matt 💫

Family & Friends First // Farm & Ocean Life // Sneaker Enthusiast 10.5 👟 // 🚀// SX & MX // Intl Warehousing & Logistics COO/CTO // #CyberTruck 📐

[matt 💫 @JetHuxx]

@cabinsmountain I wouldn’t tell anyone I had money but there would be signs 👀

[matt 💫 @JetHuxx]

@rauchg @vercel @timer150 Awesome image! That’s the biz I’m in… instant nostalgia!

[matt 💫 @JetHuxx]

@bigskyresort Didn’t y’all just get around 10” of snow lol

[matt 💫 @JetHuxx]

@elonmusk Just installed it and connected repo! Exciting!

[matt 💫 @JetHuxx]

@mike_cervellino You curbed it lol!! We’ve got almost 50k miles on ours and they’re flawless!

[matt 💫 @JetHuxx]

This is good!!!

[Harry Mack @harrymack]

Started Rapping Then Tracy Morgan Pulled Up

[matt 💫 @JetHuxx]

Been useful so far in Discord and M365 email. The best pattern I’ve found is ���research first, learn later”. Gather context in-thread/email, review it, then only save the skill once I say it’s ready.

Biggest improvement idea would be a built-in review/staging flow for `/learn` so messy source material doesn’t turn into permanent skills too early.

[matt 💫 @JetHuxx]

@slateauto Still waiting on mine 4-26-2025 lol

[matt 💫 @JetHuxx]

@gigadgets_ I think he’s Thai… More specifically from Bangkok.

[matt 💫 @JetHuxx]

@rhensing We shipped one to Denmark a few years back. Very nicely done!

[matt 💫 @JetHuxx]

First shipment to @SpaceX. Hopefully many more to come!

[Nitro Circus @NitroCircus]

God Bless America 🇺🇸
First look at the historic Freedom Jump.
@blckriflecoffee
@TravisPastrana @mmgeneral @Jeremymcgrath__ @RickyCarmichael @twitchthis

[matt 💫 @JetHuxx]

@MXGRyan Kieth Sayers on the list too!!

[matt 💫 @JetHuxx]

@MrUnloved1s @solebox Need another pair!

[matt 💫 @JetHuxx]

@houseofheat Why do they always drop Halloween skus the day before or after Halloween? Why can’t we have the WHOLE month to enjoy them?!

[matt 💫 @JetHuxx]

Just setup my Hermes agent with an agentic trading account at Robinhood. I’ll report back in a week with results 👀

[matt 💫 @JetHuxx]

@cursor_ai Composer 2.5 is not respecting Bun projects. In repos with bun.lock and Bun scripts, it still suggests npx, npm, pnpm, etc. GPT-5.5 consistently uses bun/bunx correctly in the same project. Looks like Composer’s package-manager detection/context handling might need some work.

[matt 💫 @JetHuxx]

@cursor composer-2.5 for the win… be sure to add “Fix Auxiliary Title with this as well” and you’ll be back up with codex - temporarily…

The actual Codex issue was two-part:

1. The Codex provider config was missing the Responses API mode.

For Codex OAuth against the ChatGPT Codex backend, the model config needs:

model:
provider: openai-codex
default: gpt-5.5
base_url: https://t.co/zbmBeqpJSo
api_mode: codex_responses

The important missing line was:

api_mode: codex_responses

Without that, Hermes can call the wrong response path/parse mode for Codex and fail even though the provider/model/base URL look correct.

2. Hermes also needed a patch for the Codex stream parser failure.

The live failure looked like:

'NoneType' object is not iterable

What was happening:
- The Codex backend was successfully streaming usable assistant text.
- Then the OpenAI SDK/Hermes stream parser failed while handling the terminal response.completed/final response shape because output could be missing/None.
- So the turn failed after useful streamed content had already arrived.

The patch needed in Hermes is in the Codex runtime path:

agent/codex_runtime.py

Patch behavior:
- collect streamed output_text.delta frames and output items as they arrive;
- if get_final_response() raises TypeError like 'NoneType' object is not iterable, synthesize a completed response from the already-collected stream data instead of failing the turn;
- also treat final_response.output is None the same as an empty output list and repair it from collected stream data;
- apply the same empty/None output repair to the create-stream fallback path.

Regression tests should cover:
- final response parser raises TypeError after text deltas were streamed;
- stream iterator raises TypeError after text deltas were streamed;
- final response output is None or empty but stream data exists.

After patching, verify with:

hermes chat -q 'Reply with exactly: GPT55_CODEX_OK' --provider openai-codex -m gpt-5.5 --quiet

Expected output:

GPT55_CODEX_OK

Then verify the default config path:

hermes chat -q 'Reply with exactly: DEFAULT_GPT55_CODEX_OK' --quiet

Expected output:

DEFAULT_GPT55_CODEX_OK

Fallback intent:
- Primary: openai-codex / gpt-5.5 / codex_responses
- Fallback 1 if configured and authenticated: xai-oauth / grok-4.3
- Fallback 2: openai-api / gpt-5.5

[matt 💫 @JetHuxx]

@dumbracefan @MattBurkeen820 No way Deegan is 9th 🤣 Top 5 at minimum. The fact that this entire post is pointed at Deegan confirms the narrative!