Enable ChatGPT subscription Codex support end-to-end - #43
Merged
teknium1 merged 11 commits intoMar 1, 2026
Merged
Conversation
grp06
force-pushed
the
codex/align-codex-provider-conventions-mainrepo
branch
from
February 26, 2026 02:21
0b3ade2 to
ce175d7
Compare
|
my testing in #45 found |
…vider-conventions-mainrepo # Conflicts: # cron/scheduler.py # gateway/run.py # tools/delegate_tool.py
Closed
4 tasks
Contributor
|
Okay - I am merging this and taking it from here - soon we'll all get codex in :) |
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
…der-conventions-mainrepo Enable ChatGPT subscription Codex support end-to-end
This was referenced May 29, 2026
dizhaky
referenced
this pull request
in dizhaky/hermes-agent
Jun 23, 2026
…AN-1385) (#26) baileys 7.0.0-rc.9->rc13 (clears #43 critical) + protobufjs 7.6.4 (#59,#58) in whatsapp-bridge; esbuild+tsx (#46,#61) in ui-tui; @babel/core (#84) in web; joi+http-proxy-middleware (#51,#89) in website. js-yaml #86 accepted (no in-range fix via gray-matter). Bridge startup verified. #93/#94 (code fixes) separate. Co-Authored-By: Claude <noreply@anthropic.com>
waefrebeorn
pushed a commit
to waefrebeorn/slermes
that referenced
this pull request
Jul 2, 2026
…der-conventions-mainrepo Enable ChatGPT subscription Codex support end-to-end
gonggqing
added a commit
to gonggqing/hermes-agent
that referenced
this pull request
Jul 14, 2026
…d-session catch-up) A session missed while serve was down is otherwise skipped (the runner's watermark = boot time). Add a human-triggered catch-up that runs the full pipeline into a fresh approval window — without ever auto-placing orders (Loop.md §4b, §3). - dailyloop.py: run_session_now() runs monitor→decide (RiskEngine + P0.8 dead-man's switch)→push into a confirmation window ANCHORED TO NOW (clamped so it never wraps past ET midnight), so an off-schedule publish isn't refused as WINDOW_CLOSED. finalize_session_now() is the off-schedule cutoff: places the human-APPROVED candidates, expires the rest. Neither auto-executes — approval stays per-candidate + human. - api.py: POST /v1/session/run + /v1/session/finalize — human-gated (system surface / LLM actor → 403; loop not attached → 503); FinanceRuntime gains run_session/finalize_session. - __main__.py: serve wires them to the US trading loop. 10 tests (now-anchored window incl. late-night no-wrap, finalize no-op, API guards). Suite 962 green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
gonggqing
added a commit
to gonggqing/hermes-agent
that referenced
this pull request
Jul 14, 2026
…ze buttons in the Queue A human catch-up for a missed 11:30 session, in the Finance Action Queue on both surfaces. "Run session now" runs monitor→decide→push into a fresh approval window (does NOT place orders); the pushed candidates appear in the Queue for approval; "Finalize & place approved" (confirm-gated) places the approved ones. Desktop (apps/desktop): hermes.ts postFinanceSessionRun/Finalize (surface in body); queue.tsx SessionControls card — Run (shows pushed/cutoff, dead-man's- switch warning on entries_halted) + Finalize (ConfirmDialog). 403→human-only, 503→loop-not-attached localized. i18n t.finance.queue.session.* (en+zh). Web (web): lib/api.ts financeSessionRun/Finalize (structured outcome, never throws); ApprovalQueue SessionControls (Run + second-click-confirm Finalize) in QueueView; i18n queue.session (en+zh). Both human-only (X-Finance-Surface web/desktop + human actor); never auto-orders. Desktop typecheck/build green; web typecheck/build + 88 tests green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Soju06
added a commit
to Soju06/hermes-agent
that referenced
this pull request
Jul 22, 2026
…resh restacked memory-chain SHAs; register 413-expectation pin Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Soju06
added a commit
to Soju06/hermes-agent
that referenced
this pull request
Jul 22, 2026
…tream (PR NousResearch#69209) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Soju06
added a commit
to Soju06/hermes-agent
that referenced
this pull request
Jul 27, 2026
…arch#43 route-repromote-hysteresis Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
5 tasks
1 task
Closed
choi138
added a commit
to choi138/hermes-agent
that referenced
this pull request
Aug 18, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Purpose
Let Hermes use a ChatGPT/Codex subscription (via Codex CLI auth) reliably end-to-end, so subscribers can run Hermes with
openai-codexwithout early stop/failure behavior.What changed
call_id+fc_*item ids) for replay compatibility.strict: false).Result
Hermes now works with ChatGPT subscription-backed Codex auth in a full tool-calling loop, instead of stopping after the first intermediate message.
Verification
pytest -q tests/test_auth_codex_provider.py tests/test_runtime_provider_resolution.py tests/test_cli_provider_resolution.py tests/test_run_agent_codex_responses.py