8000 [pull] main from can1357:main by pull[bot] · Pull Request #10 · ericrihm/oh-my-pi · GitHub
[go: up one dir, main page]

Skip to content

[pull] main from can1357:main - #10

Merged
pull[bot] merged 22 commits into
ericrihm:mainfrom
can1357:main
Aug 16, 2026
Merged

pull[bot] merged 22 commits into
ericrihm:mainfrom
can1357:main

Conversation

@pull
@pull pull Bot commented Aug 16, 2026 •
Copy link
Copy Markdown

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

geraint0923 and others added 22 commits August 14, 2026 22:00
Switch XAI_API_KEY models from Chat Completions to /v1/responses, default
both xai and xai-oauth to grok-4.5, and include reasoning.encrypted_content.
Stop stripping type=reasoning history for xai and xai-oauth so
encrypted_content from include is sent back on the next Responses request.
Rebase onto origin/main landed those notes in the released section; move
them back and drop duplicated 17.2.5 Changed bullets.
Invalidate cached paid-xAI ids on static fingerprint mismatch so the
Responses migration is not stuck behind a fresh completions cache overlay.
Grok 4.5 on XAI_API_KEY kept a minimal dial without SuperGrok's
minimal→low wire map, which can 400 on /v1/responses.
Paid-key-only setups were marked signed in for xai-oauth, so the shared
grok-4.5 default picker preferred SuperGrok over xai/grok-4.5.
Grok 4.5 rejects presencePenalty, frequencyPenalty, and stop. After the
paid default moved off a non-reasoning model, configured penalties 400ed.
Paid xAI models.dev regeneration still emitted Completions-era thinking
dials for off-allowlist reasoners. Bake the no-dial policy into the
resolver/generator and refresh the exported catalog snapshot.
First-party xAI /v1/responses rejects reasoning.summary. Bake
supportsReasoningSummary=false for both xai and xai-oauth so paid
grok-4.5 effort requests send only reasoning.effort, matching SuperGrok.
Rebase onto origin/main replayed the Unreleased bullets into already
released 17.2.x sections. Move them back to the top.
origin/main replaced createSimpleOpenAIResponsesOptions with the shared
OpenAI-compatible manager builder. Point xaiModelManagerOptions at that
same helper so XAI_API_KEY still discovers via /v1/responses.
api.x.ai accepts low/medium/high (and clamps minimal to low). Stop
advertising xhigh on paid xai and SuperGrok Responses rows, and map
leftover xhigh/max requests to high.
The clamp map is only used when reasoning.effort is sent. Drop it from
catalog rows that set omitReasoningEffort so the exported snapshot does
not advertise a dead mapping.
xAI's /v1/responses rejects presence/frequency penalties for every Grok
model, not only reasoners. Gate supportsPenaltyAndStopParams on isXaiHost
so xai/grok-2 no longer serializes presence_penalty.
grok-4.20-multi-agent uses reasoning.effort for agent count, and xhigh
is the 16-agent mode. Leave that tier advertised and unmapped while
Grok 4.5 still clamps leftover xhigh/max to high.
Keep hasAuth() dedicated so SuperGrok is not auto-selected from a paid
key. Explicit preflight uses hasResolvableAuth() so xai-oauth/grok-4.5
can still borrow XAI_API_KEY.
Keep applyXaiResponsesThinkingPolicy in the existing openai-compat
import so biome organizeImports stays clean on origin/main.
origin/main added grok-4.6 as Chat Completions on paid xai and as an
uncurated SuperGrok row. Keep the Responses migration complete by
allowlisting the id, seeding xai-oauth, and baking the same 4-tier
effort map as grok-4.5.
xAI documents xhigh on grok-4.6. Keep 4.5/4.3/3-mini on the 4-tier
ladder and leave leftover xhigh unmapped for 4.6, matching multi-agent.
@pull pull Bot locked and limited conversation to collaborators Aug 16, 2026
@pull pull Bot added the ⤵️ pull label Aug 16, 2026
@pull
pull Bot merged commit de6b797 into ericrihm:main Aug 16, 2026
5 checks passed
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants

0