Repository navigation
fix(hermes): unwrap known routers; fail closed on unknown models - #1039
Merged
Merged
Conversation
GLM-5.3 is missing from LiteLLM, so Hermes/Cline sessions priced at $0. Alias it to the glm-5p2 sibling and keep the display name GLM-5.3. The root Hermes profile was shown as project "default". Use "hermes" for that profile only; named profiles and cwd inference are unchanged. Scan Hermes transcripts for https GitHub pull URLs and attach them so the Pull requests page can attribute those sessions.
Hermes stores Cline Pass as cp/cline-pass/glm-5.3. One prefix strip leaves cline-pass/glm-5.3, which missed the bare glm-5.3 alias and stayed $0. Price the last path segment through the same aliases.
Tool dumps (gh pr list, changelog grep) were smearing one session across dozens of pull URLs. Capture links from user and assistant text only.
Price any OmniRoute/Cline/cmd/antigravity wrapper by peeling prefixes and, for GLM 5.x, falling back to the newest priced sibling. Do not require a new alias per model id. Classify Hermes sessions by surface and workspace: ACP is the Buzz app; project comes from git root or a real cwd, never $HOME or a profile name.
avs-io
changed the title
Extra High review held #1039. Stop pricing every future glm-5.x as 5.2, stop collapsing unknown provider/org/model trees onto a priced leaf, and stop calling ACP Buzz — source=acp is a transport and the DB has no client field. Strip trailing punctuation on PR URLs and bump the Hermes parse version so old cache rows reparse.
avs-io
changed the title
Extra High held #1039 again. An unknown provider/model still became a bare-model price via getCanonicalName's first-segment strip. Relative cwd values like '.' could inherit the invoking repo. PR scrape treated fenced dumps and other repos as attribution. Peel only known vendor/router namespaces. Require an absolute platform path before a Hermes cwd is a workspace. Ignore fenced URLs and, when a git root exists, keep only that repo's pull links. Bump the Hermes parse version so old cache rows reparse.
Extra High held 91754c5. z-ai/glm-5.2 went unpriced (Cline's real vendor spelling). Forward-slash UNC became a workspace on POSIX. PR matching used basename, so evil/codeburn collided. Tilde fences were still scanned. Add z-ai to known namespaces. Reject // UNC on POSIX. Attribute PRs only when origin yields owner/repo. Strip ``` and ~~~ fences. Bump Hermes parse version to v4.
…atalog The hand-written KNOWN_NAMESPACES set dropped pricing for vendor prefixes LiteLLM itself indexes: x-ai/, nousresearch/, zhipu/, litellm_proxy/ and openai_like/ all priced on main and went unpriced here. Derive the set from the loaded pricing keys instead, so a vendor the catalog knows is never lost to a stale list, and keep only the spellings no catalog carries as explicit extras: the routing wrappers, the client-side kimi/ and mimo/ prefixes, and the litellm_proxy/ + openai_like/ routes. Local runners are excluded on purpose, so an unlisted ollama tag cannot strip down to a priced cloud row. xiaomi/ stops being a routing wrapper: it is the namespace LiteLLM prices MiMo under, and BUILTIN_ALIASES maps the bare MiMo ids INTO it, so peeling pulled against the alias. It stays known via the derived set. Also: a user price override for a bare id now wins over the catalog row a routed spelling of it would otherwise hit, and a namespaced GLM-5.3 is no longer LABELLED GLM-5.2 by the sibling alias it prices through. Tests assert the allowlist through a price override on a synthetic id, so they cannot rot with the snapshot; the glm-5.4 assertion that pinned on the snapshot NOT carrying a model is dropped.
githubOwnerRepoFromRoot re-read .git/config once per session, so every session in the same repo paid for the same two syscalls. Memoize it per repo root for the life of the process. The prLinks plumbing from a provider call through the session cache into the session summary had no test above the provider boundary; add one that runs the real parseAllSessions pipeline against a temp HERMES_HOME. It fails against the pre-change parser.
# Conflicts: # src/models.ts
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
2 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.
Problem
Hermes sessions were wrong in three classes, not three ids:
cp/cline-pass/…,omniroute:cp/…,cmd/…. A missing LiteLLM row then showed$0and "unpriced."default.$HOMEis not a project.pr-linkjournal events created Pull request rows. A first scrape of every tool dump then smeared one session across dozens of URLs.Change
omniroute:,cp/,cline-pass/,cline-free/,cmd/,antigravity/,xiaomi/) and price the remaining id. Explicitglm-5.3/GLM-5.3alias only. Unknownglm-5.4and unknownprovider/org/modelstay unpriced.$HOMEor a profile name. Last-resort project ishermes.source=acpstays Hermes — ACP is a transport; this DB has no Buzz client field.https://github.com/org/repo/pull/Nfrom user and assistant text only, including punctuation-wrapped URLs. Ignore tool dumps. Hermes parse version bumped so old cache rows reparse.User impact
Cline Pass / OmniRoute spellings of a known model get a
~estimate instead of$0. Future GLM minors and unknown namespaces stay unpriced instead of inheriting 5.2. Hermes Desktop/CLI/ACP spend groups as Hermes. Pull requests can show Hermes work that actually named a PR.Subscription usage is still an estimate, not an invoice. Models with no LiteLLM row and no explicit alias (
kimi-k3,mimo-v2.5-pro) stay unpriced.Preservation and out of scope
Testing
npx vitest run tests/models.test.ts tests/providers/hermes.test.ts: 173 passed.gpt-5.6-sol/xhigh) review held the previous class commit; this commit addresses the HOLD items it named.Residual
PR links in assistant-quoted tool dumps can still false-positive. Relative
pull/Nis not captured. Cache retraction is "reparse after version bump," not a durable-source rewrite.