fix(analytics): prevent silent token loss and add Claude 4.5–4.7 pricing by austinpickett · Pull Request #21455 · NousResearch/hermes-agent

austinpickett · 2026-05-07T18:18:45Z

What does this PR do?

Fixes two classes of analytics bugs that cause token counts to be silently undercounted, adds pricing data for the latest Anthropic models, and surfaces reasoning tokens in the UI.

Problem: Under concurrent load (cron + kanban + delegate_task), the initial create_session() can fail due to SQLite locking. When this happens, subsequent UPDATE sessions SET ... calls affect 0 rows — token deltas are silently lost. Additionally, pricing lookups fail for dot-notation model names (e.g. claude-opus-4.7) because the pricing table uses dash notation (claude-opus-4-7).

Fix: Ensure the session row exists (via idempotent INSERT OR IGNORE) before every token UPDATE, log failures at DEBUG instead of swallowing them, and add a normalization layer for Anthropic model name variants.

Related Issue

N/A — reported by user (PatrickH) on discord for token mismatch from Claude dashboard

Type of Change

🐛 Bug fix (non-breaking change that fixes an issue)
✨ New feature (non-breaking change that adds functionality)
🔒 Security fix
📝 Documentation update
✅ Tests (adding or improving test coverage)
♻️ Refactor (no behavior change)
🎯 New skill (bundled or hub)

Changes Made

agent/usage_pricing.py: Add pricing entries for Claude Opus 4.5/4.6/4.7, Sonnet 4.5/4.6, Haiku 4.5; add _normalize_anthropic_model_name() for dot-to-dash conversion; update source URLs to platform.claude.com
run_agent.py: Retry _ensure_db_session() before token UPDATE if initial creation failed; log token persistence errors at DEBUG level
hermes_state.py: Add defensive _insert_session_row() call in update_token_counts() before the UPDATE
cli.py: Display reasoning tokens in /usage output
tui_gateway/server.py: Include reasoning in usage dict sent to TUI
ui-tui/src/types.ts: Add reasoning and cost_status fields to Usage interface

How to Test

Run with a Claude 4.7 model — verify pricing shows in /usage (previously showed $0.00 or "unknown")
Use claude-opus-4.7 (dot notation) as model name — verify pricing resolves correctly
Run concurrent sessions (e.g. cron job + interactive) — verify token counts are persisted (check agent.log for any DEBUG token persistence messages)
Check /usage with a reasoning model — reasoning tokens should appear as a sub-line

Checklist

Code

I've read the Contributing Guide
My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
I searched for existing PRs to make sure this isn't a duplicate
My PR contains only changes related to this fix/feature (no unrelated commits)
I've run pytest tests/ -q and all tests pass
I've added tests for my changes (required for bug fixes, strongly encouraged for features)
I've tested on my platform: WSL2 Ubuntu 24.04

Documentation & Housekeeping

I've updated relevant documentation (README, docs/, docstrings) — or N/A
I've updated cli-config.yaml.example if I added/changed config keys — or N/A
I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
I've updated tool descriptions/schemas if I changed tool behavior — or N/A

Screenshots / Logs

N/A — internal logic changes; no UI changes beyond an additional line in /usage output.

- Add pricing entries for Claude Opus 4.5/4.6/4.7, Sonnet 4.5/4.6, and Haiku 4.5 with updated source URLs (platform.claude.com) - Add _normalize_anthropic_model_name() to handle dot-notation variants (e.g. claude-opus-4.7 → claude-opus-4-7) for pricing lookups - Fix silent token loss: ensure session row exists before UPDATE in both run_agent.py and hermes_state.py (INSERT OR IGNORE is idempotent) - Log token persistence failures at DEBUG level instead of swallowing them silently — makes undercounted analytics diagnosable - Surface reasoning tokens in CLI /usage and TUI usage panel - Add 'reasoning' and 'cost_status' fields to TUI Usage type

github-actions · 2026-05-07T18:19:28Z

🚨 CRITICAL Supply Chain Risk Detected

This PR contains a pattern that has been used in real supply chain attacks. A maintainer must review the flagged code carefully before merging.

🚨 CRITICAL: Install-hook file added or modified

These files can execute code during package installation or interpreter startup.

Files:

hermes_cli/setup.py

Scanner only fires on high-signal indicators: .pth files, base64+exec/eval combos, subprocess with encoded commands, or install-hook files. Low-signal warnings were removed intentionally — if you're seeing this comment, the finding is worth inspecting.

github-actions · 2026-05-07T18:20:10Z

🔎 Lint report: `austin/fix/analytics` vs `origin/main`

ruff

Total: 0 on HEAD, 0 on base (➖ 0)

🆕 New issues: none

✅ Fixed issues: none

Unchanged: 0 pre-existing issues carried over.

ty (type checker)

Total: 7629 on HEAD, 7645 on base (✅ -16)

🆕 New issues (9):

Rule	Count
`invalid-argument-type`	8
`unresolved-attribute`	1

First entries

run_agent.py:2464: [invalid-argument-type] invalid-argument-type: Argument to function `get_model_context_length` is incorrect: Expected `str`, found `str | dict[str, str] | Any | ... omitted 4 union elements`
run_agent.py:2416: [invalid-argument-type] invalid-argument-type: Argument to function `_is_oauth_token` is incorrect: Expected `str`, found `(Unknown & ~AlwaysFalsy) | (str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | ... omitted 5 union elements`
tests/agent/test_codex_cloudflare_headers.py:163: [unresolved-attribute] unresolved-attribute: Attribute `get` is not defined on `str & ~AlwaysFalsy` in union `(Unknown & ~AlwaysFalsy) | (str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | dict[Unknown, Unknown] | Divergent`
run_agent.py:6645: [invalid-argument-type] invalid-argument-type: Argument to function `build_anthropic_client` is incorrect: Expected `str`, found `str | dict[Unknown, Unknown] | Any | ... omitted 4 union elements`
run_agent.py:2187: [invalid-argument-type] invalid-argument-type: Argument to function `query_ollama_num_ctx` is incorrect: Expected `str`, found `(str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | (Any & ~AlwaysFalsy) | ... omitted 5 union elements`
run_agent.py:6474: [invalid-argument-type] invalid-argument-type: Argument to function `_codex_cloudflare_headers` is incorrect: Expected `str`, found `Unknown | str | dict[str, str] | dict[Unknown, Unknown] | Divergent`
run_agent.py:12538: [invalid-argument-type] invalid-argument-type: Argument to function `len` is incorrect: Expected `Sized`, found `(str & ~AlwaysFalsy) | (dict[Unknown, Unknown] & ~AlwaysFalsy) | (Any & ~AlwaysFalsy) | ... omitted 4 union elements`
run_agent.py:2413: [invalid-argument-type] invalid-argument-type: Argument to function `build_anthropic_client` is incorrect: Expected `str`, found `(Unknown & ~AlwaysFalsy) | (str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | ... omitted 5 union elements`
run_agent.py:12535: [invalid-argument-type] invalid-argument-type: Argument to function `_is_oauth_token` is incorrect: Expected `str`, found `str | dict[Unknown, Unknown] | Any | ... omitted 4 union elements`

✅ Fixed issues (15):

Rule	Count
`invalid-argument-type`	8
`unsupported-operator`	3
`unresolved-attribute`	3
`not-subscriptable`	1

First entries

run_agent.py:6645: [invalid-argument-type] invalid-argument-type: Argument to function `build_anthropic_client` is incorrect: Expected `str`, found `str | dict[Unknown | str, Unknown | str | dict[str, str]] | Any | ... omitted 3 union elements`
run_agent.py:12521: [invalid-argument-type] invalid-argument-type: Argument to function `_is_oauth_token` is incorrect: Expected `str`, found `str | dict[Unknown | str, Unknown | str | dict[str, str]] | Any | ... omitted 3 union elements`
run_agent.py:2413: [invalid-argument-type] invalid-argument-type: Argument to function `build_anthropic_client` is incorrect: Expected `str`, found `(Unknown & ~AlwaysFalsy) | (str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | ... omitted 4 union elements`
run_agent.py:2464: [invalid-argument-type] invalid-argument-type: Argument to function `get_model_context_length` is incorrect: Expected `str`, found `str | dict[str, str] | Any | ... omitted 3 union elements`
tests/run_agent/test_provider_attribution_headers.py:131: [unsupported-operator] unsupported-operator: Operator `not in` is not supported between objects of type `Literal["X-OpenRouter-Cache-TTL"]` and `Unknown | str | dict[str, str] | ... omitted 3 union elements`
tests/agent/test_codex_cloudflare_headers.py:163: [unresolved-attribute] unresolved-attribute: Attribute `startswith` is not defined on `dict[str, str]` in union `Unknown | str | dict[str, str]`
tests/agent/test_codex_cloudflare_headers.py:163: [unresolved-attribute] unresolved-attribute: Attribute `get` is not defined on `str & ~AlwaysFalsy`, `int & ~AlwaysFalsy` in union `(Unknown & ~AlwaysFalsy) | (str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | ... omitted 3 union elements`
tests/run_agent/test_provider_attribution_headers.py:130: [unsupported-operator] unsupported-operator: Operator `not in` is not supported between objects of type `Literal["X-OpenRouter-Cache"]` and `Unknown | str | dict[str, str] | ... omitted 3 union elements`
tests/run_agent/test_provider_attribution_headers.py:65: [unresolved-attribute] unresolved-attribute: Attribute `startswith` is not defined on `dict[str, str]` in union `Unknown | str | dict[str, str]`
tests/agent/test_codex_cloudflare_headers.py:181: [unsupported-operator] unsupported-operator: Operator `in` is not supported between objects of type `Literal["originator"]` and `(Unknown & ~AlwaysFalsy) | (str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | ... omitted 3 union elements`
tests/run_agent/test_provider_attribution_headers.py:129: [not-subscriptable] not-subscriptable: Cannot subscript object of type `int` with no `__getitem__` method
run_agent.py:12524: [invalid-argument-type] invalid-argument-type: Argument to function `len` is incorrect: Expected `Sized`, found `(str & ~AlwaysFalsy) | (dict[Unknown | str, Unknown | str | dict[str, str]] & ~AlwaysFalsy) | (Any & ~AlwaysFalsy) | ... omitted 3 union elements`
run_agent.py:2416: [invalid-argument-type] invalid-argument-type: Argument to function `_is_oauth_token` is incorrect: Expected `str`, found `(Unknown & ~AlwaysFalsy) | (str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | ... omitted 4 union elements`
run_agent.py:2187: [invalid-argument-type] invalid-argument-type: Argument to function `query_ollama_num_ctx` is incorrect: Expected `str`, found `(str & ~AlwaysFalsy) | (dict[str, str] & ~AlwaysFalsy) | (Any & ~AlwaysFalsy) | ... omitted 4 union elements`
run_agent.py:6474: [invalid-argument-type] invalid-argument-type: Argument to function `_codex_cloudflare_headers` is incorrect: Expected `str`, found `Unknown | str | dict[str, str] | ... omitted 3 union elements`

Unchanged: 4003 pre-existing issues carried over.

Diagnostics are surfaced as warnings — this check never fails the build.

…ing (NousResearch#21455) - Add pricing entries for Claude Opus 4.5/4.6/4.7, Sonnet 4.5/4.6, and Haiku 4.5 with updated source URLs (platform.claude.com) - Add _normalize_anthropic_model_name() to handle dot-notation variants (e.g. claude-opus-4.7 → claude-opus-4-7) for pricing lookups - Fix silent token loss: ensure session row exists before UPDATE in both run_agent.py and hermes_state.py (INSERT OR IGNORE is idempotent) - Log token persistence failures at DEBUG level instead of swallowing them silently — makes undercounted analytics diagnosable - Surface reasoning tokens in CLI /usage and TUI usage panel - Add 'reasoning' and 'cost_status' fields to TUI Usage type

alt-glitch added type/bug Something isn't working P2 Medium — degraded but workaround exists comp/agent Core agent loop, run_agent.py, prompt builder comp/cli CLI entry point, hermes_cli/, setup wizard comp/tui Terminal UI (ui-tui/ + tui_gateway/) labels May 7, 2026

teknium1 merged commit d87c7b9 into main May 7, 2026
8 of 12 checks passed

teknium1 deleted the austin/fix/analytics branch May 7, 2026 20:24

helix4u mentioned this pull request May 8, 2026

docs(usage): document reasoning tokens and cost status #21604

Open

23 tasks

bot-ted mentioned this pull request May 8, 2026

chore: sync with upstream main (2026-05-08) bot-ted/hermes-agent#24

Merged

BrewTestBot mentioned this pull request May 16, 2026

hermes-agent 2026.5.16 Homebrew/homebrew-core#283141

Merged

1 task

github-actions Bot mentioned this pull request May 17, 2026

chore: bump NousResearch/hermes-agent version from v2026.5.7 to v2026.5.16 Docker-Hub-sirmark/docker-hermes-agent#6

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fix(analytics): prevent silent token loss and add Claude 4.5–4.7 pricing#21455

fix(analytics): prevent silent token loss and add Claude 4.5–4.7 pricing#21455
teknium1 merged 1 commit into
mainfrom
austin/fix/analytics

austinpickett commented May 7, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented May 7, 2026

Uh oh!

github-actions Bot commented May 7, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

austinpickett commented May 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What does this PR do?

Related Issue

Type of Change

Changes Made

How to Test

Checklist

Code

Documentation & Housekeeping

Screenshots / Logs

Uh oh!

github-actions Bot commented May 7, 2026

🚨 CRITICAL Supply Chain Risk Detected

🚨 CRITICAL: Install-hook file added or modified

Uh oh!

github-actions Bot commented May 7, 2026

🔎 Lint report: austin/fix/analytics vs origin/main

ruff

ty (type checker)

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

austinpickett commented May 7, 2026 •

edited

Loading

🔎 Lint report: `austin/fix/analytics` vs `origin/main`