docs: orchestration launch \u2014 platform credits, multi-harness, agent identities#98
Merged
Conversation
…web-UI coverage (#88) * docs(agent-platform): add named agents page and cross-link from related pages Adds a new dedicated page for named agents (agent identities) under cloud agents, and reconciles a handful of existing pages so that automation guidance and service-account references point to the new page. - New: src/content/docs/agent-platform/cloud-agents/agents.mdx — what a named agent is, plan limits, attaching descriptions/secrets/skills, REST endpoints, API keys bound to a named agent, running as a specific identity, and where named agents surface in the product. - Edit: agent-platform/cloud-agents/secrets.mdx — forward-links from the team-secrets recommendation and adds a brief note that secrets can be attached directly to a named agent. - Edit: agent-platform/cloud-agents/deployment-patterns.mdx — Pattern 1 checklist now references a named agent (recommended for automation) instead of an unscoped "service account". - Edit: agent-platform/cloud-agents/oz-web-app.mdx — reconciles the two meanings of the Agents page (skills browser + named-agent management) with a clear section split and a forward link. - Edit: reference/cli/index.mdx — keeps the literal `oz whoami` output intact and adds a one-line note pointing readers to the new agents page for what a service-account principal represents. - Edit: reference/cli/federate.mdx — keeps the literal `service_account:my-sa-id` example and adds a cross-reference to the new agents page. Hard rules: no edits to sidebar.ts, vercel.json, landing pages, or any pages owned by the five orchestration-launch PRs. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(agent-platform): rename to agent identities; expand secrets and web-UI coverage Revises the previous "named agents" page and related cross-links to use "agent identity" consistently, and folds in three product surfaces that land alongside agent identities at launch. - agents.mdx: retitled to "Agent identities" and reframed throughout to use the canonical term. Plan-limit table replaced with a single sentence pointing readers to warp.dev/pricing while preserving the default-identity / over-limit visibility behavior. Adds two new subsections: a service-account-to-agent-identity mapping (covers service_account:<uid> in oz whoami and oz federate) and a rationale paragraph for supporting multiple identities (CI, on-call, scheduled jobs). - secrets.mdx: new "Creating secrets in the Oz web app" walkthrough alongside the existing oz secret CLI section. New "Scoping secrets to environments and runs" section covering environment-level scoping and run-level scoping (default-inherit / explicit list / empty-list opt-out), with cross-links to environments and the Oz API reference. Terminology references updated. - oz-web-app.mdx: adds Secrets to the quick-reference table, reframes the Agents-page disambiguation to use "agent identity," and adds a step-by-step walkthrough of the New agent side pane (name, description, prompt, skills, harness, model, harness auth secret, secrets, memory stores). Cross-links to agents.mdx for the conceptual reference. - deployment-patterns.mdx: Pattern 1 checklist now references "an agent identity." - reference/cli/index.mdx and reference/cli/federate.mdx: leave literal CLI output intact; one-line notes tying service_account principals to agent identities, with cross-links to agents.mdx. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(secrets): fix two 'an cloud' → 'a cloud' grammar typos Pre-existing grammar slips picked up during the agent-identities PR audit. 'Cloud' starts with a consonant sound, so the article 'a' is correct. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(agent-identities): address audit findings - secrets.mdx: rephrase environment-level scoping as a default contribution to the run's allowlist (not a cap); drop the CLI environment-secret attachment claim; make the env-secret section self-contained with a web-UI walkthrough and attachment semantics - oz-web-app.mdx: fix the "Oz harness" noun-phrase slip in the base-harness bullet; drop the availability hedge on the memory-stores bullet while keeping the bullet Co-Authored-By: Oz <oz-agent@warp.dev> --------- Co-authored-by: Oz <oz-agent@warp.dev>
… Codex) (#87) * docs(cloud-agents): add multi-harness pages for Oz orchestration launch Add a new harnesses section under agent-platform/cloud-agents documenting the harnesses available inside Oz (Warp Agent, Claude Code, Codex), plus a procedural authentication page for connecting Anthropic and OpenAI credentials. Add 'two contexts' callouts to the existing CLI-agent pages distinguishing the local terminal toolbelt from the cloud orchestration surface, and cross-link to the new harness pages. New pages: - agent-platform/cloud-agents/harnesses/index.mdx (overview) - agent-platform/cloud-agents/harnesses/warp-agent.mdx - agent-platform/cloud-agents/harnesses/claude-code.mdx - agent-platform/cloud-agents/harnesses/codex.mdx - agent-platform/cloud-agents/harnesses/authentication.mdx Edited pages: - agent-platform/cli-agents/overview.mdx (two-contexts callout) - agent-platform/cli-agents/claude-code.mdx (cross-link) - agent-platform/cli-agents/codex.mdx (cross-link) - agent-platform/cli-agents/opencode.mdx (fast-follow note) Sidebar wiring is intentionally deferred to the cross-cutting sidebar PR per the orchestration launch tracker. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(harnesses): address PR #87 feedback, reframe "Oz harness" terminology - Retitle harness pages to "Warp Agent with Oz", "Claude Code with Oz", "Codex with Oz"; index becomes "Harnesses in Oz". Update body copy and cross-references in cli-agents/* to match. - Reconcile billing claim: customer-supplied Anthropic and OpenAI API keys mean the provider bills your account directly for inference; Warp credits cover the platform layer only. Apply across overview, Claude Code, Codex, and authentication pages. - Remove ChatGPT-auth ambiguity from Codex model list; "default" now reads as "Codex picks its own recommended model" with no provider- account claim that does not match cloud auth options. - Qualify launch surfaces accurately: Warp terminal harness dropdown lists Warp Agent, Claude Code, Gemini today (no Codex); Oz CLI accepts --harness oz|claude|gemini today (Codex is fast-follow); Oz web app and API/SDK expose all four harnesses. Mark Codex CLI selection as fast-follow in the Codex page and authentication page. - Add conservative framing for Gemini and OpenCode harnesses on the overview. - Strip internal field-name jargon from user-facing examples. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(harnesses): drop OpenCode mentions, simplify CLI cross-link, audit implementation detail Address Slack-thread feedback on PR #87: - Drop OpenCode from the harnesses overview roadmap note and remove the OpenCode-in-Oz callout from cli-agents/opencode.mdx. OpenCode is no longer mentioned anywhere in the harness docs. - Replace the six-sentence 'two contexts' callout on cli-agents/overview with a two-sentence note: Claude Code and Codex are also supported as harnesses in Oz. The matching callouts on cli-agents/claude-code and cli-agents/codex shrink to the same shape. - Audit pass for over-explanation: harness 'How it works' sections drop Docker / cli-invocation walk-throughs in favor of user-facing copy; Claude and Codex model lists trim in-product aliases (opus[1m], sonnet[1m], opusplan, gpt-5.3-codex-spark, etc.) and defer to the picker for the full list; 'What stays the same' bullets lead with the user benefit; the authentication intro and BYOK callouts drop 'cloud container' / 'injected at runtime' phrasing. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(harnesses): address audit findings - Replace "the default Oz harness" with "Oz's default harness" in Related-pages bullets to avoid the "Oz harness" noun-phrase. - Sweep "on Oz" → "with Oz" across harness page descriptions and body copy. - Drop preview/fast-follow hedges around Codex CLI launch and the Warp app's harness dropdown — treat as launching at GA. - Rewrite "GPT-5.5 family" as "the GPT-5 lineup" and drop gpt-5.5 from the cloud Codex Common picks (gpt-5.5 is ChatGPT-auth only; cloud Codex authenticates with an OpenAI API key). gpt-5.4 is now framed as the recommended cloud Codex default. - Add the \`best\` alias to the Claude Code Common picks list with a note that it resolves to the current top-of-line Claude model. Co-Authored-By: Oz <oz-agent@warp.dev> * Tweaking copy * docs(harnesses): copy polish on Lili's tweaks - Fix broken `[H]` link in cloud Claude Code Related pages. - Fix "OpenA credential type" typo in authentication.mdx. - Clean up Anthropic Console URL (drop ?returnTo=/? query string). - Capitalize "OpenAI Platform" to match "Anthropic Console". - Restore --team in CLI examples so the follow-up sentence parses. - Drop word-repeat in harnesses index ("harness from the harness dropdown"). - Switch backtick `Cloud Agent` to bold (UI/tab name per style guide). - Reword dangling preposition in Codex available-models bullet. - Trim trailing whitespace and a double-blank line. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(harnesses): second polish pass on multi-harness pages - Fix link-text/URL mismatch in harnesses overview: link reads 'triggers' but pointed to /integrations/; repoint to /triggers/. - Add Oxford comma to 'environment compute, triggers, and observability' in three places (style guide requires the serial comma). - Match the actual UI label: 'the harness dropdown' -> 'the **Agent harness** dropdown' on the Claude Code, Codex, and Warp Agent cloud pages (confirmed via harness_selector.rs). - Unify product descriptors so the auth page matches the harness pages: Claude Code is now 'Anthropic's agentic coding tool' and Codex is 'OpenAI's coding agent'. - 'Key icon above the input box' -> 'key icon above the input' (the spec uses lowercase 'key icon' and the rest of the docs say 'above the input'). - Drop redundant article: 'the same toolbelt the Warp Agent uses locally' -> '...the same toolbelt Warp Agent uses locally'. - Drop redundant qualifier: 'Warp Agent with Oz is the same agent runtime' -> 'Warp Agent is the same agent runtime' (page context already establishes Oz). - Disambiguate 'Claude Code and Codex call Anthropic or OpenAI directly' -> '...each call their provider directly' so it's clear each harness calls its own provider. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(harnesses): restore Lili's original Anthropic Console link Revert the Anthropic Console URL to platform.claude.com/login?returnTo=/? per PR review feedback that the original link was correct. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(harnesses): final polish pass on multi-harness pages - Match in-page link text to target page titles ('with Oz' instead of 'in Oz' / 'as a Cloud Agent'). - Point the harnesses index intro at the harness-specific pages instead of authentication anchors so readers land on the page that introduces each harness. - Surface every harness page from the index Related pages list. - Rename warp-agent's 'Starting a run' header to 'Starting a Warp Agent run' for parity with the Claude Code and Codex pages. - Split the team-admin disable sentence for clearer phrasing. Co-Authored-By: Oz <oz-agent@warp.dev> --------- Co-authored-by: Oz <oz-agent@warp.dev> Co-authored-by: liliwilson <lilimmwilson@gmail.com>
* docs: add Platform Credits page and three-bucket model Adds a new conceptual page introducing Platform Credits as the third credit bucket in Warp, alongside AI credits and Cloud Agent Credits. Explains when Platform Credits apply (cloud agents on any plan, and local agents on Business/Enterprise with BYOK or BYOLLM inference), when they don't, and where they appear in usage views. Also updates the existing Credits and Plans pages to introduce the three-bucket model and cross-link to the new page. Pricing specifics are deferred to warp.dev/pricing. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(platform-credits): align charge matrix and tighten copy - Fix contradiction flagged in PR #83 review: cloud agents always charge Platform Credits regardless of inference source. Reframe intro, three- bucket section, and the multi-bucket example to match the matrix in 'When Platform Credits apply'. - Point Generate link at /agent-platform/local-agents/generate/. - Remove time-unit details from the rate section; defer to warp.dev/pricing. - Drop internal tooltip-label callouts from the admin section. - Tighten plans-pricing-refunds Platform Credits one-liner to match. Co-Authored-By: Oz <oz-agent@warp.dev> * docs: reframe Platform Credits around inference / compute / platform infrastructure Per review feedback, lead with the three-infrastructure framing (inference, compute, platform) rather than the orchestration-layer framing. Each credit bucket now names the kind of infrastructure it covers. Also drop the enterprise custom-rate sentence; warp.dev/pricing remains the source of truth for rates. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(platform-credits): address audit findings - Reframe Platform Credits intro to lead with the rule (every cloud agent run, plus Business/Enterprise local agent runs with customer-supplied inference) instead of the negative 'when Warp isn't paying' framing. - Align cross-file framing in credits.mdx and plans-pricing-refunds.mdx so all three pages describe Platform Credits in the same terms. - Replace 'Workflow autofill' with linked 'AI Autofill'. - Replace 'Local Oz runs' with 'local agent runs' (Oz run is cloud-only). - Deduplicate the second BYOK parenthetical and normalize BYOLLM wording. - Clarify that self-hosted cloud workers count as cloud agents for Platform Credits purposes. Co-Authored-By: Oz <oz-agent@warp.dev> * Update src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx Co-authored-by: Rachael Rose Renk <91027132+rachaelrenk@users.noreply.github.com> * Update src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx Co-authored-by: Rachael Rose Renk <91027132+rachaelrenk@users.noreply.github.com> * docs(platform-credits): apply Rachael's wording suggestions Address remaining suggested edits from Rachael's review on PR #83: - plans-pricing-refunds.mdx: rewrite Platform Credits bullet to action-oriented form, matching sibling bullets. - platform-credits.mdx: de-dupe "charge for" repetition in intro; convert three-bucket bullets to active-voice complete sentences; rewrite "When Platform Credits apply" with "Uses Platform Credits" / "Doesn't use Platform Credits" headers and complete-sentence bullets; replace internal "harness" jargon with "which agent runs the task"; rename "Third-party harnesses run directly" to "Third-party agent CLIs run directly". - credits.mdx: same active-voice and "agent CLI" updates in the three-bucket summary and Platform Credits subsection. Validation: style_lint --changed clean (9 files, 0 issues), check_links --internal-only clean (2435 links, 0 broken). Co-Authored-By: Oz <oz-agent@warp.dev> * docs(platform-credits): reframe Cloud Agent Credits as compute bucket + add BYOK TOS rule Two pieces of feedback addressed on PR #83. 1. Cloud Agent Credits reframing. The bucket is described as compute infrastructure consumed by any agent run, local or cloud. Local agents rarely draw from it in practice because they don't run on Warp's compute, but the credit type is no longer tied to 'cloud-only by construction.' Updated: - platform-credits.mdx three-bucket bullet for Cloud Agent Credits (was 'cover compute infrastructure when cloud agents run on Warp-hosted compute,' now 'are the compute bucket... cover Warp-hosted compute consumed by any agent run, local or cloud'). - credits.mdx three-bucket bullet for Cloud Agent Credits with the same framing. - credits.mdx ### Cloud Agent Credits section intro reframed as 'the compute credits bucket - consumed when an agent run uses Warp-hosted compute. Both local and cloud agent runs can in principle draw from this pool...' - credits.mdx 'Not eligible' list intro tightened to make the reason explicit ('because they don't run on Warp-hosted compute') instead of implying the credit type is fundamentally cloud-only. 2. BYOK / customer-supplied inference TOS rule. Surfaces Warp's TOS rule wherever BYOK or customer-supplied inference is invoked as a workaround for Warp-paid inference. Added: - :::caution callout in platform-credits.mdx after the customer-supplied-inference paragraph, stating the individuals-and-organizations <=10 users rule and the Business or Enterprise requirement for orgs >10 users. Links to the canonical https://www.warp.dev/terms-of-service. - One-line forward reference at the end of the 'Local agents on Business or Enterprise with customer-supplied inference' bullet in platform-credits.mdx, pointing readers back to the callout for plan-size eligibility. - :::caution callout in bring-your-own-api-key.mdx directly after the existing :::note about BYOK paid-plan availability. - One-sentence summary of the TOS rule in the 'BYOK on Enterprise and Business plans' section, so admins reading that section see the eligibility constraint. Out of scope: renaming the 'Cloud Agent Credits' product term, changing pricing-faqs.mdx, or reworking BYOLLM enterprise gating (BYOLLM is already Enterprise-only, so the TOS rule is implicit). Validation: - style_lint --changed: 0 issues across 9 files scanned. - check_links --internal-only: 0 broken links across 319 files and 2,435 internal links. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(platform-credits): holistic polish pass after the compute/TOS reframe Tightens stale framing and copy that fell out of alignment after the last commit reframed Cloud Agent Credits as the compute bucket. credits.mdx: - Drop the orphaned 'small hosting fee, charged only when running agents in the cloud' sentence in the opener (L13). It predates the three-bucket model and now contradicts the new framing immediately below it; the bullet at the new L16 covers the same ground correctly. - Reframe the 'Cloud Agent Credits' bullet in Credit limits and billing (was L47, now L45). The old wording ('their normal Warp credits, Cloud Agent Credits, or a Build plan with available credits') treated Cloud Agent Credits as a separate currency. Rewritten as 'Cloud agents and integrations: Individual users can run cloud agents via the CLI and API, drawing from their plan credits. Slack and Linear integrations require team membership.' - Tighten 'in principle draw from this pool' to 'are eligible to draw from this pool' in the Cloud Agent Credits section intro (L122). platform-credits.mdx: - Frontmatter description shortened from 219 to 144 chars (back in the 50-160 SEO range). - Drop the redundant second sentence on L13 ('Platform Credits don't apply to local runs on Free, Build, or Max plans...'). The Doesn't use section below already covers it. The first sentence (defining customer-supplied inference) stays since the TOS callout depends on it. - Align the Admin usage breakdown bullet (L55): 'distinct from the AI and Compute segments' -> 'distinct from the AI credits and Cloud Agent Credits segments'. Uses the bucket names consistently with the rest of the page. Validation: - style_lint --changed: 2 pre-existing warnings on bring-your-own-api-key.mdx (Zero Data Retention is a proper term; Enterprise/Business are proper plan names). Acceptable. - check_links --internal-only: 0 broken links across 319 files and 2,433 internal links. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(platform-credits): rename Cloud Agent Credits -> compute credits + reframe as orthogonal credit-type/host model Per user correction: the credit type is 'compute credits' (lowercase), not 'Cloud Agent Credits.' The old name conflated the credit type (compute) with the host (cloud). The corrected conceptual model treats the three credit types (AI/inference, compute, platform) and the two host types (local, cloud) as orthogonal dimensions: any credit type can in principle apply to any host, with compute credits being the one that in practice only cloud agents consume (because local agents run on the user's machine). Files touched: Content (6): - credits.mdx: three-bucket bullets reframed to lead with the orthogonal dimension; section heading '### Cloud Agent Credits' -> '### Compute credits'; section intro rewritten; eligible/not- eligible subheadings renamed; all inline mentions and the '#cloud-agent-credits' anchor flipped to '#compute-credits'. - platform-credits.mdx: page intro three-bucket sentence updated to use 'compute credits'; three-bucket bullets reframed with the orthogonal-dimension intro; multi-bucket example updated; per-user and admin breakdown bullets updated to use bucket names consistently. - team-access-billing-and-identity.mdx: 3 references reworded to drop the 'normal Warp credits, Cloud Agent Credits, or a Build plan' stale enumeration and use plan credits / compute credits. - agent-platform/cloud-agents/overview.mdx: 2 references updated to the new terminology + anchor. - enterprise/support-and-resources/billing.mdx: 'small hosting fee' framing replaced with the explicit three-bucket model; 'no separate cloud agent credits or local credits' sentence replaced with a framing that aligns with the bucket model (credit type depends on infrastructure, not on local vs cloud). - terminal-and-agent-modes.mdx: Credits indicator description generalized from 'remaining cloud agent credits' to 'remaining credits.' Support / glossary (3): - AGENTS.md: 'Cloud Agent Credits' entry replaced with 'compute credits' (lowercase) entry; new 'Platform Credits' entry added (was previously implicit). - .agents/references/terminology.md: same swap in the billing glossary. - .agents/skills/style_lint/style_lint.py: 'Cloud Agent Credits' removed from PROPER_FEATURE_NAMES (no longer a Title-Case exception since it's now lowercase); 'Platform Credits' added to PROPER_FEATURE_NAMES; PRODUCT_CASING gains 'Cloud Agent Credits' -> 'compute credits' and 'Cloud Agent Credit' (singular) as one-way nudges so future contributors don't reintroduce the old name. Validation: - 0 remaining 'Cloud Agent Credit' or '#cloud-agent-credit' references in src/content/docs. - style_lint --changed: only the 2 pre-existing BYOK warnings (Zero Data Retention, BYOK on Enterprise and Business plans). Both are acceptable false positives flagged in prior commits. - check_links --internal-only: 0 broken across 319 files and 2,434 internal links. The Astro Starlight heading-to-anchor derivation (### Compute credits -> #compute-credits) resolves correctly. Out of scope: - Lowercasing 'Platform Credits' (user did not request). - Changes to pricing-faqs.mdx (no mentions). - vercel.json redirects (anchors aren't redirected; all inbound refs in our own docs were updated directly). Co-Authored-By: Oz <oz-agent@warp.dev> * docs: normalize credits list separators Co-Authored-By: Oz <oz-agent@warp.dev> * docs(platform-credits): restore descriptive 'cloud agent credits' on the Credits indicator UI label In the prior rename pass I over-corrected one spot: the 'Credits indicator' UI label in terminal-and-agent-modes.mdx, which described the cloud agent conversation's credit-balance indicator. The original text 'Shows your remaining cloud agent credits' was using 'cloud agent credits' descriptively (as in 'the credits cloud agents consume'), not as a formal product-name reference. Restoring the original wording. The PRODUCT_CASING lint nudge is case-sensitive on Title Case 'Cloud Agent Credits' / 'Cloud Agent Credit', so descriptive lowercase mentions like this one don't trigger it. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(platform-credits): revert compute credits rename back to Cloud Agent Credits Per user feedback: the product name is 'Cloud Agent Credits' (Title Case). The word 'compute' is the type description (what the bucket covers - the sandbox an agent runs in), not the product name. My prior rename pass conflated the two. Revert it. Kept from the prior pass: - The orthogonal credit-type/host conceptual reframe: 'Credit types and where an agent runs (local or cloud) are independent. Each agent run consumes from whichever credit types apply to it.' This framing was an improvement and stays. - The Enterprise billing page rewrite: the old 'small hosting fee' framing and the contradicting 'no separate cloud agent credits or local credits' sentence stay replaced by the explicit three-bucket explanation. Just substituted 'Cloud Agent Credits' back for the product-name reference. - The BYOK / customer-supplied inference TOS callouts in platform-credits.mdx and bring-your-own-api-key.mdx. - The Platform Credits glossary entry I added to AGENTS.md and terminology.md (was a real gap, not added by mistake). - The descriptive lowercase 'cloud agent credits' in terminal-and-agent-modes.mdx:126 (UI label restoration in 8833ded). Reverted: - credits.mdx: three-bucket bullets, section heading '### Compute credits' -> '### Cloud Agent Credits', section intro, eligible / not-eligible subheadings and intros. - platform-credits.mdx: page intro three-bucket sentence, three-bucket bullets, multi-bucket example, per-user and admin breakdown bullets. - team-access-billing-and-identity.mdx: 3 references and anchor link. - cloud-agents/overview.mdx: 2 references and anchors. - enterprise/support-and-resources/billing.mdx: product-name swap. - AGENTS.md: glossary entry back to 'Cloud Agent Credits'. - terminology.md: same. - style_lint.py: 'Cloud Agent Credits' back in PROPER_FEATURE_NAMES; removed the two PRODUCT_CASING nudges for Cloud Agent Credits -> compute credits. Validation: - 0 'compute credits' product-name references remain in src/content/docs. - style_lint --changed: only the 2 pre-existing BYOK header false positives. - check_links --internal-only: 0 broken across 319 files and 2,434 internal links. The '#cloud-agent-credits' anchor resolves via the restored '### Cloud Agent Credits' heading. Co-Authored-By: Oz <oz-agent@warp.dev> * docs: add Platform Credits AEO summary Co-Authored-By: Oz <oz-agent@warp.dev> * Split Cloud Agent Credits into Compute credits + Cloud agent credits; rename plan credits to normal Warp credits Address review feedback: 1. Split into two complementary concepts: - **Compute credits** (sentence case): the compute bucket itself, used alongside AI credits and Platform Credits when describing credit types. - **Cloud agent credits** (sentence case, 'Cloud' capitalized): credits consumed by cloud agents, in contrast with local agent credits. Both refer to the same underlying bucket; pick the term that fits the framing. 2. Rename 'plan credits' to 'normal Warp credits' in user-facing copy so it's no longer confused with 'Build plan credits' (the proper plan product noun, which is preserved). Files updated: - credits.mdx: Three-bucket bullets use 'Compute credits'. Section heading '### Cloud Agent Credits' becomes '### Compute credits' with anchor '#compute-credits', plus eligible/not-eligible subheadings switch to 'compute credits'. A short note explains the 'Cloud agent credits' alias for the host-context framing. - platform-credits.mdx: Bucket-context bullets and per-user/admin breakdown switch to 'Compute credits' (bucket framing) plus the three-bucket intro sentence. - team-access-billing-and-identity.mdx, cloud-agents/overview.mdx: Cloud-vs-local-host bullets use 'Cloud agent credits' (sentence case) pointing to '#compute-credits'. - enterprise/support-and-resources/billing.mdx: Three-bucket framing uses 'compute credits' alongside AI and Platform Credits. - add-on-credits.mdx, pricing-faqs.mdx: 'plan credits' (legacy term) swapped for 'normal Warp credits'; 'Build plan credits' (proper noun) is preserved. - AGENTS.md, .agents/references/terminology.md: Glossary updated with both 'Compute credits' and 'Cloud agent credits' entries, and the 'normal Warp credits' guidance. - .agents/skills/style_lint/style_lint.py: Removes 'Cloud Agent Credits' from PROPER_FEATURE_NAMES and adds a nudge to use sentence case ('Cloud agent credits') or 'compute credits' depending on framing. Validation: - 0 'Cloud Agent Credits' Title Case occurrences in src/content/docs - All 3 remaining 'plan credits' matches are 'Build plan credits' - style_lint --changed: only pre-existing BYOK false positives - check_links --internal-only: 0 broken across 2,434 internal links - '#compute-credits' anchor resolves via renamed section heading Co-Authored-By: Oz <oz-agent@warp.dev> * Lowercase 'cloud agent credits' mid-sentence/mid-bullet Per review feedback: the term 'cloud agent credits' is a common noun and should be lowercased anywhere it appears mid-sentence or mid-bullet. Only capitalize the first letter at the start of a sentence or bullet. Files updated: - credits.mdx L124: the alias clarification ('referred to as **cloud agent credits**') is now lowercase. - team-access-billing-and-identity.mdx L21, L41, L84: all three are mid-bullet/mid-sentence references and are lowercased. - cloud-agents/overview.mdx L120, L135: mid-bullet references lowercased. - AGENTS.md, .agents/references/terminology.md: glossary entry header is now '**cloud agent credits**' (lowercase) to match the canonical form for common-noun terms (consistent with **credits**, **normal Warp credits**, etc.). The description was updated to explain when to capitalize. - .agents/skills/style_lint/style_lint.py: PRODUCT_CASING nudge now recommends lowercase 'cloud agent credits' with a note about capitalizing the first letter at sentence/bullet boundaries. Glossary entries that lead a bullet (e.g. '**cloud agent credits**') stay lowercase to follow the existing common-noun convention in terminology.md, not because they're mid-sentence. Co-Authored-By: Oz <oz-agent@warp.dev> * Lowercase 'platform credits' mid-sentence/mid-bullet/mid-heading Per review feedback, apply the same common-noun convention to 'platform credits' that we applied to 'cloud agent credits' and 'compute credits'. Capitalize the first letter only at the start of a sentence, bullet, or heading; lowercase everywhere else. Files updated: - platform-credits.mdx: title -> 'Platform credits'. Every body, bullet, and heading occurrence reframed: - Three-bucket bullets and mid-sentence text -> 'platform credits' / '**Platform credits**' (bullet leads stay sentence-cased). - All H2/H3 headings ('## How platform credits are measured', '## When platform credits apply', '### Uses platform credits', '### Doesn't use platform credits', '## Where platform credits appear') lowercase the second word. - credits.mdx: three-bucket bullet, section heading '### Platform credits', subsection headings, and all in-text occurrences updated. Mid-sentence link text 'See [platform credits](...)' is also lowercased. - enterprise/support-and-resources/billing.mdx: the example sentence the reviewer flagged ('...AI credits..., compute credits..., and platform credits for the orchestration layer') and the three-types parenthetical (AI credits, compute credits, and platform credits) are lowercased. - plans-pricing-refunds.mdx: the related-links bullet now reads '[Platform credits](...) - learn how platform credits cover...'. - AGENTS.md, .agents/references/terminology.md: glossary entry header is now '**platform credits**' (matching the existing common-noun convention used for **credits**, **normal Warp credits**, **compute credits**, **cloud agent credits**) with a usage note explaining the casing rule. Adjacent **compute credits** entry is normalized the same way. - .agents/skills/style_lint/style_lint.py: 'Platform Credits' removed from PROPER_FEATURE_NAMES and a new PRODUCT_CASING nudge maps the title-cased form to lowercase 'platform credits' with a note about capitalizing at sentence/bullet/heading boundaries. Validation: - check_links --internal-only: 0 broken across 2,434 internal links. - The only remaining 'Platform Credits' Title Case match is the linter's own wrong->right mapping (expected). Co-Authored-By: Oz <oz-agent@warp.dev> * docs: rename 'normal Warp credits' to 'Warp credits' Drops the 'normal' qualifier across user-facing copy, the terminology glossary, and AGENTS.md. 'Warp credits' is the cleaner brand-aligned term for credits included with a subscription plan. Co-Authored-By: Oz <oz-agent@warp.dev> * docs: polish credit copy after rename - Drop now-redundant 'or Build plan credits' / 'or a Build plan with available credits' (Build plan credits are Warp credits). - Tighten 'individual Warp credits' to 'individual credits' to match the prior bullet's wording. - Remove duplicate 'Warp' in 'your included monthly Warp credits'. - Replace 'Build plan credits' with [Add-on Credits] in the cloud-agents requirements bullet so it mirrors the team-requirements bullet below it. - Restructure the Add-on Credits/limits sentence in platform-credits.mdx to make the consumption order explicit. - Update 'same plan credit pool' to 'same Warp credit pool' in credits.mdx. Co-Authored-By: Oz <oz-agent@warp.dev> * docs: drop redundant credit-type enumerations The '(any type works)' parenthetical and the 'Warp credits, cloud agent credits, and Add-on Credits all work' bullet aren't actually telling the user anything actionable — they're all credits and they all draw from the same balance. Just say '20 credits' and let the linked billing pages handle the credit-type breakdown. Touched: - agent-platform/cloud-agents/overview.mdx (2 occurrences; removed the redundant credit-type bullet under Credit requirements as well as the vague 'Usage is billed based on credit type and team configuration' filler bullet). - agent-platform/cloud-agents/team-access-billing-and-identity.mdx (2). - agent-platform/cloud-agents/quickstart.mdx (1). - agent-platform/cloud-agents/integrations/slack.mdx (1). - agent-platform/cloud-agents/integrations/linear.mdx (1). Co-Authored-By: Oz <oz-agent@warp.dev> --------- Co-authored-by: Oz <oz-agent@warp.dev> Co-authored-by: Rachael Rose Renk <91027132+rachaelrenk@users.noreply.github.com>
…ale terminology (#97) Audit pass over the three PRs merged into hyc/orchestration-launch (#83 Platform Credits, #87 Harnesses, #88 Agent identities) to catch wiring and cross-reference issues before rollout. Sidebar wiring (src/sidebar.ts): - Under 'Oz Cloud Agents & Orchestration', add 'Agent identities' (slug agent-platform/cloud-agents/agents) after Managing cloud agents, and a new collapsed 'Harnesses' subsection (Overview, Warp Agent, Claude Code, Codex, Authentication) after Secrets and before MCP servers. - Under 'Plans and billing', add 'Platform credits' after Add-on Credits. Terminology / cross-reference (one-line tweaks): - external-authentication-required.mdx:104: replace the inline '(service account)' parenthetical with 'bound to an [agent identity](...)'. Matches the alias formalized in agents.mdx and the existing phrasing in federate.mdx and cli/index.mdx. - cloud-agents/overview.mdx Learn more: add two bullets so the new Harnesses overview and Agent identities pages are discoverable from the parent overview. Validation: - check_links --internal-only: 0 broken across 2,495 internal links (up 3 from the 2,492 baseline, matching the 3 new links added). - style_lint --changed: 14 warnings, identical to baseline (all pre-existing proper-name false positives in pricing-faqs.mdx, bring-your-own-api-key.mdx, etc.). - npm run build: succeeds; 326 HTML files generated. Co-authored-by: Oz <oz-agent@warp.dev>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
|
I'm starting a first review of this pull request. You can view the conversation on Warp. I completed the review and no human review was requested for this pull request. Comment Powered by Oz |
![oz-for-oss[bot]](https://avatars.githubusercontent.com/in/3450139?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Overview
This PR adds substantial documentation for platform credits, multi-harness cloud agents, and agent identities, plus related sidebar and terminology updates. The new pages cover the intended launch areas, but several changed lines introduce contradictions or unsupported public API guidance that should be fixed before publishing.
Concerns
- The new credit model introduces
AI credits, but the repository guidance still says not to use that term. - Agent identity docs disagree on whether an unspecified run uses the default agent identity or the human caller.
- Codex API/SDK instructions point to an API reference that this PR does not update with Codex harness fields.
- The platform credits page advertises Gemini as a harness even though the launch docs only add Warp Agent, Claude Code, and Codex.
Found: 0 critical, 4 important, 0 suggestions
Verdict
Request changes
Comment /oz-review on this pull request to retrigger a review (up to 3 times on the same pull request).
Powered by Oz
|
|
||
| - **Add-on Credits** — capitalized as a product feature name | ||
| - **Cloud Agent Credits** — capitalized as a billing feature name | ||
| - **compute credits** — lowercase common noun; capitalize the first letter only at the start of a sentence or bullet. The compute bucket, consumed when an agent run uses Warp-hosted compute. Use alongside AI credits and platform credits when describing credit types. |
Contributor
There was a problem hiding this comment.
AI credits as a billing term, but the same glossary and AGENTS.md still say to use credits and not AI credits; update those guidance entries so docs authors and lint workflows do not contradict the new three-bucket model.
| * **Authenticate with a key bound to the identity** - Every run started with that key executes as the bound agent identity. This is the typical path for CI pipelines and scheduled work. | ||
| * **Pass `agent_identity_uid` on `POST /agent/runs`** - For one-off runs, send the agent identity's `uid` in the request body. The field is only valid for team-owned runs. | ||
|
|
||
| When neither path is used, runs execute under the default identity ("Quick run" in the web app). |
Contributor
There was a problem hiding this comment.
oz-web-app.mdx says Quick run runs as the user; make the default execution principal consistent so API-key binding and audit behavior are unambiguous.
|
|
||
| * **Warp app** - In Cloud Mode, click the **Agent harness** dropdown above the input and choose **Codex**. | ||
| * **Oz web app** - On the new run or new schedule pane, choose **Codex** in the **Harness** field. A **Codex auth secret** field appears below it; pick the OpenAI secret your team has stored. | ||
| * **API and SDK** - Set the agent config `harness` to `codex` and the OpenAI secret name on the matching auth-secret field. See the [API reference](/reference/api-and-sdk/). |
Contributor
There was a problem hiding this comment.
codex harness and its auth-secret field; sync the public OpenAPI/Scalar reference in this PR or remove the API claim until it exists.
|
|
||
| ### Uses platform credits | ||
|
|
||
| * **Cloud agents on any plan** use platform credits for every cloud agent run, regardless of which agent runs the task (Warp Agent, Claude Code, Codex, or Gemini), inference source (Warp-managed, BYOK, or BYOLLM), or compute source (Warp-hosted or self-hosted workers). Warp's platform infrastructure coordinates every cloud agent run. |
Contributor
There was a problem hiding this comment.
moirahuang
approved these changes
May 19, 2026
…anup (#99) Comprehensive pass over the orchestration-launch branch to catch content issues that wiring-focused audit #97 left behind. Factual corrections: - agents.mdx: drop 'getAgent' from the operationId list and remove the 'Retrieve - GET /agent/identities/{uid}' bullet. The OpenAPI spec (developers/agent-api-openapi.yaml) only ships createAgent / listAgents / updateAgent / deleteAgent under the /agent/identities path; there is no single-resource GET. - agents.mdx: replace 'pass the identity\'s UID to the generateApiKey mutation' with 'choose the identity when creating the team API key'. No generateApiKey mutation exists in the OpenAPI, and api-keys.mdx describes a UI-driven creation flow. - agents.mdx: drop the ('Quick run' in the web app) parenthetical from the default-identity fallback note. oz-web-app.mdx defines Quick run as user-attributed ('runs as your own user'), so equating it with the default agent identity contradicts the rest of the docs. Terminology unification (post three-bucket / agents-launch model): - harnesses/index.mdx, claude-code.mdx, codex.mdx: replace the vague 'Warp credits cover the orchestration platform' wording with the explicit three-bucket framing 'Warp meters compute credits for the run\'s sandbox and platform credits for the orchestration layer'. - team-access-billing-and-identity.mdx: rename every 'Reload Credits' / 'Reload Credit pool' / 'Reload Credit balance' reference to the canonical 'Add-on Credits' (5 spots, including the parenthetical '[Reload Credits (Add-on Credits)](...)'). - oz-web-app.mdx: rename the page title and 6 image alt texts from 'Oz Web App' (Title Case) to 'Oz web app' to match the canonical glossary entry and the sidebar label. Style guide cleanup: - secrets.mdx: drop a trailing ' ' GitBook artifact, replace 'just references it by name' with 'only references it by name', and backtick the bare 'oz secret' in 'oz secret command family'. - harnesses/authentication.mdx: replace 'just like any other Warp- managed secret' with 'like any other Warp-managed secret'. - deployment-patterns.mdx: drop 'just' from 'and you just need a reliable, cloud-connected agent runner'. - cloud-agents/overview.mdx: lowercase two H4 headings ('For Cloud Agents via CLI/API' -> 'For cloud agents via CLI/API'; 'For Integrations (Slack/Linear)' -> 'For integrations (Slack/Linear)') per the sentence-case style guide. Validation: - check_links --internal-only: 0 broken across 2,501 internal links (up 6 from the 2,495 baseline, matching the new compute-credits / platform-credits anchors added in the harnesses billing sections). - style_lint --changed: only pre-existing proper-name false positives in pricing-faqs.mdx (Build / Business / Pro / Turbo / Lightspeed / Add-on Credits headings). - npm run build: 326 pages built; sidebar compiles; new anchor and slug references resolve. Co-authored-by: Oz <oz-agent@warp.dev>
* docs(agent-platform): add Agent Memory research-preview pages
Add overview, memory-stores, self-hosted-memory, and api pages under
agent-platform/capabilities/agent-memory/. List the feature on the
capabilities index and add a Suggested Skills from Agent Memory note
to the skills page.
The new pages are scoped to the agent-platform topic but are not yet
wired into src/sidebar.ts; the cross-cutting sidebar PR will add the
entries so the build resolves the topic association.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): scrub internals, downsize API page, tighten tone
Address reviewer feedback and Slack-thread guidance on the Agent
Memory research-preview pages.
- Overview: narrow the API capability bullet to user-owned store
creation (team-owned creation is in the Warp app only), drop
the 'harness-support endpoint' internal reference, drop the
service-account-granted-stores phrasing, trim the data flywheel
section, and tighten the frontmatter description to fit the
50-160 char SEO range.
- Memory stores: tighter description, generalize API references
away from raw HTTP method/path callouts, drop schema field name
leaks ('memory_stores' as wire field) in favor of conceptual
prose, polish tone.
- Self-hosted memory: present as forward-looking direction for
the research preview, drop the specific Postgres/Turbopuffer/
Voyage AI vendor stack from the reference adapter section in
favor of abstract relational + vector + embedding language.
- API: downsize to a research-preview stub. Drop endpoint paths,
request/response schemas, and HTTP method signatures. Keep
authentication, capability surface at category level,
attachment behavior rules, validation error patterns, and
the design-partner contact path.
- Skills: tighten Suggested Skills from Agent Memory section to
honest, forward-looking direction-of-travel wording.
- Capabilities overview: tighten the Agent Memory entry copy.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): drop remaining internal-implementation details
Second pass of trimming on the Agent Memory research-preview pages,
following the same direction as 1564a8d.
- index.mdx: collapse the two-stage extraction/planning description
of consolidation into a single user-facing paragraph; drop the
internal facts/learnings/outcomes taxonomy; drop the reranker
mention from the retrieval bullet; tighten the matching key-features
and research-preview bullets for consistency.
- memory-stores.mdx: remove the wire-format Update semantics section
(omit / empty / non-empty) and link out to the API page instead;
replace the dependency-order permanent-deletion sentence with a
single user-facing line; drop the 409 Conflict HTTP status code
while keeping the rule and remediation.
- self-hosted-memory.mdx: replace the named interface-method list
with a one-paragraph capability summary; drop the embedding-pipeline
phrasing on both the in-scope and reference-adapter sections; drop
the extraction/planning two-stage framing.
- api.mdx: rename 'Validation errors' to 'Common rejection reasons'
and drop the 400 invalid_request / 409 Conflict codes while keeping
the rejection reasons; soften the wire-format mention for the
identity-attachment endpoint.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): use canonical "agent identity" terminology
Replace "named agent identity/identities" (and shorthand "named identity"
forms) with "agent identity/identities" throughout the Agent Memory pages
to align with the docs-wide canonical term.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): consolidate research-preview docs into a single page
Replace the four-page Agent Memory subsection with a single research-preview
overview page. The deleted pages (memory-stores, self-hosted-memory, api)
were never published and overcommitted on behavior that's still in design.
- Rewrite agent-memory/index.mdx as a tight overview: research-preview
callout with waitlist CTA, what's available today, what's not yet
available, how to get involved, related pages.
- Tighten the "Suggested Skills from Agent Memory" subsection on skills.mdx
to a single forward-looking paragraph without procedural claims.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): audit polish pass on the consolidated research-preview page
Editorial copy pass on top of 2ea77ff. No structural or scope changes;
no new claims, no new links.
agent-memory/index.mdx:
- Drop slight anthropomorphism in opener ("no recollection" -> "without context").
- Replace "verbose transcript dump" with neutral "the full conversation transcript."
- Reorder the personal-memory bullet so the actor (Oz) leads and the
harness clause doesn't bury the punchline.
- Fix awkward SVO order on self-hosted bullet.
- Replace vague "focused on the personal store" with precise
"only reads from the personal store."
- Tighten the two related-pages descriptions.
skills.mdx:
- Tighten the Suggested Skills from Agent Memory paragraph: drop the
doubled "Agent Memory" reference, replace "is being explored" with
"is in design," and remove the awkward "no concrete behavior" hedge.
Validation:
- style_lint --changed: one known false positive on the Suggested Skills
header (Skills and Agent Memory are proper feature names per AGENTS.md).
- check_links --internal-only: 0 broken links across 318 files and 2391 links.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): rewrite as unified SEO/waitlist page
Drops the "What's available today" / "What's not yet available" split in
favor of a single capability narrative. The page is now a marketing-pitched,
SEO-oriented overview that walks a prospective user through the value of
Agent Memory and pushes toward the waitlist three times (top caution,
hero closer, dedicated Get early access section).
Structural changes:
- Tightened frontmatter description (132 chars, in SEO range) leading with
the primary keyword "agent memory" and the value proposition.
- Hero is now two short paragraphs that motivate the problem (cold runs)
and introduce the product, ending with a request-early-access link.
- Five keyword-rich H2 sections describe the capability surface in one
unified narrative: Persistent memory across runs, Cross-harness
retrieval, Automatic consolidation, Personal and team memory stores,
Self-hosted memory backends. No shipped-vs-roadmap hedging in the body;
the research-preview caution at the top covers "behavior may change."
- New "What Agent Memory unlocks" section with three use-case vignettes
(debugging that resumes; repeated maintenance agents that learn the
codebase; team-shared knowledge) that give prospects concrete reasons
to want it and add SEO surface area.
- New "Get early access" section replaces the old "How to get involved."
- Switched the Agent identities related-pages link from the absolute
docs.warp.dev URL to a relative path, now that PR #88 has merged into
the gating branch and been forward-merged into this branch.
Validation:
- style_lint --changed: 0 new issues on the rewritten page (the existing
known false positive on skills.mdx:414 Suggested Skills header is
untouched).
- check_links --internal-only: 0 broken links across 319 files and 2,421
internal links.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): polish hero opener for clarity
Drop the self-referential "by default" qualifier (the non-default mode it
implied is Agent Memory itself, making the phrase quietly circular).
Make the cold-start problem more concrete by spelling out that prior
runs' learnings are lost \u2014 strengthens the value framing the page is
trying to build for the waitlist CTA.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): consolidate PR #95 content, move to top-level Memory section
Major restructure of the Agent Memory docs to address user feedback:
1. Promote Agent Memory to its own top-level section in the sidebar.
New 'Memory (Research Preview)' group sits inside the Agents topic
between Getting started and Warp Agents for top-of-list visibility.
2. Move the page from agent-platform/capabilities/agent-memory/ to
agent-platform/agent-memory/ to match the new section's IA. The
'/agent-platform/capabilities/agent-memory' URL now redirects to
'/agent-platform/agent-memory/' via vercel.json.
3. Add '(Research Preview)' marker to the sidebar label, matching the
page title and the existing Settings Sync (Beta) precedent.
4. Replace 'workspace' with 'team' in user-facing copy. The
implementation-layer WORKSPACE enum is internal and unaffected.
5. Consolidate PR #95 (hyc/memory-waitlist) content into the page.
PR #95 had been opened separately as a marketing/waitlist rewrite
from another conversation. Taking its richer body (8 capability
bullets, dedicated sections for Personal/team stores, Automatic
memory from conversations with Sparse/Reasoned/Reversible
sub-bullets, How agents retrieve memories with the
Vector+BM25+Reranking pipeline, Attaching memory to agents
covering identity-level and run-level attachments, and Built for
teams), stronger CTAs (bold-link waitlist CTA after hero + 'Ready
to give your agents memory?' closer), and richer 5-link related
pages. Restores the research-preview caution callout that PR #95
had dropped, keeps the (Research Preview) title, and uses 'team'
throughout. PR #95 will be closed in a follow-up.
6. Use generic 'agents' / 'your agents' / 'Warp agents' framing
throughout. Memory is gated to cloud agents today but will work
for local agents going forward, so the docs don't specify cloud
vs local. The research-preview caution carries any 'behavior may
change before GA' hedge.
7. Capability claims (deletion safety, per-store instructions,
versioned history, hybrid semantic+keyword search) all match
the QUALITY-585 and QUALITY-536 specs.
Files touched:
- src/content/docs/agent-platform/agent-memory/index.mdx (new)
- src/content/docs/agent-platform/capabilities/agent-memory/index.mdx (deleted)
- src/content/docs/agent-platform/capabilities/index.mdx (Agent Memory bullet removed)
- src/content/docs/agent-platform/capabilities/skills.mdx (link URL updated)
- src/sidebar.ts (new Memory group)
- vercel.json (old URL redirect)
Validation:
- style_lint --changed: only the known pre-existing false positive on
skills.mdx:414 Suggested Skills from Agent Memory header (both
'Skills' and 'Agent Memory' are proper feature names per AGENTS.md).
- check_links --internal-only: 0 broken across 319 files and 2,422
internal links. New URL resolves cleanly.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): address Suraj's review feedback
- Drop vector/keyword search and versioned history bullets; remove the
'recorded reason for every change' / 'Reasoned' bullet so the page
stays high level for waitlist-phase customers (Slack feedback +
pending inline comment).
- Replace 'Warp agents' wording and explicitly call out cross-harness
support (Warp Agent, Claude Code, Codex, Gemini) in the description
and intro paragraph (pending inline comments on multi-harness and
'Warp agents').
- Reframe automatic-memory and bullets section around 'learning over
time' instead of one-shot extraction (pending inline comment).
- Rename 'Personal and team memory stores' to 'Memory stores', explain
per-agent scoping with cross-agent sharing, and add the code-review
+ Sentry triage repo-store example (pending inline comment).
- Replace 'runs a memory synthesis pass that extracts' with 'extracts'
(pending inline comment).
- Slim 'How agents retrieve memories' to 'How agents use memory' and
note that agents can retrieve memories on demand throughout a
conversation when they decide it's the right thing to do (pending
inline comment + Slack 'how' removal).
- Collapse 'Attaching memory to your agents' to one paragraph and
remove the redundant 'Built for teams' section to keep the page
scannable and 'what/why'-focused.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): lead with async + Oz-as-the-layer framing
Follow-up to Suraj's feedback on PR #86. Verbiage inspiration from the
Claude Managed Agents memory post.
- Frontmatter description and hero paragraph now lead with the value
prop ('Your agents should learn across every conversation, every
harness, every run') instead of a descriptive opener, and explicitly
position Warp as the platform the customer already uses to run their
agents.
- Hero paragraph + a new 'Async by design' bullet + a new sentence in
each of 'Automatic memory from conversations' and 'How agents use
memory' make it clear that memory creation and retrieval happen in
the background. Agents never burn tokens or attention on memory work
during a run.
- 'Cross-harness persistence' is promoted to the first 'What you get'
bullet and reframed as 'One memory layer for every agent in Warp'.
Dropped the now-redundant 'Durable knowledge across conversations'
bullet (the intro already says it).
- New 'Built on the layer your agents already live on' subsection
drives the Oz-as-the-layer pitch home: Warp Agent locally, Oz cloud
agents in the background, and Claude Code/Codex/Gemini all go
through the same platform, so memory is a free byproduct rather than
new infrastructure.
- Final CTA sharpened to 'Your agents already live on Warp. Give them
a memory that lives there too.'
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): polish pass
- Trimmed frontmatter description so it fits the ~50-160 char target
and reads as a standalone summary.
- Split the long hero paragraph into shorter sentences so each beat
(value prop, harness list, no infra, async, each run) lands on its
own. Fixed the 'memory ... memory' repetition by referring to
creation and retrieval with 'they'.
- Reworded the 'Built on the layer your agents already live on'
paragraph: opens with 'Warp is already the platform where your
agents run', drops the dangling 'through the same platform' clause,
and avoids the 'layer ... layer too' echo by saying 'Agent Memory
turns that same platform into a memory layer'.
- Used 'Memory creation' (instead of 'Synthesis') in the 'Automatic
memory from conversations' paragraph so the async terminology
matches the 'Async by design' bullet.
- Switched the 'Sparse by design' / 'Learns over time' mini-headlines
to the bold-term + em-dash + explanation pattern used by the rest
of the page.
- Tightened the 'Per-agent access control and instructions' bullet.
- Replaced the awkward 'watch what they learn today make them
sharper tomorrow' construction in the final CTA with 'so what they
learn today makes them sharper tomorrow'.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): de-marketing pass, dev-doc tone
Strip marketing-style phrasing and rewrite the page in the descriptive,
factual tone used by the rest of the agent-platform capability pages
(skills.mdx, codebase-context.mdx, cloud-agents/overview.mdx).
- Description and intro now lead with what Agent Memory is, not a
rule-of-three pitch. Dropped 'Your agents should learn across every
conversation, every harness, every run' and 'Agent Memory makes that
real.' Replaced with: 'Agent Memory is a persistent memory layer
that lives on Warp and is shared across every supported agent
harness...'
- Renamed 'What you get with Agent Memory' to 'Key features' (matches
skills.mdx).
- Renamed 'Built on the layer your agents already live on' to 'Where
Agent Memory runs' and rewrote it as factual coverage info: storage
+ creation + retrieval are all hosted on Warp infrastructure, with
an explicit bulleted list of the agent types covered (local Warp
Agent, Oz cloud agents, third-party harnesses).
- Tightened bullets to bold-term + em-dash + plain explanation
pattern. Dropped 'draws from the same well of knowledge', 'any
harness you reach for next', 'leaves your team a little smarter
than the last', and 'Instructions matter: they're the difference
between an agent that has memory and an agent that knows what to
remember and when.'
- Tightened the 'How agents use memory' paragraph and changed
'whenever they decide it's the right thing to do' to 'when they
determine it's relevant' (preserves the intent of Suraj's earlier
feedback without the colloquial phrasing).
- Replaced the 'Ready to give your agents memory?' CTA with a plain
'Join the waitlist' section, and switched the in-body waitlist link
from bold + arrow to a plain markdown link.
All seven of Suraj's earlier pending comments are still addressed
(multi-harness, harness-agnostic wording, learning over time, no
'reason' mentions, Memory stores rename + use case, 'Warp extracts',
and on-demand mid-conversation retrieval).
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): address all of Suraj's review comments
Addresses every inline comment from szgupta on PR #86:
- Comment 3263750377 (lines 5-6, description, 'cross-harness covers
it'): dropped the trailing 'that learns over time' clause from the
description.
- Comment 3263750945 (line 14, 's/Warp/Oz'): the platform that hosts
Agent Memory is Oz. Replaced Warp -> Oz in the intro and anywhere
else the page used Warp as the platform noun ('Where Agent Memory
runs', the Oz API bullet, 'Oz extracts...', 'Oz searches...'). Kept
Warp where it means the product (Warp Agent harness name, Warp
client, warp.dev URLs).
- Comment 3263752096 (line 14 reply, 'Gemini isn't officially supported
in Oz yet'): removed every Gemini mention from the page (description,
intro, Cross-harness bullet, 'Where Agent Memory runs' bullet).
- Comment 3263755700 (line 25, 'focus more on sharing'): replaced the
'Personal and team stores' Key features bullet with 'Agent-scoped,
shareable stores' that leads with default agent-scoping and
cross-agent sharing. The Memory stores section now also notes that
stores can be shared 'across teammates when knowledge should travel
with the team'.
- Comment 3263756525 (line 27, 'seems irrelevant?'): dropped the
Deletion safety Key features bullet entirely.
- Comment 3263761292 (line 20, suggested 5 new bullets): added Both
local and cloud agents, Fully accessible via API, Traceability,
Auditability, and Self-hostable to Key features.
- Comment 3263763038 (line 31, 'we should mention self-hosted'): the
'Where Agent Memory runs' section now says memory runs on the same
Oz instance that hosts your agents - Warp-hosted Oz by default, or
a customer-hosted Oz instance for teams that need to keep memory
inside their own perimeter. Paired with the new Self-hostable bullet
in Key features.
- Comment 3263765714 (line 35, '3P harnesses are Oz-cloud-only for
now'): scoped the third-party harnesses bullet to 'Third-party
harnesses running as Oz cloud agents' and added an explicit '(Running
third-party harnesses locally isn't supported during the research
preview.)' qualifier. Same scope is mirrored in the Cross-harness
Key features bullet.
- Comment 3263767235 (lines 52-53, replace Sparse/Learns with
'evolves+resolves contradictions'): replaced the two bullets with
a single 'Memories evolve over time' bullet that says agents update
and supersede their own memories as new information arrives,
including to resolve contradictions with prior memories.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): polish pass after review-comment rewrite
- Intro: separated the 'regardless of which harness' clause with an
em-dash so the second sentence parses more cleanly.
- 'Both local and cloud agents' bullet: 'Works for' -> 'Supports' for
a slightly more formal verb.
- Memory stores intro: replaced the em-dash construction with a comma
so the two sharing scopes (across agents, across teammates) read as
a single list, and tightened 'named container of memories' to
'named collection of memories'.
- Attaching memory paragraph: 'free-form instruction string' ->
'per-store instructions', matching the terminology already used in
the Key features bullet.
No factual changes.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): make self-hosted explicit + small polish
- 'Where Agent Memory runs' now calls out self-hosting by name:
'either Warp-hosted Oz (the default) or a self-hosted Oz instance
that your team operates inside its own perimeter', replacing the
previous 'customer-hosted Oz instance' phrasing.
- 'Automatic memory from conversations': 'from what happened' ->
'from the transcript'; 'during the run that produced it' ->
'during that run'.
- 'Attaching memory to your agents': 'Each attachment carries
per-store instructions' -> 'Each attachment includes per-store
instructions'; cleaned up the 'Without instructions' sentence to
'the agent can access the store but won't know when to read from
or write to it'.
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): cross-link self-hosting + Oz API, tighten store bullet
The page mentions self-hosting and the Oz API prominently in Key
features and 'Where Agent Memory runs', but those concepts weren't
linked to the dedicated reference pages. Add the links so readers
can follow up:
- Inline-link 'Oz API' in the 'Fully accessible via API' bullet to
/reference/api-and-sdk/.
- Inline-link 'self-hosted Oz' in both the 'Self-hostable' bullet
and the 'Where Agent Memory runs' paragraph to
/agent-platform/cloud-agents/self-hosting/.
- Inline-link 'Rules' and 'Codebase Context' in 'How agents use
memory' (and capitalize 'rules' to match the feature name).
- Add 'Self-hosting overview' and 'Oz API and SDK' to Related pages.
Also tightened the 'Agent-scoped, shareable stores' bullet so its
sharing phrasing varies slightly from the near-identical sentence in
the Memory stores section ('shared across multiple agents, or across
an entire team, when the same knowledge should travel with the
work').
Co-Authored-By: Oz <oz-agent@warp.dev>
* docs(agent-memory): final scan nits
- 'Attaching memory': 'Each attachment includes per-store instructions'
-> 'Each attachment can include per-store instructions'. Removes a
small logical contradiction with the very next sentence, which
treats instructions as optional ('Without instructions, the agent
can access the store but won't know when to read from or write to
it.').
- 'Team stores' bullet: replaced the coined adjective 'any
team-authorized agent' with 'any agent the team authorizes',
matching the active-voice phrasing used elsewhere on the page.
Co-Authored-By: Oz <oz-agent@warp.dev>
---------
Co-authored-by: Oz <oz-agent@warp.dev>
* docs(handoff): add local↔cloud handoff documentation Add a new handoff section under cloud-agents that documents the three directions of handoff supported by the orchestration launch: - Overview (conceptual) explaining what handoff is, the three directions, and what carries over. - Local→cloud (procedural) for promoting a local Warp Agent conversation to a cloud agent run. - Cloud→local (procedural) for picking up a cloud run inside the Warp terminal via /continue-locally and equivalent UI entrypoints. - Cloud→cloud (procedural) for follow-ups that span multiple executions of the same run. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): scrub internals, drop cloud-to-local, tighten copy Address PR review feedback and Slack-thread direction. - Drop cloud-to-local.mdx; existing fork-to-local docs in viewing-cloud-agent-runs.mdx already cover the capability. Overview now references that page for cloud-to-local. - Scope the snapshot rehydration mechanism in the overview to local-to-cloud and cloud-to-cloud only; cloud-to-local does not apply workspace patches. - Replace the inaccurate `git diff --binary HEAD` capture description in local-to-cloud with a high-level summary that covers tracked and untracked changes without committing to a specific git command. - Soften the local-to-cloud entry point: do not document a specific keyboard shortcut, add a note that the affordance may evolve during the Oz launch rollout. - Strip internal-only details from user-facing copy: GCS paths, manifest filenames, `git apply` mechanics, internal routing names (appended/injected/requeued), API endpoint paths, and rehydration checklist references. - Senior-writer pass: tighten descriptions to 50-160 chars, reduce marketing fluff, normalize cross-references. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): second editor pass to drop residual internal jargon - Replace 'execution' with 'session' across cloud-to-cloud.mdx so the user-facing unit of work stays 'the run', not the internal model. - Drop 'rehydrate'/'rehydration' in favor of 'restore'/'carry over'; fold the standalone 'Rehydration behavior' section into 'What carries over' in the overview. - Drop the 'server-side' qualifier on 'fork' throughout; users don't care where the fork happens. - Collapse the cloud-to-cloud 'How follow-ups route' state-machine into a single user-facing description; remove the two routing-paths items from troubleshooting since they describe normal behavior, not problems. - Collapse local-to-cloud's 'Verifying the handoff' debugging walkthrough into one sentence pointing readers to the management view. - Cut meta self-descriptions: 'The handoff entry point is integrated into the cloud agent launch flow...' and 'Cloud-to-cloud handoff is automatic...'. - Drop the rollout caveat note on local-to-cloud. - Reduce 'sandbox' references where they leak infrastructure. Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): trim overview description to fit 50-160 char range Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): address audit findings - cloud-to-cloud.mdx: soften per-session timeline claim to API-only (UI render not present) - cloud-to-cloud.mdx: gloss 'ambient agent task' inline for clarity - local-to-cloud.mdx: switch primary credits link to credits page; fix link text casing for access page Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): address Safia's review feedback - index.mdx: drop launch-anchored framing; reframe Directions list as evergreen capability statement; add third-party-harness coverage subsection (cloud<->cloud works on 3P with Continue+input prompt; local->cloud is Warp Agent only). - local-to-cloud.mdx: replace /cloud-agent entry-point claim with the '&' shortcut and the '/handoff' slash command; add note that the model can't be changed during handoff. - cloud-to-cloud.mdx: consolidate duplicate scheduled/integration bullets; add 'same Git branch' detail to workspace-state carryover; add :::caution that handoff requires a prior-execution snapshot; note that local->cloud-originated runs can only be continued by the creating user; scope send-follow-up to the Warp app and drop the Oz-web-app/integration follow-up sections; add third-party harness Continue-button flow; soften per-execution timeline claim (transcript is the source of truth, not the API). Co-Authored-By: Oz <oz-agent@warp.dev> * Update src/content/docs/agent-platform/cloud-agents/handoff/cloud-to-cloud.mdx Co-authored-by: Rachael Rose Renk <91027132+rachaelrenk@users.noreply.github.com> * docs(handoff): apply Rachael's review suggestions and final copy polish Apply all 9 of @rachaelrenk's suggested edits on PR #85 and run a final senior-copywriter pass for consistency across the three handoff pages. index.mdx - Intro: "your local Warp terminal" -> "a local Warp session" so the intro talks about a session rather than the terminal application. - "Third-party harness coverage" -> "Third-party agent runtime coverage"; same swap in the two bullets underneath. "Harness" is internal vocabulary; "agent runtime" is the user-facing term. - "spiraled into work" -> "grown into work" (less idiomatic). - "Managing Cloud Agents" -> "Managing cloud agents" in Related pages to match the sentence-case nav style used elsewhere. - Consistency polish: "Fork a cloud conversation into your local terminal" -> "into a local Warp session" so the cloud-to-local bullet uses the same terminology as the rewritten intro. local-to-cloud.mdx - Intro: "Hand off a conversation from the Warp terminal" -> "Hand off a local Warp conversation" (same reason as above). - "This direction is the right move when:" -> "Use this handoff direction when:" (less conversational, matches docs voice). - Post-handoff pointer: linked the management view doc -> deep-linked the [Runs page](https://oz.warp.dev/runs) in the Oz web app, which matches the pattern added in PR #84. - "Cloud Agents quickstart" -> "Cloud agents quickstart" (sentence case). cloud-to-cloud.mdx (consistency polish, same patterns Rachael called out in the other two pages) - "This direction is the right move when:" -> "Use this handoff direction when:". - Step 1 of "Sending a follow-up": linked the management view doc -> deep-linked the Runs page in the Oz web app. - Removed a stray duplicate `### Third-party harnesses` heading that was sitting directly above the correct `### Third-party agent runtimes` heading, and inserted a missing blank line before the next `## Inspecting a run that's been handed off` section. - "Managing Cloud Agents" -> "Managing cloud agents" in Related pages. Validation - python3 .agents/skills/style_lint/style_lint.py --changed -> 0 issues. - python3 .agents/skills/check_for_broken_links/check_links.py --internal-only -> 0 broken links (2,439 internal links across 321 files). Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): second copy polish pass on handoff pages A senior-copywriter follow-up on commit b45a4e8. Focuses on terminology consistency, list parallelism, active voice, and a few style-guide nits caught on the second read. index.mdx - Frontmatter description: "Move an agent conversation between your terminal and the cloud" -> "Move agent work between a local Warp session and the cloud" so the description matches the body intro (which Rachael's review moved to "local Warp session" terminology). - "Directions of handoff" Local-to-cloud bullet: "more compute, longer-running work, or to fan out variants in parallel" -> "more compute, longer-running work, or parallel variants of the same task". Now all three list items are parallel noun phrases. - "Workspace state" bullet: "The cloud-to-local direction does not currently apply" -> "doesn't currently apply" (contractions are encouraged in the style guide for an approachable tone). local-to-cloud.mdx - "Use this handoff direction when:" list: first bullet started with "The task is going to run for a long time..." while the other three start with "You want...". Rewrote it to "You have a long-running task and don't want to keep your laptop awake." so all four bullets open the same way. - Step 1: "trigger handoff with the `&` shortcut or the `/handoff` slash command" -> "press `&` or run the `/handoff` slash command". Direct verbs match the style guide pattern for keyboard / slash commands. - Step 2: "Pick the environment whose..." -> "Pick the one whose..." (avoids repeating "environment" right after the bold header). "create one first and add" -> "create one and add" ("first" was doing no work). - Post-steps prose: "After submission, the cloud agent applies your workspace snapshot" -> "After you submit, the cloud agent...". Active voice; readers don't talk about "submission." - Troubleshooting (uncommitted changes): "Without it, the conversation can't be forked" -> "Otherwise, the conversation can't be forked". "Without it" had a fuzzy antecedent; "Otherwise" reads cleanly off the preceding sentence. cloud-to-cloud.mdx - "Use this handoff direction when:" list: first bullet "A cloud agent finished and you want to send a follow-up after the session has ended." -> "You want to send a follow-up to a cloud agent after its session has ended." Now parallel with the second bullet ("You want to continue an ambient agent run..."). - Cleaned up three lingering uses of "execution" that the earlier internals scrub missed. All three were re-introduced when applying Safia's audit-fix feedback in e4bdd4b. Replaced with "session": - "the new execution runs on the same Git branch as the prior session" -> "the new session continues on the same Git branch" (avoids both the internal term and the "new ... prior" cycle). - ":::caution Cloud-to-cloud handoff relies on a snapshot from the prior execution" -> "...the prior session". - "Click into the run to see the full transcript: each execution appears in order, and you can scan the transcript to see where one execution ended and the next began. Per-execution timestamps aren't currently exposed in the API..." -> all three "execution"s -> "session" / "Per-session". - "What carries over" trailing sentence: "...proceeds with what it could before continuing to your follow-up." -> "...rather than starting over silently." Now parallel with the same sentence on the other two handoff pages. - "Sending a follow-up" lead-in: dropped the orphan third sentence ("Send-follow-up support is available in the Warp app.") and folded it into the first: "you send a follow-up from the Warp app, and the run continues." - Step 2: "Type the next message into the conversation's input" -> "Enter the next message in the conversation's input" ("Enter" is the style guide's verb for text fields). - Troubleshooting (old runs): "Start a new cloud agent run with the prompt you want and reference the prior run in the prompt if needed." -> "Start a new cloud agent run with the prompt you want, referencing the prior run if needed." (drops the "prompt" repetition). Final grep over the handoff folder for "execution", "harness", "spiraled", "right move", "Cloud Agents", "Warp terminal" -> zero hits. Validation - python3 .agents/skills/style_lint/style_lint.py --changed -> 0 issues. - python3 .agents/skills/check_for_broken_links/check_links.py --internal-only -> 0 broken links (2,439 internal links across 321 files). Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): address two missed Rachael comments on cloud-to-cloud I missed two of @rachaelrenk's review comments on the cloud-to-cloud page in earlier passes because they weren't returned by the first `gh pr view` query. Applying them now. cloud-to-cloud.mdx - "ambient agent run" -> "background cloud agent run". Rachael flagged "ambient agent run" as abstract/internal-feeling; "background cloud agent run" keeps the example concrete and matches the user-facing framing on the surrounding pages. Per her suggested edit verbatim. - Removed `blocked` from the example list of terminal states. The API treats BLOCKED as terminal for cancellation purposes, but the spec describes it as "awaiting user input or approval" — so it isn't a natural place to send a follow-up via cloud-to-cloud handoff (responding to the prompt on the original run is the right path). Added a sentence to the prereq calling that out explicitly so readers don't try to hand off a blocked run. Validation - python3 .agents/skills/style_lint/style_lint.py --changed -> 0 issues. - python3 .agents/skills/check_for_broken_links/check_links.py --internal-only -> 0 broken (2,439 internal links, 321 files). Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): audit polish for cloud-to-cloud prereqs Two small consistency fixes caught on a third audit round: - L29 "An ended cloud agent run" prereq: "Blocked runs ... aren't continued through cloud-to-cloud handoff" -> "...can't be continued via cloud-to-cloud handoff". Makes the carve-out parallel with the very next sentence ("Very old runs ... can't be continued via handoff"), and reads more directly than "aren't continued through". - L30 "A snapshot from the prior session" prereq: "the run still continues -- it just starts without restored workspace state" -> "the run still continues, just without restored workspace state". The em dash + "it just starts" was colloquial and a bit redundant ("continues" and "starts" describe the same event); the comma-led adjective phrase is cleaner. Validation - python3 .agents/skills/style_lint/style_lint.py --changed -> 0 issues. - python3 .agents/skills/check_for_broken_links/check_links.py --internal-only -> 0 broken (2,439 internal links, 321 files). Co-Authored-By: Oz <oz-agent@warp.dev> * docs(handoff): add Handoff sidebar group + drop tombstone wording The "cross-cutting sidebar PR" that the original PR description referred to doesn't exist — none of the orchestration-launch content is currently registered in `src/sidebar.ts`. PR #84 (multi-agent) doesn't touch the sidebar either; only PR #86 (memory) adds its own entries. Following that pattern: register the three handoff pages here so they actually appear in the docs sidebar when this branch merges. src/sidebar.ts - Added a new "Handoff" collapsible group inside the "Oz Cloud Agents & Orchestration" topic, slotted right after "Viewing cloud agent runs" since that's the closest thematic neighbor (it covers `Continue locally` / `/continue-locally`, the cloud-to-local path). The group contains: - Overview -> agent-platform/cloud-agents/handoff - Local to cloud -> agent-platform/cloud-agents/handoff/local-to-cloud - Cloud to cloud -> agent-platform/cloud-agents/handoff/cloud-to-cloud Mirrors the existing collapsible-group shape used by Triggers, Integrations, and Self-hosting in the same section. src/content/docs/agent-platform/cloud-agents/handoff/cloud-to-cloud.mdx - "(from the conversation details panel or the end-of-run tombstone)" -> "(from the conversation details panel or the artifacts shown after the run)". "Tombstone" is the internal code-level term for the post-run view (`shared_session/conversation_ended_tombstone_view.rs`). Even though it shows up in telemetry-event descriptions in `privacy.mdx`, it's not natural user-facing copy. Switched to a plainer reference to the artifacts surfaced after the run. Validation - python3 .agents/skills/style_lint/style_lint.py --changed -> 0 issues on the files this PR touches. (The pre-existing pricing-faqs.mdx warnings are out of scope.) - python3 .agents/skills/check_for_broken_links/check_links.py --internal-only -> 0 broken (2,440 links, 322 files). - `npm run build` fails on an UNRELATED orphan page (`agent-platform/cloud-agents/agents.mdx` is not registered in the sidebar). That page was added earlier on this branch by a different PR and is pre-existing breakage on `hyc/orch/handoff` — my edits don't touch it. Co-Authored-By: Oz <oz-agent@warp.dev> --------- Co-authored-by: Oz <oz-agent@warp.dev> Co-authored-by: Rachael Rose Renk <91027132+rachaelrenk@users.noreply.github.com>
…ries (#101) * Audit pass 3: Memory + Handoff polish, cross-references, glossary entries Final audit pass over hyc/orchestration-launch ahead of the rollout PR. Covers the deltas from #86 (Agent Memory research preview) and #85 (local\u2194cloud handoff) that landed after audit pass 2. Sentence case / Title Case: - capabilities/skills.mdx:414: '## Suggested Skills from Agent Memory' -> '## Suggested skills from Agent Memory'. The section body uses lowercase 'skill drafts', so the heading should match. Also clears the one new style_lint warning introduced by #86. Stale config: - agent-platform/agent-memory/index.mdx: drop '(Research Preview)' from the frontmatter sidebar.label. sidebar.ts already overrides the label to 'Agent Memory' under a group named 'Memory (Research Preview)'; the duplicate annotation was dead config. Cross-link gaps from neighboring pages: - cloud-agents/viewing-cloud-agent-runs.mdx (the '5. Fork the session to your local Warp' section): add a one-line reference to the new Handoff overview, so the cloud-to-local direction is discoverable from the broader handoff doc. - cloud-agents/managing-cloud-agents.mdx: add a Related pages section that links to the Handoff overview and the other neighbors that weren't surfaced before. - local-agents/cloud-conversations.mdx (Related features): add a link to the Handoff overview, since handoff relies on cloud-synced conversations. Style: - cloud-agents/handoff/index.mdx:30: drop 'just' from 'not just read about it' -> 'not only read about it'. Same ableist-language pattern audit pass 2 cleaned up elsewhere. Glossary additions: - .agents/references/terminology.md (Agent concepts) + AGENTS.md (Core features): add canonical entries for 'Agent Memory', 'memory store', and 'Handoff' so the launch terms ship with documented capitalization rules ('Agent Memory' Title Case as a feature; 'memory store' lowercase common noun; 'Handoff' Title Case as the feature, lowercase 'hand off' / 'handed off' as the verb). Validation: - check_links --internal-only: 0 broken across 2,543 internal links (up 6 from the 2,537 baseline, matching the 6 new cross-refs). - style_lint --changed: 14 warnings (one fewer than baseline; the skills.mdx Title Case heading is no longer flagged). The remaining warnings are all pre-existing proper-name false positives. - npm run build: 330 pages built; sidebar still resolves all slugs; new anchor reference (#5-fork-the-session-to-your-local-warp) resolves. Co-Authored-By: Oz <oz-agent@warp.dev> * Restore (Research Preview) suffix in agent-memory sidebar.label Revert the sidebar.label change from the audit pass. Keeping the research-preview annotation in the frontmatter as a defensive fallback in case the sidebar.ts override is ever removed. Co-Authored-By: Oz <oz-agent@warp.dev> --------- Co-authored-by: Oz <oz-agent@warp.dev>
…ew (#102) Brings 121 files of main back into the orchestration-launch rollout branch, resolves two conflicts, reconciles terminology drift introduced on both sides, and addresses both rounds of Oz review feedback (#98 + #102). ## Conflict resolution * .agents/skills/style_lint/style_lint.py - PROPER_FEATURE_NAMES: combined main's 'Cloud Agents' rename (replacing 'Ambient Agents') with orchestration-launch's removal of 'Cloud Agent Credits' (split into 'compute credits' + 'cloud agent credits' as common nouns). * enterprise/.../billing.mdx: kept orchestration-launch's three-bucket framing but dropped the 'Oz ' prefix. ## Terminology drift fixups Aligned with main's new OZ_TERMS_TO_AVOID patterns: * agent-memory/index.mdx (4x), harnesses/index.mdx, cloud-agents/agents.mdx, platform-credits.mdx - 'Oz cloud agents' / 'Oz agent' → 'cloud agents' / 'agent' * deployment-patterns.mdx (2x) - wrapped 'oz agent run-cloud' CLI references in backticks * slack.mdx, federate.mdx - same drift fixups * agents-in-warp.mdx intro - 'Warp includes Oz agents' → 'Warp's agents' ## PR #98 review feedback * Remove Gemini reference from platform-credits.mdx * Resolve default-identity vs Quick run contradiction in cloud-agents/agents.mdx * Kept 'AI credits' in glossary (per user direction) * OpenAPI/Scalar sync deferred to a fast-follow PR ## PR #102 review feedback * IMPORTANT: agents-in-warp.mdx intro paragraph - deprecated 'Oz agents' terminology rewritten to 'Warp's agents' / 'They' * SUGGESTION: cloud-providers.mdx GCP federation caution - 'any agent' → 'any cloud agent' (scoped to OIDC-capable cloud agents) Validation: 0 broken links / 2539 internal, 14 baseline HEADER-CASE warnings only (plan-name false positives), 330 pages built. Co-Authored-By: Oz <oz-agent@warp.dev>
PR #102 squash-merged main's content into hyc/orchestration-launch but the squash discarded the merge commit, so git no longer sees main as an ancestor. This makes PR #98 (hyc/orchestration-launch -> main) show spurious conflicts even though the content is already consistent. This commit uses '-s ours' to record main as merged WITHOUT changing any file content. The tree on hyc/orchestration-launch is unchanged (verified before and after); only the commit graph gets a second parent pointing at origin/main so PR #98 can merge cleanly. Co-Authored-By: Oz <oz-agent@warp.dev>
Memory was sitting in the #2 slot, right after 'Getting started' and above 'Warp Agents'. Reorder so the research-preview section sits at the bottom of the Agents tab (after 'Oz Cloud Agents & Orchestration'), matching the visual hierarchy of stable → preview content. Co-authored-by: Oz <oz-agent@warp.dev>
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.
Rolls up the orchestration-launch documentation drop. Combines three feature additions (#83, #87, #88) plus the pre-rollout audit pass (#97). 31 files changed (+735 / \u221250).
What's new
Platform Credits and the three-bucket credit model (#83)
support-and-community/plans-and-billing/platform-credits.mdxdocuments platform credits \u2014 the bucket that covers Warp's platform layer (run lifecycle, integrations, dashboard, APIs, observability) for every cloud agent run plus local runs on Business / Enterprise plans with customer-supplied inference.credits.mdxreframed around the three-bucket model: AI credits (inference), compute credits (the sandbox), and platform credits (orchestration). Compute credits get their own canonical section and#compute-creditsanchor;cloud agent creditsis documented as the host-context alias for the same bucket.AGENTS.md,.agents/references/terminology.md) updated forcompute credits,cloud agent credits,platform credits(all common nouns \u2014 lowercase except at the start of a sentence/bullet/heading), plusWarp creditsreplacing the ambiguous "plan credits."style_lint.pyremoves Title-CaseCloud Agent Credits/Platform CreditsfromPROPER_FEATURE_NAMESand adds nudges to lowercase.add-on-credits.mdx,pricing-faqs.mdx,plans-pricing-refunds.mdx,bring-your-own-api-key.mdx,enterprise/.../billing.mdx,cloud-agents/overview.mdx,team-access-billing-and-identity.mdx,integrations/{slack,linear}.mdx,quickstart.mdxall reframed against the new buckets and casing.Multi-harness cloud agents (#87)
agent-platform/cloud-agents/harnesses/:index.mdx\u2014 overview of choosing a harness; what stays the same across harnesses; how to switch from the Warp app, Oz web app, or API.warp-agent.mdx\u2014 default Oz harness; the only one that can orchestrate cross-harness subagents.claude-code.mdx\u2014 Anthropic's Claude Code as a cloud harness, model picker, credentials, run flow.codex.mdx\u2014 OpenAI's Codex as a cloud harness, model picker, credentials, run flow.authentication.mdx\u2014 storing Anthropic/OpenAI credentials as Warp-managed secrets, including CLI and UI flows, plus troubleshooting.cli-agents/{claude-code,codex,overview}.mdxget cross-reference notes pointing readers at the new cloud-harness pages.Agent identities (#88)
agent-platform/cloud-agents/agents.mdxdocuments agent identities (team-scoped bot accounts that own and execute cloud agent runs), the alias relationship withservice_account:principals, the public CRUD API, key binding, and how identities surface in the Oz web app.secrets.mdxandoz-web-app.mdxexpanded to cover attaching secrets to an agent identity, the Agents page in the web UI (including new-skill / new-agent-identity flows), and run-level / environment-level secret scoping.deployment-patterns.mdxswaps "service account (recommended for automation)" for the new agent-identity link.reference/cli/federate.mdxandreference/cli/index.mdxnote thatservice_account:principals are agent identities on your team.Audit pass (#97)
src/sidebar.ts: wires the new content into the topic tree.external-authentication-required.mdx: replaces the stale(service account)parenthetical with a link to the agent identities page.cloud-agents/overview.mdxLearn more picks up the new Harnesses and Agent identities pages.Validation
check_links --internal-only: 0 broken across 2,495 internal links.style_lint --changed: 14 warnings, all pre-existing proper-name false positives (Build / Business / Pro / Turbo / Lightspeed / Add-on Credits / BYOK / Slack & Linear integration headings). None introduced by this drop.npm run build: succeeds.Out of scope
Three feature branches still have open PRs into
hyc/orchestration-launchand intentionally do not land in this rollout: #84 multi-agent orchestration, #85 local\u2194cloud handoff, #86 Agent Memory research-preview.Co-Authored-By: Oz oz-agent@warp.dev