent allowlist
  plus mention-required rooms.
- Restates the deploy norm to match standing practice (bug and security
  fixes deploy immediately and are reported; member-visible or risky
  changes are confirmed first) and points a stricter norm at the forum.
- Off switch: who can actually reach it, and that stopping is not
  restarting.
2026-11-04 01:17:33 +00:00
solo.ist 9b5eff63fb docs: add "Working with the agent" (norms for reading and instructing inferencebot)
A first draft of the member-facing norms listed as a design goal on
co-op/support#17: where the agent speaks and listens, what to ask it for,
what not to ask it in a shared room, what it does without confirmation,
what always needs a human, and how it is stopped. Linked from the README
index and the Matrix section of getting-started. Nothing here changes how
the agent is configured.
2026-11-04 01:17:33 +00:00
inference-bot 08ad0c42ee ci: run the docs pipeline on the agent's local backend (no container images) 2026-11-04 01:08:17 +00:00
docs-agent 4f07c2d3ac docs site: content-hash the site's own stylesheets (cache-proof URLs)
brand.css and typography.css are referenced at fixed URLs via extra_css, so a
warm browser cache could keep serving the previous stylesheet after a deploy.
Add on_post_build to publishing/hooks.py: at build time copy each extra_css
file to <name>.<sha256-8>.css in the output and rewrite the <link> in the built
HTML. Any content change now yields a new URL. Sources keep their names; hashed
copies exist only in the build output and stale ones are pruned on rebuild.
2026-11-04 00:23:28 +00:00
inference-bot 492a64fa43 docs site: gentler header -- a pale wash instead of a saturated green bar
The light scheme filled the header and tabs with green-deep, which read as heavy. They now
use the homepage's "open source" pill colour #e8f5e8 with ink text, and the deeper greens
are kept for accents -- links, active navigation and rules -- rather than as background
fills. The dark scheme is unchanged.
2026-11-03 23:57:36 +00:00
inference-bot e0b9c0cd7e docs: clickable Key links, footer source link, move operator material to co-op/ops-docs
- README: render the Key links as real Markdown links (mailto: for the
  contact address); drop the 'lives in a public git repository' note now
  that the footer carries the source link.
- mkdocs.yml: add a theme override (custom_dir: overrides) that puts a
  'Documentation source' link in the footer of every page.
- Move the operator runbook, maintenance notes and incident write-up out
  of the published site into the git-only co-op/ops-docs repository;
  remove them from the nav and repoint cross-references at Gitea.
2026-11-03 23:30:58 +00:00