pi-agent-browser-native 0.2.0 → 0.2.2

package/CHANGELOG.md

@@ -1,5 +1,25 @@
 # Changelog
 
+## 0.2.2 - 2026-04-12
+
+### Fixed
+- plain-text inspection commands like `agent_browser --help` and `--version` now stay stateless: they no longer claim the implicit managed session or leave behind ambiguous `parseError` details on success
+- extension-managed session ownership is now reconstructed from persisted tool details on resume/reload while still preserving cwd-hash isolation across same-named checkouts and worktrees
+- echoed tool updates/details now redact sensitive invocation values and structured secret-bearing fields instead of replaying headers, proxy credentials, cookies, or auth-bearing URL params back into `pi`
+- the subprocess wrapper no longer forwards ambient parent-shell `AGENT_BROWSER_*` state into child runs, reducing surprising hidden configuration leaks from the caller environment
+- browser-specific system-prompt injection is now minimal and only added for clearly browser-oriented turns, while the full playbook stays in tool metadata where it belongs
+- published docs and changelog notes now match the current result/details contract, resume behavior, prompt behavior, and release workflow
+
+## 0.2.1 - 2026-04-12
+
+### Fixed
+- the GitHub source trial docs now use `pi --no-extensions -e https://github.com/fitchmultz/pi-agent-browser-native` so published-package users do not hit duplicate `agent_browser` registration conflicts during source-path testing
+- successful unnamed `sessionMode: "fresh"` launches now rotate the extension-managed session to the new browser, and later default `sessionMode: "auto"` calls keep following that fresh session instead of silently snapping back to the older one
+- mixed-success `batch` failures now preserve per-step rendering, include the first failing step in the visible output and structured details, and still mark the overall tool call as an error so agents can recover from partial progress
+- implicit `piab-*` session names now include a stable cwd hash in addition to the `pi` session id so same-named checkouts and worktrees no longer collide onto the same browser session
+- value-taking flags like `--session`, `--profile`, `--session-name`, and `--cdp` now fail locally with direct validation errors when the value is missing or replaced by another flag, instead of producing confusing downstream JSON parse failures
+- the bash guard now catches wrapped `agent-browser` invocations such as `env agent-browser ...`, `npx --yes agent-browser ...`, `pnpm dlx agent-browser ...`, `yarn dlx agent-browser ...`, `bunx agent-browser ...`, and absolute-path execution, reducing accidental bypasses of the native-tool path
+
 ## 0.2.0 - 2026-04-12
 
 ### Changed
@@ -8,7 +28,7 @@
 - plain-text inspection commands like `agent_browser --help` and `--version` are now always allowed, removing the old prompt-dependent inspection gate and making the inspection contract local and predictable
 - navigation actions like `click`, `dblclick`, `back`, `forward`, and `reload` now include lightweight post-action title/url summaries when the wrapper can address the active session, reducing guess-and-check follow-up snapshots
 - compact snapshot rendering is leaner by default: fewer additional sections, fewer refs, smaller role summaries, and the raw spill path now stays in `details.fullOutputPath` instead of dominating the visible snapshot body
-- README and injected tool guidance now include a compact agent quick start with the core call shapes for `open` + `snapshot`, `click` + re-snapshot, `batch`, `eval --stdin`, and fresh profiled launches
+- README and tool prompt guidance now include a compact agent quick start with the core call shapes for `open` + `snapshot`, `click` + re-snapshot, `batch`, `eval --stdin`, and fresh profiled launches, while turn-level system-prompt injection stays minimal
 
 ### Migration notes
 - replace any use of `useActiveSession` with `sessionMode`
@@ -19,7 +39,7 @@
 ### Changed
 - hardened the implicit browser-session lifecycle so failed first launches no longer mark the convenience session active, startup-scoped flags behave correctly across launches and closes, and the highest-risk entrypoint paths now have direct automated and isolated-`pi` coverage
 - added explicit temp-root ownership markers, aggregate spill-file disk budgeting, inline image size limits, and graceful fallback behavior when large snapshot or stdout artifacts exceed temp budgets
-- consolidated the shared browser operating playbook across the injected system prompt and tool prompt guidance while adding direct extension-hook coverage for prompt injection, bash blocking, and session resets
+- consolidated the shared browser operating playbook into the tool prompt guidance while keeping turn-level system-prompt injection minimal, and added direct extension-hook coverage for prompt injection, bash blocking, and session resets
 - split the old result-rendering god module into focused envelope, presentation, shared, and snapshot modules, and made snapshot compaction fall back to a resilient outline mode when upstream raw snapshot formatting is unfamiliar
 - refactored the release-package verification script into smaller testable helpers, preserved the retired autoload-shim guard, and aligned the tarball gate with the split result-rendering module layout
 

package/README.md

@@ -69,12 +69,14 @@ For the source install path, prefer the repository URL:
 pi install https://github.com/fitchmultz/pi-agent-browser-native
 ```
 
-To try the GitHub source without installing it permanently:
+To try the GitHub source without installing it permanently, isolate that temporary source extension from your normal installed package set:
 
 ```bash
-pi -e https://github.com/fitchmultz/pi-agent-browser-native
+pi --no-extensions -e https://github.com/fitchmultz/pi-agent-browser-native
 ```
 
+This avoids duplicate `agent_browser` registrations when you already have `pi-agent-browser-native` installed globally.
+
 ### Current practical local-checkout flow
 
 Until you are using a published package release, prefer an explicit checkout-only run instead of installing the checkout into your normal `pi` package set:
@@ -89,8 +91,8 @@ The native tool exposed to the agent is named `agent_browser`.
 
 The primary session control parameter is `sessionMode`:
 
-- `"auto"` (default) reuses the implicit `pi`-scoped session when possible
-- `"fresh"` skips that implicit session so startup-scoped flags like `--profile`, `--session-name`, and `--cdp` can launch a fresh upstream session
+- `"auto"` (default) reuses the extension-managed `pi`-scoped session when possible
+- `"fresh"` switches that managed session to a fresh upstream launch so startup-scoped flags like `--profile`, `--session-name`, and `--cdp` apply and later auto calls follow the new browser
 
 ## Agent quick start
 
@@ -99,8 +101,8 @@ The primary session control parameter is `sessionMode`:
 - `args` — exact CLI args after `agent-browser`
 - `stdin` — raw stdin only for `batch` and `eval --stdin`
 - `sessionMode`
-  - `"auto"` — default, reuse the implicit `pi`-scoped session
-  - `"fresh"` — skip the implicit session for a new profile/debug launch
+  - `"auto"` — default, reuse the extension-managed `pi`-scoped session
+  - `"fresh"` — switch that managed session to a new profile/debug launch
 
 ### Common call shapes
 
@@ -136,7 +138,9 @@ Start a fresh profiled launch after you already used the implicit session:
 { "args": ["--profile", "Default", "open", "https://example.com/account"], "sessionMode": "fresh" }
 ```
 
-Name a new upstream session explicitly when you want to keep reusing it:
+After a successful unnamed fresh launch, later `sessionMode: "auto"` calls follow that new browser automatically.
+
+Name a new upstream session explicitly when you want to keep reusing it yourself:
 
 ```json
 { "args": ["--session", "auth-flow", "open", "https://example.com"] }
@@ -177,15 +181,17 @@ Validated workflow examples:
 - run `batch` with JSON via `stdin`
 - run `eval --stdin`
 - take a screenshot with inline attachment support
-- inspect `agent_browser --help` and `--version` via the tool's plain-text inspection fallback
+- inspect `agent_browser --help` and `--version` via the tool's stateless plain-text inspection fallback
 
-Inspection commands like `agent_browser --help` and `--version` are always supported. They return plain text and are useful for debugging or capability checks, but they are not required for normal browsing workflows.
+Inspection commands like `agent_browser --help` and `--version` are always supported. They return plain text, are useful for debugging or capability checks, and stay stateless: the extension does not inject its implicit session for them and they do not consume the managed-session slot needed for a later `--profile`, `--session-name`, or `--cdp` launch.
 
 Current cautions:
 - passing `--profile` is an explicit upstream choice; this extension does not add its own profile-cloning or isolation layer
 - startup-scoped flags like `--profile`, `--session-name`, and `--cdp` are for the first command that launches a session; if the implicit session is already active, retry that call with `sessionMode: "fresh"` or provide an explicit `--session ...` for the new launch
-- implicit `piab-*` sessions are extension-managed convenience sessions; they are best-effort closed on `pi` shutdown, get an idle timeout to reduce stale background daemons, and clean up private temp spill artifacts on shutdown
-- explicit upstream sessions like `--session`, `--profile`, `--session-name`, and `--cdp` are treated as user-managed and are not auto-closed by the extension
+- implicit `piab-*` sessions are extension-managed convenience sessions; they are best-effort closed on `pi` shutdown, get an idle timeout to reduce stale background daemons, clean up private temp spill artifacts on shutdown, and are reconstructed from persisted tool details on resume/reload so later default calls keep following the active managed browser
+- `sessionMode: "fresh"` without an explicit `--session` rotates that extension-managed session to the new browser so later auto calls keep using it
+- explicit caller-provided `--session` values are treated as user-managed and are not auto-closed by the extension
+- tool progress/details redact sensitive invocation values such as `--headers`, proxy credentials, and auth-bearing URL parameters before echoing them back into Pi
 
 ### Switching from public browsing to a fresh profile/debug launch
 
@@ -203,6 +209,8 @@ Use `sessionMode: "fresh"` for that transition instead of relying on the implici
 }
 ```
 
+After that call succeeds, later default `sessionMode: "auto"` calls continue in the new fresh browser.
+
 If you want to name the new upstream session yourself, pass an explicit session instead:
 
 ```json

package/docs/ARCHITECTURE.md

@@ -59,7 +59,7 @@ The published package should exclude agent-only and superseded repo materials su
 
 ### Default
 
-If the caller does not provide `--session`, the extension should default to `sessionMode: "auto"` and use an implicit session name derived from the current `pi` session id.
+If the caller does not provide `--session`, the extension should default to `sessionMode: "auto"` and use an implicit session name derived from the current `pi` session id plus a hash of the absolute cwd.
 
 Why:
 - works out of the box
@@ -70,20 +70,23 @@ Why:
 
 If the caller provides `--session`, `--profile`, `--cdp`, or similar upstream flags, the extension should respect them with minimal interference.
 
-The tool should also expose a first-class `sessionMode: "fresh"` escape hatch so agents can intentionally skip the implicit session and launch a fresh upstream session without inventing a fixed explicit session name.
+The tool should also expose a first-class `sessionMode: "fresh"` escape hatch so agents can intentionally rotate the extension-managed session to a fresh upstream launch without inventing a fixed explicit session name.
 
 ### Ownership
 
 V1 ownership rule:
 - implicit auto-generated sessions are extension-managed convenience sessions
+- unnamed `sessionMode: "fresh"` launches rotate that extension-managed session to a new upstream browser
 - explicit/user-managed sessions are not auto-managed by default
-- implicit sessions should be reusable during an active `pi` session, but should still be cleaned up predictably
+- extension-managed sessions should be reusable during an active `pi` session, but should still be cleaned up predictably
 
 Practical policy:
-- on normal `pi` shutdown, best-effort close the implicit session
-- also set an idle timeout on implicit sessions so abandoned daemons self-clean after inactivity
-- clean up private temp spill artifacts owned by the implicit session on shutdown
-- leave explicit upstream sessions like `--session`, `--profile`, `--session-name`, and `--cdp` alone unless the caller closes them explicitly
+- on normal `pi` shutdown, best-effort close the current extension-managed session
+- also set an idle timeout on extension-managed sessions so abandoned daemons self-clean after inactivity
+- clean up private temp spill artifacts owned by the extension-managed session on shutdown
+- reconstruct the current extension-managed session from persisted tool details on resume/reload so later default calls keep following the active managed browser
+- if an unnamed fresh launch replaces an active extension-managed session, best-effort close the old managed session after the switch succeeds
+- leave explicit caller-provided `--session` choices alone unless the caller closes them explicitly
 
 This is primarily about ownership clarity and avoiding surprise, not adding a heavy safety wrapper. If the extension invented the session, the extension should clean it up. If the caller explicitly chose the upstream session model, the extension should stay out of the way.
 
@@ -98,6 +101,8 @@ If the implicit session is already active and one of those startup-scoped flags
 
 That failure should include a structured recovery hint pointing to `sessionMode: "fresh"` as the first-line fix, while still allowing an explicit `--session` when the caller wants to name the new upstream session.
 
+A successful unnamed `sessionMode: "fresh"` launch should become the new extension-managed session so later default calls follow that browser instead of silently snapping back to the older managed session.
+
 ## Preferring the native tool
 
 Keep the handling simple:

package/docs/REQUIREMENTS.md

@@ -84,7 +84,7 @@ The design should comfortably support workflows such as:
 - web research
 - using browser UIs for other LLMs such as ChatGPT, Grok, Gemini, and Claude
 - isolated authenticated browser sessions
-- cloned-profile workflows similar to the patterns used in `pi-oracle`
+- upstream profile/debug workflows without adding a local profile-cloning layer in this package
 
 ## Implications for the implementation
 

package/docs/TOOL_CONTRACT.md

@@ -77,8 +77,8 @@ Examples:
 
 Behavior:
 - if `args` already include `--session`, upstream session choice wins
-- `"auto"` prepends the implicit active session when appropriate
-- `"fresh"` skips the implicit session so startup-scoped flags like `--profile`, `--session-name`, or `--cdp` can launch a fresh upstream session
+- `"auto"` prepends the current extension-managed active session when appropriate
+- `"fresh"` rotates that managed session to a fresh upstream launch so startup-scoped flags like `--profile`, `--session-name`, or `--cdp` apply and later default calls follow the new browser
 
 Recommended use:
 - use `"auto"` for the common browse/snapshot/click flow inside one `pi` session
@@ -121,7 +121,8 @@ Recommended details:
 ```json
 {
   "args": ["snapshot", "-i"],
-  "effectiveArgs": ["--session", "pi-abc123", "--json", "snapshot", "-i"],
+  "effectiveArgs": ["--json", "--session", "pi-abc123", "snapshot", "-i"],
+  "command": "snapshot",
   "sessionMode": "auto",
   "sessionName": "pi-abc123",
   "usedImplicitSession": true,
@@ -131,10 +132,21 @@ Recommended details:
       "e1": { "name": "Example Domain", "role": "heading" }
     },
     "snapshot": "- heading \"Example Domain\" [level=1, ref=e1]"
-  }
+  },
+  "summary": "Snapshot: 1 refs on https://example.com/"
 }
 ```
 
+Additional structured fields can appear when relevant:
+- `batchFailure` and `batchSteps` for `batch` rendering, including mixed-success runs
+- `navigationSummary` for navigation-style commands like `click`, `back`, `forward`, and `reload`
+- `imagePath` / `imagePaths` for screenshots and batched image outputs
+- `fullOutputPath` / `fullOutputPaths` when large snapshot output is compacted and spilled to a private temp file
+- `sessionRecoveryHint` when startup-scoped flags need `sessionMode: "fresh"`
+- `inspection: true` plus `stdout` for successful plain-text inspection commands like `--help` and `--version`
+
+When the tool echoes `args` or `effectiveArgs` back into Pi, sensitive values such as `--headers`, proxy credentials, and auth-bearing URL parameters should be redacted first.
+
 For oversized snapshots, details should switch to a compact metadata object and include `fullOutputPath` pointing at a private temp JSON spill file with the full upstream snapshot payload.
 
 ## High-value result rendering
@@ -157,15 +169,19 @@ If `agent-browser` is not on `PATH`, fail with a message that:
 
 ## Session behavior
 
-- maintain one implicit active session per `pi` session for the common path
-- derive that implicit session from the official `pi` session id
+- maintain one extension-managed active session per `pi` session for the common path
+- derive the base implicit session name from the official `pi` session id plus a cwd hash so same-named checkouts do not collide
 - respect explicit upstream `--session` with minimal interference
-- treat the implicit session as extension-managed convenience state
-- on normal `pi` shutdown, best-effort close the implicit session
-- set an idle timeout on implicit sessions so abandoned daemons eventually self-clean
-- clean up private temp spill artifacts owned by the implicit session on shutdown
-- treat explicit upstream session choices like `--session`, `--profile`, `--session-name`, and `--cdp` as user-managed
+- treat the extension-managed session as convenience state owned by the wrapper
+- on normal `pi` shutdown, best-effort close the current extension-managed session
+- set an idle timeout on extension-managed sessions so abandoned daemons eventually self-clean
+- clean up private temp spill artifacts owned by the extension-managed session on shutdown
+- reconstruct the current extension-managed session from persisted tool details on resume/reload so later default calls keep following the active managed browser
+- when an unnamed `sessionMode: "fresh"` launch succeeds, make it the new extension-managed session so later default calls keep using it
+- if that unnamed fresh launch replaced an already-active managed session, best-effort close the old managed session after the switch succeeds
+- treat explicit caller-provided `--session` choices as user-managed
 - pass explicit `--profile` straight through to upstream `agent-browser`; no profile-cloning or isolation layer is added in v1
+- treat successful plain-text inspection commands like `--help` and `--version` as stateless: do not inject the implicit managed session and do not let those calls claim the managed-session slot
 - if startup-scoped flags like `--profile`, `--session-name`, or `--cdp` are supplied after the implicit session is already active while `sessionMode` is `"auto"`, return a validation error with a structured recovery hint that recommends `sessionMode: "fresh"`
 
 ## Non-goals