inference-bot
fbfca9624e
infrastructure: say which Matrix account is which, and start retiring @inference-bot
...
Four automated accounts touch the homeserver and two of them differed by one
character, which caused real confusion (a bot appearing to announce itself; the
steward unable to post in a room it had been asked to report to). This records
the distinction rather than leaving it to be rediscovered.
Power belongs to @inference-admin , voice belongs to @inferencebot, and
@inference-admin never speaks in a member room. @inference-bot is being retired:
its room power was transferred to @inference-admin , which is now administrator of
record for #general, #community, #design, #skillshare, #updates and
#infrastructure.
Also records the one live dependency that blocks finishing: the portal's member
invites still authenticate as the old account via MATRIX_BOT_TOKEN, so that has
to be repointed before its credentials are revoked. Without this written down the
next person would revoke the token and silently break member invites.
Verified while writing: the portal's token hashes to the old account's device
VYQDYBXULA, which is also the unexplained python-httpx client seen using that
account today.
2026-10-29 17:45:04 +00:00
inference-bot
e0732af1fd
models: apertus-70b is 262K context, not 65K — measured, not copied
...
The provider's published catalog says this model takes 30K input and has no
vision support. Both of those are wrong. Sent through our own gateway:
- an image returns the right answer ("Red" for a solid red PNG)
- prompts of 32K, 70K, 130K and 262K input tokens are all accepted, with
Regolo's own usage accounting reporting prompt_tokens=262021
Our own description of the v1.5 generation — image understanding and a 262K
context window — matches what the model demonstrably does, which is why the
figure goes to 262K. The old 65K undersold the model by roughly 4x.
Regolo's meta-model for qwen3.5-122b says 120K; it processed 262,023 tokens and
still followed the instruction at the end, so that row's 262K is confirmed as
written and is left alone.
Adds a line under the table recording that context figures here are measured
through the gateway rather than copied from provider catalogs, because that
difference is exactly what caused a member to report this as an error.
2026-10-29 17:11:17 +00:00
inference-bot
6cf50e6a5d
docs: link the energy and carbon page from the model list
2026-10-29 04:16:48 +00:00
inference-bot
f6dcde3cbb
docs: how the co-op estimates energy and carbon (method, factors, and limits)
2026-10-29 04:16:36 +00:00
inference-bot
95c6258594
runbook: how to confirm the webhook URL match, and what the watch job does and does not cover
2026-10-28 14:19:37 +00:00
inference-bot
682b5530be
runbook: correct the WEBHOOK_TOKEN rotation state (rotated 2026-10-27; URL match unverified)
2026-10-28 14:03:56 +00:00
inference-bot
f27621d4de
runbook: admin/webhook token split, metrics_snapshot task, correct sweep auth
2026-10-28 13:55:28 +00:00
inference-bot
e7c86b16ba
models: fix incorrect 'biggest context' claim for qwen3.5-122b (issue #4 — GLM/DeepSeek have 1M)
2026-10-16 16:32:08 -06:00
inference-bot
d3c3c8f8f7
models: normalize Green column to ✅ format; explain privacy column terms (architectural/policy/ZDR)
2026-10-16 11:05:11 -06:00
inference-bot
884340427f
models: dedupe green emoji legend; fix image-gen instructions (Integrations button > Image)
2026-10-16 10:59:05 -06:00
inference-bot
9699ff08cc
models: remove PublicAI provider; Regolo becomes the Apertus provider; emoji = feature tier; add Qwen-Image image-generation section
2026-10-16 10:50:46 -06:00
inference-bot
0d4a62a2da
models: add Regolo provider (Apertus 70B, Qwen 3.5 122B) + image generation via regolo/qwen-image
2026-10-16 10:29:48 -06:00
inference-bot
7ea5e1a4a1
runbook: spaCy model in /app/data for EPUB parsing + restore caveat (issue #20 )
2026-10-14 10:27:24 -06:00
inference-bot
1e57fd8f00
docs: correct tool-server howto — personal connections are OpenAPI-only; MCP is admin-added
2026-10-13 22:37:01 -06:00
inference-bot
af2b6eacd0
MCP howto: document the Type selector (MCP vs OpenAPI) and auth field
2026-10-13 20:12:24 -06:00
inference-bot
fd2cf4089a
MCP section: restore HTTP-only and refresh gotchas (verified against UI)
2026-10-13 11:52:46 -06:00
inference-bot
d047ced4c6
docs: correct MCP path to actual UI labels (Settings > Tools > External Tool Servers)
2026-10-13 11:43:47 -06:00
inference-bot
d0ec489af7
docs: clarify Tools tab requires fresh session after capability change
2026-10-13 11:39:13 -06:00
inference-bot
ccebba45af
docs: move MCP howto under 'Use the chat' (was misfiled under governance)
2026-10-13 11:24:23 -06:00
inference-bot
b9953ed086
docs: fix MCP howto — Tools tab requires the permission to reach the user session; clarify HTTP-only servers
2026-10-13 11:15:45 -06:00
inference-bot
4f995be9f1
docs: members can connect their own MCP tool servers in chat (direct tool servers enabled)
2026-10-13 08:49:24 -06:00
inference-bot
fed58a3437
docs: scheduled tasks in portal/gateway (self-maintaining apps) + operator verification steps
2026-10-12 19:32:32 -06:00
inference-bot
0f657b7cf4
docs: add #design room to Matrix section
2026-10-11 17:02:45 -06:00
inference-bot
a3defe1bed
docs: add #inferencebot-updates room to Matrix section
2026-10-11 16:53:28 -06:00
inference-bot
e175f07cb5
Matrix docs: note Element X apps are not currently supported (legacy SSO)
2026-10-07 22:30:10 -06:00
inference-bot
a5e33b73dd
Swap tinfoil/glm-5-3-flash (deprecated 10-09) for tinfoil/glm-5.3 flagship
2026-10-07 22:08:48 -06:00
inference-bot
21b31b3a0a
ToS + privacy: make model/provider agnostic; user assesses per-model affordances
2026-10-07 07:18:32 -06:00
inference-bot
9d520130f4
Privacy policy: correct per-model privacy claims (TEE vs renewable vs open)
2026-10-07 07:15:53 -06:00
inference-bot
7b0b13a54a
ToS: accurate privacy framing, expanded acceptable use, member indemnity clause
2026-10-07 07:13:58 -06:00
inference-bot
bed53d6cbd
Membership pricing: sliding scale from $5/mo (suggested $15) across docs
2026-10-05 10:09:15 -06:00
inference-bot
121afa101a
infrastructure: big-picture diagram now shows all three providers with value tiers
2026-10-05 09:23:33 -06:00
inference-bot
d865501fbf
README: add Matrix/community chat entry to Start here
2026-10-05 08:49:35 -06:00
inference-bot
adabc8bccd
Merge pull request 'models: Correctly document greenpt/glm-5.3 cache read pricing' ( #2 ) from slomo/docs:greenpt-glm-5.3-cache-pricing into main
2026-10-05 14:39:29 +00:00
inference-bot
7313f821e3
getting-started: document members-only unencrypted Matrix space + admin-only invites
2026-10-03 12:43:25 -06:00
inference-bot
d8bd033f05
docs: Matrix chat on home page + self-serve federated MXID in getting-started
2026-10-03 11:29:53 -06:00
inference-bot
c022a0b52e
models: add cached-input pricing column (cache-read rates per model)
2026-10-03 09:34:32 -06:00
inference-bot
a647284170
models: remove phantom tinfoil/glm-5-3 and kimi-k3 (not served); reconcile to gateway catalog
2026-10-02 22:36:28 -06:00
inference-bot
888ac8c299
models: value-tier emoji (🔒 /🌱 /📖 ) matching the chat picker
2026-10-02 22:31:51 -06:00
inference-bot
dcdde204b0
models: greenpt/deepseek-v4.1-flash as default; Tinfoil deepseek as TEE twin
2026-10-02 22:15:47 -06:00
inference-bot
0a79c80483
docs: remove green-l/green-r from model list and API examples
2026-10-02 22:04:51 -06:00
inference-bot
d2e90c6dc3
getting-started: Matrix — how to connect from any client (custom homeserver steps, separate identities)
2026-10-02 13:25:33 -06:00
inference-bot
7e2fa8c0a3
getting-started: Matrix chat for members
2026-10-02 12:35:52 -06:00
inference-bot
85a6045389
docs: Matrix (Synapse) — member chat, Space auto-invite via portal sync
2026-10-02 12:35:34 -06:00
inference-bot
2509cd47df
Document the Open Collective bot account: purpose, verified read-mostly scope, supervision
2026-10-01 17:22:13 -06:00
inference-bot
4966931a8c
Privacy policy: note operational log retention (from security review)
2026-10-01 09:51:47 -06:00
inference-bot
5f0c7b4513
Models page: vision column (verified), context windows, provider education, how-to-pick guide, same-model-two-providers note
2026-09-29 12:16:31 -06:00
inference-bot
09f88f650f
Document credit packs and per-member reset dates
2026-09-28 16:46:05 -06:00
inference-bot
34ce3b6753
Document audio models (STT/TTS) with API examples
2026-09-27 11:25:50 -06:00
inference-bot
40925b82b5
Add greenpt/glm-5.3 to model list
2026-09-26 16:52:24 -06:00
inference-bot
b40552d57e
Update tagline to 'AI, governed together'
2026-09-25 22:15:16 -06:00
inference-bot
4710df17ef
Add PublicAI Apertus models + sovereignty/open-source notes
2026-09-25 15:56:12 -06:00
inference-bot
6a005947a9
Merge naming and provider comparison into one Providers table
2026-09-24 11:49:38 -06:00
inference-bot
f3007e4c7b
Add provider comparison chart with privacy and green-energy gradations
2026-09-24 10:56:10 -06:00
inference-bot
27d41a840e
Add greenpt/glm-5.3-flash to model list
2026-09-24 10:43:18 -06:00
inference-bot
830aabb9b2
Harmonize tagline to 'Our AI, governed together'
2026-09-24 08:26:40 -06:00
inference-bot
d1412c0993
Link to the new support/feature-request repo
2026-09-24 08:20:34 -06:00
inference-bot
faeb958232
Update model names to tinfoil/* prefix
2026-09-24 08:16:19 -06:00
inference-bot
a92251d80e
Note models.md pricing mirrors LiteLLM config (kept in sync)
2026-09-23 21:08:30 -06:00
inference-bot
9fd074aaa7
Add per-model pricing (in/out per 1M tokens) to the model list
2026-09-23 21:07:04 -06:00
inference-bot
811da1617a
Rename privacy caveat heading to 'Limitations on privacy'
2026-09-23 21:06:09 -06:00
inference-bot
c6b659aeef
Extract model catalog into a single models.md; point chat + API docs at it
2026-09-23 20:47:38 -06:00
inference-bot
5724b0ca2f
Document multi-provider model choices (Tinfoil private + GreenPT green)
2026-09-23 20:34:33 -06:00
inference-bot
89152f0724
Remove completed Cloudron 10 follow-ups section
2026-09-23 14:17:09 -06:00
inference-bot
94d7971812
Mark proxyAuth->OIDC migration done; only SnappyMail remains
2026-09-23 14:16:04 -06:00
inference-bot
7f3dc0903e
Move SSO migration plan out of public docs (tracked internally)
2026-09-23 08:09:58 -06:00
inference-bot
c96de68f21
Track Cloudron 10 follow-ups and add SSO migration plan
2026-09-23 08:03:21 -06:00
inference-bot
d6e697a0c3
Correct OC runbook: email null was a missing email scope, not a regression
2026-09-22 15:50:27 -06:00
inference-bot
16b4d6368c
Document OC email-visibility regression and manual-provision workaround
2026-09-22 15:45:22 -06:00
inference-bot
290779494d
Add operator token runbook (two-token split, configure/env gotcha)
2026-09-19 17:21:08 -06:00
inference-bot
c8dd247b4f
Document Git access and fork-and-PR contribution model
2026-09-18 17:09:18 -06:00
inference-bot
35b8eb1ef4
Remove landing-page pointer callout
2026-09-18 16:51:06 -06:00
inference-bot
e8981be8b3
Point docs at the landing page for newcomers
2026-09-18 16:47:39 -06:00
inference-bot
4cccc521e8
Split docs into README TOC + getting-started, api-access, infrastructure guides
2026-09-18 16:44:32 -06:00
inference-bot
39b6bfa770
Remove internal planning docs (implementation-plan-api-dashboards, mvp-planning); drop Planning section
2026-09-18 11:56:24 -06:00
inference-bot
54b4603ffa
Add MVP planning doc (moved from wiki inference-coop/README.md)
2026-09-18 11:39:43 -06:00
inference-bot
inference-bot