Models: Cloudflare AI Gateway auth for OpenRouter#1
Draft
Models: Cloudflare AI Gateway auth for OpenRouter#1
Conversation
…dding it The system prompt intentionally excludes the current date/time for cache stability (see 66eec29). This leaves agents without date awareness, causing wrong day-of-week claims (openclaw#1897, openclaw#1928, openclaw#2108). Instead of reverting the cache optimization, add a one-line hint directing agents to use session_status when they need the current date/time. This keeps the prompt stable while teaching frontier models where to look. Also adds a negative test ensuring the date/time is NOT re-added to the system prompt, with comments explaining why and pointing to openclaw#3658 for the complementary gateway-level timestamp injection approach. Refs: openclaw#1897, openclaw#1928, openclaw#3658
Messages arriving through the gateway agent method (TUI, web, spawned subagents, sessions_send, heartbeats) now get a timestamp prefix automatically. This gives all agent contexts date/time awareness without modifying the system prompt (which is cached for stability). Channel messages (Discord, Telegram, etc.) already have timestamps via envelope formatting in a separate code path and never reach the agent handler, so there is no double-stamping risk. Cron jobs also inject their own 'Current time:' prefix and are detected and skipped. Extracted as a pure function (injectTimestamp) with 12 unit tests covering: timezone handling, 12/24h format, midnight boundaries, envelope detection, cron detection, and empty messages. Integration test verifies the agent handler wires it in correctly. Closes openclaw#3658 Refs: openclaw#1897, openclaw#1928, openclaw#2108
The chat.send handler (used by webchat and TUI) is a separate path from the agent handler. Inject timestamp into BodyForAgent (what the model sees) while keeping Body raw for UI display. This completes timestamp coverage for all non-channel paths: - agent handler: spawned subagents, sessions_send, heartbeats - chat.send: webchat, TUI
Verifies that America/New_York correctly resolves to midnight for both EST (winter, UTC-5) and EDT (summer, UTC-4) using the same IANA timezone. Intl.DateTimeFormat handles the DST transition.
Replace verbose formatUserTime (Wednesday, January 28th, 2026 — 8:30 PM) with the same formatZonedTimestamp used by channel envelopes (2026-01-28 20:30 EST). This: - Saves ~4 tokens per message (~7 vs ~11) - Uses globally unambiguous YYYY-MM-DD 24h format - Removes 12/24h config option (always 24h, agent-facing) - Anchors envelope detection to the actual format function — if channels change their timestamp format, our injection + detection change too - Adds test that compares injection output to formatZonedTimestamp directly Exported formatZonedTimestamp from auto-reply/envelope.ts for reuse.
Changes [2026-01-28 20:30 EST] to [Wed 2026-01-28 20:30 EST]. Costs ~1 extra token but provides day-of-week for smaller models that can't derive DOW from a date. Frontier models already handle it, but this is cheap insurance for 7B-class models.
Changes [Wed 2026-01-28 20:30 EST] to [Current Date: Wed 2026-01-28 20:30 EST]. Tested with qwen3-1.7B: even with DOW in the timestamp, the model ignored it and tried to compute the day using Zeller's Congruence. The "Current Date:" semantic label is widely present in training data and gives small models the best chance of recognizing the timestamp as authoritative context rather than metadata to parse. Cost: ~18 tokens per message. Prevents hallucination spirals that burn hundreds or thousands of tokens on date derivation.
Small model testing showed the label did not meaningfully help: - Sub-3B models fail regardless of format - 8B models untested with label specifically - Frontier models never needed it The bracket convention [Wed 2026-01-28 22:30 EST] matches existing channel envelope format and is widely present in training data. Saves ~2-3 tokens per message vs the labeled version.
…ent LFI (openclaw#4880) * Media: restrict local path extraction to prevent LFI * Lint: remove unused variable hasValidMediaOnLine
…for Zsh, Bash, PowerShell, and Fish.
feat: Add shell completion for Zsh, Bash, Fish, and PowerShell
Co-authored-by: CLAWDINATOR <clawdinator@openclaw.ai> Co-authored-by: Scott Hanselman <scott@hanselman.com>
* docs: document cacheRetention parameter (openclaw#6240) * docs: standardize cacheRetention value quoting style * style: format anthropic.md table * Docs: align cacheRetention inline example --------- Co-authored-by: Sebastian <sebslight@gmail.com>
* Docs: add zh-CN entrypoint translations * Docs: harden docs-i18n parsing
…penclaw#5967) * docs: fix anchor link for Google Vertex/Antigravity/Gemini section * Docs: fix model provider MDX markers --------- Co-authored-by: Sebastian <sebslight@gmail.com>
* fix: satisfy lint curly rule * docs: apply oxfmt formatting
…claw#5663) * docs(install): add pnpm approve-builds step for global installs pnpm requires explicit approval for packages with build scripts. Without running `pnpm approve-builds -g`, openclaw and its dependencies (node-llama-cpp, sharp, protobufjs) won't have their postinstall scripts executed, causing runtime errors. Fixes openclaw#5579 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs(install): clarify pnpm reinstall step after approve-builds Address review feedback: after running `pnpm approve-builds -g`, users need to re-run the install command for postinstall scripts to actually execute. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Update remaining __moltbot__ references in canvas skill documentation to match the CANVAS_HOST_PATH constant (/__openclaw__/canvas).
* Docs: Direct link to BotFather on Telegram, sparing users from searching and potentially encountering impostors. * Update numbering syntax Update numbering syntax to match PR to latest doc layout. * Docs: add BotFather verification note --------- Co-authored-by: Sebastian <sebslight@gmail.com>
* docs: add device pairing section to Control UI docs Explains that new browser connections require one-time pairing approval, what error message users will see, and how to approve devices using the CLI. This was a gap in the documentation that caused confusion for users connecting via Tailscale Serve. * docs: clarify Control UI pairing error * docs: clarify device revoke flags --------- Co-authored-by: Lucifer (via OpenClaw) <lucy@neuwirth.cc> Co-authored-by: Sebastian <sebslight@gmail.com>
…enclaw#4502) Co-authored-by: Jarvis <jarvis@openclaw.ai> Co-authored-by: CLAWDINATOR Bot <clawdinator[bot]@users.noreply.github.com> Co-authored-by: Shadow <shadow@openclaw.ai>
joncooper
force-pushed
the
cloudflare-aig-openrouter-auth
branch
from
373aa1b to
2048533
Compare
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
20 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.
Work-in-progress PR on my fork to refine the Cloudflare AI Gateway (Authenticated Gateway) approach for OpenRouter.
Next steps: tighten scope, add docs polish, and upstream once final.