Daily Edition Sources +6

Agent Identity Is Becoming Runtime Infrastructure

Fresh Hermes Agent, OpenClaw, and Codex commits show profile, credential, and model-choice state moving out of setup screens and into live agent runtime controls.

Rough zine diagram titled The setting is now part of the run, with evidence cards for Hermes profiles, Hermes sockets, OpenClaw auth SQLite, Hermes credentials, and Codex reasoning efforts feeding into a circled conclusion: Right identity context or wrong action.
Diagram Punkthe setting is now part of the run.
repos openai/codex + 2 more evidence
6 source signals 3 repos 6 linked commits
Evidence: 6 linked commits / June 5, 2026 / Daily Edition
Open Edition Evidence below

The old mental model was simple: pick an account, paste a key, choose a model, then start the agent.

The new code tells a messier story. Once an agent desktop can keep several sessions alive, switch profiles without restarting, route credentials by channel, and let models advertise their own reasoning controls, identity stops being a static preference. It becomes part of the runtime.

The one-sentence map is this: Hermes is turning profiles into live session and socket scope, OpenClaw is making auth profiles durable database state, Hermes is reorganizing provider credentials as a first-class surface, and Codex is letting model-specific reasoning options flow through the protocol. These are independent changes, not a shared standard. Together they show agent products converging on the same pressure: the system has to know which person, profile, credential set, model mode, and working session owns the next action.

Profiles are no longer just folders

Hermes Agent commit b94b3622b adds per-session profile switching and cross-profile sessions to the desktop app. The commit message is unusually explicit about what changed: the app can lazily swap the live gateway onto a session's profile, aggregate sessions across profiles by reading each profile's state database read-only, and route profile-scoped REST calls for config, environment, skills, tools, and model settings to the active gateway profile.

That is more than a user-interface convenience. A profile now decides which backend, state database, environment, tools, skills, and model settings the session is talking to. The desktop adds an "All profiles" view, but the default remains scoped to one profile because a profile is a working context, not a decorative label.

The practical consequence is easy to miss. Multi-profile support used to sound like account management. In an agent app, it becomes execution routing. Opening a session from another profile means the gateway, cache, settings reads, and new-chat defaults have to move with it or the agent can write to the wrong place.

Background sessions need their own sockets

Later the same day, Hermes commit 4891f9ae7 hardens that model. Instead of closing the single gateway socket every time the user switches profiles, the desktop keeps one persistent socket per profile with live work. A registry owns the primary window socket plus lazy secondary sockets, and all of them feed the same session-keyed event handler.

This is the moment profile support crosses from preference into operations. If profile A has a running agent and profile B becomes the foreground, profile A still needs a transport. The patch also parks approval, sudo, and secret prompts per session so background work can block without hijacking the foreground. Single-profile users keep the simple path, but multi-profile users get a small distributed system inside the desktop.

The category consequence for agent infrastructure is sharp: account switching is no longer the same problem it was for a notes app or a chat client. An agent profile can own live work, security prompts, tool approvals, and stateful gateway connections.

Auth state is becoming database state

OpenClaw commit e16ac0433 attacks the same class of problem from the storage side. The refactor moves auth profiles into SQLite-backed state, creates auth_profile_store and auth_profile_state tables, adds a dedicated SQLite store implementation, and removes the older JSON auth-profile store files and tests.

The article is not claiming SQLite is automatically better because it is SQLite. The signal is architectural. Auth profile state now sits in the same kind of durable, transactional substrate as other agent state. The patch also touches doctor commands, backup creation, secrets application, stale OAuth shadow checks, model discovery, and generated database schema files. Authentication is no longer a loose sidecar to the agent; it is something the runtime audits, repairs, backs up, and queries.

That matters because agent identity has to survive more than login. It has to survive profile selection, OAuth refreshes, model discovery, external CLI passthrough, secrets scanning, and failure marking. The narrower question becomes: which auth profile is this agent allowed to use right now, and what should the system do when that profile is stale or broken?

Credentials are becoming working controls

Hermes commits 9cbc37e2 and acce1a245 show the product-facing version of the same shift. Provider configuration moves into a dedicated Providers settings page with separate Accounts and API-keys views. Key rows get inline save/remove behavior, redacted set values, provider grouping, OAuth launch paths, advanced URL and region overrides, and messaging credential routing.

This can look like polish, but the commit surface is full of runtime clues. The code distinguishes channel-managed messaging credentials from provider API keys. It exposes deep links into account and key settings. It aligns credential controls across Providers, Tools & Keys, and Messaging. A credential is no longer just a secret pasted before work begins; it is a live control the operator may inspect, route, replace, or remove while the agent product is running.

Even model steering is opening up

OpenAI Codex commit 8ac304c2 adds a different piece of the identity stack: model-defined reasoning efforts. Codex had known effort values. The patch accepts non-empty model-defined values, preserves string wire encoding, exposes an open-string schema to clients, and updates model selection and shortcut behavior around model-advertised effort values.

That is not about accounts or OAuth. It is about who gets to define the control surface. If a model can advertise a reasoning option the client did not know in advance, the runtime cannot treat the settings schema as closed forever. It has to carry model-specific intent through core, app-server, TUI, telemetry, persistence, and protocol surfaces without flattening it back into a fixed old enum.

The control plane is getting personal

The May 30 edition argued that agent control settings are becoming session state. Today's evidence moves that argument one layer deeper. The settings are not only becoming state; they are becoming identity-bearing state.

Hermes profiles decide which live backend and session database a desktop is using. Hermes secondary sockets keep background profile work alive. OpenClaw stores auth profiles in a database that the runtime can audit and repair. Hermes turns provider keys and messaging credentials into dedicated operator surfaces. Codex opens reasoning controls to model-advertised values.

This does not prove a common agent identity standard, and it does not prove every agent app needs the same profile model. It does show the shape of the next infrastructure argument. As agents take more delegated actions across more tools, surfaces, models, and accounts, "the user selected a setting" becomes too weak. The runtime needs to know which identity context is in force, which work belongs to it, which credentials it may touch, and which controls are safe to change while the agent is still moving.

Evidence Trail

Receipts below the story

The article above is the public narrative. This section keeps the source trail, limits, and reporting notes on the same page.

Edition
DateJune 5, 2026
LaneDaily Edition
Confidence87%
Sources6
Reposopenai/codex, openclaw/openclaw, NousResearch/hermes-agent

Reporter Notes

The article follows the June 5 scan's strongest `Human interface for agent

work and Runtime governance` themes, but avoids another broad event

provenance article after the June 4 lead. The fresh angle is identity-bearing

runtime state: profiles, credentials, auth stores, model controls, and live

session routing.

The reporting deliberately does not use the word "standard" except as a limit.

The repos solve different problems:

  • Hermes shows the richest profile/runtime surface, including gateway routing

and concurrent sockets.

  • OpenClaw shows auth profiles moving into durable agent database state.
  • Codex shows model-advertised reasoning controls breaking a closed client enum.

Together they justify the headline without implying coordination.

Primary Evidence

  • NousResearch Hermes Agent commit b94b3622b, "feat(desktop): per-session profile switching + cross-profile sessions": https://github.com/NousResearch/hermes-agent/commit/b94b3622b5faabadf36d8d51f5804c0a655553e7
    • Evidence used: The desktop app can lazily swap the live gateway onto a session's profile, aggregate sessions across profiles by reading each profile's state database read-only, and route profile-scoped REST calls for config, environment, skills, tools, and model settings to the active gateway profile.
  • NousResearch Hermes Agent commit 4891f9ae7, "feat(desktop): concurrent multi-profile gateway sockets": https://github.com/NousResearch/hermes-agent/commit/4891f9ae78b099472a22f66d037ec1619f5358d5
    • Evidence used: The desktop keeps one persistent socket per profile with live work, feeds all sockets into a session-keyed event handler, prunes secondaries to profiles with work or needs-input sessions, and parks approval, sudo, and secret prompts per session.
  • OpenClaw commit e16ac0433, "refactor(auth): store auth profiles in sqlite": https://github.com/openclaw/openclaw/commit/e16ac0433092da879e88213a47d6f4dae0432a6e
    • Evidence used: The refactor replaces JSON auth-profile storage with SQLite-backed auth_profile_store and auth_profile_state tables, adds a SQLite store implementation, and updates auth discovery, doctor commands, backup, secrets, OAuth, and generated schema code around that state.
  • NousResearch Hermes Agent commit 9cbc37e2, "feat(desktop): dedicated Providers settings + polished Accounts/API-keys UX": https://github.com/NousResearch/hermes-agent/commit/9cbc37e25b64a018e0dc537f9b2fc470f9fc1e4a
    • Evidence used: Provider configuration moves into a dedicated Providers page with Accounts and API-keys views, OAuth launch behavior, provider grouping, inline key fields, redacted set values, and advanced credential fields.
  • NousResearch Hermes Agent commit acce1a245, "feat(desktop): polish credentials settings and messaging env routing": https://github.com/NousResearch/hermes-agent/commit/acce1a2452f8b85343db1b057c1d98717c421522
    • Evidence used: The desktop aligns Provider API Keys, Tools & Keys, and Messaging credential controls, adds messaging env routing, and treats channel-managed credentials differently from provider keys.
  • OpenAI Codex commit 8ac304c2, "[codex] Support model-defined reasoning efforts": https://github.com/openai/codex/commit/8ac304c2997529d3b6fe4be4ba032e0f2dac16af
    • Evidence used: Codex accepts non-empty model-defined reasoning effort values, exposes an open-string schema, preserves string wire encoding, and carries those effort values through protocol, app-server, TUI, telemetry, persistence, and shortcut behavior.

Evidence Limits

  • These commits do not prove coordination among Hermes Agent, OpenClaw, and Codex, and they do not define a shared agent identity standard.
  • "Identity" is used here as an editorial frame for profile scope, auth profile state, credential routing, and model-control context. The cited projects use different names and data models.
  • The article does not claim SQLite, multiple sockets, or open-string reasoning efforts are universally correct designs. It argues that each change moves identity-bearing state closer to runtime behavior.
  • The Hermes evidence is concentrated in one very active repository, so OpenClaw and Codex are used as counterweights rather than proof of industry-wide adoption.
  • Public source state is a June 5, 2026 snapshot and may change after publication.
Letters & Corrections

Send a note to the desk

Corrections, missing context, or a follow-up lead.