hermes-models · diff
git:20261118.7b3f760 to git:20261119.c8fb133
79 added, 213 removed. Audit A to A.
What this update changes in the checks
No check changed: every fixed check gives the same answer before and after this update.
A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.
---
name: hermes-models
description: >-
Configure Hermes model providers, transports and routing: provider entries, default-route
switching, reasoning effort, delegation pins, per-profile copies, and proving a route with live
signals. Use when a model 404s or rejects an endpoint, a profile ignores its key, config drifts
between root and profiles, vision or image generation errors, or a relay's effort/cost looks
wrong. Not for another harness's own model configuration.
metadata:
- revision: "2"
+ revision: "3"
areas: "software-development"
targets: "hermes"
summary: "configure Hermes providers, transports and routing; prove every route with live signals, not `config get`"
summary_zh: "配置 Hermes provider、传输与路由;用实时信号证明路由,而非 `config get`"
kind: "entry"
---
+ # Hermes Models & Providers
+
+ ## Gates
+
+ - Back up before changes; use `hermes config set`, not patch/write tools for protected
+ `config.yaml`. For dotted IDs, use whole-map JSON and parse YAML on read-back.
+ - Writing `model.provider` clears `model.base_url` and `model.api_mode`; set them after the
+ provider. Reorder any self-fallback in the same pass.
+ - **Prove the route with three signals**, never `config get`: a real one-shot, the per-home
+ session row, and resolved reasoning configuration.
+ - `agent.reasoning_effort` is global; use per-model overrides and confirm the surface before
+ aligning tiers. Test transport and effort variants before editing configs.
+ - Assume drift: distinguish deliberate overrides, read back every write, regenerate the
+ config snapshot. Verify per-home provider, catalog and credentials before pinning; never
+ accept a same-provider fallback or a green doctor as proof of vision.
+ - Name the routing layer first. Inventory all seven layers and every cron store for a full
+ audit; do not count `no_agent` pins or infer a live harness catalog from its config.
+ - Use `-t clarify` for text-only probes; empty `-t` enables the full toolset. Wait on background
+ generation events without blocking on foreground sleeps. Prove inertness before batch use.
+ - For any gateway restart, check real traffic first and obtain explicit approval; do not
+ restart while another session is writing.
+ - Treat a provider outage as a fleet cutover. Inventory before changes, keep the old catalog
+ entry, edit generator sources rather than generated homes, preserve independent routes and
+ verify per surface. Back up, validate all targets, and review dry-run diffs before applying.
+ Stop on unknown/empty targets or concurrent writers. Writes, restarts, commits, pushes and
+ rollback require their own authorization; leave binding publication to the sync owner.
+
## Install-side hooks (the check is required, the script is not)
`$HERMES_HOME/scripts/*.py` in these docs names a hook the install may ship — a config snapshot
(`config-snapshot.py`), an install-facts snapshot (`snapshot-install-facts.py`), a fleet-switch adapter
(`model-switch.py`), catalog sync/smoke helpers, and the fleet verification pair
(`profile-layer-reconcile.py`, `contract-drift-check.py`). What matters is the outcome each one
verifies (the route is live, the metadata resolves, the generated layer agrees with its source), not the
filename. Resolve the command from the install or from this skill's config keys; when the install ships
none, say the check is **unavailable** instead of implying it passed.
- # Hermes Models & Providers
-
<!-- install-root: `$HERMES_HOME` below means the install root; it defaults to `~/.hermes` -->
- Provider keys in these examples (`local-chat`, `local-openai`, …) belong to the reference install:
- read your own `providers:` block and substitute.
+ Substitute provider keys from your install's `providers:` block.
## When to Use
| You hear / see | Load |
|---|---|
+ | fleet cutover (including planning, inventory, drift checks and dry runs), or same-provider ID swap at any scope | rule 20 below |
| 换默认模型 / 加 provider / 换 endpoint | rules below + `references/model-switching.md` |
| 某模型 404、`does not support the responses endpoint` | `references/custom-providers.md` |
| "让 subagent 用便宜点的模型" | `references/delegation-routing.md` |
| "routing 机制怎么运作" / "能不能按任务自动选模型" | rules 6 + 16 + 18, `references/delegation-routing.md` |
| profile 里模型/密钥不生效、只有 root 能用 | `references/delegation-routing.md` → per-profile provider |
| 配置在 root 和 profile 之间漂移 | `references/config-drift.md` |
| "review 全部 model routing" / 审计整条路由策略 | rules 16 + 18, `references/config-drift-audit.md` |
| vision / image_gen 报错、`auto` 路由 | `references/config-drift.md` |
| 给模型声明 context_length / 元数据 | `references/provider-metadata-audit.md` |
| 某 relay 的 effort/成本/流式行为异常 | `references/model-endpoint-matrix.md` |
- **Not for**: harness-level endpoints (pi/omp/opencode/dsh) → `agent-harness-model-gateways`.
-
## Rules
- 1. **Transport is per model, not per endpoint.** One proxy serves `/v1/responses` for some ids and
- `/v1/chat/completions` for others; probe both before concluding a capability is missing.
- 2. **Provider entries** live under top-level `providers:`; `model.provider` normally names the bare
- key (`local-openai`). A `custom:<name>` prefix is also accepted for custom-gateway entries, so a
- drift check must strip a leading `custom:` before comparing against the `providers:` keys — a raw
- string compare reports every valid custom route as undefined. Declare `context_length` per model.
+ 1. **Transport:** probe both endpoint types before declaring a capability missing.
+ 2. **Providers:** use top-level `providers:`, normalize `custom:` during drift checks,
+ and declare each model's `context_length`.
3. **Switching the default route:** writing `model.provider` **clears** `model.base_url` / `model.api_mode`.
Order: backup → `model.default` → `model.provider` → `model.api_mode` → `model.base_url` →
`agent.reasoning_effort`. Takes effect on `/new` or next session start. Promoting a provider that
already led `fallback_providers` leaves the chain starting with the new default itself — reorder
the chain in the same pass so entry 1 is a different provider.
- 4. **Prove the route with three signals**, never `config get`: one-shot `hermes chat -q 'Reply with
- exactly: PROBE_OK'`; the `sessions` row it created (read-only `state.db`); and
- `resolve_reasoning_config(load_config(), "<model>")`.
- 5. **`agent.reasoning_effort` is global**, not per model — change it and every selectable model re-tiers.
- Put per-model levels in `agent.reasoning_overrides` and say which models moved. The "not a recognized
- config key" warning is noise; the runtime reads it. Effort is also **per surface**: the Hermes session,
- `opencode` (`#max` variant), and `omp`/`omo` (thinking level) can legitimately sit on different tiers for
- the same id — e.g. `deepseek-v4.1-flash` at `high` inside Hermes while the CLIs run `max`. Ask which
- surface the owner means before "aligning" them; do not raise the session tier because a CLI is higher.
- 6. **Delegation pin** is global to the profile; `delegate_task` has no per-task model parameter and its schema
- is built at session start (never flip mid-conversation). Per-task granularity = Kanban card override, cron
- pin, or independent spawn. Verify with a real child spawn + its live transcript.
- The section is **re-read on every spawn** (`_load_config()` inside `delegate_task`), so editing
- `delegation.provider|model` applies to the next child — no restart, no `/new`; blank means "inherit the
- parent model". True per-task routing needs `delegation.backend` set to a registered
- `DelegationProvider` (`agent/delegation_registry.py`); the only bundled one is
- `plugins/delegation/default`, which merely applies the `delegation.*` section. A custom backend returns
- one route per task (`provider`, `model`, optional `reasoning_effort` / `profile`) and may declare extra
- `task_parameters()` to the model — that is the seam for "background work → cheap pool, hot path → fast
- pool". Until such a plugin exists, per-task routing is the caller's job: name the model explicitly on the
- `pi`/`omp` spawn.
- 7. **Profiles carry their own `providers:` and `.env`.** Add the block, delete any inherited inline
- `model.api_key` (it outranks `key_env`), copy the key into that profile's `.env`, then verify with a
- live one-shot under `HERMES_HOME=<profile>`.
- 8. **Dotted model ids** cannot go through a dotted path — `providers.<n>.models.deepseek-v4.1-flash.context_length`
- builds a phantom nested mapping. Set the whole map as one JSON value instead
- (`hermes config set providers.<n>.models '{"GLM-5.3":{"context_length":1048576},"deepseek-v4.1-flash":{"context_length":1000000}}'`),
- or edit YAML with plain dotted keys. Back up first, then read the file back with a YAML parse — a
- masked `config get` cannot prove the map shape, and a successful chat does not prove the override
- was read.
- 9. **Reasoning effort is a hint, not a guarantee**, and the effort→cost ladder is per relay and
- non-monotonic. Judge from `usage.reasoning_tokens`; size `max_tokens` per model because reasoning is
- charged against it on chat-completions transports.
- 10. **`auxiliary.vision: auto` is a trap** — doctor green only proves routing resolved. Pin provider+model
- in root **and** every profile, then run one real image call per profile.
- 11. **Config drift is the default failure mode.** Classify root-only keys as "never overrode" vs
- "deliberately different" before mirroring; read back after every write; regenerate
- `$HERMES_HOME/scripts/config-snapshot.py`.
- 12. **Text-only one-shot generation is `-t clarify`, not `-t ""`.** An empty `-t` value leaves the
- FULL toolset enabled — the model can write files and emits tool/diff previews into stdout,
- corrupting programmatic parsing; `-t none` is rejected as an unknown toolset name. Inert form:
- `hermes chat --query-file <f> -m <model> --provider <p> -t clarify -Q --ignore-rules --max-turns 1`,
- then strip the trailing `session_id:` line from stdout. `hermes chat` takes `-q/--query` (add
- `--oneshot` to answer and exit) — there is no `-p`; `-p` is the `pi`/`omp` flag. Prove inertness once
- per model by asking it to create a file and checking it cannot.
- 13. **Aliases and fallbacks are separate records from the provider entry.** `model_aliases.<name>` is a
- DirectAlias (`model`, `provider: custom`, `base_url`, `key_env`) resolved *before* the catalog, so
- it needs its own copy of the URL and key variable. `fallback_providers` entries are
- `{provider: <provider key>, model: <id>}` resolved through the provider registry, and they are
- per-home — set them in root **and** every profile. Prove both with one probe: point a throwaway
- alias at a nonexistent model id; the error names that id (alias routed) and the run continues on
- the fallback (`Model fallback: … via <provider>`), which proves the chain end to end. Delete the
- probe alias afterwards. A fallback entry must name a **different provider** than
- `model.provider` — same-provider fallback dies with the outage it was meant to cover, so a
- default on `opencode-go-flash` falls back to a second gateway, not to another id on the same one.
- 14. **A single bounded task on a non-default model: harness CLI first (`pi`, then `omp`), not
- `hermes chat`.** `pi -p --no-tools --no-skills --model <provider>/<id> --thinking high @prompt.md`
- carries the prompt and nothing else — no tool schemas, no session context — so instruction
- following on long writing/analysis prompts is measurably tighter. Resolve the binary before
- concluding it is missing: `command -v pi`, then the install's own lookup if it has one
- (`mise which pi`), then an explicit path the operator keeps. A CLI installed through npm, a
- tool manager, or a pinned path is just as valid — and `command -v` returning empty in a
- non-interactive shell means "not on this PATH", not "not installed". Export whatever directory
- holds it, or call the absolute path. `omp -p` is the fallback (it truncates large attachments).
- 15. **Long generation runs in the background; wait on the event, never on a foreground `sleep`.**
- `terminal(background=true, notify_on_complete=true)` then end the turn, or block once with
- `process_manage wait` (600 s) — do not poll a file size with `sleep 60..240` calls: each one
- blocks the same wall-clock, blocks every other task, and any sleep over the 180 s foreground
- timeout dies empty-handed. `sleep` is only for a fixed delay with no event to wait on (e.g. a
- CI run not yet visible in `gh run list`), and then ≤30 s. If a long generation comes back
- truncated (a few hundred bytes instead of a full answer), re-run with `--thinking medium` plus
- an explicit stop condition ("write through to the last section") rather than the same call again.
- 16. **Name the layer before the model.** Seven places decide a model, each with its own lifetime:
- `model.default|provider` (per session, `/new` or `/model`), `delegation.*` (per spawn),
- `delegation.backend` (per task, plugin), per-job cron pin (`hermes cron edit --model/--provider`),
- each profile's `profile.yaml`, per-invocation `pi`/`omp --model`, and `fallback_providers`
- (runtime). Instruction files (AGENTS.md / SOUL.md) only steer **which** layer the agent reaches
- for — they never change resolution, so "I edited AGENTS.md" is not an implementation of routing.
- Always report which layers changed and which stayed instruction-only.
- A whole-surface audit must enumerate all seven **plus every cron store**: each profile home keeps its own
- `cron/jobs.json`, so a job pinned only in root leaves the same work unpinned where it actually runs. Pins
- on `no_agent` script jobs are inert — nothing reads them, so they never count as free-pool coverage — and
- a harness catalog must be read from that harness's own `models` command, not from its config file.
- 17. **`$HERMES_HOME/config.yaml` cannot be edited with `patch`/`write_file`** — the tool refuses it ("Refusing
- to write to Hermes config file"); route every write through `hermes config set <dotted.key> <value>`.
- List-valued keys take a JSON string (`hermes config set fallback_providers '[{"provider":"p",
- "model":"m"}]'`) and land as proper YAML; back up the file first, then `hermes config get <key>`
- plus a read of the YAML block for shape.
- 18. **Tiered routing: fast pool on the hot path, free/slow pool for everything that can wait.** The
- default session and anything the user waits on stay on the fast provider; subagents, cron agent
- jobs, batch lanes, self-improvement runs and isolated-context work go to the free pool; paired or
- multi-view lanes (blind review, MoA references) keep at least one free-pool model so the cheap
- capacity actually gets used. When the free pool is one gateway with several ids, a 5xx rotates
- across ids — the failure is the upstream id, not the route config, so probe each id once before
- blaming the config.
- 19. **A fallback or pin is only as real as that home's catalog.** `providers.<p>.models` is a per-home
- map: root can be missing an id that several profiles already run as their *default* (`gpt-6.1-sol`
- ran in three profiles while root's catalog never listed it), and a fallback entry naming a missing
- id fails at failover — exactly when it is needed. Read the catalog of the home you are editing and
- add the id there first (whole-map JSON, rule 8), then wire the fallback. Effort variants: a
- `#variant` is supplied by the client config, so prove the relay accepts it with a CLI override
- *before* editing anything — `opencode run -m <provider>/<id>#max 'Reply with exactly: V_OK'`.
- Editing the config first leaves you unable to tell a rejected variant from a flaky relay.
- Config surgery inside generated/provider files (repeated blocks) → `references/config-drift.md`.
- 20. **A provider outage is a fleet cutover, not a default change.** Every home and every harness that
- names the dead provider moves in one pass, and the provider entry itself stays in `providers:` so
- restoration is a single key flip. Two places make a half-cutover look finished: a generated home whose
- route lives in its generator's repo (editing the generated config is reverted on the next apply), and
- per-harness effort metadata (`thinkingLevelMap` / `#variant`) that lacks the new id's top tier, which
- silently downgrades every "max" pin. Inventory → migrate → verify against every surface:
- `references/fleet-cutover.md`.
- 21. **A fleet cutover is one command, not 16 edits.** An adapter — resolved as
- `HERMES_MODELS_SWITCH_CMD` (env → `$XDG_CONFIG_HOME/hermes-models/config.yaml` → a `model-switch.py`
- the install ships) — applies a preset from `HERMES_MODELS_PRESETS` across Hermes root + every enumerated profile,
- `omp`, `omo` (settings + `thinkingLevelMap`), `opencode` (`model`, `agents.build.model`, effort
- variants), the OMP wrapper script defaults and the roster repo's bot bindings; `<preset> --check`
- reports drift, `--dry-run` diffs, `--rollback` restores the newest backup, `--restart-gateway`
- schedules the post-cutover restart (whether a hosted bot needs it is per-home — read that home's own
- `state.db` rows after real traffic instead of assuming, and treat restart as gated).
- Edits are line/block
- level so comments, key order and byte layout survive a round trip. Extend the preset file for a new
- fleet state instead of hand-editing or writing another script; the binding files stay uncommitted
- on purpose (repo sync owns commit+push). An install without such an adapter does the same cutover by
- hand — the contract above is the requirement, the command is configuration. Document the adapter's
- own usage next to it, not in a personal notes tree.
- Two presets-file landmines abort every subcommand, `list` included: an `overrides` entry naming a
- profile that no longer exists (`target file missing` kills the whole run), and a preset still
- describing the *previous* fleet state, which silently reports "drift" and would apply the old route.
- So the order is always `list`/`--check` → fix stale overrides + bring `free` up to the intended
- state → `--dry-run` (read the 6 line-level diffs) → apply. A wrong-state preset is worse than no
- preset: it is a one-command rollback to a route you already left.
- **Preset targets are discovered, never typed.** `overrides` and `nana_bindings` keys must resolve as
- exact name → glob (`*-nrs`) → `all`, expanded against what exists (`$HERMES_HOME/profiles/*/config.yaml`;
- the roster repo's own bot matrix file — the SSOT the binding files must agree with). A hand-typed roster drifts **both** ways: a stale name aborts every subcommand, and a
- missing name half-applies a "switch the fleet" pass while reporting success. So an unknown exact name is
- a hard error that lists the discovered candidates, and an empty expansion (glob matching nothing, `all`
- discovering nothing) is an error too — "switch everything" must never silently become "switch zero".
- The caller that wants precision passes `--profiles a,b,*-nrs` / `--bots …` at invocation (and can list
- candidates first with `--list-profiles` / `--list-bots`); the on-disk preset carries the fleet-wide
- default. Those subcommands, the `--check`/`--dry-run`/`--rollback`/`--restart-gateway` surface and the
- line-preserving edits are the adapter contract: a reference adapter implements them, a hand pass
- reproduces them. Validate every target and print **all** errors before writing anything; `--check` = 0 match /
- 1 drift / 2 spec error. Any change to this tool ships a stdlib-unittest fixture suite under
- the adapter's own test directory, driven through `--home <tmpdir>` — a fleet-switch script edited
- without tests is an outage waiting for the next quota reset.
-
- 21b. **A new id in the same provider is an id swap, not a cutover** — the old id stays in every catalog
- (rollback), and only live routes move: `model.default`, `delegation.model`, MoA aggregator,
- `model_aliases.*`, `fallback_providers`, cron pins, harness `model`/`modelRoles`, wrapper `DEFAULT_MODEL`.
- Three silent-failure traps (`model_aliases` needs `--force`, catalog copies need a comma/section-boundary
- insert, omo keeps the id in three files) → `references/fleet-cutover.md` §6.
-
- ## Proof
+ 4. **Proof:** see the three signals below; a config echo is not live proof.
+ 5. **Effort:** use `agent.reasoning_overrides` for per-model tiers. Read
+ [config drift](references/config-drift.md) for surface differences and precedence.
+ 6. **Delegation:** pin per profile; pin values reload on spawn. The schema is built at session
+ start; never flip it mid-conversation.
+ Verify a real child. For per-task paths, read [delegation routing](references/delegation-routing.md).
+ 7. **Profiles:** provider maps and `.env` are per-home; remove inherited inline keys that win over
+ `key_env`, then probe live in that home.
+ 8. **Dotted IDs:** use whole-map JSON (not a dotted key). Verify parsed shape.
+ 9. **Reasoning:** compare usage, not requested effort; size the token budget per relay and model.
+ 10. **Vision:** pin root and every profile and prove each with a real image call.
+ 11. **Drift:** classify differences before mirroring; read back and regenerate the snapshot.
+ 12. **Text-only one-shot:** see [endpoint matrix](references/model-endpoint-matrix.md) for inert invocation.
+ 13. **Aliases and fallbacks:** separate per-home records. Prove the chain and remove the probe alias.
+ 14. **Bounded non-default task:** use an isolated harness CLI (`pi`, then `omp`) before `hermes chat`.
+ 15. **Long generation:** background + notification or one event wait. On truncation, retry with a
+ lower tier and explicit stop condition. See [endpoint matrix](references/model-endpoint-matrix.md).
+ 16. **Routing layers:** session default, delegation pin, backend, cron, profile, invocation and
+ fallback differ in lifetime. Instructions select a layer; they do not implement resolution.
+ Report changed vs instruction-only layers. Read [delegation routing](references/delegation-routing.md).
+ 17. **Protected config:** use `hermes config set` and verify the YAML shape.
+ 18. **Tier policy:** fast pool for the hot path, free pool for background and at least one paired
+ lane. Probe each ID before blaming routing config.
+ 19. **Catalog scope:** resolve pins against the actual home's catalog. Probe effort before edits.
+ 20. **Fleet cutover gate:** an outage, retirement or restore moves all affected homes and harnesses;
+ an ID swap moves only live references and preserves the old ID. Keep old provider definitions,
+ verify generated homes and harness effort metadata. For any fleet cutover or same-provider
+ ID swap, even in a single home, read the child before planning, inventory, `--check`, or
+ `--dry-run`. Re-read it after compaction. Read-only work does not require mutation approval;
+ the Gates above still apply to every mutating step.
- **The scope is the operator's fleet, not a fixed roster.** A "switch the default model" request spans the
- root `model` entry plus every home and binding that pins a model: enumerate `$HERMES_HOME/profiles/*/config.yaml`
- (`hermes config` paths), the harness settings that carry ids, and the roster repo's per-bot bindings **before**
- deciding the scope, then state what you enumerated. A home you could not enumerate is not covered — say so
- rather than assuming it is. Bindings and a roster `tiers:` block are prose-level truth: the materializer only
- validates tier *names*, so a tier left naming the old model makes that repo lie about the fleet after a cutover.
+ Read `../hermes-models-cutover/SKILL.md` (relative to this skill's directory) and follow it. Do not call the Skill tool for it.
- ```bash
- hermes chat -q 'Reply with exactly: PROBE_OK' # 1. live answer
- hermes -p <profile> chat -q 'Reply with exactly: PROBE_OK' \
- -t clarify -Q --ignore-rules --max-turns 1 # 1b. same, inside one home
- uv run --no-project python - <<'PY' # 2. the session row
- import glob, os, sqlite3
- root = os.path.expanduser(os.environ.get("HERMES_HOME", "~/.hermes")) # quoted heredoc: bash does not expand
- for home in [root] + sorted(glob.glob(root + "/profiles/*")):
- c=sqlite3.connect(f"file:{home}/state.db?mode=ro",uri=True)
- print(home, c.execute("select model from sessions order by started_at desc limit 2").fetchall())
- PY
- python3 - <<'PY' # 3. effort resolution
- import os, sys
- root = os.path.expanduser(os.environ.get("HERMES_HOME", "~/.hermes"))
- sys.path.insert(0, root + "/hermes-agent")
- from hermes_constants import resolve_reasoning_config
- from hermes_cli.config import load_config
- print(resolve_reasoning_config(load_config(), "<model>"))
- PY
- # if the install ships a fact-snapshot hook (look under $HERMES_HOME/scripts), run it here;
- # with none, record this check as unavailable rather than implying the sheet matches
- ```
+ Install the parent and child into the same skills root using the catalog's generated Install row;
+ an update alone does not install a new skill name.
- Read the session rows as a **before/after pair**: the newest row must show the new id *and* the row under it
- must still show the old one — one new row alone cannot distinguish a real switch from a route that was already
- there. Each home has its own `state.db` (`$HERMES_HOME/profiles/<p>/state.db`); root's rows say nothing about a
- profile. The `sessions` table has **no `provider` column** — selecting it raises `no such column: provider`, so
- prove the provider from the config/preset and let `model` carry the runtime evidence. Free-pool probes answer in
- 10–40 s each; run the per-home loop as one background command with a per-home `timeout`, not one foreground
- call per profile.
+ ## Proof
- Delegation: spawn one real child and read `$HERMES_HOME/cache/delegation/live/<id>/task-0.log`.
- Vision: one real `vision_analyze` call per profile.
+ Follow [live proof](references/model-switching.md#proof): enumerate the affected homes, harness
+ settings, bot bindings and roster tiers. Report uncovered homes. In each changed home get a live
+ reply, compare the before/after `sessions.model` rows in its own read-only database, and resolve
+ reasoning effort. Compare the configured provider separately: the sessions table has no provider
+ column. Batch per-home calls in the background with individual timeouts. Verify delegation with a
+ real spawn and live transcript; verify vision with one real image call per profile.
## References
- - `references/custom-providers.md` — provider YAML shape, transport table, per-model sizing, relay header
- quirks, and **the install's own policy overlay** (banned ids, unavailable families, vision pinning) —
- the method for each is above; the list itself belongs to the install, not to this skill.
+ - `references/custom-providers.md` — provider shape, transport, sizing, aliases and install policy.
+ The provider list itself belongs to the install, not to this skill.
- `references/model-switching.md` — switching order, three-signal proof, ghc-proxy deployment, Copilot
fallback hygiene.
- - `references/fleet-cutover.md` — multi-home, multi-harness provider cutover (quota outage, retirement,
- restore): inventory map, generated homes, effort-tier gaps, verification matrix, rollback.
- - `references/delegation-routing.md` — which layer decides the model (7-row table), delegation precedence,
- fast-pool/free-pool tier policy + pool probe loop, per-profile provider migration checklist.
+ - `references/delegation-routing.md` — layer lifetimes, overrides, pool tiers and profile routing.
- `references/config-drift.md` — drift audit, lettered tier menu, reasoning-effort layers, auxiliary vision.
- `references/provider-metadata-audit.md`, `references/model-endpoint-matrix.md`,
`references/config-drift-audit.md` — audit detail.
- Only if a script command fails (for example `uv` is not found), read [references/troubleshooting.md](references/troubleshooting.md).
- `references/cases.md` — historical cases: Copilot fallback cleanup, ghc-proxy deployment.
+ - `scripts/audit-routing-inventory.py` — dumps every routing layer for all homes into JSON
+ and flags self-fallbacks and cron coverage.
- `scripts/audit-provider-metadata.py`, `scripts/audit-config-drift.py`,
- `scripts/audit-routing-inventory.py`, `scripts/probe-provider-endpoint.sh` — runnable probes (the
- inventory one dumps every routing layer for all homes into JSON and flags self-fallbacks and cron
- coverage); `templates/ghc-proxy.service` — unit template.
+ `scripts/probe-provider-endpoint.sh` — audit scripts and endpoint probes; `templates/ghc-proxy.service` — unit template.