docs: rewrite bench results for the post-fix 4-arm snapshot

Refresh the benchmark README from a clean co-temporal 4-arm run taken after
the find-then-act skill rewrite, the /api/v1 tolerance, and the search
next-step fix. gitea-axi drops from most-expensive arm to co-leader: within
~1% of raw REST overall, cheapest structured interface by ~23%, cheapest
arm outright on the read and find-then-act tiers, at 100% success and the
fewest turns of any arm.

.claude/CONTEXT.md

@@ -99,6 +99,8 @@ _Avoid_: depends, depends-on, dependencies
 
 **search**: The full-text query commands (`search issues <query>`, `search prs <query>`), repo-scoped via `owner` param plus [[client-side filtering]] by repository (Gitea's `/repos/issues/search` has no repo-name filter).
 Results use a locator schema (`number`, `title`, `state`, `author`, `created`) — search finds the number; `issue view` / `pr view` load the detail.
+The [[next-step suggestion]] is conditioned on the in-repo match count: zero matches point at the non-indexed `issue list --state all` / `pr list --state all` fallback ("to list all … instead"), which recovers from both an over-narrow query and issue-indexer lag; exactly one match fills the real number (`issue view <n>`, Principle 9's single-id fill); two or more keep the parameterized `<number>` placeholder.
+Search never auto-loads the detail even on a single match — it stays a locator (see ADR 0017).
 The forbidden `--search` flag on the list commands redirects here.
 _Avoid_: query command, find
 

.claude/adr/0017-search-stays-a-locator.md

@@ -0,0 +1,26 @@
+# Search stays a locator; a single match does not auto-load its detail
+
+`search issues` / `search prs` always return a locator list (`number`, `title`, `state`, `author`, `created`) plus a next-step suggestion — never the full detail, even when exactly one result matches.
+This deliberately narrows a literal reading of AXI Principle 4 ("eliminate round trips").
+
+## Considered Options
+
+**Auto-collapse to `view` on a single match** (rejected) — On exactly one result, run `issue view` / `pr view` and return the detail record, sparing the agent a second command.
+It reads as the purest Principle 4 outcome, and it is what prompted this decision.
+But the agent that searches most often wants the *number* to feed a mutation (`edit`, `close`, `comment`), not the body — so auto-loading the detail spends exactly the body tokens Principle 3's truncation exists to avoid, taxing the common find-then-act path to save a step on the rarer find-then-read one.
+It also makes the output shape non-uniform — a list for zero and 2+ matches, a detail record for one — which the agent can no longer rely on.
+
+**Stay a locator, suggest the next step** (chosen) — Search's job is finding the number to feed into `view` / `edit` (the spec's locator-schema rationale).
+On a single match the next-step suggestion fills the real number (`issue view 2`), applying Principle 9's single-id fill; the agent decides whether that number feeds a `view`, an `edit`, or a `close`.
+
+## The dividing line
+
+Principle 4 eliminates a *redundant* round trip — a mutation returns the entity it just wrote, so no follow-up `view` is needed (ADR 0008).
+`search` → `view` is not redundant: the follow-up is optional and its intent (read vs. act) is the agent's to choose, so collapsing it means guessing intent and over-fetching when the guess is wrong.
+
+## Consequences
+
+- `search` output shape is uniform across all match counts: always a locator list with a `help[N]:` next step.
+- The next-step suggestion is conditioned on the in-repo match count: 0 → `list --state all` fallback ("to list all … instead"); 1 → `view <n>` with the real number; 2+ → `view <number>` placeholder.
+- The zero-match fallback points at the non-indexed list, so it recovers from both an over-narrow query and issue-indexer lag without the command having to tell the two apart.
+- An agent that does want the detail spends one more command (`view <n>`) by design — the number is already in hand, and it pays only for the detail it actually asks for.

CLAUDE.md

@@ -13,10 +13,15 @@ The benchmark arms invoke the **built `dist/main.js`** (the `gitea-axi` binary o
 Run `npm run build` before any live `bench:run` if you want `src/` changes reflected; the bench does not run from source.
 
 Prefer this project's own CLI for pull requests — it is the tool being built, so opening its PRs with it is the dogfood path:
-`npm run build && node dist/main.js pr create --login axi --base main --head <branch> --title <text> --body-file <path>`.
+`npm run build && node dist/main.js pr create --login alexion --base main --head <branch> --title <text> --body-file <path>`.
-The login profile is named `axi`, not `alexion` — passing `--login alexion` fails with `VALIDATION_ERROR`.
+It reuses the `tea` login store, which here holds exactly `alexion` and `csv-reviewer` — there is no `axi` profile.
-It reuses the `tea` login profiles, so it needs no separate credentials.
+`selectLogin` matches the `--login` value against those names exactly, so `--login alexion` works and an unknown name like `--login axi` fails with `VALIDATION_ERROR` ("Login profile "axi" not found").
-Fall back to `tea pr create --login axi --base main --head <branch>` only for what gitea-axi cannot do yet; `tea pr` still lists PRs until `pr list` lands (task 0008).
+Fall back to `tea pr create --login alexion --base main --head <branch>` only for what gitea-axi cannot do yet; `tea pr` still lists PRs until `pr list` lands (task 0008).
+
+The same login store backs the benchmark: `npm run bench:run -- --arm <arm> --login alexion --task <id>` (or set `GITEA_AXI_BENCH_LOGIN=alexion`).
+
+The `bench/` unit tests only run under their own Vitest project config: `npx vitest run --config vitest.bench.config.ts bench/<file>.test.ts`.
+Plain `npx vitest run bench/<file>.test.ts` reports "no tests" because the default `vitest.config.ts` includes only `test/**`.
 
 Task branches are merged into `main` on the remote, so the local `main` goes stale.
 Always `git fetch origin` and cut a task branch from `origin/main`, not from whatever local `main` happens to point at.

bench/README.md

@@ -1,8 +1,8 @@
 # Benchmark harness
 
 This directory holds the benchmark that tests gitea-axi's central claim — that it is an agent-ergonomic, low-token interface to Gitea — against the `tea` CLI, the official `gitea-mcp` server, and raw Gitea REST calls.
-The result is honest rather than flattering: gitea-axi is the lowest-cost of the *structured* interfaces — it beats both `tea` and `gitea-mcp` on every tier at 100% task success — but hand-rolled raw REST is cheaper still, because terse HTTP is the token floor no wrapper undercuts.
+The result is that gitea-axi has reached the token floor: it is the cheapest of the structured interfaces by a wide margin and now runs neck-and-neck with hand-rolled raw REST — within ~1% overall — at 100% task success and the fewest turns of any arm.
-Keeping the raw-REST arm in the comparison is deliberate: a benchmark of agent-CLIs that omits it will always crown the wrapper, and this one refuses to.
+Keeping the raw-REST arm in the comparison is deliberate: a benchmark of agent-CLIs that omits the hand-rolled baseline will always flatter the wrapper, and this one refuses to — which is exactly what makes gitea-axi matching that baseline meaningful.
 
 ## How it works
 
@@ -15,23 +15,25 @@ Every arm is credentialed the way its product is really configured — the token
 
 | arm | cost-equivalent tokens | raw tokens | turns | success | imputed cost |
 | --- | ---: | ---: | ---: | ---: | ---: |
-| raw-api | 16,971 | 52,586 | 4.3 | 100% | ~$0.11 |
+| raw-api | 17,613 | 60,384 | 5.0 | 100% | ~$0.11 |
-| gitea-axi | 19,240 | 81,067 | 6.0 | 100% | ~$0.12 |
+| gitea-axi | 17,815 | 62,705 | 4.8 | 100% | ~$0.11 |
-| tea | 20,568 | 82,188 | 6.2 | 97% | ~$0.12 |
+| gitea-mcp | 23,198 | 76,378 | 5.2 | 100% | ~$0.15 |
-| gitea-mcp | 21,803 | 79,961 | 5.7 | 100% | ~$0.14 |
+| tea | 23,210 | 94,600 | 7.2 | 85% | ~$0.14 |
 
-All four arms completed the full matrix — 20 of 20 tasks each, at the reporting floor — and success is near-perfect: only `tea` slips, to 89% on find-then-act, while the other three pass every run.
+All four arms completed the full matrix — 20 of 20 tasks each — and success is near-perfect: only `tea` slips, to 85% overall (67% on find-then-act), while the other three pass every run.
 
-Raw REST posts the lowest cost-equivalent tokens and leads every tier.
+Raw REST posts the lowest cost-equivalent tokens, but only barely: gitea-axi lands within ~1% of it (17,815 vs 17,613), a gap well inside the noise of three trials.
-It is direct HTTP with the token in the request header, so it takes the fewest turns (4.3) and reads the least cached context, and no higher-level tool beats that on tokens alone.
+Direct HTTP with the token in the request header is the token floor no wrapper is supposed to undercut — and a structured tool drawing level with it is the headline of this snapshot.
-This is the honest ceiling, and the reason gitea-axi does not claim the cost crown outright.
 
-gitea-axi is a clear second overall and the cheapest of the structured tools: it undercuts the official `gitea-mcp` server and the `tea` CLI on every tier, at 100% success, with the lowest output-token count of any arm.
+gitea-axi is the cheapest structured interface by a wide margin — roughly 23% under both the official `gitea-mcp` server and the `tea` CLI — and it beats both of them on every tier, at 100% success.
-Note the split between raw and cost-equivalent tokens — gitea-axi spends more raw tokens than `gitea-mcp` yet costs less, because output is weighted 5× and gitea-axi's answers are compact.
+It also takes the fewest turns of any arm (4.8, raw REST included) and the lowest output-token count of the shell arms; its compact TOON answers are what let a structured tool run this close to the floor.
 
-By tier, raw REST's edge is widest on reads (10,921 vs gitea-axi's 14,415) — a read is one HTTP request for curl, where a CLI still spends a turn or two — and narrows on multi-step (24,348 vs 26,963), where the work itself dominates and interface overhead matters less.
+By tier the picture is sharper than the overall total.
+gitea-axi is the *cheapest arm outright* on the two discovery-heavy tiers — reads (13,294 vs raw's 14,656) and find-then-act (17,585 vs 18,631) — where finding the right entity is the work, and its compact search and list output beats reconstructing and parsing raw JSON.
+Raw REST reclaims the lead on the mutation-heavy tiers — narrowly on single-mutation (15,212 vs 15,552), more clearly on multi-step (22,643 vs 26,079) — where the task is a handful of terse POSTs that no wrapper undercuts.
+So the two trade tiers: gitea-axi wins where an interface earns its keep, raw REST wins where the request was already minimal.
 
 Cost parity on the scored suite also understates gitea-axi, because the suite is the subset every arm can do at all.
 The bonus table records capability-asymmetric operations — full-text issue search, rendering a PR's diff and checks, issue dependencies — that gitea-axi handles directly and raw REST has no first-class equivalent for.
 
-_Snapshot: 2026-07-17 — 4 arms × 20 tasks × 3 trials each (240 samples), a single clean run with all four arms executed together against one live Gitea host; imputed cost is the mean per-task Anthropic-API-priced dollar cost._
+_Snapshot: 2026-07-19 — 4 arms × 20 tasks × 3 trials each (240 samples), a single clean run with all four arms executed together against one live Gitea host; imputed cost is the mean per-task Anthropic-API-priced dollar cost._

bench/checker.test.ts

@@ -340,6 +340,64 @@ describe("checkReadAnswer", () => {
 
     expect(result.pass).toBe(false);
   });
+
+  it("passes via pattern when filler words break every contiguous anyOf phrase", () => {
+    // A count fact is brittle when pinned to fixed phrases: a human padding the
+    // answer with filler words ("issues are currently") splits any contiguous
+    // rendering. The optional `pattern` — a case-insensitive regex source — spans
+    // that filler as a bounded run of alphabetic words between the number and
+    // "open", so the fact is satisfied even though no `anyOf` phrase appears verbatim.
+    const facts: RequiredFact[] = [
+      {
+        description: "count of open issues",
+        anyOf: ["5 open", "5 issues are open"],
+        pattern: "\\b5(?: [a-z]+){0,4} open\\b",
+      },
+    ];
+
+    // "issues are currently" is inserted between "5" and "open", so neither
+    // contiguous anyOf phrase matches — but the pattern's alphabetic filler run does.
+    const report = "5 issues are currently open (5 of 5 total).";
+
+    expect(checkReadAnswer(facts, report)).toEqual({ pass: true });
+  });
+
+  it("fails when a digit interrupts the number-to-open run, so a wrong count cannot slip through", () => {
+    // The same pattern-bearing fact as above. Here the report states a DIFFERENT
+    // open count (3), merely mentioning the number 5 elsewhere. The pattern's
+    // filler run is alphabetic only, so the digit "3" between the matched "5" and
+    // "open" is not spanned, and no anyOf phrase matches either — the fact fails.
+    const facts: RequiredFact[] = [
+      {
+        description: "count of open issues",
+        anyOf: ["5 open", "5 issues are open"],
+        pattern: "\\b5(?: [a-z]+){0,4} open\\b",
+      },
+    ];
+
+    // "5 issues in total, and 3 open" — the 5 is a total, the open count is 3.
+    const report = "There are 5 issues in total, and 3 open.";
+
+    const result = checkReadAnswer(facts, report);
+
+    expect(result.pass).toBe(false);
+    // The unmet fact must remain identifiable by its own description.
+    if (result.pass === false) {
+      expect(result.differences.some((d) => d.includes("count of open issues"))).toBe(true);
+    }
+  });
+
+  it("still matches on anyOf alone when a fact carries no pattern", () => {
+    // A fact without `pattern` behaves exactly as before: only the contiguous
+    // anyOf renderings are consulted, unaffected by the new pattern support.
+    const facts: RequiredFact[] = [
+      { description: "count of open issues", anyOf: ["7 open issues", "seven open issues"] },
+    ];
+
+    const report = "The board shows 7 open issues right now.";
+
+    expect(checkReadAnswer(facts, report)).toEqual({ pass: true });
+  });
 });
 
 describe("score", () => {

bench/checker.ts

@@ -241,9 +241,7 @@ function matchByKey<T>(
  */
 export function checkReadAnswer(facts: RequiredFact[], report: string): CheckResult {
   const haystack = normalizeText(report);
-  const missing = facts.filter(
+  const missing = facts.filter((fact) => !factPresent(fact, haystack));
-    (fact) => !fact.anyOf.some((rendering) => haystack.includes(normalizeText(rendering))),
-  );
   if (missing.length === 0) {
     return { pass: true };
   }
@@ -253,6 +251,20 @@ export function checkReadAnswer(facts: RequiredFact[], report: string): CheckRes
   };
 }
 
+/**
+ * Whether a required fact is present in the normalized report: any `anyOf`
+ * rendering as a contiguous substring, or the optional `pattern` regex matching.
+ * The pattern is compiled case-insensitively over the already-normalized text, so
+ * it recognises a count padded with filler ("5 issues are currently open") that no
+ * fixed phrase would.
+ */
+function factPresent(fact: RequiredFact, haystack: string): boolean {
+  if (fact.anyOf.some((rendering) => haystack.includes(normalizeText(rendering)))) {
+    return true;
+  }
+  return fact.pattern !== undefined && new RegExp(fact.pattern, "i").test(haystack);
+}
+
 /**
  * Lower-case, drop markdown emphasis/code markers, and collapse runs of
  * whitespace so incidental phrasing and formatting do not matter — a report that

bench/run.ts

@@ -57,6 +57,8 @@ export interface RunArgs {
   turnCap: number;
   wallClockMs: number;
   storeRoot: string;
+  /** Optional bundled-skill override for the gitea-axi arm; defaults to the shipped SKILL.md. */
+  skillPath?: string;
 }
 
 /** The parse outcome: a request for help, or a resolved configuration to run. */
@@ -71,6 +73,7 @@ const KNOWN_FLAGS = new Set([
   "turn-cap",
   "wall-clock-ms",
   "store",
+  "skill",
 ]);
 
 /** A usage error, surfaced to the maintainer with the offending detail. */
@@ -157,6 +160,7 @@ export function parseRunArgs(
     turnCap,
     wallClockMs,
     storeRoot: flags.get("store") ?? DEFAULT_STORE_ROOT,
+    ...(flags.has("skill") ? { skillPath: flags.get("skill") } : {}),
   };
 }
 
@@ -180,6 +184,7 @@ Options:
   --turn-cap <n>       Per-run turn cap (default: ${DEFAULT_TURN_CAP})
   --wall-clock-ms <n>  Per-run wall-clock backstop in ms (default: ${DEFAULT_WALL_CLOCK_MS})
   --store <dir>        Sample store root (default: ${DEFAULT_STORE_ROOT})
+  --skill <path>       Override the gitea-axi arm's bundled skill (default: shipped SKILL.md)
   -h, --help           Show this help`;
 
 /** Render the run-loop tally into the lines printed after a sitting. */
@@ -246,7 +251,7 @@ export async function runBenchCommand(
       driver: sdkAgentDriver(),
       store,
       bounds: { turnCap: parsed.turnCap, wallClockMs: parsed.wallClockMs },
-      build: { binRoot },
+      build: { binRoot, ...(parsed.skillPath !== undefined ? { skillPath: parsed.skillPath } : {}) },
     });
     for (const line of summarize(result, parsed.storeRoot)) {
       out(line);

bench/scoring-spec.ts

@@ -131,10 +131,21 @@ export interface RepoState {
  * whitespace and case normalization), so a count or a name can be phrased
  * variously without resorting to an LLM judge. `description` names the fact in
  * diagnostics when it is missing.
+ *
+ * `anyOf` matches a *contiguous* substring, which is brittle for facts a human
+ * naturally pads with filler — "5 issues are currently open" does not contain
+ * the fixed phrase "5 issues are open". For those, supply `pattern`: a regular
+ * expression (matched against the same normalized report) that satisfies the
+ * fact when it matches, so the count itself can be recognised rather than one
+ * exact wording. A fact is present when any `anyOf` rendering *or* `pattern`
+ * matches; `anyOf` stays the human-readable renderings even when `pattern`
+ * carries the real matcher.
  */
 export interface RequiredFact {
   description: string;
   anyOf: string[];
+  /** Optional regex (source, matched case-insensitively against the normalized report). */
+  pattern?: string;
 }
 
 /**

bench/seed.ts

@@ -359,12 +359,122 @@ async function ensurePullRequest(
   await ensureReviews(access, coords, number, pr.reviews);
 }
 
+/** How long the readiness gate polls before giving up, and how often it re-checks. */
+const READINESS_TIMEOUT_MS = 60_000;
+const READINESS_INTERVAL_MS = 750;
+
+/** Resolve after `ms` milliseconds. */
+function delay(ms: number): Promise<void> {
+  return new Promise((resolve) => setTimeout(resolve, ms));
+}
+
+/** A search hit's minimal shape: the repository the matched issue/pull belongs to. */
+interface SearchHit {
+  repository?: { name?: string } | null;
+}
+
+/**
+ * Whether the issue indexer has caught up: a full-text search for `title` of the
+ * given kind returns a hit in this repository. The endpoint spans every repo the
+ * owner can access (mirroring `gitea-axi search`), so a hit only counts when its
+ * repository matches. A non-2xx or a not-yet-indexed title reads as not-ready.
+ */
+async function searchIndexed(
+  access: BenchAccess,
+  coords: RepoCoords,
+  type: "issues" | "pulls",
+  title: string,
+): Promise<boolean> {
+  const query = new URLSearchParams({ q: title, type, owner: coords.owner, state: "all", limit: "50" });
+  const res = await request(access, "GET", `/repos/issues/search?${query.toString()}`);
+  if (!res.ok) {
+    return false;
+  }
+  const hits = (await res.json()) as SearchHit[];
+  return hits.some((hit) => hit.repository?.name === coords.repo);
+}
+
+/**
+ * The reason a freshly seeded repository is not yet ready for the agent, or `null`
+ * when it is. Ready means an independent read sees the repository and its full
+ * seeded issue and pull spread, and the issue indexer returns a seeded issue and
+ * pull — the two consistency windows (repo visibility and index lag) an agent
+ * would otherwise race and fail against. Every read is non-throwing, so a
+ * transient error reads as not-ready and is retried rather than propagated.
+ */
+async function readinessGap(access: BenchAccess, coords: RepoCoords): Promise<string | null> {
+  const repoPath = `/repos/${coords.owner}/${coords.repo}`;
+  const repoRes = await request(access, "GET", repoPath);
+  if (!repoRes.ok) {
+    return `repository read returned ${repoRes.status}`;
+  }
+  const issuesRes = await request(access, "GET", `${repoPath}/issues?type=issues&state=all&limit=100`);
+  if (!issuesRes.ok) {
+    return `issue list returned ${issuesRes.status}`;
+  }
+  const issues = (await issuesRes.json()) as GiteaIssue[];
+  if (issues.length < SEED_PLAN.issues.length) {
+    return `only ${issues.length}/${SEED_PLAN.issues.length} issues visible`;
+  }
+  const pullsRes = await request(access, "GET", `${repoPath}/pulls?state=all&limit=100`);
+  if (!pullsRes.ok) {
+    return `pull list returned ${pullsRes.status}`;
+  }
+  const pulls = (await pullsRes.json()) as GiteaPull[];
+  if (pulls.length < SEED_PLAN.pullRequests.length) {
+    return `only ${pulls.length}/${SEED_PLAN.pullRequests.length} pull requests visible`;
+  }
+  const sampleIssue = SEED_PLAN.issues[0]!.title;
+  if (!(await searchIndexed(access, coords, "issues", sampleIssue))) {
+    return `issue "${sampleIssue}" not yet indexed for search`;
+  }
+  const samplePull = SEED_PLAN.pullRequests[0]!.title;
+  if (!(await searchIndexed(access, coords, "pulls", samplePull))) {
+    return `pull request "${samplePull}" not yet indexed for search`;
+  }
+  return null;
+}
+
+/**
+ * Block until a freshly seeded repository is fully consistent for the agent, or
+ * fail loudly if it never settles within the timeout. Gitea makes a just-created
+ * repository and its just-written issues and pulls visible to the seed's own
+ * writes immediately, but an independent reader — the agent, a fresh process
+ * moments later — can hit a brief 404 window on the repository and a longer lag on
+ * the async issue indexer. Both are the benchmark's races, not the tool's, so
+ * closing them here keeps a scored run measuring gitea-axi rather than host
+ * propagation. A timeout is a harness failure surfaced to the maintainer, never a
+ * scored agent failure.
+ */
+export async function waitForSeedReady(
+  access: BenchAccess,
+  coords: RepoCoords,
+  timeoutMs = READINESS_TIMEOUT_MS,
+  intervalMs = READINESS_INTERVAL_MS,
+): Promise<void> {
+  const deadline = Date.now() + timeoutMs;
+  let gap = await readinessGap(access, coords);
+  while (gap !== null) {
+    if (Date.now() >= deadline) {
+      throw new Error(
+        `seeded repository ${coords.owner}/${coords.repo} not ready after ${timeoutMs}ms: ${gap}`,
+      );
+    }
+    await delay(intervalMs);
+    gap = await readinessGap(access, coords);
+  }
+}
+
 /**
  * Seed a freshly provisioned repository to the ground truth, idempotently. Labels
  * come first (so issues and pull requests can apply them), then the issue spread,
  * then the pull requests. Returns the deterministic ground-truth RepoState the
  * checker scores against; on a fresh repository the created numbers match it,
  * and a re-run leaves them unchanged.
+ *
+ * Before returning, it waits out the repository-visibility and issue-indexer
+ * consistency windows (see waitForSeedReady), so the agent that runs next never
+ * races a repository that is not yet readable or searchable.
  */
 export async function seedRepo(access: BenchAccess, coords: RepoCoords): Promise<RepoState> {
   const user = await currentUser(access);
@@ -384,6 +494,7 @@ export async function seedRepo(access: BenchAccess, coords: RepoCoords): Promise
     await ensurePullRequest(access, coords, pr, labelIds, pullsByTitle);
   }
 
+  await waitForSeedReady(access, coords);
   return groundTruth(user);
 }
 

bench/task-suite.ts

@@ -92,6 +92,11 @@ function readTasks(): BenchTask[] {
         {
           description: "the repository has 5 open issues",
           anyOf: ["5 open", "five open", "open issues: 5", "open: 5", "5 issues are open"],
+          // "5" followed by "open" across up to four alphabetic filler words, so
+          // natural padding ("5 issues are currently open") is recognised while a
+          // digit between them (a wrong "5 issues, 3 open") is not: the filler run
+          // is alphabetic only, so it cannot span another count.
+          pattern: "\\b5(?: [a-z]+){0,4} open\\b",
         },
       ]),
     },

skills/gitea-axi/SKILL.md

@@ -6,43 +6,34 @@ description: Use when working with a Gitea repository's issues, pull requests, l
 # gitea-axi
 
 `gitea-axi` is an agent-ergonomic CLI for a Gitea repository's issues and pull requests.
-Its output is compact TOON built for another program to read, and its errors are structured with actionable suggestions.
+Its output is compact TOON meant to be read directly, and a failed command's error names the fix — follow that suggestion rather than guessing at another command.
-
-## When to use it
-
-Reach for `gitea-axi` whenever a task touches a Gitea repository's issues, pull requests, labels, or reviews.
-
-- **Over `tea`:** `gitea-axi` returns structured output and typed errors instead of human-formatted tables, and it defaults the repository and login from the local checkout.
-- **Over raw Gitea API calls:** it handles auth, pagination, name-to-ID resolution, and review-decision aggregation for you, so you do not hand-roll HTTP.
-- **Over improvised `git`:** for anything about issues or pull requests as entities (state, reviews, labels, comments) rather than local commits and branches.
 
 ## Targeting and authentication
 
-Every command resolves two things: which repository to act on, and which credentials to authenticate with.
+Every command resolves a repository and credentials; getting both right on the first call is the difference between one command and a retry.
-Get both right on the first call — they are the usual reason a command fails and has to be retried.
 
-- **Repository.** Inside a Gitea checkout it is taken from the `origin` remote automatically.
+- **Repository.** Inside a Gitea checkout it comes from the `origin` remote.
-  Outside a checkout you must name it: pass `-R OWNER/NAME` on every command (or set `GITEA_AXI_REPO=OWNER/NAME` once for the session).
+  Outside one, pass `-R OWNER/NAME` on every command, or set `GITEA_AXI_REPO=OWNER/NAME` once for the session.
-- **Credentials.** When the environment is pre-configured — `GITEA_AXI_TOKEN` together with `GITEA_AXI_API_URL` — authentication is automatic and you need nothing more.
+- **Credentials.** With `GITEA_AXI_TOKEN` and `GITEA_AXI_API_URL` set, authentication is automatic.
-  Otherwise credentials come from a `tea` login: pass `--login <name>` (or set `GITEA_AXI_LOGIN=<name>`) unless the checkout's remote already selects one.
+  Otherwise pass `--login <name>`, or set `GITEA_AXI_LOGIN`.
 
-So outside a checkout with the token in the environment, `gitea-axi <command> -R OWNER/NAME …` is all you need; do not go hunting for a config file or a login profile.
+Outside a checkout with the token in the environment, `gitea-axi <command> -R OWNER/NAME …` is the whole invocation — don't look for a config file or a login profile.
 
-## Command groups
+## Commands
 
-- `issue` — list, view, create, comment on, edit, close/reopen, pin, and link issues.
+- `issue` — list, view, create, comment, edit, close, reopen, pin, and link (blocks / blocked-by).
-- `pr` — create, view, comment on, edit, review, merge, check out, diff, and inspect the checks of pull requests.
+- `pr` — list, view, create, comment, edit, review, merge, close, reopen, diff, checks, and checkout.
-- `label` — list, create, edit, and delete labels.
+- `label` — list, create, edit, delete.
-- `search` — full-text search; it takes a subcommand, so search issues with `search issues "<query>"` and pull requests with `search prs "<query>"` (a bare `search "<query>"` is not valid).
+- `search issues "<query>"` and `search prs "<query>"` — full-text search (a bare `search "<query>"` is not valid).
-- `setup` — install this skill (`setup`) and, opt-in, the SessionStart dashboard hook (`setup hooks`).
 
-To read one issue's fields, reach straight for `issue view <number>`: it shows labels and state by default, and takes `--fields assignees,milestone,…` for the rest.
+## Finding and acting
-You rarely need `issue list` to answer a question about a single issue.
 
-## Discovery
+Find the target, then act on it — two commands, not a survey of the repository.
 
-This skill is a pointer, not a command reference — the CLI is the single source of truth for its own interface.
+- **Find it.** If you already know the number, act on it directly.
-
+  Otherwise reach for one command — `search issues "<query>"` for a title or keyword, or `issue list --state all --label <name>` to narrow by a property — not both.
-- Run `gitea-axi` with no arguments for the repository dashboard (open issues and pull requests).
+- **Read one issue or PR.** `issue view <number>` (or `pr view <number>`) shows labels and state by default, and takes `--fields assignees,milestone,…` for the rest.
-  Add `--full` for the open-PR table and issue counts by label.
+  You do not need `issue list` to answer a question about a single known issue.
-- Run `gitea-axi <command> --help` (or `gitea-axi <group> <command> --help`) for the exact flags of any command.
+- **Act on it.** `issue edit <number>` and `pr edit <number>` change fields with repeatable `--add-label` / `--remove-label` and `--add-assignee` / `--remove-assignee`, plus `--title`, `--body`, and `--milestone`.
+  Reviewing is `pr review <number>` with exactly one of `--approve`, `--request-changes`, or `--comment`, and an optional `--body`.
+  A comment is `issue comment <number> --body <text>`; a new label is `label create --name <text> --color <hex-without-#>`.

src/commands/search.ts

@@ -107,6 +107,10 @@ interface SearchKind {
   noun: string;
   /** The command a matched number feeds into. */
   viewCommand: string;
+  /** The list command suggested as the fallback when a search finds nothing. */
+  listCommand: string;
+  /** Human plural for the fallback note, e.g. "issues" or "pull requests". */
+  things: string;
   /** The `--help` text for this variant. */
   help: string;
 }
@@ -116,6 +120,8 @@ const SEARCH_ISSUES: SearchKind = {
   type: "issues",
   noun: "issues",
   viewCommand: "issue view",
+  listCommand: "issue list",
+  things: "issues",
   help: SEARCH_ISSUES_HELP,
 };
 
@@ -124,6 +130,8 @@ const SEARCH_PRS: SearchKind = {
   type: "pulls",
   noun: "pull_requests",
   viewCommand: "pr view",
+  listCommand: "pr list",
+  things: "pull requests",
   help: SEARCH_PRS_HELP,
 };
 
@@ -217,11 +225,24 @@ async function runSearch(deps: CliDeps, args: string[], kind: SearchKind): Promi
     extractRow(issue, [...SEARCH_FIELDS, ...extraFields], { now, host: context.host, full }),
   );
 
+  // The next-step suggestion is conditioned on the match count. On a miss the
+  // `view` hint is nonsensical, so point at the non-indexed list as a fallback
+  // (it recovers from both an over-narrow query and index lag); on a single match
+  // fill the real number (Principle 9's single-id fill); otherwise leave the
+  // number parameterized. Search stays a locator either way — it never auto-loads
+  // the detail (see ADR 0017).
+  const suggestion =
+    total === 0
+      ? suggestCommand(context, `${kind.listCommand} --state all`, `to list all ${kind.things} instead`)
+      : total === 1
+        ? suggestCommand(context, `${kind.viewCommand} ${matches[0]!.number}`, "to see it in full")
+        : suggestCommand(context, `${kind.viewCommand} <number>`, "to see a match in full");
+
   return renderList({
     noun: kind.noun,
     rows,
     countLine: formatCountLine(rows.length, total, false),
-    help: [suggestCommand(context, `${kind.viewCommand} <number>`, "to see a match in full")],
+    help: [suggestion],
   });
 }
 

src/context.ts

@@ -60,6 +60,17 @@ function hostnameOf(url: string, origin: string): string {
   }
 }
 
+/**
+ * Normalize a Gitea base URL to the host root the client expects. The client
+ * (gitea-js) appends `/api/v1` itself, so a value that already carries it — a
+ * natural guess when the variable is literally named `..._API_URL` — would double
+ * the segment and 404 as a spurious `REPO_NOT_FOUND`. Strip a trailing `/api/v1`
+ * (with any trailing slashes) so the host base and the API endpoint both work.
+ */
+function normalizeApiBase(url: string): string {
+  return url.replace(/\/+$/, "").replace(/\/api\/v1$/, "");
+}
+
 function resolveTestModeContext(
   deps: CliDeps,
   apiUrl: string,
@@ -72,10 +83,11 @@ function resolveTestModeContext(
       ["Set `GITEA_AXI_REPO=OWNER/NAME` or pass `-R OWNER/NAME`"],
     );
   }
+  const base = normalizeApiBase(apiUrl);
   return {
     ...parseRepoSpec(overrides.repoSpec, overrides.repoOrigin),
-    host: hostnameOf(apiUrl, "`GITEA_AXI_API_URL`"),
+    host: hostnameOf(base, "`GITEA_AXI_API_URL`"),
-    apiUrl: apiUrl.replace(/\/+$/, ""),
+    apiUrl: base,
     token: deps.env.GITEA_AXI_TOKEN ?? "",
     repoSource: overrides.repoSource,
     loginSource: overrides.loginSource,
@@ -184,7 +196,7 @@ export async function resolveRepoContext(deps: CliDeps): Promise<RepoContext> {
     owner,
     name,
     host,
-    apiUrl: login.url.replace(/\/+$/, ""),
+    apiUrl: normalizeApiBase(login.url),
     token,
     repoSource: overrides.repoSource,
     loginSource: overrides.loginSource,

test/context.test.ts

@@ -1,4 +1,6 @@
 import { afterEach, describe, expect, it } from "vitest";
+import { resolveRepoContext } from "../src/context.js";
+import type { CliDeps } from "../src/deps.js";
 import { startFixtureServer, type FixtureServer } from "./fixture-server.js";
 import { runCliTest, testModeEnv } from "./harness.js";
 
@@ -117,3 +119,49 @@ describe("context overrides", () => {
     expect(exitCode).toBe(0);
   });
 });
+
+describe("apiUrl normalization", () => {
+  function depsWithApiUrl(apiUrl: string): CliDeps {
+    return {
+      env: {
+        GITEA_AXI_API_URL: apiUrl,
+        GITEA_AXI_REPO: "acme/widgets",
+        GITEA_AXI_TOKEN: "test-token",
+      },
+      cwd: process.cwd(),
+      globals: {},
+    };
+  }
+
+  it("strips a trailing /api/v1 suffix from the host base", async () => {
+    const context = await resolveRepoContext(
+      depsWithApiUrl("https://git.example.com/api/v1"),
+    );
+
+    expect(context.apiUrl).toBe("https://git.example.com");
+  });
+
+  it("strips a trailing /api/v1/ with a trailing slash", async () => {
+    const context = await resolveRepoContext(
+      depsWithApiUrl("https://git.example.com/api/v1/"),
+    );
+
+    expect(context.apiUrl).toBe("https://git.example.com");
+  });
+
+  it("leaves a host base without an /api/v1 suffix unchanged", async () => {
+    const context = await resolveRepoContext(
+      depsWithApiUrl("https://git.example.com"),
+    );
+
+    expect(context.apiUrl).toBe("https://git.example.com");
+  });
+
+  it("strips a lone trailing slash from the host base", async () => {
+    const context = await resolveRepoContext(
+      depsWithApiUrl("https://git.example.com/"),
+    );
+
+    expect(context.apiUrl).toBe("https://git.example.com");
+  });
+});

test/search.test.ts

@@ -402,3 +402,149 @@ describe("search empty results", () => {
     });
   }
 });
+
+/**
+ * The `help[1]:` next-step line is emitted by `suggestCommand`, so it appears
+ * wrapped in a `Run \`gitea-axi …\`` line with `-R`/`--login` normalization.
+ * These tests pull that help block out of the output and assert on the
+ * count-conditional suggestion within it.
+ */
+function helpBlock(stdout: string): string {
+  const lines = stdout.split("\n");
+  const start = lines.findIndex((line) => /^help\[\d+\]:/.test(line));
+  expect(start).toBeGreaterThanOrEqual(0);
+  // The block runs from the help[N]: header to the next blank line / EOF.
+  const rest = lines.slice(start);
+  const end = rest.findIndex((line, i) => i > 0 && line.trim() === "");
+  return (end === -1 ? rest : rest.slice(0, end)).join("\n");
+}
+
+describe("search issues count-conditional next-step suggestion", () => {
+  it("suggests the list fallback when there are zero in-repo matches", async () => {
+    server = await startFixtureServer([
+      { method: "GET", path: SEARCH_PATH, headers: { "X-Total-Count": "0" }, body: [] },
+    ]);
+
+    const { stdout, exitCode } = await runCliTest(
+      ["search", "issues", "login bug"],
+      { env: testModeEnv(server.url) },
+    );
+
+    expect(exitCode).toBe(0);
+    const help = helpBlock(stdout);
+    expect(help).toContain("issue list --state all");
+    expect(help).toContain("to list all issues instead");
+    expect(help).not.toContain("issue view");
+  });
+
+  it("fills the real number when there is exactly one in-repo match", async () => {
+    server = await startFixtureServer([
+      {
+        method: "GET",
+        path: SEARCH_PATH,
+        headers: { "X-Total-Count": "1" },
+        body: [searchIssueOf(2, { title: "Fix login redirect loop" })],
+      },
+    ]);
+
+    const { stdout, exitCode } = await runCliTest(
+      ["search", "issues", "login bug"],
+      { env: testModeEnv(server.url) },
+    );
+
+    expect(exitCode).toBe(0);
+    const help = helpBlock(stdout);
+    expect(help).toContain("issue view 2");
+    expect(help).toContain("to see it in full");
+    expect(help).not.toContain("issue view <number>");
+  });
+
+  it("keeps the <number> placeholder when there are two or more in-repo matches", async () => {
+    server = await startFixtureServer([
+      {
+        method: "GET",
+        path: SEARCH_PATH,
+        headers: { "X-Total-Count": "2" },
+        body: [
+          searchIssueOf(42, { title: "Fix login redirect loop" }),
+          searchIssueOf(41, { title: "Login button unresponsive" }),
+        ],
+      },
+    ]);
+
+    const { stdout, exitCode } = await runCliTest(
+      ["search", "issues", "login bug"],
+      { env: testModeEnv(server.url) },
+    );
+
+    expect(exitCode).toBe(0);
+    const help = helpBlock(stdout);
+    expect(help).toContain("issue view <number>");
+    expect(help).toContain("to see a match in full");
+  });
+});
+
+describe("search prs count-conditional next-step suggestion", () => {
+  it("suggests the list fallback when there are zero in-repo matches", async () => {
+    server = await startFixtureServer([
+      { method: "GET", path: SEARCH_PATH, headers: { "X-Total-Count": "0" }, body: [] },
+    ]);
+
+    const { stdout, exitCode } = await runCliTest(
+      ["search", "prs", "flaky ci"],
+      { env: testModeEnv(server.url) },
+    );
+
+    expect(exitCode).toBe(0);
+    const help = helpBlock(stdout);
+    expect(help).toContain("pr list --state all");
+    expect(help).toContain("to list all pull requests instead");
+    expect(help).not.toContain("pr view");
+  });
+
+  it("fills the real number when there is exactly one in-repo match", async () => {
+    server = await startFixtureServer([
+      {
+        method: "GET",
+        path: SEARCH_PATH,
+        headers: { "X-Total-Count": "1" },
+        body: [searchIssueOf(2, { title: "Retry flaky CI jobs" })],
+      },
+    ]);
+
+    const { stdout, exitCode } = await runCliTest(
+      ["search", "prs", "flaky ci"],
+      { env: testModeEnv(server.url) },
+    );
+
+    expect(exitCode).toBe(0);
+    const help = helpBlock(stdout);
+    expect(help).toContain("pr view 2");
+    expect(help).toContain("to see it in full");
+    expect(help).not.toContain("pr view <number>");
+  });
+
+  it("keeps the <number> placeholder when there are two or more in-repo matches", async () => {
+    server = await startFixtureServer([
+      {
+        method: "GET",
+        path: SEARCH_PATH,
+        headers: { "X-Total-Count": "2" },
+        body: [
+          searchIssueOf(73, { title: "Retry flaky CI jobs" }),
+          searchIssueOf(72, { title: "Stabilize CI runners" }),
+        ],
+      },
+    ]);
+
+    const { stdout, exitCode } = await runCliTest(
+      ["search", "prs", "flaky ci"],
+      { env: testModeEnv(server.url) },
+    );
+
+    expect(exitCode).toBe(0);
+    const help = helpBlock(stdout);
+    expect(help).toContain("pr view <number>");
+    expect(help).toContain("to see a match in full");
+  });
+});

test/skill.test.ts

@@ -36,19 +36,23 @@ describe("bundled Agent Skill markdown", () => {
 
   it("references each command group as a one-liner", () => {
     const body = skill.toLowerCase();
-    for (const group of ["issue", "pr", "label", "search", "setup"]) {
+    for (const group of ["issue", "pr", "label", "search"]) {
       expect(body, `expected the skill to mention the ${group} command group`).toContain(
         group,
       );
     }
   });
 
-  it("points at the bare dashboard and per-command help for discovery", () => {
+  it("steers find-then-act and does not push exploratory discovery", () => {
     const body = skill.toLowerCase();
-    // Bare dashboard: running the binary with no arguments.
+    // The intended steering: find the target, then act on it.
-    expect(body).toContain("no argument");
+    expect(body).toContain("find the target");
-    expect(body).toContain("dashboard");
+    expect(body).toContain("act on it");
-    // Per-command help.
+    // The find/act discipline: not a full survey, and not both find commands at once.
-    expect(body).toContain("--help");
+    expect(body).toContain("not a survey");
+    expect(body).toContain("not both");
+    // The removed exploratory anti-pattern must be gone.
+    expect(body).not.toContain("dashboard");
+    expect(body).not.toContain("no argument");
   });
 });