Add discovery detail controls and search/scrape guidance by developersdigest · Pull Request #262 · firecrawl/cli

developersdigest · 2026-09-19T11:59:40Z

Integrates tool discovery and execution into the search and scrape skills, with progressive catalogue inspection and guidance for large retained results.

Search defaults to compact tool identities and descriptions. --tool-detail summary adds metadata; full includes contracts. URL Scrape keeps its summary default. Inspect selected tools with list. Requires the corresponding API deployment.

Validation: build and focused CLI tests. Production skill changes remain here; beta skill updates are separate in #266.

cubic-dev-ai

0 issues found across 5 files (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would auto-approve. Updates Firecrawl skill documentation to integrate Alexandria tool discovery into search/scrape guidance and add large-result recovery instructions via bounded remote Bash reads; docs-only change with CLI behavior unchanged and safety guidance included.

Re-trigger cubic}

cubic-dev-ai

0 issues found across 4 files (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would auto-approve. This PR only changes Firecrawl agent-skill and reference docs: it integrates Alexandria discovery into search/scrape guidance and adds bounded remote-Bash recovery instructions; any remaining risk is ordinary doc correctness, not runtime behavior.

Re-trigger cubic}

cubic-dev-ai

0 issues found across 2 files (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would auto-approve. Documentation-only update to Firecrawl agent skills making search/scrape the reference workflow for Alexandria tool discovery and adding remote-Bash large-result recovery guidance; runtime and CLI are unchanged, so remaining risk is doc correctness.

Re-trigger cubic}

cubic-dev-ai

All reported issues were addressed across 12 files (changes from recent commits).

_{Shadow auto-approve: would not auto-approve because issues were found.
Tip: Review your code locally with the cubic CLI to iterate faster.

Fix all with cubic | Re-trigger cubic}

cubic-dev-ai

0 issues found across 2 files (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would not auto-approve. Auto-approval blocked by 1 unresolved issue from previous reviews.

Re-trigger cubic}

cubic-dev-ai

0 issues found across 1 file (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would auto-approve. Adds an optional --tool-detail summary|full flag to search and scrape discovery with local validation, forwards it to the API when set, and expands skill guidance. Default behavior is unchanged, so risk is bounded to opt-in use.

Re-trigger cubic}

cubic-dev-ai

All reported issues were addressed across 10 files (changes from recent commits).

_{Shadow auto-approve: would not auto-approve because issues were found.
Tip: Review your code locally with the cubic CLI to iterate faster.

Fix all with cubic | Re-trigger cubic}

cubic-dev-ai

0 issues found across 2 files (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would auto-approve. Adds an opt-in --tool-detail compact mode to search/scrape discovery and expands skill/reference guidance; default summary behavior is unchanged and tests cover forwarding and local validation, keeping risk limited to explicit opt-in use.

Re-trigger cubic}

cubic-dev-ai

All reported issues were addressed across 5 files (changes from recent commits).

_{Shadow auto-approve: would not auto-approve because issues were found.
Tip: Review your code locally with the cubic CLI to iterate faster.

Fix all with cubic | Re-trigger cubic}

cubic-dev-ai

0 issues found across 1 file (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would require human review. Adds --tool-detail controls to search/scrape and changes search's default tool detail from summary to compact, changing output for all users and always sending a new API parameter; default change requires human review.

Re-trigger cubic}

cubic-dev-ai

All reported issues were addressed across 5 files (changes from recent commits).

_{Shadow auto-approve: would not auto-approve because issues were found.
Tip: Review your code locally with the cubic CLI to iterate faster.

Fix all with cubic | Re-trigger cubic}

cubic-dev-ai

0 issues found across 5 files (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would not auto-approve. Auto-approval blocked by 2 unresolved issues from previous reviews.

Re-trigger cubic}

cubic-dev-ai

0 issues found across 1 file (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would not auto-approve. Auto-approval blocked by 2 unresolved issues from previous reviews.

Re-trigger cubic}

cubic-dev-ai

0 issues found across 1 file (changes from recent commits).

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Shadow auto-approve: would require human review. Adds --tool-detail controls to search/scrape and changes search's default tool detail from summary to compact, altering default output for all users and always sending a new toolDetail API parameter. The default-output and API-contract change needs human sign-off.

Re-trigger cubic}

cubic-dev-ai

1 issue found across 7 files (changes from recent commits).

Confidence score: 3/5

src/commands/list.ts: the root auth hook prompts for stored credentials before the --api-key child option can be used, so otherwise-authenticated users may be blocked or prompted unnecessarily; update the hook to honor actionCommand's API key.

Prompt for AI agents (unresolved issues)


Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="src/commands/list.ts">

<violation number="1" location="src/commands/list.ts:535">
P2: When users run `firecrawl alexandria feedback --api-key <key>` without stored credentials, the root auth hook prompts before the handler can use the child option. Update the auth hook to honor `actionCommand`'s API key before calling `ensureAuthenticated`.</violation>
</file>

_{Shadow auto-approve: would not auto-approve because issues were found.
Tip: Review your code locally with the cubic CLI to iterate faster.

Fix all with cubic | Re-trigger cubic}

cubic-dev-ai · 2026-09-21T22:08:09Z

    )
    .addCommand(createListCommand())
    .addCommand(createTermsCommand())
+    .addCommand(createAlexandriaFeedbackCommand())


P2: When users run firecrawl alexandria feedback --api-key <key> without stored credentials, the root auth hook prompts before the handler can use the child option. Update the auth hook to honor actionCommand's API key before calling ensureAuthenticated.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At src/commands/list.ts, line 535: <comment>When users run `firecrawl alexandria feedback --api-key <key>` without stored credentials, the root auth hook prompts before the handler can use the child option. Update the auth hook to honor `actionCommand`'s API key before calling `ensureAuthenticated`.</comment> <file context> @@ -531,5 +532,6 @@ export function createAlexandriaCommand(): Command { ) .addCommand(createListCommand()) .addCommand(createTermsCommand()) + .addCommand(createAlexandriaFeedbackCommand()) .addCommand(browse, { isDefault: true, hidden: true }); } </file context>

cubic-dev-ai

1 issue found across 3 files (changes from recent commits).

Confidence score: 4/5

src/__tests__/alexandria-beta.test.ts sets FIRECRAWL_NO_ENDPOINT_FEEDBACK, causing executeEndpointFeedback to return before reaching API-key/auth logic; authentication regressions could therefore pass unnoticed—disable or remove the environment override for the auth-focused test.

Prompt for AI agents (unresolved issues)


Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="src/__tests__/alexandria-beta.test.ts">

<violation number="1" location="src/__tests__/alexandria-beta.test.ts:1164">
P2: This test never exercises the API-key/auth code it is named after. With `FIRECRAWL_NO_ENDPOINT_FEEDBACK: '1'` set, `executeEndpointFeedback` returns `{ disabled: true, disabledSource: 'env' }` from its first line (src/commands/feedback.ts:231-238), before `getClient`, `getConfig`, or `validateConfig` run, and `handleEndpointFeedbackCommand` then exits 0 for `disabledSource: 'env'`. All three assertions (code 0, zero requests, no auth-error text) hold even if the child-api-key-before-auth handling regresses, so this test cannot catch a regression of the fix it claims to validate. Point `--api-url` at the local test server (`baseUrl`), drop the opt-out env var, and assert the POST to `/v2/feedback` carries `Authorization: Bearer fc-child-key` while the root FIRECRAWL_API_KEY stays empty.</violation>
</file>

_{Shadow auto-approve: would not auto-approve because issues were found.
Tip: Review your code locally with the cubic CLI to iterate faster.

Fix all with cubic | Re-trigger cubic}

cubic-dev-ai · 2026-09-21T22:24:05Z

+it('honors the child feedback API key before root authentication', async () => {
+  const result = await cli(
+    [
+      ...sessionFeedbackArgs,
+      '--api-key',
+      'fc-child-key',
+      '--api-url',
+      'https://api.firecrawl.dev',
+    ],
+    '',
+    { FIRECRAWL_NO_ENDPOINT_FEEDBACK: '1' }
+  );
+  expect(result.code).toBe(0);
+  expect(requests).toHaveLength(0);
+  expect(result.stdout + result.stderr).not.toMatch(
+    /not authenticated|log in|login required/i
+  );
+});


P2: This test never exercises the API-key/auth code it is named after. With FIRECRAWL_NO_ENDPOINT_FEEDBACK: '1' set, executeEndpointFeedback returns { disabled: true, disabledSource: 'env' } from its first line (src/commands/feedback.ts:231-238), before getClient, getConfig, or validateConfig run, and handleEndpointFeedbackCommand then exits 0 for disabledSource: 'env'. All three assertions (code 0, zero requests, no auth-error text) hold even if the child-api-key-before-auth handling regresses, so this test cannot catch a regression of the fix it claims to validate. Point --api-url at the local test server (baseUrl), drop the opt-out env var, and assert the POST to /v2/feedback carries Authorization: Bearer fc-child-key while the root FIRECRAWL_API_KEY stays empty.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At src/__tests__/alexandria-beta.test.ts, line 1164: <comment>This test never exercises the API-key/auth code it is named after. With `FIRECRAWL_NO_ENDPOINT_FEEDBACK: '1'` set, `executeEndpointFeedback` returns `{ disabled: true, disabledSource: 'env' }` from its first line (src/commands/feedback.ts:231-238), before `getClient`, `getConfig`, or `validateConfig` run, and `handleEndpointFeedbackCommand` then exits 0 for `disabledSource: 'env'`. All three assertions (code 0, zero requests, no auth-error text) hold even if the child-api-key-before-auth handling regresses, so this test cannot catch a regression of the fix it claims to validate. Point `--api-url` at the local test server (`baseUrl`), drop the opt-out env var, and assert the POST to `/v2/feedback` carries `Authorization: Bearer fc-child-key` while the root FIRECRAWL_API_KEY stays empty.</comment> <file context> @@ -1142,3 +1147,107 @@ it('rejects missing session requirements before sending feedback', async () => { + 'Missing documents', +]; + +it('honors the child feedback API key before root authentication', async () => { + const result = await cli( + [ </file context>

Suggested change

it('honors the child feedback API key before root authentication', async () => {

const result = await cli(

[

...sessionFeedbackArgs,

'--api-key',

'fc-child-key',

'--api-url',

'https://api.firecrawl.dev',

],

'',

{ FIRECRAWL_NO_ENDPOINT_FEEDBACK: '1' }

);

expect(result.code).toBe(0);

expect(requests).toHaveLength(0);

expect(result.stdout + result.stderr).not.toMatch(

/not authenticated|log in|login required/i

);

});

it('honors the child feedback API key before root authentication', async () => {

const result = await cli(

[

...sessionFeedbackArgs,

'--api-key',

'fc-child-key',

'--api-url',

baseUrl,

],

''

);

expect(result.code).toBe(0);

expect(requests).toHaveLength(1);

expect(requests[0].url).toBe('/v2/feedback');

expect(requests[0].headers.authorization).toBe('Bearer fc-child-key');

});

developersdigest added 2 commits September 19, 2026 07:59

Guide search and scrape agents through large-result recovery

7a3b0a5

Scope guidance to standalone Alexandria beta skill

7884dad

developersdigest changed the title ~~Guide search and scrape through progressive discovery and large-result recovery~~ Add Alexandria beta skill with progressive discovery and remote Bash recovery Sep 19, 2026

Fold Alexandria workflows into search and scrape skills

72a3f3e

developersdigest changed the title ~~Add Alexandria beta skill with progressive discovery and remote Bash recovery~~ Fold Alexandria beta guidance into search and scrape skills Sep 19, 2026

Frame Alexandria as going beyond web results

9810075

developersdigest changed the title ~~Fold Alexandria beta guidance into search and scrape skills~~ Integrate Alexandria discovery and large-result guidance into search and scrape Sep 19, 2026

Highlight efficient structured data workflows in Alexandria skill

e25d4bb

cubic-dev-ai Bot reviewed Sep 19, 2026

View reviewed changes

developersdigest added 4 commits September 19, 2026 08:17

Add CLI help and contract inspection path to scrape skill

2b17170

Make search discovery and execution progression explicit

76ebef9

Make search and scrape the canonical structured data workflow

deddc0a

Use discovered provider and capability IDs in skill examples

af14212

developersdigest mentioned this pull request Sep 19, 2026

Add Alexandria search, progressive discovery and scrape execution to MCP firecrawl/firecrawl-mcp-server#405

Open

cubic-dev-ai Bot reviewed Sep 19, 2026

View reviewed changes

Explain semantic and domain paths to deeper Alexandria data

f608a67

cubic-dev-ai Bot reviewed Sep 19, 2026

View reviewed changes

Expose compact and full discovery detail in search and scrape

163d01e

developersdigest changed the title ~~Integrate Alexandria discovery and large-result guidance into search and scrape~~ Add discovery detail controls and search/scrape guidance Sep 20, 2026